Video recording of our Opulent Voice hardware description language (HDL) design review, held 19 November 2024.
Roundup of SDR Talks from RTL-SDR Blog includes ORI
Thank you to RTL-SDR.com for posting this informative article about talks from
DEFCON32.
The article references a talk from our CEO about good news concerning the Synthetic Aperture Radar regulatory situation.
Check the article out here: https://www.rtl-sdr.com/sdr-and-rf-videos-from-defcon-32/
Opulent Voice Lab Implementation Matches Simulation
“Space Frequency Block Coding” Article to Appear in ARRL QEX
Neptune Project’s Space Frequency Block Coding article will appear in the next issue of QEX Magazine, from ARRL. Learn all about this modern digital signal processing technique in a friendly and accessible way.
See https://www.arrl.org/qex for more information about this magazine for amateur radio experimenters.
Inner Circle Newsletter: Winter 2024 Call for Participation
Want to write for our Winter 2024 Inner Circle Newsletter?
Planning and design is already underway!
Have an #opensource #digital or #hamradio project you want more people to know about?
Get in touch today with any board member or email us at hello at openresearch dot institute.
Early draft cover of our Winter 2024 Inner Circle Newsletter is pictured at right. Thank you to all our wonderful contributors for making Inner Circle a joy to share with our community.
Inner Circle Newsletter: Autumn 2024
A Harvest of Regulatory and Technical Updates
Open Research Institute is a non-profit dedicated to open source digital radio work. We do both technical and regulatory work. Our designs are intended for both space and terrestrial deployment. We’re all volunteer. You can get involved by visiting https://openresearch.institute/getting-started
Membership is free. All work is published to the general public at no cost. Our work can be reviewed and designs downloaded at https://github.com/OpenResearchInstitute
We equally value ethical behavior and over-the-air demonstrations of innovative and relevant open source solutions. We offer remotely accessible lab benches for microwave band radio hardware and software development. We host meetups and events at least once a week. Members come from around the world.
Subscribe to this newsletter at http://eepurl.com/h_hYzL
Ribbit Radio Update
It isn’t often that a completely new way of using existing technology in a truly innovative way on the amateur bands excites the community, but Ribbit consistently delivers.
What is Ribbit?
Ribbit is a novel digital text messaging mode for VHF/UHF communications for recreational and emergency use. It radically increases the density of information transmitted by spectrum used. Ribbit turns text into encoded audio, which can be played from your smartphone into the microphone of any radio, on any band, under even very noisy conditions. A smartphone with the Ribbit application on the other side can recover this message. Your information will get through.
Ribbit leverages the computing power of the modern smartphone to increase the capabilities of any Handy Talkie without requiring any additional hardware or cable.
Its redundant distributed nature allows it to function even when internet connectivity is lost during emergencies or just not available due to poor coverage.
Developer Updates
Project Lead Pierre W4CKX and Rattlegram Developer Ahmet Inan supported a transition of project development to Alex Okita KO6BVA in late 2023. Since then, Alex has made several big strides forward in both development and demonstration.
Alex’s most recent TO DO list included the following tasks.
1) Building a scheme to compact the header for Ribbit. The header is a bit long and could be shortened to save some bits using a raw bit stream of a simplified character map.
2) Add a keyEncoder to Code Witches as the keyboard input gets letters added. When the “Enter” key is pressed begin encoding/consuming the characters in the input area.
3) May also want to add in a sort of message queue above the input area.
4) Build a useful CW-Font for code witches and anything else anyone wants to use it for.
All of this work enabled a highly successful demonstration of Ribbit at DEFCON 32 in Las Vegas, Nevada, in mid-August 2024. A special thank you to RF Village for hosting ORI’s Open Source Showcase.
Visitors to the exhibit were able to see Ribbit work in a busy and noisy environment. DEFCON, like most other very large conferences, is acoustically noisy, but also very electrically noisy. Ribbit was demonstrated all weekend long in a very harsh environment, as the WiFi Capture the Flag competition was happening literally steps away from the Ribbit demonstration. The venue, Las Vegas Convention Center West, was full of conference attendees. Despite the background noise and substantial RF interference, Ribbit worked from Smartphone app speaker output, to Family Radio Service microphone input, over the air on a busy FRS channel, to the receiving FRS radio speaker output, to a Ribbit application microphone input on the monitoring smartphone. Being able to transmit and reliably receive accurate text data is a notable achievement.
Alex has integrated the Ribbit functionality into a web application. This makes Ribbit even easier to use than traditional native applications. The live web app demonstration can be found at https://badkangaroo.github.io/
Recordings of presentations about Ribbit, along with posters and diagrams, can be found at https://www.ribbitradio.org
The source code can be found at https://github.com/OpenResearchInstitute/ribbit_webapp
Practical Real World Use
The technical demonstration for Ribbit, called Rattlegram, got very positive reviews for utility in the field from Chile and Argentina mountain rescue groups. The challenge is supporting hikers and skiiers in places where cellular coverage is limited or not available. Ribbit functionality provided clear benefits with no downsides.
Carlos, our contact in Argentina who supports mountain rescue operations, described his experiences using Ribbit technology.
“Hi everyone, how are you? I’m just back from the mountains in Chile. We did some testing with Rattlegram, in very windy conditions (without any cables) and worked just great !
Send you a picture & video of one of the test we made. We were at this summit:”
In Argentina, Carlos reported:
“These past few months, we have been going out to the mountains, and been using Rattlegram with lot of success. In one of the ‘refugio’ we left an old cell phone with Rattlegram loaded besides the base radio, and we have been sending messages in all the backcountry ski outings and all the messages arrived without a problem.”
If Ribbit can work on the top of the mountains in Chile and Argentina, and if it also performs really well in noisy urban environments, then what can’t it do?
Ribbit Can’t Flourish Without Your Support
Ribbit is innovative, useful, and fully supported by Open Research Institute. But, it won’t realize its full potential without continuing development and community support. If you are excited about Ribbit and want to help, please join ORI at https://openresearch.institute/getting-started and let us know you want to get involved with Ribbit. We’ll make sure you get on the mailing lists and Slack channels.
ORI graciously accept donations for Ribbit development. Ribbit has a dedicated bank account, follows non-profit best practices, has an enforced code of conduct, and regularly reports to ORI leadership.
Thank you to everyone helping make Ribbit successful, useful, exciting, and fun to use!
Opulent Voice Comes to the PLUTO SDR
An Open Source Minimum Shift Keying Implementation
Opulent Voice is the native digital voice and data protocol for ORI’s open source satellite (or terrestrial) system called Haifuraiya. With high fidelity voice quality, seamless integration of data, keyboard chat, and authentication and control messages, amateur operators experience something truly new and enjoyable. As described by ORI Director Steve Conklin AI4QR, “Leave scratchy and harsh proprietary vocoders with clunky or incomplete data mode integration behind for good.” All source code at https://github.com/OpenResearchInstitute/pluto_msk
Things worth doing are rarely easy. The Minimum Shift Keying (MSK) implementation of Opulent Voice (OPV) on the PLUTO SDR is no exception. Challenges to the documentation, design, implementation, and test cycles have come up throughout the process. The response from the open source digital radio community has been solid, inspiring, and productive, with patient problem-solving winning the day every time.
Michelle Thompson, ORI’s CEO, described her perspective on OPV’s progress recently at an IEEE event, stating:
“I would like to thank everyone helping ORI achieve ambitious goals for our uplink protocol. It’s a real pleasure to serve this community and meet the needs of this project. It’s a privilege to be part of something so innovative and relevant.”
This feeling is reflected by the OPV volunteer team, who are actively involved around the world in promoting open source work and helping ORI projects like OPV succeed.
Successes Over the Past Quarter and Current Status
OPV was the communications downlink for a NASA RockSat-X mission executed by the University of Puerto Rico, one of the most consistent and successful teams participating in this competitive program. The mid-August 2024 launch from Wallops went flawlessly. The performance of OPV met all expectations and data recovered from the launch is being used to further develop and improve the communications protocol.
OPV presentations at HamCon:Zion and DEFCON during the summer of 2024 were extremely well received, giving positive educational value to the community. Amateur Radio deserves quality digital communications. OPV delivers excellent results and is well-documented.
There is still a long way to go. The physical layer work is currently focused on tuning the tracking loops in the demodulator. Once the physical layer is reliable, then the functions that integrate voice, data, keyboard, and channel control messages will be integrated into the PLUTO SDR build and tested. Application layer functions in HTML 5 have a head start, with some tests already completed. Parallel integration efforts from F5OEO and OpenCPI, both of which will expand the number of hardware platforms that OPV can use, are well underway.
Below, an example of bit-accurate simulation results for OPV, with signal names on the left and waveform values on the right.
Below, the spectrum of OPV, showing main lobe null-to-null span of 81 kHz, and signal sidelobes.
Haifuraiya and Modem Module Update
The work on Haifuraiya has broader appeal than just as a HEO/GEO satellite design. The “modem module” approach, developed by Matthew NB0X, is summarized at left.
At left is the most recent high level block diagram.
Haifuraiya – Open Source HEO/GEO Amateur Satellite Update
The multirate channelizer has been implemented in Remote Labs West on the zc706/ADRV9009 station. At left is a summary of the channel plan for the satellite receiver.
Regulatory Work at ORI
Making Open Source Easier for Everyone
Past regulatory work at ORI can be found at
https://github.com/OpenResearchInstitute/documents/Regulatory
A special Halloween season workshop about exorcising the Haunted Band of 219-220 MHz was held by IEEE and ORI on 29 October 2024.
The Zoom meetup was well attended with the majority of RSVPs participating on the call. The meeting was recorded for those that couldn’t make it. The video recording of the background session, followed immediately by the workshop, can be found at https://youtu.be/wGX__qcFrT4
219 MHz is a secondary allocation for amateur radio. It has excellent channel characteristics, is open to fixed point-to-point digital links only, allows 100 kHz bandwidths, has a minimum of 56 kbps data rates, and has had no activity for decades. It’s time to take this band back!
Why is there no activity? We believe this band is inactive because of the notification requirements in FCC part 97 and part 80. We assert that these notification requirements, which pull ARRL into the loop from two different directions, are impossible for both amateurs and commercial licensees to comply with.
What are these notification requirements? If you as an amateur want to operate on 219 MHz, you have to determine if there’s an Automated Maritime Telecommunications System (AMTS) station within 80 km of your amateur station. You then have to ask permission from the AMTS station(s) in order to legally operate with at least 30 days notice. If you are between 80 km and 640 km, then you have to notify the AMTS stations at least 30 days in advance of activating the band.
A publicly accessible database of amateur and AMTS stations on 219 MHz is supposed to be maintained by ARRL. This is a rule in Part 97 (for the amateur radio stations) and in Part 80 (for AMTS stations). This database does not appear to exist.
AMTS stations did not report their information to ARRL. Requests to ARRL for a copy of AMTS stations have not been answered. Requests for a copy of amateur radio stations that have notified the ARRL of intent to operate have also not been answered.
These requests were made by multiple amateur radio operators in the October – December 2023 time frame. This was before the cyberattack in 2024, which did sideline a lot of ARRL’s services and activities.
The 219 MHz band regulations need a serious overhaul. We believe a proposal for new rules for this band are a necessary step towards restoring amateur use of this band. We believe that rules can be proposed that will both promote modern and innovative digital activity, and at the same time, not endanger the primary licensees in any way. While the AMTS service no longer exists as originally envisioned, the AMTS licenses have been leased out to fundamentally different services, such as railroads. These primary licensees can share the band with amateur radio in, at the very worst, a mutually inoffensive way and, at the very best, a mutually beneficial manner. It’s up to us to make this better future happen.
In order to make an effective proposal to the US FCC for updated rules for this band, there are things that we need to sort out. We need to know what we want and we need to know what the primary users want. We need to anticipate and answer objections to dropping the onerous notification requirements, and we need to clearly state the value that an amateur radio allocation on this band brings to education, public service, citizenship, and technical advancement of the radio arts.
The workshop on 29 October was the first strong step towards sorting out a draft of proposed rulemaking for restoring amateur radio service use of the 219 MHz band.
Discussion during the workshop resulted in an outline for a draft rulemaking proposal. ORI sincerely thanks everyone that participated during the event and through email correspondence.
Draft Outline
1) Demonstrate that the current rules are not working. State our case that the notification requirements are impossible to comply with and are the reason that there is no activity on this band.
2) Cite 60m as an example of successful similar activity.
3) Assert, providing evidence, that amateur radio operators already know how to share spectrum with other services. We already know how to not cause problems for the services that we share spectrum allocations with. We do not need additional notification requirements or to sign declarations to the ARRL in order to be able to successfully operate on an amateur radio band as a secondary user.
4) Show, from a ULS database perspective, the current utilization of 219-220 MHz. Amateur activity does not threaten primary licensees.
5) Show, to the best of our ability, the actual use of 219 – 220 MHz. This will require a call for participation for sensing stations, such as WebSDRs, amateur operators, receiver enthusiasts, and distributed receiver networks such as SatNOGS, to monitor 219-220 MHz for some period of time, in order to measure primary licensee activity on the band.
5) We assert that AMTS no longer exists. The current primary licensees are not coastal stations. The rules assuming coastal activity do not reflect the reality of this allocation as it exists today. Old rules are hampering efficient use of the spectrum.
6) Propose specific deletions of rules. What exactly should and could be struck down?
7) What are the anticipated effects, repercussions, both positive and negative, of deleting the notification requirements.
8) Is there anything else that could or should be changed? We discussed the 100 kHz bandwidth requirement and it’s origins in specific equipment available to amateurs at the time. Current FCC thinking is to not have rules that hardcode in equipment requirements. Deleting the 100 kHz bandwidth limit in favor of no bandwidth or symbol rate limit had broad support at the workshop.
Thank you to all of you that support our regulatory work. It will take a lot of time and effort to draft proposed rules and to go through the proposal process. The FCC may or may not choose to entertain new rules for 219 MHz. If they do, then a public comment period will happen. If they do not, then the draft rules will still be of benefit, as they will record the point of view and consensus of digital mode amateur radio experimenters and enthusiasts.
Please join this effort at ORI by visiting https://openresearch.institute/getting-started
Sphere of Activity
July 12-13 2024 – ORI exhibited at HamCon:Zion in St. George, Utah, USA. We invited Deep Space Exploration Society (DSES) and QRZ.com columnist Dave Jensen to join our booth. We showcased their work alongside our technical and regulatory acheivements. Total staff was three for this weekend event at a very nice conference center. Some of the travel expenses were reimbursed by ORI. This collaboration was entirely successful. Our CEO gave a talk about AI/ML in Amateur Radio at HamCon’s forum, which can be seen at https://www.youtube.com/watch?v=ZgHUavf5Ddo
August 8-11 2024 – Our Open Source Digital Radio exhibit at DEFCON 32 in Las Vegas, Nevada USA was a big success. ORI hosted demonstrations from RFBitBanger, Ribbit, Opulent Voice, and our Regulatory team in the RF Village. A staff of four set up, staffed, and tore down the exhbit. Travel and lodging was funded by ORI. Our CEO gave an RF Village talk about Synthetic Aperture Radar and Amateur Radio, which can be seen at https://www.youtube.com/watch?v=fiR4woe4O5Q
August 29 2024 – ORI participated in the quarterly Federal Communications Commission Technology Advisory Council meeting and presentation in Washington, DC. ORI is represented on the FCC TAC by Michelle Thomposn and Matthew Wishek. Open Source and Amateur Radio interests have been defended at the federal level. ORI Contributions to the Dynamic Spectrum Sharing and 6G Working Groups can be seen in the video at https://www.fcc.gov/news-events/events/2024/08/technological-advisory-council-meeting-august-29-2024 If you are interested in supporting regulatory participation and defense, please join ORI, support ORI’s work, and let us know how you want to help.
October 2-9 2024 – ORI organized a week-long event called Digital Update for Microwave (DUM) in Vancouver, British Columbia, Canada. There were 3 on site for this event and 9 participants virtually. Housing was reimbursed by ORI. The focus of the workshop was Opulent Voice and Iterative Receiver Theory technical work. We did not address the 10 GHz antenna questions posed from our outreach prior to the event due to time limitations. Better 10 GHz mobile radio gear is what people are looking for, and this will get attention from ORI over the next quarter. DUM is an event that provides opportunities for people interested in digital communications on the amateur microwave frequencies. The contributions to ORI’s GitHub repositories showed that DUM was well worth the effort. Should ORI have a DUMII?
Thank you to all who support our work! We certainly couldn’t do it without you.
Anshul Makkar, Director ORI
Frank Brickle, Director ORI
Keith Wheeler, Secretary ORI
Steve Conklin, CFO ORI
Michelle Thompson, CEO ORI
219 MHz FCC Rules Revision Workshop Announcement
All of us at ORI are looking forward to the “let’s take back 219 MHz for innovative and awesome digital operations” workshop coming up in a few days. (This is a US centric spectrum management issue.)
The response has been very strong. Thank you!
Yes, the workshop will be recorded. No, it will not be successful without participation. If you care about completely unused VHF/UHF spectrum in the US, and want to see educational, modern, non-commercial use of this band happen without unnecessary impediments and silly rules, then we need your input now.
Here’s the link to RSVP (no you do not have to be an IEEE member to use vTools and sign up and attend):
https://events.vtools.ieee.org/m/439290
Even if you simply want a recording of the workshop, please register. Then you can get a notification.
If you would like to participate in “The Haunted Band” or any of the other 9 open source amateur radio projects at ORI, then it’s easy to join.
Please visit https://openresearch.institute/getting-started to get involved.
Inner Circle Newsletter: Summer 2024
A Sizzling Summer Summary prepared just for you!
Read on for highlights from all our technical and regulatory open source digital radio work. ORI’s work directly benefits amateur radio, provides educational and professional development opportunities for people all over the world, and puts ethics and good governance first.
Opulent Voice Flying High
Opulent Voice is an open source high bitrate digital voice (and data) protocol. It’s what we are using for our native digital uplink protocol for ORI’s broadband microwave digital satellite transponder project. Opulent Voice has excellent voice quality, putting it in a completely different category than low bitrate digital communications products such as D-Star, Yaesu System Fusion, and DMR.
Opulent voice switches between high resolution voice and data without requiring the operator to switch to a separate packet mode. Opulent voice also handles keyboard chat and digital file transmission. Seamless integration of different data types, using modern digital communication techniques, differentiates Opulent Voice from any other amateur radio protocol.
Opulent Voice will fly on the University of Puerto Rico’s RockSat-X launch on 13 August 2024. It’s been a very positive experience working with the students and faculty at the University.
An implementation on FPGA for the PLUTO SDR is well underway, with a active international team delivering quality results. This implementation will not only turn your PLUTO SDR into an Opulent Voice transceiver, but it will have remote operation functionality.
Hear what Opulent Voice sounds like by following the links in an earlier update at https://www.openresearch.institute/2022/07/30/opulent-voice-digital-voice-and-data-protocol-update/
We’ve come quite a long way in less than two years! The FPGA implementation upgrades the modulation from 4-ary frequency shift keying to minimum shift keying, and increases forward error correction performance and flexibility.
HAMCON:ZION 2024 is This Week!
Please visit us at HAMCON:ZION 2024 this weekend, 12-13 July 2024 in St. George, Utah, USA.
The event website is https://www.hamconzion.com/
ORI will have a club booth at the event. We opened our space to QRZ.com (https://www.qrz.com/) and Deep Space Exploration Society (https://dses.science/). This combined exhibit is a one-stop shop for the best in community, technical, and citizen science amateur radio activity.
We have a volunteer presenting on Artificial Intelligence and Machine Learning in Amateur Radio. The talk opens with a brief summary of the history of our relationship with created intelligence and then explores case studies of the use of artificial intelligence and machine learning in amateur radio. Talk is 1pm on Friday in Entrada B.
Open Research Institute at DEFCON32
We will present an Open Source Showcase at DEFCON in the Radio Frequency Village 12-13 August 2024, with accessible exhibits and demonstrations. Here is the list of scheduled project demonstrations.
Regulatory Efforts: ORI works hard for open source digital radio work and moves technology from proprietary and controlled to open and free in intelligent and mutually beneficial ways. Our work on ITAR, EAR, Debris Mitigation, AI/ML, and Synthetic Aperture Radar will be presented and explained. Find out more at https://github.com/OpenResearchInstitute/documents/tree/master/Regulatory
Ribbit: this open source communications protocol uses the highest performance error correction and modern techniques to turn any analog radio into a digital text terminal. No wires, no extra equipment.. Learn how to use this communications system and get involved in building a truly innovative open source tactical radio service. Find out more at https://www.ribbitradio.org
Satellite: ORI has the world’s first and only open source HEO/GEO communications satellite project. All working parts of the transponder project will be demonstrated, from Opulent Voice to antenna designs.
The Dumbbell antenna: We have an HF antenna design based on a highly effective inductive loading technique first written about in 1958. Learn about this antenna and find out how to make your own. Repository can be found at https://github.com/OpenResearchInstitute/dumbbell
RFBitBanger: an HF QRP system and novel digital protocol called SCAMP. Kit information and updates will be available. Get your Batch 2 kit today at https://www.ebay.com/itm/364783754396
Radar: Our regulatory and technical work in synthetic aperture radar will be demonstrated. One of our volunteers will be giving a talk about open source synthetic aperture radar in the RF Village speakers track. Here is the abstract.
Synthetic Aperture Radar (SAR) is one of the most useful and interesting techniques in radar, providing high resolution radar satellite images from relatively small satellites. SAR is not limited by the time of day or by atmospheric conditions. It complements satellite photography and other remote sensing techniques, revealing activity on the Earth that would otherwise be hidden. How does the magic happen? This talk will explain the basics of SAR in an accessible and friendly way. That’s the good news.
The bad news? SAR is controlled by ITAR, the International Traffic in Arms Regulations, and is listed in the USML, the United States Munitions List. ITAR regulates the export of defense articles and services and is administered by the US State Department. This includes both products and services as well as technical data. Such as, catalogs of high resolution radar imagary. The articles and services regulated by ITAR are identified in the USML. If ITAR doesn’t get you, then EAR just might. The Export Administration Regulations (EAR) are administered by the US Commerce Department, and items are listed on a Commerce Control List (CCL). Commercial products and services and dual-use items that are not subject to ITAR could be regulated by EAR. Even if you are free of ITAR and EAR, you may still be regulated by yet another agency, such as the FCC.
Regulation of SAR chills commercial activity, creating costly and time-consuming burdens. But why does any of this matter to signals hackers? Because technology has overtaken the rules, and devices used by enthusiasts, researchers, students, and hackers are increasingly likely to have enough capability to fall into export-controlled categories. The penalties are harsh. Fear of running afoul of ITAR is enough to stop a promising open source project in its tracks.
Is there a way forward? Yes. ITAR has a public domain carve out. Information that is published and that is generally accessible or available to the public is excluded from control as ITAR technical data. That’s great in theory, but how can we increase our confidence that we are interpreting these rules correctly? How can we use and build upon these rules, so that our community can learn and practice modern radio techniques with reduced fear and risk? Can we contribute towards regulatory relief when it comes to SAR? We will describe the process, report on the progress, and enumerate the challenges and roadblocks.
RFBitBanger Batch 2 Kits Available
Kits are available at our eBay store at this link https://www.ebay.com/itm/364783754396
Be a part of the future with a prototype Batch 2 kit build of the RFBitBanger, a low-power high-frequency digital radio by Dr. Daniel Marks KW4TI. Presented by Open Research Institute, this kit is designed to produce 4 watts of power and opens up a new digital protocol called SCAMP.
SCAMP Is now available in FLDigi!
Source code and extensive instructions can be found at https://github.com/profdc9/fldigi
Your donation in exchange for this kit directly enables the further development of an innovative Class E amplifier based radio design. It has a display, button menu navigation, and keyboard connection for keyboard modes and keyboard-enabled navigation. This radio can be taken portable or used in a case. If you have a 3d printer, then Dr. Marks has a design ready for you to print in the repository linked below.
- Built-in digital modes: CW, RTTY, SCAMP (FSK and OOK, multiple speeds)
- Key jack supports straight keys and iambic paddles
- Open Source hardware and firmware, Arduino UNO compatible https://github.com/profdc9/RFBitBanger
- External sound-card FSK digital modes supported (including FT4/FT8)
- Experimental SSB support
- Serial port support (2400 baud) for send and receive in keyboard modes
SCAMP is a new protocol that allows keyboard-to-keyboard contacts with a digital protocol that has excellent connection performance. See Dr. Marks presentation about RFBitBanger at QSO Today Academy in September 2023 to learn more about SCAMP and the RFBitBanger project. Link below:
All surface mount parts on the main board are pre-installed at the factory. All the through-hole parts you need to complete the radio are provided for you to solder yourself.
Builder’s notes and photos of all the components to help you identify and install them can be found here:
https://github.com/OpenResearchInstitute/RFBitBanger-kit/tree/main/batch2
If you don’t know how to wind toroids or solder surface mount capacitors, this is an excellent kit to learn on. There are just six toroids on the main board, and two on each band pass filter board. You can build just one band pass filter board and operate on a single band, or you can build an assortment. We provide 12 filter boards, enough toroids to build any 9 filters, and a supply of capacitors that will let you build those 9 filters for 9 different HF ham bands. These capacitors are size 1206, which is the largest common size for SMT capacitors and the easiest to solder manually. All you’ll need is a pair of tweezers and your regular soldering iron and solder. We provide detailed instructions on winding the toroids and soldering the capacitors. You get spare filter boards to experiment with.
Friendly Support is provided through a dedicated Open Research Institute Slack channel.
Instructions on how to join this community are here:
https://www.facebook.com/openresearchinstitute https://www.instagram.com/open_research_institute/
https://x.com/OpenResearchIns
Standards Groups and Advisory Work
We have been hard at work defending #opensource and #hamradio in multiple ways by actively supporting standards committees and advisory groups.
We are a member of the United States Federal Communications Commission Technological Advisory Council, serving on the Advanced Spectrum Sharing and 6G Working Groups.
We serve on IEEE P1954 Standard for Self-Organizing Spectrum-Agile Unmanned Aerial Vehicles Communications working group.
We participated in several notices for proposed rulemaking at multiple government agencies over the past year, and expect this work to continue.
We have assisted in several successful experimental license applications for amateur radio satellite communications projects.
ORI is doing the work that helps the future of open source digital radio.
Thank you to all who support our work.
DUM: Digital Update for Microwave
2-9 October, Vancouver BC
Informal meetups, workshops, salons, food, and tours.
Lots of digital amateur microwave discussions with friends.
Interested? write fpga at openresearch dot institute and help us be as DUM as we can be.
Q: Will there be a schedule?
A: Yes. It will be posted on the website, on our Slack, and to the ORI mailing list.
Q: Are there going to be proceedings?
A: We will publish what we call “DUM Notebooks”. This isn’t a formal proceedings, but it will capture the content of the meetups in notebook format, probably Jupyter notebooks. There may also be video recordings of some of the events and lab sessions.
Q: Tell me about the lab?
A: A lab will be set up for the event that includes computers, PLUTO SDRs, spectrum analyzers, other test equipment, and access to full Vivado/Vitis licenses for the larger FPGAs used for the topics under consideration.
Q: What are the topics of the workshop?
A: Topics include but are not limited to the following.
1) An OFDM-based drone physical link work for project Neptune, featured in not one but two upcoming ARRL QEX articles. This is at 5 GHz and leverages 5G waveforms. Unlike commercial options that use the amateur bands without benefiting amateur radio, Neptune is by hams for hams and provides a competitive option to proprietary and commercial designs.
2) Opulent Voice (can also be found in QEX) was used during the most recent RockSat-X launch at Wallops by University of Puerto Rico, a “frequent flyer” in NASA’s university space program. Opulent Voice is a microwave-ready minimum shift keying protocol with very high voice quality. No more scratchy digital audio. It delivers data seamlessly, without a clunky separate packet mode. If you’re not familiar with MSK or minimum shift keying, then this is an excellent project to get to know, as the entire design is open source. Available now at https://github.com/OpenResearchInstitute/pluto_msk
3) Omnidirectional 10 GHz investigations. Inspired by requests from the contensting community, we look at how 10 GHz mobile contesting can be improved by taking a hard look at antenna designs. MATLAB antenna analysis tools will be used to quantify traditional and proposed designs.
4) Polyphase and multirate processing for amateur microwave, where powerful FPGA-based techniques can channelize large swaths of our microwave bands and put more people in touch with each other. A polyphase channelizer is at the heart of the open source GEO/HEO design under active development. Downlink is DVB-S2. That part of the design is working and available today at https://github.com/OpenResearchInstitute/dvb_fpga
Q: Where is this going to be held?
A: At AirBNBs and local restaurants.
Q: Where are people staying? In some DUM hotel?
A: We don’t have an official DUM hotel. Attendees that aren’t local are at AirBNBs or hotels near the VanDusen Botanical Garden. Lodging coordination is on our Slack. To join ORI and access the Slack, please visit
https://openresearch.institute/getting-started
A: Next, you’re going to tell me about how great public transit is in Vancouver.
Q: How did you know??
Q: If I’m at MUD, can I also attend DUM?
A: Yes of course. However, the MUD hotel is on the other side of a tunnel with frequent bad traffic. We hope you have a great time at MUD.
Q: What if I don’t feel I’m smart enough to attend?
A: If you feel DUM, you will fit right in.
Q: Does it cost anything?
A: There is no additional cost to be DUM. Food, lodging, and transportation are the responsibility of the individual participating.
Q: I have a call sign from the US. Can I operate in Canada?
A: AB2KT/VE7 explains “There is complete reciprocity between Canada and the US as far as ham operating is concerned. People are free to bring gear and use it if they’re so inclined.”
7 February 2024 Neptune Project Meetup
Today’s #neptune meetup video recording is here:
We discussed techniques to lower #OFDM latency, including cyclic suffix instead of cyclic prefix. We updated the progress on space frequency block coding integration and documentation. We talked about the #DEFCON demonstration changes after the venue change for August 2024. Finally, we talked about the Zadoff-Chu AGC Burst insertion challenges in #Simulink.
6 February 2024 Haifuraiya GEO/HEO Digital Satellite Meetup Video Recording
Our 6 February 2024 #fpga meetup for #haifuraiya, our #opensource #hamradio #digital #satellite project, can be found here:
We talk about the integration of the #polyphase channelizer on the receiver and other updates. Thank you to those that support our work at ORI.
Open Research Institute Update: January 2024
Greetings all,
Thank you for being part of what Open Research Institute does.
There is a lot going on! If you are unfamiliar with our work, please visit our homepage at https://openresearch.institute and look at the news feed.
Published work and detailed documentation is available on GitHub at https://github.com/OpenResearchInstitute
All of the project leads at ORI do their best to report all of their technical progress. All work is free for anyone to use.
A lot of ORI’s work is done in areas that are often overlooked by other technical or membership organizations. This work is overlooked not because it’s worthless, but because there’s additional baggage or burdens that keep innovative and modern things unnecessarily difficult for amateur radio to use and enjoy.
Sometimes these burdens are purely pecuniary. Sometimes these burdens are regulatory in nature. Sometimes these burdens are driven by fear of competition, an aversion to collaboration, personal ego, or political problems.
Sometimes the fear or caution is justified. An example would be for specific issues of national defense, as summarized in our developer and participant policies page on our website.
Often, the fears are not justified. ORI asserts that motivated and competent individuals, like the many members of our community, are fully capable of figuring out what is “FUD” (the conditions of fear, uncertainty, and doubt deliberately exploited in order to control a particular outcome) versus what is a real issue.
We directly oppose unnecessary burdens. We do accept legitimate limitations. We are here to relieve the risks related to unnecessary impediments, and we have been highly successful at this.
We will be continuing this work.
We do all we can to make it possible for citizen scientists and citizen engineers to fully participate in everything modern science and technology has to offer. That is our mission. This mission is worth supporting. We have increasingly broad support.
We will continue in 2024 to do exactly what we have been doing, and we welcome your continuing involvement.
Do you have opinions on how we can “up our game”? Please share them with ORI’s board of directors. Contact information below:
To write the entire board, please use hello@openresearch.institute.
Thank you all for being a part of this very exciting movement! We have a positive impact on the amateur radio and amateur radio satellite service, and beyond.
-Michelle Thompson
ORI CEO
RFBitBanger Kit “Solstice Special” Successfully Concludes
Thank you to our supporters from around the world who will soon be receiving these open source innovative HF digital QRP kits.
Here’s the geographical distribution of the Solstice Special Batch 2 kits.
Find out more about this project at https://www.openresearch.institute/rfbitbanger-project/
Batch 2 RFBitBanger Kits Available Now
Geostationary Amateur Payload Call for Proposals
The European Space Agency has a Call for Proposals concerning Geostationary Amateur Payloads. We have contributed a technical support package and communicated our standalone HEO/GEO design to the ESA.
Thank you to all the volunteers that have contributed towards this achievement.
RFBitBanger Batch 2 kits available
Want a fun ham radio HF QRP open source digital radio kit? Link below.
Comments from ORI to the FCC on Advancing Understanding of Non-Federal Spectrum Usage
The comments as filed can be found here:
https://www.fcc.gov/ecfs/document/1009106258899/1
Text of the comments is below.
Comments of
Open Research Institute, Inc.
#1873 3525 Del Mar Heights Road
San Diego, CA, 92130
United States of America
9 October 2023
Open Research Institute (ORI) is a non-profit research and development organization devoted to Open Source digital radio technology.
ORI’s mission is to provide practical open source wireless communications solutions for terrestrial and space applications. ORI provides significant workforce development opportunities to the volunteers engaging in Open Source technical work.
Open Source means that everything required to reproduce a software, hardware, or firmware design is freely available to the general public. An Open Source design must have free redistribution, allow modifications and derived works, and be non-discriminatory against persons, groups, or fields of endeavor. Open Source work cannot be specific to a particular product, it cannot restrict other software or hardware, and needs to be technology-neutral.
Open Source is vital to the United States’ economic competitiveness in telecommunications. The Internet runs on Linux, an Open Source computer operating system, as 96.3% of the top one million web servers run on Linux, and the vast majority of the underlying networking infrastructure uses either Linux or other Open Source operating systems and libraries.
The telecommunications industry has historically been heavily reliant on proprietary software and hardware. An increase in the adoption of Open Source, from OpenRAN to Nephio, has enabled telecommunications companies to more quickly and efficiently meet market demands. There is a broad trend towards the continuing increase in adoption of Open Source designs in order to avoid silos of wheel reinvention and to promote effective interoperability.
The Open Source community can address this inquiry.
Introduction
ORI agrees that spectrum usage information is generally nonpublic and infrequently available. In the spirit of Open Source and Open Access, we believe that publicly available high-quality data about spectrum usage is in the national interest.
ORI agrees that the need for spectrum usage information will only continue to grow. In order to produce useful models, artificial intelligence and machine learning require enough data to complete the training process. Without enough data, a machine learning model can suffer from a condition called overfitting. When this happens, the model becomes a very expensive copy machine, presenting the training data as output, regardless of the input. The lack of sufficiently large high quality radiofrequency data sets is widely acknowledged as an impediment to research and development for radiofrequency machine learning.
ORI agrees that the development of new and innovative spectrum sharing techniques, allowing increased co-existence among users and services, will improve spectrum management. Spectrum usage
information is required in order to develop new spectrum sharing techniques. This is true whether or not machine learning is used either in the process or in the product. In other words, even if only ordinary humans had the task of improving spectrum sharing over and above what we have today, those humans would still need spectrum usage information to achieve their goal.
Without good spectrum usage information, neither machine learning nor human architects will be able to confidently produce quality results. The most common outcome to making the best guess in the absence of spectrum usage information is highly conservative spectrum sharing arrangements that do not fully utilize spectrum, overly restrict licensees, and prevent innovation in the field.
Central Question
We want a more sophisticated knowledge of non-Federal spectrum usage. The central question of this inquiry is how can we take advantage of modern capabilities for gaining this knowledge in a costeffective, accurate, scalable, and actionable manner?
In addition to the other spectrum monitoring efforts listed in this inquiry, we can start with the concepts established by the Spectrum Monitoring Pilot Program from NTIA/NIST.
This program measured spectrum occupancy with standardized distributed receivers reporting to Measured Spectrum Occupancy Databases. These databases publish the metadata of their measurements so that measured data can be retrieved over https:// connections. The concepts of federation are used in order to avoid inefficient and expensive replication of measured data.
The Spectrum Monitoring Pilot Program had two classes of receivers. One was dedicated to radar and the other to communications. The communications receiver approach is an order of magnitude less
expensive than the radar receiver approach.
Restricting the hardware package to the less expensive category of communications receiver, and using modern software-defined radios with Open Source software, and incorporating existing online radios (“WebSDRs”) alongside the standardized stations, and being deliberate and innovative about incentives, then we assert that a low-resolution receiver network that can produce useful spectrum usage information is achievable.
A Low Resolution Receiver Network – Why?
Why low resolution? Because a broad heatmap of spectrum usage, even at low resolution, is valuable in a different way for spectrum management purposes than a small amount of high resolution data from
one service in one geographical area.
The current situation is of essentially no real-time spectrum usage information. Even if we simply had noise floor measurements across the bands across the country, and even if those measurements were
gathered from stations of varying quality, we would have an immense improvement in our capacity to intelligently manage our spectrum over having no measurements at all.
Towards a Weather Map of the National Noise Floor
Noise floor is the measure of the noise power per bandwidth. Getting a snapshot of something like a National Noise Floor, comparable to a national radar weather map, needs a diversity of radio receivers.
We need to be able to measure or estimate power spectral density from these receivers. Services with intermittent use must be measured often enough to produce minimally accurate data, or those services
must be covered with alternate techniques.
As an example of where alternate techniques can work, FT8 mode contacts on the 17 meter Amateur Radio Service band can be obtained from https://gridtracker.org/. These reports, which are text based, can be used to estimate the power spectral density at the radios using Grid Tracker. Reports from radios can be used to create a map of real-time spectrum usage without directly measuring the spectrum. These are estimates, but they are based on measured signal-to-noise reports that all the radios are giving each other, in each 15-second long exchange.
We can compare this type of observation to eavesdropping on roomfuls of people talking to each other, and writing down how many conversations (and attempted conversations) there were. Multiple
eavesdroppers can spread through the house, combine their notes, and show where the conversational density was highest.
What does this look like on the 17 meter Amateur Radio Service allocation with a typical FT8 station?
A stream of which stations contacted other stations is reported from a single radio. The stream consists of all the contacts that the radio has heard from that location. The radio is not directly contacting all of
these other stations, but it can hear them all and tracks who is trying to talk to who and when. Any radio on the band can act like the eavesdropper above.
Open Source software (called WSJT-X) is controlling the radio and demodulating and decoding all received transmissions across the entire sub-band. WSJT-X does include a spectrum waterfall display,
which could be used to obtain power spectral density of all the simultaneous transmissions, but we do not have to do this. We instead use another commonly installed Open Source software program (called
Grid Tracker) which takes the text output of WSJT-X and provides a text list of active stations and their reported signal power. This list can produce a calculated estimate of the power spectral density in the band. It’s less math intensive to work with text based signal reports for fixed formal signals like FT8 than it is to use a spectrum analyzer waterfall, or deal with the IQ recordings of a radiometer.
The addition of additional radios (more eavesdroppers) improves coverage.
Does this exact network exist today? It almost does. Instances of Grid Tracker, very commonly installed alongside WSJT-X and running whenever the station is active are reporting all of this information, but they do not have coordinated reporting, as of today. However, since the software is Open Source, adding a function to opt in to do some math and donate the data to a server to produce a National Noise Floor snapshot, for this particular mode, is achievable.
This example outlines a proof of concept of a very tiny slice of the HF spectrum at 18.100 MHz, but it shows the advantage of using existing Open Source software, existing radios and existing communities
of licensed operators. Incentives to licensees to participate could be as simple as getting an opportunity to defend their licensed spectrum up to recognition awards for donating data consistently over time.
Achieving Aggregated Wireless Sensing
How can we broaden this concept? First, leverage existing online radio receivers, such as broadband WebSDRs. See http://www.websdr.org/ for deployed examples. Power spectral density measurements or estimates can be obtained from receivers already on the air and already connected to the Internet.
An anticipated and understandable objection is that the multitude of WebSDRs across the country are not calibrated stations and they are not standardized. The owner could take them down at any time. A
new one might be put on the air tomorrow. The answer to these objections is that the aggregation of these observations, even if the observations are of varying quality, provides immense value in efforts to
improve spectrum management because these receivers can produce real-time spectral usage information with no additional radio hardware investment.
We should, of course, not stop there. We must commit to a both/and and not an either/or approach to answer the central question of this inquiry.
Second, deploy inexpensive, standardized, and calibrated receivers to libraries, schools, post offices, and any other institution or organization that can be either incentivized or mandated.
For a model of an Open Source standardized distributed receiver system producing real-world practical radio results, please refer to the SatNOGS project at https://satnogs.org/
What are some standardized station examples that we could deploy in the United States to achieve the
goals of this inquiry?
An Open Source PLUTO SDR running Open Source Maia software creates an inexpensive spectrum analyzer with a built-in webserver. The addition of the federated reporting functions is possible because
the source code for Maia can be modified to include these additional functions. Maia can be found at https://maia-sdr.org/. Documentation for the standard PLUTO firmware (which is largely replaced by
the Maia firmware) can be found at
https://github.com/analogdevicesinc/plutosdr-fw
and documentation for the PLUTO hardware can be found at
https://wiki.analog.com/university/tools/pluto/hackers
A PLUTO/Maia package can cover frequencies from 70 MHz to 6 GHz. It would requires one or more antennas (depending on how many bands are to be monitored by that station), a power supply, a weatherproof enclosure, mechanical attachments, and cables. A proof of concept would be expected to cost less than the Spectrum Monitoring Pilot Program communications receiving station proof of concept, which came in at $6000 according to “An Overview of the NTIA/NIST Spectrum Monitoring Pilot Program”.
This can be read at
https://its.ntia.gov/umbraco/surface/download/publication? reportNumber=CottonSpectMonIwssSubmitted.pdf
A second and even less expensive example of a standardized station would be an RTL-SDR
https://www.rtl-sdr.com/about-rtl-sdr/
and a Raspberry Pi
https://www.raspberrypi.com/
running Linux. This kit can use a large number of Open Source software-defined radio packages. It can be tuned to any of the bands in its operating range of 2.4 MHz to 2 GHz. For a sweep of the entire operating range, multiple antennas and combiners would be necessary along with an amount of additional equipment and software.
The WebSDRs combined with the standard package stations form a heterogeneous distributed receiver network. In aggregate, with enough stations, the resulting network can provide useful real-time reports
of spectrum usage information. A centralized visualization of actual spectrum usage, even if not realtime, would be very informative. If a picture is worth a thousand words, then a video is worth a thousand pictures. People seeing gaps in the data may be motivated to put up or sponsor a station to fill in the gaps, similar to the effect we see with personal weather stations that measure temperature, wind
speed, and other meteorological aspects.
TAC Working Group as Asset
The Dynamic Spectrum Allocation Working Group of the Technological Advisory Council of the Federal Communications Commission could provide advisory feedback on real-time spectral usage information obtained through opportunistic and inexpensive sensor networks, invite speakers to present about the topic, and give specific recommendations. Leveraging an existing Working Group with familiarity in this particular topic would be an efficient use of already-available expert advice.
Conclusion
A National Noise Floor heatmap, even if low resolution, is achievable and it is valuable. Any reasonable real-time data, whether obtained opportunistically or purposefully, is an enormous step forward compared to no data at all.
There are drawbacks to low resolution data. The limits of the resolution must be acknowledged. The measurements have to at least be reasonable, meaning that a snapshot of noise floor includes enough
information to where lower power signals aren’t completely overlooked or missed. For each frequency allocation measured, a subject matter expert in that allocation would be expected to compare the realtime spectrum usage information to a model of expected spectrum usage. The difference between this theoretical or calculated model and the real-time spectrum usage information is valuable and informative in many ways. A subject matter expert would be able to explain observed differences, explain whether and why any difference was sufficient reason to make spectrum management adjustments, and provide feedback for improved spectrum sensing. There is no one-size solution for either the measurement stations involved or the allocations they are measuring.
The architecture for gaining visibility of spectral usage has been previously piloted in the Spectrum Monitoring Pilot Program. This and other excellent prior work can be adapted, and citizens can be
incentivized to participate in order to scale up the sensor network. Incentives range from the simple fact of being able to individually contribute directly towards the defense of a spectral allocation, to awards or recognition for the technical achievement of constructing and calibrating a station to a published standard, to a scoreboard of who provided the most consistent reports of real-time spectral information
over specific lengths of time.
There is a large amount of Open Source software and hardware that can be used to reduce costs and reward high quality collaborative and cooperative work. A “lower-tech, inexpensive, diverse, and start now” instead of a “high-tech, expensive, maybe sometime in the future” approach is cost-effective, accurate (enough), scalable, and actionable.
Respectfully,
Michelle Thompson
CEO ORI
400 Subscriber Milestone on YouTube
Thank you to everyone reading this that has supported ORI and how we publish our work on YouTube.
I know YouTube is not for everyone, but it is an effective way to communicate what we do, what challenges we face, and it lets people know there’s a community out there 1) doing things that they might find wonderful and 2) is worth hearing more about.
We have 400 subscribers, which is a bit of a milestone. This is a lot for a very technical all-volunteer organization that devotes its time supporting and promoting project work, while staying firmly in the background.
Our proudest moments are when projects succeed and are recognized on their own merits, under their own name, and under their own branding. Ribbit, RFBitBanger, Haifuraiya, a variety of published Open Source FPGA work, FPGA training, Opulent Voice, Versatuner, Dumbbell, actively participating in IEEE, FCC TAC membership, Remote Labs, our many regulatory successes, and our active and successful mentoring in professional and academic settings – these are all clear indications that we’re on the right track and doing a great job.
Not explicitly mentioned are the many places we’ve helped projects succeed behind the scenes, around the world.
We are committed to an altruistic approach that delivers clear value to project work. This approach has been abused only once, by one organization.
Being accountable, open, and successful is the cost of doing our type of business. This is a price happily paid.
Thank you for being part of it!
https://www.youtube.com/c/OpenResearchInstituteInc
Amateur Radio Article from BBC Futures
Our CEO, Michelle Thompson, was quoted in this article about amateur radio citizen science from BBC Futures.
https://www.bbc.com/future/article/20231005-eclipses-do-odd-things-to-radio-waves-to-learn-more-an-army-of-american-amateurs-will-broadcast-during-the-next-ones
ORI at IWRC2023
Link to the report (google document) can be found here:
https://docs.google.com/document/d/1eR1-vwJFJj4KzKUYbko7iHQptf8fbr_A9G2jIJ3uZfU/edit?usp=sharing
Content of the document as of 25 September 2023 reproduced below:
IWRC2023
Learn About the CHIPS Act and How It Relates to Arkansas
WASHINGTON (22 August 2023) – From 13-15 September, IWRC (the Innovation, Workforce, and Research Conference) will bring together stakeholders from industry, government, and academia in Little Rock. There, attendees will meet, learn, talk, and discuss the CHIPS Act along with other government programs that promote innovation and small business in rural America.
Congress last year allocated $56 Billion for chip manufacturing in the United States with a mandate that the government funding should be allocated throughout the United States. IWRC will provide an opportunity to meet potential partners from the U.S. federal agencies and learn more about how to contribute to the Arkansas innovation ecosystem.
At this event, experts from the region and across the country will discuss research grants, technology transfer programs, start-up funding, intellectual property, and a host of other topics related to inspiring and empowering true innovation in the Heartland and Delta Regions.
“IEEE-USA is excited to be bringing the IWRC conference to Little Rock to help Arkansas engineers and entrepreneurs connect with the CHIPS Act and the federal agencies supporting it,” said Ed Palacio, 2023 IEEE-USA President. “IEEE-USA supported the CHIPS Act’s passage through Congress and we look forward to seeing its impact across the United States.””
Arkansas Economic Development Commission
Document Authorship
This memorandum about the IWRC2023 conference was written by Michelle Thompson and Paul Williamson of Open Research Institute, a non-profit dedicated to open source research and development in digital radio.
ORI operates a Remote Lab, which provides field programmable gate array development boards for open source work. The development stations have Analog Devices radio cards, software licenses for the development environments, and remotely accessible test equipment for digital communications work up to 6 GHz. ORI can provide professional development opportunities through open source work to anyone with internet access. Contact ORI at hello@openresearch.institute
IWRC2023 Day 1
Matt Francis of Ozark Integrated Circuits, Region 5 Representative Elect for IEEE, explains how IWRC2023 came about. He and other like-minded people had the idea for this conference, organized some people to start working on it, things started happening, and now here it is. “How are we going to respond to the CHIPS act? What about the rest of the country?” IEEE USA “took the ball” and ran with it. Russ Harrison, executive director of IEEE USA, and Jennifer Flower were introduced. The goal is to bring the CHIPS act to Arkansas, including the lower Mississippi Delta Region.
What can we expect to experience and learn at IWRC2023?
1) Information about federal funding.
2) Bringing the research community together.
3) CHIPS act is not about rewarding the traditional silos. Having to work together to build ecosystems, this is the power of the chips act.
4) 9 federal agencies present today.
5) An invitation to become part of the teams that are forming in this area.
6) Thanks to the sponsors (Standard Lithium, Philander Smith University)
7) Thanks to the exhibitors. They’re in the foyer. ArcBest, Arkansas APEX accelerator, NCTR, Ozark Integrated Circuit, Power Technology Incorporated, SURGE
Jennifer Fowler speaks next. She is the Director of EPSCoR for Arkansas. EPSCoR is Established Program to Stimulate Competitive Research. Thanks everyone for joining us, some coming from out of state. Thank you for being on the journey.
https://new.nsf.gov/funding/initiatives/epscor
How significant and novel is IWRC2023? When we were reaching out to sponsors and recruiting attendees, “Is it an entrepreneurial event? A data science event? A workforce thing? Academic? No, you can’t publish a paper.” Difficult to convince people to take a step outside their normal networks to do this with us. This is an interdisciplinary event. The people that are here are worth paying attention to because they want to form partnerships to get difficult and ambitious work done for the region.
Program, content, networking <== of value.
This is an important meeting for AEDC and the Department of Commerce, these events are imperative. Ideas for proposals and capital projects is what we should leave with.
IEEE USA staff thanked: Deb Cooper, past president. Ed Palacio, current president (not here). Both are consultants and small business owners and understand the conference goals and such. IEEE USA mission fits this conference. IEEE “Advances technology for humanity”. Deb speaks about IEEE USA.
She’s pinch hitting for Ed Palacio, she explains that she doesn’t have the swagger but does have more hair. Kathy Hyashi got a photo with the Little Rock Mayor (Mayor Scott) at yesterday evening’s opening reception. IEEE is a professional association of technologists. Deb is a mathematical technologist with a cybersecurity bent. IEEE helps innovators reach across industry sectors to find new partners. Help people and industry find new partners to find success. This includes partners within the federal and state government.
Matt Francis Region 5 Coordinator
Kathy Hyashi Region 6 Coordinator
Chris Sanderson
John Birgenkur ? IEEE GLobal
Eric Blagorian?
Will Smith from Standard Lithium, plant manager El Dorado, chemical and project engineers, testing and trials. Standard Lithium is explained as a company and participating partner for CHIPS, then Will introduces Hugh McDonald, Secretary of Commerce for the state of Arkansas.
Standard Lithium is an up and coming lithium extraction facility, started 6 years ago, when some scientists from Canada said 7000 feet down was some Lithium in an existing and operating mine. “responsible lithium production” is achievable, as in there will be zero waste. There have been some very exciting announcements recently and they will be building the first commercial plant here soon. Feasibility study turned out very positive. The lithium formation is called the Smackover Formation.
Hugh McDonals was recently appointed. From Entergy, joined in 1982, worked his way up LA, TX, AR, MS. He retired in 2016. Got called out of the blue and appointed in 2023. Always been in the private sector. When you get announced as a Commerce Secretary, he explained that you get emails from all over the country from people trying to sell you stuff. One lobbying firm kept sending him stuff. About the CHIPS act. Not knowing many people in the State Government, he asked “what are we doing on the CHIPS act?” He got silence. He checked around, and finally after getting zero comment from everybody, he finds out that Jennifer Fowler of AEDC was the subject matter expert concerning CHIPS. He thanks and acknowledges Jennifer’s leadership. SURGE would not have happened without her, either. We learn more about SURGE later in the conference.
Scaling up regional economies is a priority. Improving education, growing the AR economy, creating meaningful careers, and not just jobs, is a clear focus. “A workforce development system second to none” is the goal.
Do all the departments that are focused on Workforce ever meet? Not before this. Working on big things you can’t really work it alone in your silo is what has to happen in order to take advantage of CHIPS. Seven state agencies are in the Workforce Cabinet, Mike Rogers has been appointed to a newly created position of Workforce Chief. He is profiled in an Arkansas Money and Power magazine that was current as of IWRC2023. Article included below.
It’s not about resources and who’s got the most, but it’s about thinking creatively and strategically, committing to a decision, and having the right people in the room. That’s what he is trying to do here. Seriously collaborating and working together, not just on paper, but actually doing it. That is how Arkansas can win, and that’s why SURGE was developed.
Early March late February was the first meeting for SURGE.
Within Commerce, there’s 9 different divisions. AEDC is one of them and it gets a lot of press. Main focus of commerce is to drive the state’s top line growth.
1) expanding existing business
2) recruiting businesses
3) growing small business.
Entrepreneurship has traditionally gotten less of a focus than it probably should have.
Workforce has to be calibrated and aligned to supply the workforce needs that are driven by the demand. Students need to be pulled through the system by the demand. Pushing the students through does not appear to work as well as it needs to.
1:50 engineers to technicians ratio was mentioned as an economic statistic.
Shortage of skilled workers exists in every category. Hugh says we have to focus on workforce. Manufacturing sector growth? We’re seeing more of this happening and the trend may continue. Companies have moved to diversify the risk of their supply chain to move production to more friendly countries, re-shore companies, and if the US continues to provide subsidies to US based manufacturing, then this will continue.
Economy in the US and the state? He feels pretty good about the economy. Unemployment rate here is 2.6% for two months in a row. This is the lowest it’s ever been.
Lots of projects are in the pipeline at Commerce. It feels good, but inflation is still here, fuel and energy prices were up 10% last month. Will the FED pause things with another rate increase? Who knows. We’ve got some opportunities and some threats and risks on the horizon. Fortunately we have strengths and a diversified economy. Pros and cons to that. When there’s a recession we mitigate the dips, but we also give up on enjoying the big peaks.
JB Hunt, Tyson, WalMart, FinTech are all in Central AR, Desaux Falcon, Agriculture products, steel business (US Steel) in MS county is now the top steel producing county in the US. Lithium will be mined in South AR. Hugh claimed Arkansas was #1 drone readiness. Arkansas has the 3rd Lowest cost of living in the US, and is rated as the best place to start a business. Arkansas claims to be the mountain biking capital of the world, especially in NW AR.
We discussed what “#1 in drone readiness” meant among ourselves, since we have a drone project and at least one licensed drone pilot on the ORI board. We concluded that this status does not directly relate to open source drone technology.
Hugh continued his pro-Arkansas speech. Arkansas does punch above its weight class in many categories, and produces a disproportionate number of technical leaders. As we will see in several of the discussions throughout the conference, brain drain is a significant challenge for Arkansas. Very capable and intelligent people are educated in the state and then leave after graduation.
Hugh stated that there is “Not a lot of big city dysfunction. Quality of life and quality of place is high.”
There are lots of trails and outdoors and entertainment. “If you’re moving here, we’ll give you back 2-3 days of your life in terms of commute time saved.”
Collaboration emphasized. Build some alliances. Come back. We have a lot of work to do.
Dr. JD Swanson from the NSF was introduced next. The person introducing him took some time to describe the exhibitors present. For example, the “Transfer” table opens up the opportunity to see what jobs really are like. What is it like doing a day in the life of several different jobs? This system is Snapdragon, Unity, and XR headset. This allows for safe hands-on simulation training in a 360 degree environment. You feel like you’re there. Line worker simulation walks you through what it’s like to replace a transformer. It helps you to experience what it’s really like in order for people to be better aware of the jobs available to them. Simulations include engineers, scientists, and healthcare workers. Transfer is, essentially, a Digital Coach. A classroom-to-career pathway was mentioned several times. Job placement and retention are the goal.
JD then speaks. NSF is addressing historically underfunded places. JD is program director for EPSCor, at NSF.
Where are we thinking at the federal level about building innovation ecosystems? How can we develop research capacity? Create opportunities to be able to participate in the stem research enterprise.
This is a place where ORI can participate, with professional development through open source work.
NSF strategic plan 2022-2026 described and highlighted.
1) enable STEM talent to fully participate. He is the son of a plumber and a hairdresser. He “shouldn’t be here”. But people took chances on him. He’s from New Zealand. Open up the opportunities for others like him. He lived here in Arkansas and his wife worked in schools in Mayflower.
2) We are the NSF. Make new science! Include everyone! Critical to our nation’s wellbeing.
3) What are the societal benefits of the work we’re doing? If we create knowledge for knowledge’s sake, and we don’t consider science and society, then we are not doing what we should be doing.
Bob Anderson, Structures of Mind <== book recommendation.
4) Where are we as a community? Reaction is a “sine curvy” amount of output. As a community, go into a creation mindset. Plan, predict, move as a group. As a jurisdiction, this will help you in many ways, only one of which is to increase the probability of success in obtaining grant money.
This is a great talk by a talented speaker who genuinely cares about the NSF’s mission.
Ecosystem approach, collaborate together, include, think about end-use.
NSF EPSCoR, stimulates competitive research. The program has a broad spectrum, from Guam to South Carolina. How can these states build and develop research capacity over time? Research Capacity – what is it? How can we define it? How does it connect to education? Industry? Economic development?
EPSCoR was established 1979. Where are we? Where are we going? Informed by a lot of feedback. “Envisioning the Future of EPSCoR”, 2M study, NSF Strategic Goals.
The jurisdictions under EPSCoR were introduced and explained.
Top four jurisdictions take 32% of all the money. Underserved jurisdictions are now a focus. EPSCoR is where it’s at in terms of diverse engagement. Key elements that lead to success in building research capacity were listed:
Resource Acquisition
Knowledge Production,
Attractiveness of Jurisdictions (this was not explained)
Visibility and Reputation
Economic Development
Building research capacity takes time.
It takes 3-10 years to just build a team.
Universities move at glacial pace. 10-20 years to build research capacity in any sense.
20-50 years within a jurisdiction, looking at the broader picture.
EPSCoR has been around for 40 years, and is just now seeing results.
This is very slow. How do we get this to happen now? Sooner?
Research ecosystem approach is the focus of the work today at the NSF.
E.g. Guam’s needs are very different from Arkansas, which are very different from Montana’s. Recognizing that each place has a distinct ecosystem is a necessary and fundamental step. NSF wants to enable the growth of the partnerships and push for the collaboration that will allow broad and deep development of research capacity.
Scalable and dynamic ecosystem structures are what we are after.
What does an ecosystem look like?
Multi-jurisdiction, multi-state efforts are something he highlighted repeatedly.
“Regional innovation engines” mentioned. This is a concept and program from the NSF. https://new.nsf.gov/funding/initiatives/regional-innovation-engines/about-nsf-engines
This is a large funded program and we heard a lot more about it during the rest of the conference. The way that Engines fit into Tech Hubs (which are from the EDA, or Economic Development Administration, in the Department of Commerce) was the subject of discussion during a breakout session.
Partnerships with industry, public/private, tribal, and other federal agencies all provide support. What does the ecosystem look like?
“Re-envision what Track 1 grants look like.” Results were presented. Two new solicitations have replaced the Track 1 solicitations. E-CORE NSF 23-587 and E-RISE NSF 23-588.
What does research capacity look like? It consisted of two levels, a fundamental level on the bottom that stimulates actual research competitiveness. It includes all sorts of infrastructure and administration. Therefore E-CORE.
So, design something around those core needs. At the same time, there are strengths within a jurisdiction that need to be specifically addressed. This is what E-RISE handles. This sounds like the customization required by that jurisdiction.
EPSCoR is 2.9% of the NSF budget. So, there’s much more to go after. For example, “NSF Funded”.
E-CORE connects ecosystem entities together. It will also be housed in a total process improvement cycle.
Track 1: 5 years, not renewed, one per jurisdiction.
E-CORE 4+4 years renewal, not limited to jurisdiction.
E-RISE: 4+3 years renewal, not limited to jurisdiction.
What does E-CORE look like? There is an Administrative Core, which connects individuals and makes it possible for them to fit. Connect them together. E-CORE provides a path. E-CORE entities are expected to know who is who at the zoo. Measurable progress in building research capacity is expected. Playing the connection role. The Jurisdictional Science and Technology Plan is a living document. Knowing your sphere of influence helps with connecting people. Steering committees allow a wider reach.
These are excellent plans from NSF. For many of us, doing this sort of work is a vocation. Connecting people to create and build research capacity is grossly under-appreciated. Build out the capacity with E-RISE. The reach might be a few folks, but the jurisdiction steering committee can reach farther.
Strengths and challenges identified. Modular Cores are listed. Including “Other”. There’s no way as a jurisdiction that you can tackle all of these at once. Build metrics and milestones to show what you’ve met. In the renewal phase you can identify where to go from there. Swap out these modular cores. Dynamism comes through as you progress forward. SNT plans are the way these are recorded.
Sustainable infrastructure. Question/Hypothesis driven. What does the jurisdiction really want? Research is at the top of the pyramid. It needs to be housed within time-bounded societal impact. Workforce development relevant to that particular J topic. These topics have to be translated to realtime stuff. Like what we do at Remote Lab South. Culture of inclusion. Everybody that wants to take part, can. This leads to renewal.
There’s a lot more to NSF than this. CHIPS and Science act is about, to him, broadening participation. By 2029 20% needs to go to EPSCoR jurisdictions. This is a 2x increase over today’s numbers, where it’s around 10%.
Where do you want to go as a jurisdiction? Ask hard questions. Where are you as a community? Be in the creation mindset.
NSF is a small part of this, but there are a lot of other divisions.
“Granted” program, and TIP. Technology, Innovation, Partnerships. <== both have been mentioned to ORI as something we should try for and be part of. TIP Director is scheduled to speak tomorrow.
TIP weaves things together.
There are different models of innovation represented by these different programmatic approaches. Pure Basic Research, Use-inspired basic research, Tinkering, and applied research.
The “Dynamic and Complementary STOKES Model” from 2005 was mentioned. It’s not a linear transition to the “Revised Dynamic Model”.
Regional innovation engines: Final merit review process for Type II. ArkLaMiss won one, $160 million “get the gang together” awards. “Connected health” and other things addressed by this grant.
“Connecting Communities” building bridges to use-inspired research and science-informed practices. For example, the people that are funded by USDA often don’t talk to the “odd” people that do cell biology, for example. Workshops to build bridges (above) was a program to connect communities that need to talk to each other but haven’t before. 900 participants were drawn from every state and every sector. Down-selection happened, and then they had a meeting at Boise State, developed a community that came out with 23 different initiatives, in order to move communities forward.
This is very new for these communities and is the sort of work that NSF would like to see more of.
Office of Integrated Activities: “Granted” program. Marta recommended us to look at this program. Reduces barriers in accessing resources to support competitive research and training programs and projects.
Think wide
Ecosystem approach
Collaborate together
Include
Think about end-use.
That’s why we do this at the end of the day. It’s for real people that we know and see in our communities.
1) Advancing the frontiers of research and innovation
2) Ensure accessibility
3) Be the best at what your do.
The guidance is to think as a jurisdictional ecosystem. NSF is trying to deliver the tools. EPSCoR is a federal state partnership that is working to support increasing research capacity.
Deb is back up on the stage and she thanks the speakers and explains that a networking session is next. We come back at 10:30.
IWRC2023: Breakout Session 10:30am Thursday “Advanced Energy & Critical Minerals”
Moderator: Becky Keogh, Arkansas Department of Finance and Administration
Panelists:
Lisa Perry, Walmart Energy Services
Will Smith, Standard Lithium
Dr. John Verboncoeur, Michigan State University
Dr. Branden Bough, National Nanotechnology Coordination Office
Moderator’s introduction.
There’s big federal money, combined with state and local resources. She’s been working with the governor’s cabinet, “taking them through a visioning process.” Looking for ways to create meaningful, sustainable investment. Public safety, education, infrastructure, clean energy, and other “stuff that will move us forward.” $7 billion has been announced for Arkansas already, with more pending. Mostly it has been transportation and broadband. There is a “hydrogen hub” initiative, with awards to be announced in October, a regional hub with Oklahoma and Louisiana. A “halo hub” in finger quotes. Hydrogen “based on electrolyzer technology”, domestically sourced, to deal with intermittency. For everything from long haul transportation to fork lifts, and to reduce emissions. Something about carbon sequestration on the Louisiana side, too.
Speaker introductions.
Lisa Perry is a senior manager in energy services for Walmart, dealing with regulatory and innovative technology programs. She has a bachelor’s degree in criminology and psychology, and became an attorney working in estate planning. She found that her engineer clients were more time consuming, because of their attention to detail and compulsion to understand everything.
Walmart has aggressive sustainability goals for their huge transportation fleet: 50% renewable energy by 2025, 100% renewable energy by 2035, and carbon-free (with no offsets) by 2040. They have the largest privately-owned fleet in the United States. Working with rooftop solar, energy storage, electrifying buildings (heating), and alternative fuels for delivery vehicles. They’ve installed 1200 public EV chargers at stores, but only as site host for third-party companies. They intend to add Walmart-owned chargers at thousands of stores. Scaling things up to Walmart scale is a big deal, with thousands of stores, and customer expectations of low prices.
Will Smith is the plant manager for Standard Lithium’s pilot plant (so far) in El Dorado, Arkansas. Standard Lithium is a Canadian company now, but plays to re-headquarter in El Dorado in the near future. At El Dorado they are working with Great Lake Chemical Corporation, which has been extracting bromine from underground saltwater (“brine”) for 60 years. They took a sample of the brine to Canada and figured out how to economically extract lithium from it. The formation containing lithium is huge, extending into Florida, Louisiana, Arkansas, and Texas. Oil and gas were extracted from the top of the foundation, and the brine was dumped into evaporation ponds as a waste product. Now, the brine is pumped up, the valuables extracted, and then pumped back into the formation, with no waste products. There is future potential to add carbon sequestration into this cycle. Standard Lithium has already purchased a 118 acre site near Magnolia for a second production plant.
The product (battery grade lithium carbonate) is a fine, white powder. They are careful to label it very clearly, lest it be mistaken for some other highly lucrative powders cooked up out in the desert.
Branden Brough is the director of the National Nanotechnology Coordination Office (NNCO), which is under the White House Office of Science and Technology Policy. In 2003 legislation was signed codifying the National Nanotechnology Initiative: every federal agency and department would make some contribution to nanotechnology. 20+ agencies are coordinated by NNCO. By nanotechnology they mean cutting edge science and technology, dealing with materials almost atom by atom. Mostly, that seems to be semiconductor fabrication. There are existing technology centers in Texas and other places, with more to come, maybe even in Arkansas.
John Verboncoeur is associate dean of research and graduate studies at Michigan State University. Michigan, he notes, is a manufacturing state much like Arkansas. He has a PhD in nuclear engineering from UC Berkeley. “I was told I can’t show my equations.”
He says there are 1.3 billion vehicles in the fleet that need to be converted to electric, but supply contracts for materials such as lithium only extend to about 2026, not enough to make a big dent in the job. In Arkansas natural gas is finally a bigger energy source than coal, within the last three years. Nuclear energy is also a big fraction, and renewable energy is a significant fraction. He’d prefer to lump together nuclear and renewable sources and call them green energy. There is work on biofuels, with the goal of making them good enough to use for jet fuel. He sees that non-thermal electron distribution is a key to higher efficiencies in chemical processes. He believes that component-driven optimization needs to yield to a more systems-level approach. For example, the electricity delivery grid is not able to adapt quickly enough for Arkansas to switch to fully electric vehicles, so hybrids might be better overall in the short term.
He sees a big problem with highly skilled workers aging out, but universities are not able to change their curricula to match industry needs rapidly: it takes a few years for all the administrative approvals, then five more years before the first graduates pop out. His proposed solution to this is a less math-intensive degree called “engineering technology”. He wants to funnel people who are either not interested in engineering because of the heavy math, or who are failing engineering, into this path, because, he says, there’s a bigger need for people who can fix things than for people who can design them. Supposedly this kind of degree could be rapidly approved under an umbrella program and then pop out graduates in just two years. (It was not quite possible to hear the Arkansans’ eyes rolling; they’ve had engineering technology degrees for decades.)
All those speaker introductions took up a lot of time. There was some time left for Q&A.
Q & A
Q: What are the barriers to electrification of vehicles?
Walmart and JB Hunt have enormous fleets, spanning many different kinds of trucks. The same emissions-reduction technologies won’t work for all classes of truck.
Rural areas are a big challenge for the EV charging network.
For commercial trucking, you’d like to build big charging centers at strategic locations, which are likely to be in rural areas. However, the grid providers have major logistical challenges in supporting concentrated loads like that. It takes them 18 months just to source a new transformer, for instance.
Q: Does the difficulty of extracting lithium cleanly impact the rollout of electric vehicles?
Absolutely. Today, electric vehicles are backordered. You can’t just go into a dealership and buy one. The supply chain is simply not there yet.
There are presently 136 publicly-traded lithium extraction companies (versus 35 for copper), but almost every company is still in the test-tube phase. Standard Lithium is the only company with a full demonstration plant, which is a necessary step between the lab and production plant. Theirs is fully automated and produces lithium, with process improvements being worked on all the time.
For many extraction processes, water pollution is a big concern. Some of those 136 companies claim to be nearly ready to go, but they don’t have water use permits and might not be able to qualify for them. Some are also on hilltops with no feasible plan to get electric power to the site.
Smith believes that in places like Arkansas, extraction companies have a sort of “social license” that’s unavailable in other areas. He means that people here are more comfortable with the idea and willing to accept more industrialization.
Standard Lithium does have difficulty hiring workers. They already have to hire workers and train them afterwards.
Standard Lithium welcomes all the competition; there’s plenty of demand to go around. They compute that if all goes well for their new plants, in the 2026-2027 time frame they will only able to supply 10% of the projected demand … from JUST ONE of their customers.
Q: Are there other critical minerals?
Yes. There are other battery chemistries and architectures besides lithium ion, suitable for other use cases. Engineers need to think about end use cases! Maybe sulfur or solid-state batteries, biofuels, or hydrogen. There is no one critical element; we need to use everything. “We need more darts to throw at our dartboard.”
Arkansas has one of the lowest energy rates in the country. New solutions need to be low-cost, too.
John also serves on the IEEE nanotechnology council. They are looking for alternative materials to replace expensive rare earths.
John (nuclear engineer) reminds us that fusion power is 50 years away (and has been for a long time). He says that applies to big tokamak-style reactors. The capital costs of such reactors may be permanently out of reach for commercial deployment. He thinks smaller classes of reactors are more likely to be commercially viable. Modular fission reactors can be built in factories, instead of custom-built on site, at a savings of 2x to 10x.
There is some commercial investment in fusion already, but it’s high risk venture capital. Recently the news reported that the National Ignition Facility achieved what’s called “scientific break-even”, where the amount of energy generated exceeds the energy fed into the reactor itself. But that’s maybe 1/50th of the total energy consumed, so we’re still a long way from a practical fusion reactor. And neutrons are still a problem. But there are alternate fusion pathways that are inherently neutron-free. John thinks smaller fusion reactors are possible. Maybe even small enough to power a vehicle. (Nobody actually said the words “Mr. Fusion” loud enough for me to hear).
In the brief open-mic Q&A, a participant begged Standard Lithium to consider extracting other valuable elements from the brine. Sodium, for example.
And then it was time for “networking lunch”.
IWRC2023 Breakout Session: “Education and Workforce Panel”
Brittney Hilliard, works with Jennifer Fowler at AEDC.
Dr. Tina Moore, Arkansas Department of Higher Educatio, and workforce development activist, is our panel moderator.
CHIPS act is the primary focus of the conference, but we are also discussing adjacent funding and activities, such as the Infrastructure Act with 700,000 jobs and Broadband Expansion and Access Deployment Program. 23,000 jobs in telecom and 800,000 jobs overall. The Inflation Reduction Act was also another infrastructure development act.
There is a declining workforce situation, according to the moderator. The age and type of workforce we need, really needs support.
LEARNS Act – what does the R stand for? Career Readiness. The executive order and the act is about readiness. Apprenticeship, recognized credentials while in high school, etc.
8 minutes in and we begin introductions of the panelists. This is done quickly and well.
Q: We often speak of H3 (High Wage, High Skill, High Demand) jobs, but it’s not actually well defined or quantified. Let’s focus on highly skilled jobs. What are the relevant credentials or skills for your specific focus area?
A: Amy Elrond from Acxiom: it is a customer intelligence company. Understand your company’s customers better. We use data and technology therefore CS BS, data science, cyber security, those sorts of things. Degrees. Certifications are a huge focus right now. Development of the current workforce with respect to carts is a big deal. AWS, GCP, Snowflake, as well as cloud partners that are specific to a use case. Like Salesforce. Huge company and we have lots of different ways we interact with them. Training is often industry specific, but cloud certs are a big deal right now.
Q: Audience: cloud certs are they internal or are you working with outside certificate authorities? What is the metric for validity?
A: Acxiom: Certifications are proctored and administered through orgs that do those types of things. Outside bodies and third party content providers like A-Cloud guru and O’Reilly. This is designed to help associates educate themselves on these cloud platforms. And we have an on-staff technical trainer. He works with the associates to help them understand what they should study. We do look for certifications when we hire people.
A: Lonnie Emard from Arkansas Center for Data Sciences says that they set up apprenticeships and are trying to define career paths and look for standardization across the industry. As opposed to any one company’s requirements. Finding ways to get the most efficient way to increase research capacity. Individual company vs. a big picture view.
A: Educational Part (Dr. Suzan Anwar from Philander Smith University) from the point of view of the University, requirements are what is at stake and is centered. Learning how to learn new technologies. Skill gaps are addressed by educators in two ways. Vocational tech approach or a learn how to learn approach. Internships do help. Students go out and apply curriculum to the practical arts. This is from a computer science perspective. Education and Workforce development is crucial.
A: Dr. Argelia Lorene from Arkansas State University: thanks JD Swanson and EPSCoR for empowering good science at a scale that hasn’t been able to be done before. (I’m a big fan of Argelia’s work and was hoping to hear from her). Greenhouses in the field to test large collections of rice varieties that are more resistant to heat stress. The way this relates to workforce development is that the thing that made this project possible was a large vertical accessibility, starting by including high school students and letting them stay involved and active until graduation from University. This long relationship with a large project teaches people things that a classroom cannot. Power skills, not soft skills, are being developed here.
A: Acxiom: don’t lose sight of the fact that we need technical education, but we have to have the education that Argelia is talking about – emotional intelligence, empathy, science and society, tough conversations that you don’t want to have but have to have forthrightly, these are the things that are taught by a different type of educational structure, the sort that we want to see more of.
Q: As we talk about workforce gaps, like the “skills gap”, what are the biggest workforce challenges that you have?
A: Lonnie: with respect to apprenticeships, is invited to address this question first. The moderator is a proud parent to a plumber, and apprenticeship is a huge win. There’s so much more to apprenticeships.
We heard an excellent talk about this at Comic-Con with respect to artist apprenticeships. The presentation was by Cutter Hays, and was in the program here: https://comiccon2023.sched.com/event/1OXXb/old-school-apprenticeships-today
There is a lot of synergy between these two efforts, with the presenters saying things that aligned and reinforced each other.
A: Lonnie says that they learned very quickly that they had to grow their own. Apprenticeships in non-traditional pathways. People sitting in claims processing with music degrees became software developers. Sitting side by side with the Georgia Tech graduates. “How can we do this?” With an end-to-end process, degree or not, to close the capacity gap and fill all up and down the levels. Apprenticeship is the epitome of workforce and education coming together. This is the proof of how it works. Plumber, IT software, electrician, developer – doesn’t matter, apprenticeship works. That training in the classroom coupled with on the job training with a mentor – all of a sudden that learning is rich and applied immediately. 127 employers now use this. 630 apprentices in the last 3 years. Leads the country in IT apprenticeship. CHIPS act, how it can help. If we can do this for IT, then we can do this for the workforce development asked for from CHIPS.
Collaborative ecosystem. Apprenticeships are quite often skipped over. Apprenticeships from ACDS are a strategy, not a flavor of the month. Yes, you have to go to campus, hire people through traditional college output, sure, but this is not enough people. There are not enough graduates to meet the need.
Q: audience: I am running a startup doing biotech. Can’t find employees. Pure skill is lacking. We need clinical lab skills, but can’t afford to pay an intern.
A: Lonnie: your question isn’t new. They don’t all have the same circumstances. There’s an economic value. Apprenticeships and internships are not the same. Very different. Apprenticeship is a commitment from the employer. Internships really only help the student. Investment is made in the apprentice. We’ve been able to get a $2000 per apprentice tax credit here in AR, and maybe that will help you. Short term? Apprenticeship might work if you catch someone moving around in their career. Rob Peter to pay Paul but it’s not capacity building to snipe or poach skilled people from other companies. Where is the next career changer? We can backfill from a pipeline of talent from all levels. Use the apprenticeship model and don’t settle for something less. They’re not a perfect fit (apprentices) but the upside is tremendous.
E.g. The moderator gave an example of a cybersecurity person with an MBA, and who was apprenticed to a bank that needed security. They already understood banking, and were learning cybersecurity.
A: comment from the audience: Office of Skills Development and Arkansas Economic Development might be able to help this startup. AEDC may be able to provide funding. Lonnie reiterates the same message.
Support for professional development is from the Office of Skills Development.
Internships from Universities for the summer are important. When they put people in front of an employer, and they have a certification, they may not have any practical experience.
A: Dr. Anwar: co-design courses based on what students need to learn. Can partner with the schools in order to get the student ready upon graduation. Blue Cross Blue Shield partnerships and on the advisory board for CS.
A: Argelia: later today in another panel Air Force IP talk will touch on some of this. Biotech graduates are actually available so get in touch. Real life example of how we interact with partners. Using NSF EPSCoR we acquired specialized equipment that lets us quantify something in particular very quickly. We were the first university to get this online. 12 years later, since we were first, Google X is doing plant science and they chose our lab. Research contract with Google X and now undergrads are gaining skills and being offered internships there. There’s a lot of talent in AR and there’s a lot of talent that can come here if the conditions are good. That’s why I am here. I love science and research and is all in. Thank you for this conference and it’s energizing to learn from other fields.
Q: Question for Amy (Acxiom): how do you partner with education?
A: Amy: we partner a lot with higher ed, but programs like “Girls of Promise” are ways we are lowering the ages of these partnerships. We are actively seeking internships for students. Sometimes this results in a full time offer. Having people on boards that serve on institutions is something that helps increase the vascularity of the connected educational places with companies like Acxiom. People that haven’t traditionally pursued a STEM pathway, let’s make it more inclusive to anyone that wants to participate. Let’s break down the barriers that have grown up. We fund a scholarship for underrepresented groups for a $5000 award. We have done a little bit to get earlier in the pipeline, called Hip Hop Express. Turns out it was a bus and traveled to the Girls and Boys Club, come on to the bus, and learn the science behind music engineering, using hip hop. It’s hard to be what you don’t see. If there aren’t people that look like you then it’s hard to imagine that pathway. A culture of inclusion – anyone that wants to participate, can be, because of a practice of radical inclusion.
Q: Rodney Block was cited by the introducer. Music is math. To this point, Jennifer Fowler says it seems like we should be starting earlier. We don’t do a great job of showcasing everything that a STEM career might include or look like. Industrial engineering, for example. It’s more about there are ways to look for meeting the students where they are, and showing them all the elements present in the world of STEM. Students often say “I just can’t do math” but they really can, and they get turned off by middle school. You have to be earlier than middle school and how do we pull this off? The Innovation Hub twice a year has activities that promote girls specifically.
Empowering girls in cyber and technology. Bringing everyone together is the goal. So many adults care and want to help and want to share and show what is going on. Especially when they see someone that looks like them. Dr. Reina “what does it look like when you’re in a research lab” program cited by moderator. Moderator comes from a low education family, whose father didn’t graduate high school. She stumbled in the dark and managed to get up and out of it on her own. How much better a job we can do if we all help each other achieve a lot more.
Q: Audience: we don’t lack in ways to produce engineers. We lack true workforce development. I need wire bonders, people that can fix the machines, not IT! We don’t have maintenance and fixers and doers and technicians.
(Please see previous comments about the Innovation Hub. If it was run in the way it was originally envisioned and deployed, then it would help directly address this need in an energetic manner)
We have a lot of people with book learning (maybe not a lot, honestly) and we have lots of entitled managers with turf issues. We need more real workers. We need practical skills in the labor force.
A: Lonnie: maintenance repair and technical jobs are a targeted space for registered apprenticeships.
A: Argelia: science communication is important and not happening to the level it needs to be happening.
Q: We have enough BS degrees. But they are not in the right things. We are woefully behind in mid-skills people. High School grads are not going to get good jobs.
A: audience: How do we get the word out to the students? We have no way to connect students with good apprenticeships and opportunities? Can we reignite closed schools? Technical schools closing down?
A: Lonnie: supply side vs. consumer side problems. End to end apprenticeships have an applicant tracking system, collective tracking. 16,000 applications received. Lots of stories that have been built over 3.5 years over “what could be possible”. Trying to find ways to market this. Mike Rogers as the state workforce chief is trying to unify a system to help address this at ACDS. How is this going to get marketed? Hodgepodge but mostly old school channels through municipalities. Match made in Arkansas is a catchphrase from this apprenticeship program. Employers are one side of the chasm with a job requirement and they expect a bunch of people to meet this overconstrained position. Then there are a lot of people looking across the chasm wanting to participate and not knowing how.
A: Dr. Anwar: shares a story about working with UALR on something about cyber, and they brought in middle and high schoolers to teach them security and she was teaching through Escape Rooms. Middle schoolers started investigating, and at the end accessed the data center. Several students said they wanted to be a technician. “I want to be the person that goes to the data center and fixes things.” They really liked it and it clicked with them. If they get involved with these types of activities like during the summer workshops or camps, they will really like it and it makes a positive difference.
A: Argelia: making our students, no matter their age, that they need to be perpetual learners, this is what makes life exciting.
Q: moderator: 22 two-year public colleges in the state. The driving distances shouldn’t be bad. Even in the Delta. You do not have to go to a two-year college to pursue a degree. And there’s shorter term training. Like, broadband and fiber academies, to certify people in technicians. $50,000 a year jobs.
Q: US Steel audience member brought challenges: We are 5 minutes from MO, 30 minutes from TN, which means other states pull talent away. We have jobs that pay over $100,000. It’s one of the biggest and poorest counties. We have a vast amount of resources in the two-year colleges, but marketing opportunities? He’s been there 27 years, but one can drive 30 minutes in any direction and people have never heard of his company!
A: Comment, audience: Got to get inside schools. FFA used to come to schools with the cool jackets and make impressions. We have to be very intentional and very non-traditional. Reaching the population at risk, felons, females, veterans, and the forgotten. We have a job ahead of us. We’re better positioned now than we ever have been. Market like you have never marketed before. Reach the people!
Steel industry faces challenges from the economy around them. They can’t improve the schools and the economy unless we can employ AR, and not MO and TN people.
NWTI program mentioned twice. Representation in welding, trucking, etc.
Q: moderator: retention of top talent can be a challenge. Our brilliant and most brightest may leave the state. How do we keep these people here? (This was going to be my question)
A: Argelia: people that have started their own companies instead of leaving have been a big step forward. Creating an inclusive environment is extremely important. She can share a personal story about living in Jonesboro.
A: Dr. Anwar: if they don’t see arms opening for them, they will leave. We have to create a conducive environment. Multi-pronged approach necessary.
A: Amy Acxiom: twofold – first, companies have to create an environment that makes people want to stay. Continuous learning and development opportunities. Connect and identify or ally communities.
IWRC2023 Plenary Panel
Kathy Hyashi (K) moderating. Deb introduces her. They’ve known each other for many years.
K introduces herself. Amazing discussions so far, and more to come. Region 6 director. Largest non-profit for technologists in the world. Co-chair of future directions for semiconductors (global). Informing and engaging and supporting them for all the initiatives around the world, including the CHIPS act.
Introduces the panel at 7 minutes. How it is going to impact the regional areas.
Dr. Hugh Churchill U of A (Dr. H): confession – not an engineer, but a physicist. A sheep in wolf’s clothing. He is involved with MonArk Quantum Foundry https://www.monarkfoundry.org There was some sort of delay with his microphone and he had to repeat his introduction. He said “The joke would have been much more funnier if you all had heard it” and the audience appreciated his sense of humor.
The MonArk Foundry uses robots and AI to dramatically accelerate quantum material device development. Many other institutions are involved. Revolutionary technologies for quantum computing and sensors. He explains two pipelines for this quantum foundry. Crystal in, package out. 2d crystals? Automation and AI means we’ll be a service to broad collaboration. World leading source of 2d semiconductors. UAF has two other strong pillars of excellence. Allen Mantouth silicon carbide facility in Fayetteville. First low volume open access site in the country. Applications include night vision and other integrated photonics. Their efforts allowed us to put together a proposal to DoD commons solicitation involving 20 states that could push beyond silicon semiconductors for future commercial development of technologies. This involves startups and big iron companies. Specific to our state, rather than small aircraft or soybeans, the most impactful export we have is people. Hundreds of AR working in leadership positions are all over the place. Lots of AR people leave. Imperative that we create opportunities for these people so they do not leave. Companies that exploit the things brought about by the innovations, too – these are super important for retention.
Q: K: give me one word to describe the chips act?
A: Insufficient
Q: K: next, let’s have John Hardin from NC Department of Commerce speaking. He is a political scientist by training. This is a very difficult science. The subject matter changes and knows it’s being studied. Discord and social media have changed things. He dIdn’t want to be a full time academic. Wanted to do applied work. UNC has 16 UNC institutions that allow for this sort of work that he wanted to do. After working there for 7 years, moved to the department of commerce in tech-based economic development. 1) he joined the advisory board (the oldest science technology and innovation board in the country, established 1963, quietly responsible for most of the science and technology advancements and programs in the state of NC, and the politicians take the credit), and 2) runs grant programs, the most important of which is a matching grant program for small businesses in the state that have received SBIRs and STTRs. Those programs go directly from 11 different federal agencies to the company, but it’s often insufficient. Therefore, NC has a matching program and he thinks AR does too. The work is policy, programs, tactics. CHIPS act is a big deal in NC and mobilizing business, communities, and non-profits is his focus. Take advantage of the CHIPS act as much as possible.
Q: K: Give me one word to describe the CHIPS act?
A: Opportunity
Q: K: April Campbell US Economic Development Administration. Been with EDA 30 years, and worked in state government before that. Community development is a focus. Feel a bit out of her realm being here with scientists, but when she talks about tech hubs, she gets a lot of traction because she knows how to help bring them about and support them. EDA got $10 billion to create these regional innovation and technology hubs. Infrastructure for manufacturing, and a little bit of R&D and a little bit of workforce development. Cities, counties, universities, and some non-profits are involved. Business and marketing, all coming together to make good things happen. EDA is very excited about the opportunity to be involved.
Q: K: Give me one word to describe the CHIPS act?
A: Growth
Q: K: Dr. Craig Scott with NIST advanced manufacturing program. He is from Morgan State University HBCU in Baltimore MD, and has done everything one could do as a professor there. He went to NIST on sabbatical to work with the office of advanced manufacturing. At these two-ish offices he’s been involved with at NIST, he’s done work for CHIPS and “Manufacturing USA” program. MUSA is a public private partnership (involving 17 institutions) which helps bring innovation about. Product realization. Two parts to it, MUSA and M extension program, that works for smaller companies. Within 17 institutions there are 2500 members and they collaborate on 670 projects. 106,000 people trained. A large number of dollars invested. HBCU are historically black colleges or universities. These schools were established prior to the Civil rights Act in 1964 and serve Black students. There’s 101 in the US. They are 3% of the accredited institutions, producing 30% of the STEM graduates in this country. There are 4 HBCU in AR. People do not understand HBCUs and how important they are to the economy. His primary responsibility was to develop better relationships with HBCUs.
Q: K: Give me one word to describe the CHIPS act?
A: Unprecedented
Q: K: Knowing the strengths? AR and other regions have been looking at the strengths they have and what opportunities might exist to leverage these strengths in the CHIPS act. CHIPS act specifically – what is the most impactful to your regions? In terms of programs, technology, technology transfer, workforce development?
A: April: Tech hubs portion of it for us is the biggest, $10 billion is a lot of money for us to help develop. 5 states, HQ in Austin. Yearly budget is $40 million, but a $10 billion infusion is enormous. Workforce centers, rail lines, sewers are what we do. 10 billion coming into the region is a landmark enormous event. High hopes for AR – there’s 6 or 7 applications to be recognized as a tech hub. Build Back Better was a regional program focused on economic development. AR received zero money from that, and all other surrounding states did receive funding so maybe this tech hub thing can counterbalance that disparity
A: Craig Scott thinks the largest impact will be from the workforce part of it. All of the components of the CHIPS act have a workforce component in it. Technology innovation and industry and workforce to respond to it – getting the people trained and the right credentialing system in place is important.
A: John Hardin says that his department of Commerce has a lot going on with CHIPS but it hasn’t hit NC yet at all. The office of science technology and innovation didn’t focus on this, though. His office deals with small business and universities. The biggest opportunities in the short run has been the regional tech hubs program. The most impactful for his purposes: NC technology strengths are concentrated all in the research triangle area. Three R1 universities and an airport and a tech hub have emerged over decades. Outside of that? Not as strong. His board produces “Tracking Innovation” metrics from across the state, and does a comparison to other states. As a state they rank 20th, but if you look only at RTP, it’s in the top 5. We have been trying to push out into the other parts of the state and it’s not worked so far. They have not had a lot of success. It takes a lot of time and money and sustained leadership (this is key). It just hasn’t had this going on long enough or effectively enough. The tech hub program is going to help with this to bolster up other regions in the state. There have been 6-7 tech hub applications.
Q: K:Considering your proposals, who took the first step? Who started the initiatives?
A: John Hardin: this was a bottom up effort. Consortium in NC was formed organically. His advice: “Just make sure you’re not cannibalizing each other.” Work together and partner together to make things go faster. Top down in the sense that the applications were coordinated. Mainly from universities.
A: April: similar in AR, universities, two HBCUs maybe three, in other parts of the state it was economic development people involved. Regionalism, collaboration, encouraged and fostered.
Q: K: As part of the CHIPS act, we need to make sure that this is a catalyst for private investment and incentivizing collaboration. Not easy asks. What are the biggest hurdles?
A: Dr. Hugh: Spurring conversations that were not happening before. Big challenge is if you think about taking something from concept to commercial product, in my lab the starting point is a rock. We turn the rock into a device. Huge gulf between the end point and the starting point that is acceptable to a company. Bridging that gap is an important thing to address in this context.
A: Craig: when you talk about collaboration especially at this scale, and trust is a key aspect. Hard to think about because you have a bunch of competitors. You have to trust them enough to communicate and collaborate to lift all the boats. There is enough for everybody.
How can you develop something like a uniform credentialing system? It requires honesty. E.g. cybersecurity, solved it by using a device framework. Sitting down together and trusting each other. This leveled the playing field for a lot of people.
A: John Hardin: Another burden or hurdle is culture. Regional tech hubs formed a consortium and EDA had five required components: These organizations must be part, all components must be represented, and these all must play their part. This list leads to some diversity in the types of organizations represented. Each has a different culture. No culture is better than the other but they are all different. Overcoming those differences is not easy. Money certainly helps, and CHIPS will bring money. People will minimize their differences if they can get more money, but in order to create good work, trust has to come along as well, and collaboration and bridges between cultures is required.
A: April: rural areas are frequently left behind. CHIPS act meant that they could trust they were going to get a seat at the table, and they indeed got a seat at the table, and this trust was reinforced.
Q: K: Dr. Hugh, tell us about the impact of quantum tech?
A: Hugh: not going to happen fast enough to have an impact here, with the CHIPS act. There is one outcome of current efforts in quantum, where silicon can win again. It may be the material of choice for quantum computing too.
A: Craig: Going back and re-examining relationships with the underserved groups, and making sure that policy allows for a global participation by people from other countries. In the middle, there is this large group of people “is everyone that wants to be at the table, at the table?” When we look at this, there are effective ways to be able to communicate. There’s things going on that people need to know about and do not know about. No one is going to go out and send someone to 101 HBCUs to let them know of opportunities. Funding for people to participate in training exercises. Not just academic, but credentials. How do people get to school? How do we deal with complex family situations? It’s not just the trainee, but the faculty may need these too. The faculty may be teaching a ton of courses and need to train to be more relevant and keep up. Success level needs to increase.
A: April: Our greatest export is people. We can talk about steel or rice or whatever it is at the moment, but when the best people leave, this is a huge issue. If these investments can keep some of the best people here, then we can begin to get more traction.
A: John Hardin: Research Triangle Park was designed on purpose. Unrelated private land was all brought together to build the park. The reason it was built was to help prevent brain drain out of NC. We had strong universities but we didn’t have the jobs that these university graduates wanted. 1950s it was textiles, tobacco, and furniture. They were beginning to fade out. They had to do something to create jobs for people to take. Otherwise the people were going to leave. If there are no opportunities then the people will leave. CHIPS act may do the same thing for more places.
Q: Audience: Jennifer Fowler (insufficient or collaboration) asks 1) for John, states matching funds for SBIR STTR, how big is the fund? Ours is very small. And only SBIR. How is it filled? A: 2005 established, 36 million over this time, all comes from state appropriations, non-recurring, had to go back every year and make the case. The most it’s ever been funded was $5 million least was $700,000. Forces outside of our control mean different amounts of money were available. Maximize everything we could do, statutorily, then we’d need $24 million to meet all demand, but the legislature is at a stalemate so we don’t know how much we’ll get this year. They get $2 million recurring now. 2) Dr. Scott, you told us a little bit more about your fellowship focused on partnerships, HBCUs over performing with insufficient resources, what are some hallmarks of successful partnerships that. you wish could be replicated in other places?
A: Craig Scott: helping bridge better partnerships: when you look at your steering committees, what are the representations of those boards? Do they really represent underrepresented people? In your planning for workforce development, it is very important when you do your strategic planning, including your DEI goals from the beginning. It’s not an afterthought. American Semiconductor Academy e.g. started before CHIPS. It’s going to get passed one day so let’s start now. Reach out early and don’t wait until the solicitation is due. Start beforehand and put the work in. He thinks there will be a round two of CHIPS. I’m not so sure, but it would be good. Be ready beforehand. ASA reached out to everyone, all the R1s and the HBCUs. What is it that we can do to make you feel more included? Representation on steering and boards is mentioned again.
Q: Becky Taylor from Austin technology incubator, lots of startups, semiconductor related (confusion is her one word to represent CHIPS act) Sounds good, but no idea how to engage. Have any of your orgs given any thought to try to integrate the startup community?
A: John Hardin agrees with the term confusion. Very hard to plug into the CHIPS act. Not intentionally designed to be hard to engage, but you almost had to be a large organization to get any traction. Tech hubs consortia can plug in the startups, but this depends on existing relationships and this is too cozy to compliment.
A: April: it is an issue and I thank you for bringing this up. There are some consortiums that have some luck with startup involvement but overall it’s a missing piece without a good answer at this time.
A: Dr. Hugh: AI, 5G, 6G, Quantum, electronic warfare, the way this program will operate, startups can collaborate with universities and such on proposals, to pursue technologies through hubs. The consortiums are not set in stone, either.
A: Craig: There’s funding for three additional institutions through MUSA and there is space for small and medium sized startups.
A: John Hardin: applications that were due August 15th were phase 1 (not sure of the technologies) strategy development grant, tech hubs, etc. Phase 2 stuff is larger and those opportunities are more likely to be realized if it’s acknowledged that it’s been confusing. (Not sure I follow what he’s trying to say).
A: Becky Taylor: we don’t have grant writers or people on staff to follow some websites. Not unique to this particular act. This is a problem across the board with respect to funding and NSF activity etc.
Q: John from Michigan State University and IEEE (one word is future) question is: how do you actually make semiconductors? About 70% is dry processes. We have to consider building this capacity and thinking about new materials is how we are actually going to lay out stuff and mass produce it economically. We have to understand the processes and those are mass production things. Now at the 2 nm scale. There’s big industries producing it, but they’re focused on existing technologies. Space electronics probably need to mitigate radiation. This hasn’t been brought into the conversation yet. What do people need to know to operate these machines? What are we doing to address this?
A: Craig Scott: This is a serious consideration in the office. Low volume manufacturing with a high mix of technologies. Intel etc. all probably not going to do that. Hopes for new institutes through MUSA… nothing firm here though. He doesn’t know.
A: Dr. Hugh: That’s why my answer was “insufficient”. We gave up on this for 25 years or more and the starting point with low volume facilities is just not going to cut it. It’s going to take so much longer to build this back and the CHIPS act is not going to close this gap magically in a couple years. These are US driven and US IP. We do actually own this and we need to re-establish the middle pieces. Firmly, and well. Who has access to it? Small companies need these proving grounds for their work. Collaboration might help here.
A: Kathy: Packaging and other areas, and chiplets, these things can make workable parts faster. Prototypes turning into reality, trust, collaboration, and system on chips – being able to package together multiple functionalities across all factors, is going to be required. We are asking for very big leaps on some of these innovations.
Q: Walter from Power Electronics says most states aren’t going to get a foundry in their backyard. We have like 3 million people in Arkansas. What areas are other states our size focused on?
A: John Hardin: NC has 10 million people. We do have the potential for a foundry. That part of the CHIPS act, the semiconductor part, is something we are going after pretty hard. The regional tech hubs – we are going after this. None of the other categories are semiconductor related. We’re strong there already so the CHIPS act is more about building up the non-semiconductor.
Q: April: OK and NM there is not a lot of interest. LA is going after some pretty hard, so is TX. LA is sort of like AR and there’s a lot going on there for funding in the tech hub designation. Not seen a lot of that from OK and NM.
A: John Hardin: South Carolina has about 3 million people and they had a single application, came together around Advanced Energy, and applied for a tech hub.
IWRC2023 Breakout Session 3pm Thursday “Innovation & Intellectual Property”
Moderator: Becky Taylor, Austin Technology Incubator, interim director
Panelists:
Neil Merrett, Air Force Research Lab
Matt Schanz, Frost Brown Todd LLP
Luna Acosta, Arkansas State University
Weston Waldo, Austin Technology Incubator
Moderator’s introduction.
Suppose you’re a researcher at a university and you’ve come up with something patentable. You face a decision: am I content to sit back and collect occasional royalty checks, or do I go start my own company and try to turn the invention into a big pile of money?
Q: Please introduce yourself, and say at what point you think an inventor should start to think about getting patent protection and what should they do about it?
Matt Schanz is an attorney working in the field of patent, trademark, and intellectual property law for a big law firm. He says to start thinking pretty early. A patent itself doesn’t generate revenue; it’s all expenses. Think about how the invention can be used to actually make something. Often, that means collaboration with other people and companies with different areas of expertise. For example, he knows of a case where an inventor worked with someone expert in the relevant industry, and they were able to find companies to license the invention at mutually-acceptable rates. The inventor was able to just sit back and cash the royalty checks. This is great, right?
Neil Merrett is at the Air Force Research Laboratory, physicist from Alabama. After grad school he worked with a startup in semiconductors. At the Air Force Research Laboratory, he often works with businesses through SBIR and STTR grants. University professors often start their own small business just to interact with SBIR programs, and that’s good. The military actually wants you to commercialize your product, so they can buy it. In most cases, military needs are not enough to sustain a product on the market.
Neil says the inventor should start thinking about patents very early. But they shouldn’t publish too soon, that might cause problems for the patent! Consult with a patent attorney. Consider whether the invention might be better treated as a trade secret instead of patented.
Luna Acosta is Director of Technology Transfer at Arkansas State University, and Director of the Catalyst Innovation Center at the Arkansas Biosciences Institute. She takes a holistic view of the four phases of the “innovation life cycle”: ideation, protection, development, and commercialization. The purpose is to get the next generation of things out into the world. In the United States, our culture of innovation, propelled by universities and companies, is why we are the number one economy in the world. “Talk to me BEFORE you have an invention.”
Weston Waldo is the director and program manager at the Austin Technology Incubator at the University of Texas at Austin, and the NSF I-Corps Southwest Region Hubs program.
Weston says the inventor should ask whether they have a business that’s worth pursuing around their innovation. Begin thinking about patent protection at the earliest stage possible.
Q: What about issues of trust when adding outsiders to the innovation team?
Matt says trust is critical. Build and maintain relationships for the long term.
Neil suggests getting a non-disclosure agreement (NDA) in place before discussing the innovation with anyone. He says “this helps to build trust.” Federal employees are not allowed to sign an NDA, but they are also not allowed to disclose your confidential information without your permission.
Becky interjects that you need to develop the confidence to describe your work in a non-confidential way, because some people (startups?) can’t sign an NDA either.
Luna says to tell her your dreams (such as publishing early) and we can find a way to make it work. Also: “I have templates!” Work with your technology transfer people. Companies can often offer other ways to collaborate that might suit you well. After all, if the company doesn’t grow or there are no royalties, that’s not good!
Weston says the higher the degree of trust, the faster you can move. You might worry that you don’t deserve a seat at the table (with smart technology transfer people) but you shouldn’t. Find out about who is good to work with (or not) by word of mouth recommendations.
Q: So you’re a researcher, and you’ve already disclosed your invention to your university, and you decide that you want to form a startup to use the invention. Now what? Should you incorporate? Should you get all your grad students to sign employment agreements?
Matt says you should look for collaborators.
Luna says, “Yay startups!”. We (the technology transfer people) will take you even if it’s later rather than sooner. You can’t do it by yourself.
Q: What if you’re a business person? You find out about an invention and you want to license it.
Weston says universities have way more good ideas than people who can turn an idea into a business. At UT we have a web site that lists all the IP that’s available for licensing, with non-confidential summaries. You may find one there that matches your expertise and can help your business or help you make a new one.
Luna says, “We like sponsored research.” Come to us and propose sponsored research. Also note that inventorship is a thing, different from authorship.
Matt agrees, inventorship and academic authorship are different. Consult a patent attorney. We know where things can go wrong. That might be our most important skill.
Becky suggests that if you’re a business and you need good ideas in your subject area, but don’t know what specific ideas you might need, consider attending conferences on that subject. Say, IEEE conferences, or events at your local university.
Q: Technology transfer is hard. There are always three parties: a business, an inventor, and their university. Which order?
Luna says it’s chicken-and-egg. The technology transfer people just want the inventions to get out into the world.
Matt says that revenue is important, but it’s not the only thing. Know what you want to get out of your invention. Maybe academic publication is more important to you than revenue maximization.
Luna says it’s a long term relationship. You might not see payout anytime soon. Think of it as a marriage.
Weston says that if the faculty member and their students go off to form a company, they end up in a whole different kind of negotiation with the university.
Q: The process is all wrapped up in human nature and human behavior. Among the multiple players in the university situation, everybody has some feeling of ownership of the innovation. Can you describe a scenario where feelings of ownership led to conflict?
Weston says that if you don’t know the ropes, you can get into catastrophic failure scenarios. Know what you want. A cookie-cutter approach might not work for every situation. Think about what’s fair, and what success would look like, to avoid catastrophe.
Neil says tension can arise in the distinction between inventorship and authorship. As a surprising example, a patent can even be invalidated if it’s found that there’s a named inventor on the patent who wasn’t actually involved in creating the invention. Negotiate with your team members and make a (legal) agreement about how you’re going to allocate inventorship and royalties on any patents that may arise.
Luna points out that if you’re faculty at a university or an employee at a company, you may well already be under contract concerning rights to your inventions. Know and understand what you’ve already agreed to.
Matt describes a situation where a patent was licensed from Purdue. The details were worked out, and the technology was licensed to appropriate vertically-integrated businesses. This has led to success in some areas, and hope exists for success in others. They were able to apply the basic technology in a variety of production spaces.
Luna says it has only been 20 years since the founding of the Biosciences Center. That’s early days in that field. One case is looking successful, but money isn’t pouring in yet. Just creating some startups that have survived so far is a success.
Q: When should you get a patent and when should you rely on trade secret protection?
Panel: You need to have the implementation details worked out (if not actually tested) before you can get a patent. You need to be able to detect if a product uses your invention before you can claim patent infringement. And, you need to have the resources to litigate to enforce your patent. If you can’t meet all these needs, maybe trade secret would be better. As always, consult an IP attorney.
IWRC2023 Breakout Session: “The Good, The Bad, and the Money”
No photography or recording allowed in this session due to the nature of the participants.
Russ Harrison, managing director of IEEE USA, is moderating. There were some changes to the panel due to the flu and a mechanical issue with United Airlines.
Notes were ok to take during this session.
IEEE hosts about 2100 conferences a year. Innovation is about partnerships. No one succeeds by themselves. When we started working with EPSCoR and this particular event, this session was the first thing that they thought of. Government – university – industry partnerships and what it takes. Help you and us figure out how to work with people that may not be like us.
That’s what this panel is about – people in the partnership business. Figure out how we can do this stuff better.
Dr. Zeeshan Habeeb, UAPB biocompatible materials, and is a leader in culturally appropriate science communication.
Benito Lubazibwa, CEO Remix Ideas, director of advanced Black entrepreneurship, helping people succeed.
Todd Paulson, needipedia invites collaborations with defense intelligence agency
Bruce Edwards, 38 years experience government side, moved to small business DIA recently, needipedia.
https://www.dia.mil/Business/Needipedia/
Q: Russ: what barriers do you face when you try to start partnerships outside of your sphere?
A: Bruce: the biggest impediments are FAR/DFAR, and that the conversations are secure and so that everyone is protected. Security is a difficult thing, and those are the barriers. Since it’s in the context of a procurement, even a grant has to be controlled. Past the security point, past the paperwork point, what he’s noticed is that the primary barrier is balancing the security between all the people that are part of the mission, balancing the mission objectives are needed, against the needs of the partners, like academia who must publish, and the industry partner that needs to sell a product. Mission implies that there is something that can be published or sold. Contracts that articulate what and when given all these constraints are hard to write.
A: Dr. UAPB: the academic point of view and amongst all three the academic is the most unstructured work environment that there is. What drives us? Tenured promotion. Academia recognizes certain things, research measured by published work, teaching measured by student evaluations, and public service and community service, which is measured by activities and records. Easiest ways to make partners is to find people at the similar stage of career. People understood what was what, and could better partner. Partnering with nonprofits is challenging, e.g. because NSF Convergence Accelerator grants require addressing food insecurity, and requires partnerships of this type, finding the trust here can be hard. People are already overwhelmed and are after action and impact, and can’t slow down very much to do “research”. Communication is crucial. Communicating about science is rarely done well.
CEO Remix: focus is on supporting Black entrepreneurs. Systemic barriers are significant, and this is the number one challenge. There is a lot of mistrust. A feeling that you don’t belong or are not welcome. 1) Values to values, aligned with mission? Entrepreneurial ecosystem that is equitable and just. 2) How are you going to form the collaboration and what will it look like? You can ask other questions, but this is the central question. Orgs sometimes want to collaborate just to say they are working with a Black empowerment organization. There’s no substance to the proposal. There isn’t any delivered value.
Todd Paulson: there’s barriers not just between DIA and small businesses, but there are also barriers internally. At least within the intelligence community (IC) it is very stovepiped. People do not talk to each other about their programs. The programs may be classified. You might sit next to them and have the same clearances, but cannot talk to them. This becomes a habit. It’s hard to get them to talk about requirements and needs, and it’s even harder for an outside entity to talk to the end users. We are the face to industry and it’s our job to find the new directions and provide advice and advocacy for small businesses. After doing contracting for so long, and then coming into the small business office, it was a good fit. Meetings on Tuesdays and Thursdays and guest speakers and try to build some communications. Programs to help industry where we’re coming from, and also allow you to tell us what you’re good at.
Q: Russ: what are the other internal constraints when you try and work with partners outside of your world, what are your concerns? First problems?
A: Dr. UAPB: bandwidth. Can I handle yet another massive amount of work to communicate and collaborate on yet another project? Restrictions on time and resources are serious and severe. Delegate, hire people, advocate how good these things are for students. Internally, sometimes our internal mechanisms need more time to work through.
A: CEO Remix: There is an African saying, if you want to travel fast, travel alone, if you want to travel far, travel together. Everything has to be we, and not me. Think as “we”. How can you disrupt intergenerational poverty in the Black community? Inception to Invitation is a progression of ideas. That process needs a village and collaboration.
A: Bruce: you can’t just walk over and surprise someone. Issues also related to funding. There are a bunch of different flavors of money. Most of our officers are afraid to talk to you. They will not pick up the phone and talk to you. They have to get approval to talk to you. You hear radio silence from us, but we need you to get things done. Look for the ways the government is trying to solve the problem of trying to talk to you. Asking for a 2 page white paper? That is a good thing for you to do. Look for Broad Agency Announcements. Look for those and respond to them. These mechanisms allow us to DARPA our way to starting a conversation that can end in procurement. Once that paper gets a serial number we can start a two-way conversation. Especially after it gets a serial number. We have to do a kabuki dance to even be able to talk to you. Now I can talk to you a little bit about the mission. And then it progresses. The conversation scales with government interest and ratchets up through a procurement ladder, supported by documented contacts. That radio silence is in your interest. As long as you have submitted something, and there’s no answer, that means we’re still talking about it. You send something in, like a white paper or proposal. That conversation internal to the government is something you never see. If you get back an answer of no current interest, then the conversation is over. Radio silence means the conversation is still ongoing. Any forward facing website or email exposed means you can contact them whenever you want. They may not be able to answer right away. They may ask you to back up and go into some other process. If you are a small business, and you email someone, then it may be rerouted to get the proper serial number. These processes may not be obvious or visible before you try and reach out.
A: Todd Paulson explains Intelligence Community (IC). DHS is part of it, but also does other things. There’s something of a Venn diagram. What the small businesses are facing in challenges dealing with the DIA is that 1) getting a facility clearance. In order to sell hardware or software, you may not need one. If you are providing services then you need a clearance to get a contract. You won’t get a contract without this clearance. Going through another contractor that has the contractor or has this facility clearance, then they can sponsor you. That’s the easiest and most direct way to get a facility clearance. This is the biggest challenge in working with the IC. If you see an announcement that comes out on SAM. An RFI or solicitation, you have to respond to that. Answer it. If you don’t respond, we won’t know you are there. If we don’t know you are there then we cannot direct the acquisition.
If you win a contract, then perform the contract. “Ok we won the contract! What do we do now!” This is not ok. This is a failure.
Statements of Work and Planning Documents are crucial for the proposals. They are distinct documents. They are not the same thing.
Q: ORI: how best to collaborate and share the value of open source hardware and software with you all?
A: GitHub, and if the design has been beat up on, and if the license allows it, we will use it. We might not let you know we’re using it, and might not be able to participate in your open process, but we’re there, and we use a lot of open source work. Comment every line. We have to do a code review to use it and anything that you can do to make this easier and quicker is of direct benefit.
Q: Russ: building partnerships in your fields, the first interaction with another group that really worked, what did they do right to make things work really well?
A: CEO Remix: two years ago, I was thinking about innovative loan financing, because access to capital is a big challenge for Black entrepreneurs. Lack of access to good credit, lots of reasons, some of them systemic. How can we solve this problem? We need to find another way to get access to capital. He described a specific example to illustrate how their loan financing model got off the ground. We just looked at the business model and the ability of the person to execute, and he found a funding source to collaborate with, and the financial institution was very excited and respectful. There was trust. Coming together and working hard, Remix and financial institutions raised a large amount of money, and so far, no one has defaulted. Your past relationship with money doesn’t determine your future success. Bankruptcy doesn’t matter. There are always reasons and humans behind the numbers and the stats. A lot of these numbers and stats are biased, anyway, and don’t tell the whole story. Working in the Delta, same deal – access to capital is the biggest challenge. You pay us back when you make money. Like, with farmers, it’s cyclic and seasonal and dynamic. Loan is paid back when they make money. The fact that this is considered innovative and not commonly done is uncomfortable. It just makes sense. Values aligned to values, and trust, and what kind of impact can we make. That is how we are innovating our way to successful outcomes with underrepresented people.
A: Dr. UAPB: Convergence accelerator – all teams applying were going to need experts from different disciplines and when you think of food security do you think of a chemist? Probably not. But food literacy work turned out to need educators that had a variety of backgrounds. These are disciplines that we don’t normally work together, and we are in completely different buildings. But now we see each other more often than the people we sit next to. How do we keep a group like this together? This is where the trust building comes in. You have to be clear about your goals and how we are going to handle challenges. Things are not going to go as expected. We have to have some leaders and leaders have to keep earning trust. Things are valued, but actions may not be able to be taken right away. Trust holds things together through the hard work of interdisciplinary efforts.
Q: Russ: how little communication there are within institutions – this is something that people really don’t know, or don’t remember. People assume that just because you are talking to one person in an organization, that you are talking to all of them. Do not assume this. Sometimes, communication within an organization is not happening at all.
A: Todd: Collaborate? With spies??! We increase the probability of success by planning an increase of the collision frequency of your innovation. Heat and containment can be used as a model. The best friend that you have in planning is the map of where you think the nodes of your success might be. Who owns the budget? It might be your five eyes partners. Doing the mechanism of the partnership – it has to be planned out and it has to be recognized. Planning out the engagement increases the collision frequency, which increases the probability of innovation. Design a space where they all have to go get lunch in the same place. Design the mechanisms of innovation. Highlights the advantages of smaller vs. larger companies. Design in ways to increase collisions of the people that need to talk to each other.
Q: audience: institutional or inter-organizational logics – entrenched beliefs and practices and societal values. E.g. capitalism, wealth builds on wealth and therefore systemic barriers and generational wealth creates unequal opportunities. Academia, at the beginning, policies around promotion may prevent collaboration and cooperation. Non-tenure track faculty is speaking from the floor, but she has a real promotion pathway at her work. Because she has a different promotion focus, she does not have the same focus on publications, and promotions can be based on cooperation and impact and other metrics. It changes the norms. This enables her to do what she is doing. It’s different. We’re trying to push more positions like this.
A: CEO Remix: business model financing <== explained before; everything that we do includes the people that are facing the problem. The people involved are involved in solving the problem. The people facing the problem have to be at the table in order to solve the problem. The customers have to be at the table. They are then co-creators of the ideas. The ideas are of higher quality when you do this.
A: Bruce: the thing that really makes the difference: communication. Good communicators drive everything else. If this isn’t happening, then the probability of success is greatly diminished. When an RFI is put out, do companies respond? Once we do this source selection, and do a debrief, he went the extra mile to communicate why the contract might have been declined or the company passed over. A form letter doesn’t help the company at all. In all the years he did this, he got one protest. The mindset of a typical office or organization, especially in one that is inherently security focused or secrecy focused, prevents this because there’s a minimization of information in the IC and the default is to not communicate details. Utilize things like APEX and SBA PCRs. They can be super helpful. CMMC certification was mentioned. OSD has Project Spectrum, which is funded by OSD, to help small businesses get certification. Utilize them. Project spectrum will help people in the room. DIA.mil homepage there’s three bars in the left hand corner, including a small business office. Until this conference, Todd and I didn’t know each other. Now we do.
A: AR APEX Accelerator (audience) explains that they have offices around the state. We help Arkansas businesses sell to the government. SBIR and STTR assistance. We are here to support you and work with others like SBA, Remix.
Q: Jennifer Fowler: learning about the defense world, since most experience in NSF. These clearances and security issues, I have realized that a lot of defense work requires US citizenship.
A: Todd: Not always.
Q: Jennifer Fowler: take semiconductors. Graduates etc. have to be US Citizens. I’m trying to reconcile this with the people that come here and face a really long wait to become US citizens. What is your experience with this being a barrier? Are you talking about how we can bridge the gap between foreign people?
A: Todd Paulson: we will steal talent from anywhere. If they’re smart and on the other side of the planet we will take them. We are in a special category in IC though. DoD they have more limits. There’s a misconception about this. You do not necessarily need to be a US citizen. Last project was mostly foreign. Closer to classified information, means more scrutiny. The contract might give them a path to citizenship. It’s a strategic thing. It’s our mission to partner with anyone we can. We have friends and people we have issues with do not. Anyone can send a white paper to needipeDIA from anywhere. We will figure a way out.
A: Russ: is shocked at the answer. Happily shocked.
A: Jennifer: There’s enough tangible examples of foreign people from being rejected to make this a problem.
A: Dr. UAPB I’m restricted from some things. And have to ask first. It’s easier to say no than yes, and the answer varies because it’s not a great system we have. The regulations are not clear, they are not black and white, and it’s up to interpretation.
A: CEO Remix: traveling to different countries it is clear that the US welcomes ideas. Very successful because of welcoming ideas and embracing different ideas. There are still systemic challenges. But there is no country out there in the world that does it quite the same. If you’re smart you’re welcome.
Q: audience: students would go to where they are meeting different companies and ask do you hire international students and the answer is no. Hearing that over and over – how do you move beyond that. No reason given when told no.
Q: audience: ditto.
A: Russ: it depends on who you are asking. The rules may vary hugely. When you talk to one person, you haven’t talked to the agency.
Q: audience: I used to work in career services – the number of students being lost before even getting to apply is so sad. We are losing so much good talent. It’s systemic. Almost no companies will take international students.
A: Jennifer: I confronted WalMart and they said they would sponsor international students. Enough people have been told no that people stop asking. Then WalMart says they will accept international students. It’s very frustrating.
A: Russ: the immigration is a complete mess. It’s super hard. The more smart people we can get to come here and stay the better.
A: Bruce: DoD has recognized that there is a shortage of small businesses. Along with the Secretary of the Navy. Since 2015 the defense industrial base has decreased by 40%. There are a lot leaving. There are a lot of reasons why. There’s been a huge reduction in small businesses participating in the industrial base. Small businesses drive the economy and innovation and the defense of this country. Don’t give up. Please pursue it.
Q: Audience: do you ever work with OTAs? Everything has to work within FAR and DFAR for DIA.
A: Bruce: Yes, but not widely used. DIA has identified a contracting officer that has gone out and got the authority to issue OTAs. It’s an avenue that they need to pursue. This was recognized and there is much more flexibility now than before.
Q: audience: how are clearances coordinated? Organizations have not in the past acknowledged clearances. Where does DIA stand in this realm?
A: Bruce: “It depends”, which is the answer to all good questions. For employment, there’s no reciprocity. You have to redo it all the time. A visit doesn’t count. Agency badges and an IC wide badge, but this is for visitation purposes, not employment. You have to go through the whole accreditation process again. They do not trust each other. There may not ever be a resolution on this one.
Q: Russ: If someone wants to start. They’ve never worked with you all before. What’s the first thing that they should do?
A: Dr UAPB: Just Start. Find the people. Just do it. “You get good at something by doing it” The end goal is worth it.
A: CEO Remix: find the problem! Know the difference between a painkiller and a vitamin.
A: Bruce: Dealing with the federal government is not easy. There is reward in the end. To start with, read SAM.gov. Register. Stay on top of announcements. Answer the mail. You’ll never see the set asides. Talk to APEX.
A: Todd: Be brilliant at the basics. Accounting – use the standards. A good accounting system lets you submit a proposal to the government. Be brilliant at regulations. It’s a numbers game. One proposal – repurpose it and submit again. Those proposals are not nothing. Just completing a proposal gives you lots of materials ready to go. Difficult but very rewarding. Don’t completely rely on funding from the government for your business plan. Once you start to make a profit throw some feelers out. We have the ability to literally kill a small business. Get a number, get a cage code number, and look for announcements. Run a tight security ship. Adhere to a standard. Even if you never do anything with the government, the DCA standards help you! Build your business to be able to work without you.
A: Amanda: from audience, answers same question – contact APEX.
Russ thanks the panel.
IWRC2023 Day 2
Erwin Gianchandani TIP NSF, on Zoom (University of Virginia, biotech background, award winner)
Introduced by Jennifer Fowler
JD Swanson moderates the talk with Erwin, who apologizes for not being here in person. There are budget meetings that interfere. Erwin asks if he can get a camera pointing out to the room to see us and Jennifer attends to that while JD enthusiastically dives in and asks Erwin questions.
Q: JD: you’ve been at the NSF for 10 years. We see the agency from different directions. JD program management and Erwin at the “AD” level. How has the CHIPS act impacted the agency?
A: Erwin: 11 years next week at the foundation in a variety of different roles, and now head of the new TIP directorate. If you have an interest in working at NSF it is a fabulous place to work. We could always use more talent to come work behind the curtain, so to speak. Where and how we should be investing, etc. Notwithstanding all the drama you hear in the news and the budget crisis (impending shutdown) he cannot recall a time in the last 2-3 years where things have been better. The past 2-3 years have seen the run up to the CHIPS and science act, which got 64 votes. We had Congress really keen on something like this in a bipartisan way, and a Director with a real focus on broad participation all across the country local-level place-based activity. The moment in time that we’re living in today, the first time in 32 years that NSF has stood up a new directorate, is a great one. This positive spirit largely stems from where the scientific community is today, compared to the past. Key technology areas, competition, and geo-strategic challenges are all things that the NSF is dealing with today. There are a lot of challenges. The US is combating climate changes and trying to improve equitable access to education and technology. The scientific ecosystem is evolving before our very eyes. Regardless of the discipline. Being able to extract value from data in new ways that were not possible before is a fundamental shift that we need to pay more attention to. Today’s students look different than before the pandemic. People have seen what science and technology do and want to extend this power and success. There’s been a transition from 25% PhDs going into industry to 75% PhDs going into industry. The Director’s priority of “creating opportunity anywhere” is real. It’s had a profound and positive impact on the agency. It’s a transitional moment that we are all living through and a lot of positive good can happen. This is a “behind the curtain” soliloquy, about a very exciting time for the NSF.
Q: Jennifer: Speaking more about the TIP directorate and the CHIPS act, and the impact on the agency, now we have the ENGINES program and the ART program – what is next? There’s a lot more stuff in the legislation, what’s the most exciting to you, what’s keeping you up at night, what’s giving you heartburn, about TIP?
https://new.nsf.gov/funding/initiatives/regional-innovation-engines
https://www.nsf.gov/pubs/2023/nsf23558/nsf23558.htm
A: Erwin: what gives him heartburn is that there are two sides to every coin. So, we have use-inspired and translational research, we are the agency that piloted SBIR/STTR, first agency with ICOR program that allowed us to provide entrepreneurial education for lab to market and customer discovery stuff, so it’s not the case that we haven’t invested in translational research, but anytime you do something new, there’s a lot of skepticism. Can you deliver? Is it moving us too far afield from the NSF’s mission? We are the only agency in the federal government that supports basic research. Over the last year and a half, I’ve done a lot of evangelizing about TIP. Here is an illustrative store. I had two groups in back to back meetings. The first group asked some questions that were polite, and in a polite way, but said what you’re doing is moving NSF too far away from the basic mission of basic research. Next half hour meeting, with a different group, went the same way with a presentation and then a discussion, and at the end, they said you know NSF can’t move fast enough to move something like this. It is too wired around basic research to adapt like this. It would be great if those two groups could talk to each other and find some common ground. Maybe this means we’re doing something right, by threading the needle in how we’re launching TIP and doing translational research. TIP has a very modest budget and pretty much was a bunch of stuff merged together. 2023 was the single largest increase in the NSF’s history of 1.1 Billion, but TIP didn’t get anywhere close to all of this. Concerns of the folks in the community somewhat keep him up at night. This is a virtuous cycle. TIP can contribute to future success but this determination is still in the future. Excited about the ENGINES and ART program, and the EXCELLENT program.
https://new.nsf.gov/funding/opportunities/experiential-learning-emerging-novel-technologies
How do we help people pivot from where they are to being able to work in a new space? The response from the community is key in whether or not this is successful. What’s next? We’re using the CHIPS and Science act as a playbook. Section 10.3.1 establishes Directorate and through 10.3.9 lays things out. We’re just following this and trying to do pilots. We want to do pilots that let us test out our approaches, get feedback from the community, then scale the pilots to have impact for the nation. We’re trying to do the engines at scale today. ART and EXCELLENT are trying to get to a place where they are scalable, today. Translation Accelerator is another one, working with researchers to identify directions that are more viable for commercial and societal impact. Wireless testbeds, for example, distributed across the nation to enable next generation wireless protocols. Experimentation with those – building out partnerships.
We could do a better job of preparing our talent for academic and industry practice, through practical experience, for example. Those are the things that are top of line for us. We’ll do pilots and activities that are very much in line with trying to follow the CHIPS act playbook.
A: Jennifer: one of the things I’ve had to do about communicating the CHIPS act is the difference between authorization and appropriation. A lot of that money doesn’t go to internal operations at the NSF.
A: Erwin: Yes, absolutely, fundamental differences here. CHIPS and Science is billed at 200 billion – biggest increase for NSF ever, up to 80 billion at NSF over next 5 years. But if you add up the numbers, you will get 200 billion, but not all of that has been appropriated. 50 billion going to commerce for new fabs. 150 Billion left is authorized but Congress has yet to appropriate the money. And, Congress might not move forward. The vision of CHIPS and science is going to take resources and those resources have to come from Congress over time. 94% of the funding at NSF goes out the door at NSF. It’s a very lean agency. This is problematic when you are trying to start something new. There’s a big lift to recruit folks and get them in the organization, so they can run these programs. We need to fill these positions.
Q: JD: We’ve talked about ecosystems. The key to their success is in the concept of partnerships. We’ve done some work across EPSCoR, but I see a very small piece. To the folks in this room (not sure how to state his question but it seemed to be about universities).
A: Erwin: when we think about partnerships we think about them in two forms, direct ones that NSF enters into, and trying to partner with industry, non-profits, agencies. We do those partnerships because it allows us to inject into our own thinking valuable points of view. We only have so many dollars, and being able to leverage resources or in kind contributions, this means that we stretch the money a lot further. Then there are the partnerships that NSF catalyzes. The money creates opportunities for groups and organizations to work together. Further enhancements to the research. The industry – university program IUCRC is an example. This is not in TIP – IUCRC has been around for 40 years.
This lets PIs and students build partnerships with local industry. In this spirit of catalyzing partnerships, it is absolutely the case that we want to see the investments from TIP drive different types of partnerships. A lot of what NSF has done historically is to fund “great” research and ultimately we push this out into society and the market. This has had great impact. But, given the moment in time that we are in today, with diverse challenges and technologies and local-level issues surfacing, climate change for example is different threats in different places, thus this is about bringing together the users, practitioners, with the researchers, and co-create and co-pilot solutions. Expand “great new ideas” pushed to society, but let’s include society more in order to improve the research. Depending on the research area and the topic, we can imagine partnerships across the spectrum. We want to see results of the research affecting things on the ground. Non-profits, philanthropic organizations, etc. Define shape and collaborate on the shape of the research agenda. For TIP to be successful it cannot be its own unit off in the corner. We have to build partnerships internally within NSF too. One of the things I’m proud of is that if you talk to my colleagues, many people will say that TIP in its first year has found ways to creatively partner with all the other directorates. E.g. between bio and the TIP. Computer science, math, physical science, etc. (echoes the advice we heard yesterday about not assuming people within an organization talk to each other). We do all these partnerships externally, but we also have to do a great job internally too.
Q: Jennifer: We talked about the EDA tech hubs programs yesterday quite a bit. There’s been a lot of interesting dialogue as to whether or not engines are in competition with tech hubs? Should they be competing? Collaborating? What do you think about the EDA announcements? Partnership with EDA in administering the tech hubs. We are trying to figure out exactly what to do and how to navigate through these two solicitations.
A: Erwin: great question – EDA from Commerce, and modeling behaviors, and encouraging the broader community, and to work collaboratively and be synergistic. Even before we put out an ENGINES funding opportunity, for months before we had been having conversations with (he interrupts himself to explain the difference in philosophy between EDA and NSF in terms of appropriation and authorization) between EDA and NSF. These conversations are recurring and productive. Erwin says this is new and welcomes evolution in the way government agencies work together. Collaborating between EDA and tech hubs is happening. Purdue University has a team working on metrics that will best measure success and milestones. Both entities are funding this group. Erwin makes efforts to reassure the audience that this is not a bad idea. I say all of this to emphasize that the collaboration has never been this good. Something has changed. TIP and EDA have signed an MOU to share information because this is helpful. Giving the community consistent feedback is important. We shouldn’t be giving widely divergent messages to the community. This is actually very good news. They are supposed to be synergistic. It’s a spectrum from use-inspired research all the way to workforce development. EDA is further down the spectrum and overlaps. Sometimes overlap in Washington is bad, but in this case it is working out well. Depending how you scope a tech hub (supposed to be 10 across the country, and EDA is working this) our hope is to fund more than 10 innovation Engines. They are smaller investments individually, so more of them makes sense. Maybe multiple engines serve each tech hub that covers a larger geography. Use-inspired and translational research is directly supported by the innovation engines, and this feeds into the tech hubs, which are not as close to the research. This is supposed to be a meaningful and thoughtful collaboration between NSF and Commerce. We are trying. We welcome feedback on what we can do or say to clarify the symbiosis that we hope to see here.
Q: Jennifer: From the audience, when we get solicitations, they are so broad. Could you talk about the review process and lessons learned? Academic dominated review panels. Academics really struggle to form partnerships and get collaborators. If it should be led by industry, then how are the review panels going to be built to make this work better for industry?
A: Erwin: what are we finding? We are learning as we go, no doubt about that. We have a terrific team with a good background that can run the competition and can make decisions about the proposals. But, as we go through this process we are going to learn by doing it, what’s working, what’s not working. What can we be more precise about, so we can improve effectiveness, and so you all can be more responsive to the funding opportunities. Later this year, we’ll review the review process. And, communicate what we saw and what will be changed. How do we broaden the tent? NSF is very focused on the academic community and the academic community relies on NSF. This has to change. We want to open things up appreciably here in terms of trying to deliberate about wanting engines to be real ecosystems from different sectors. The academic doesn’t have to be the lead. Barriers need to be broken down. In certain fields there are challenges with faculty time, and resources. How do you create appointments that span academic and industrial interests and communities? Who retains the IP? ENGINES proposals are asking for this sort of thing. Multidisciplinary and multi-sector things need to be reviewed by people that look like these teams. Our team has worked really hard to do this outreach to state and tribal and industry and venture and fortune 100. Yes, he did say non-profits earlier, and he reiterates that academia has to be at the table. There is always room for improvement, but “we’re trying very hard” and “we are doing much better than people expect”. It’s not as diverse a review panel as we would like.
Q: Jennifer: what are the NSF’s goals for diversity equity and inclusion? Dr. Chuck Barber (from AR) and his team? (He’s been in executive leadership at NSF for 8 months) Any collaboration there? How workforce development is handled with broadened participation?
A: Erwin: Dr. Barber is doing great and working hard. We view the notion of trying to be able to create opportunity everywhere is ingrained into how we think and everything we do. We publish all the concepts of ENGINES and this was based on diverse institutions conversing with us. We wanted to hear from diverse institutions and find out what their pain points were in engaging with NSF and participating in programs. Hearing that and translating that back into the design, and publishing the design concepts so everyone could see the ideas and feel like the opportunity was accessible. By publishing the concept outlines we are creating a more level playing field. This shouldn’t be a competition in every region. It’s about bringing people together. We’d rather see one proposal that includes people than a bunch of proposals all competing against each other. E.g. cybersecurity as an afterthought vs. cybersecurity designed in from the beginning. Diversity and equity needs to be designed in from the start, not an afterthought. (Louder for people in the back doing amateur radio grants in the worst possible way). Being so focused on silicon valley – how do we get more focus on other parts of the country that have excellent people and resources? TIP directorate and EPSCoR is directly addressing this.
This was an excellent conversation.
IWRC2023 Advancing Equitable Access to Food and Health Technologies in the Delta
Joe Thompson, President and CEO, ACHI, Profession UAMS Colleges of Medicine and public Health
PI of the only engines award in AR (Type 1)
Arkansas Center for Health Improvement ACHI
First public presentation after the award. Status report on where we are. ACHI has been around for 25 years. Catalysts make things happen without getting burned up in the process. This is sometimes harder than it looks. ACHI does a lot in the background and has been very effective. As stated, the engines program fosters the development of innovative ecosystems. Inclusive economic growth.
AI: find out more about the regional engines that we can be part of.
Deliverables are to submit something that leads to a type 2 award. Nascent, Emergent, Growth are the three phases in Type 2. With partners the grant grows the ecosystem of research capacity.
How did we get a Type 1 grant? What are we doing?
Two months put together a descriptive grant. This grant was written to try and solve problems in some of the harshest health environments in the US. The Delta has serious health and equity challenges. Yes, we have vibrant places in the South, but three states share a burden and challenge with the lower MS river delta. Economic vibrancy in the past was built on racism, pure and simple. ArkLaMiss proposal ideas came out of, in part, lessons learned from the pandemic. The pandemic affected all of us, but vulnerable communities were affected much more harshly. We walk through the grant application. First, if we can do in-home testing for covid, what else can we do? Move the tests to the home. Two, more effective methods to get fresh foods to people. Food deserts exist in this area. In some places it is a 60 mile round trip to go to the grocery store. Mobility issues and disabilities and gas prices all make it nearly impossible. Telehealth is the third part. Jennifer Fowler was key in helping with this grant (Marta had a significant role here I believe). Partners listed (at least six). Diverse partnership. Target is the alluvial plain, which spans three states. We now need to identify partners that want to help. Pair those communities and those innovators to figure out how to fix the problems and do real work. Identifying individuals that want to help us (flyer on table today) is going on right now. You can get in the loop and help create the clusters. There’s a list of partners and this is an un-blazed path right through some very hard work. Any and all assistance is deeply appreciated. Coming up at the end of October there’s a symposium on 25 October (Central Arkansas Symposium) and 2 November (Northwest Arkansas Symposium). He ended with a very firm statement about the failures of our healthcare system to perform adequately. This was a clear call to action from someone that understands the assignment.
Q: Matt Francis: I’m a councilman in a small town, and with your partnerships, please consider using the AR municipal league. There’s lots of challenges in small communities, and there’s not very many knobs to turn with healthcare. This is so hugely needed. However I can help connect you into that I will.
A: Dr. Thompson: if we can get it right in the lower MS delta, it’s transferable to 35 other regions. This is a threat to the nation, not just to the region. There’s substantial benefits here and involvement
Q: :Meredith Atkins U of A: “last mile” innovation solutions are usually solutions that are meant for big orgs, but co-developed innovation that can actually be built within communities, how can that play a role in this engine? In other words, AI may not matter much here. We don’t need complex solutions that we can’t afford to deploy.
A: Dr. Thompson: Our capitalist system works against rural America. Grocery stores markup rural delivery and they only go because of volume, once every two weeks. Automatically the system is biased against the same opportunities for rural America. If we count on the traditional investment strategy we will not find the solutions. There has to be a better way and we have to find it.
Q: Jennifer: could you share your experiences with your coalition? The collaboration, described?
A: Dr. Thompson: (@JoeThompsonMD, @ACHI_net, ACHI.net) there are two things that we are being challenged by. The six orgs that I put up had never worked together before, despite working in the same space. Forming and storming phases are in. Each org has a different perspective. We are trying to adopt a new NSF vision that has never been seen before. We are actually trying to do something that has not been done before, underneath something that has not been done before. Team may change and adapt and we are prepared to engage with the 35 other orgs that we need in order to be successful. We need to get people out of their current way of thinking. It’s new and different. Not about getting another clinic, getting another pharmacy, saving a hospital. It’s getting outside of the box of survival and into an innovation space of “what if”. We have to get the right people in the room. We need an advisory group of just high school students, for example. We need to include people that are great and innovative and successful and we need to include them. This is hard. It’s hard in multiple dimensions. Most of this tuff that has been done is in the opposite direction.
Q: Joe director of workforce training in Helena at the university: our hospital has only 100 beds and only operates an ER at this time. Rumored to be closing soon. This is a huge problem. 10,000 in Helena and 24,000 in the county and now it’s way farther to a hospital.
A: Dr. Thompson: yes this is a huge problem and there’s serious concerns. Out-migration of the working age population with insurance is ongoing. Centralized urban areas are ok, but this leaves rural people having to drive 60 miles for prenatal care. If that particular hospital goes out it means 120 miles. This is going on all over the US. They can’t find a model that works in rural America, at Medicare and Medicaid, that works. They see massive failure. Medicaid expansion in AR prevented hospital closing. Net neutral for rural hospitals because we took the deal and surrounding states did not. You cannot have a viable ecosystem without education and health care. This innovation vision is great, but we have short term challenges that have to be addressed and this is a full-bore effort to do just that.
IWRC2023 Panel: Business Innovation
Joined mid-panel.
Jeff Amerine from Startup Junkies
Erica Brigance from ArcBest Technologies
Chad Martin from Standard Lithium
Lenore Trammel from Big River Steel
Bill Yoder from Arkansas Center for Data Sciences
Sensors installed into the steel recycling building and the forge help deliver metrics that head off problems that can be corrected without having anyone intervene. If we see something, we can fix it, but fixing things that we can’t see, and using machine learning, will let us reduce the number of defects. People are not replaced by this. It’s a force multiplier. It’s not skynet and it’s not the end of the world. It’s not magic pixie dust.
AI and ML will change the way we work. The way we get information will change and the way that we think critically about that information will change. A focus on the data infrastructure makes you change the way you do business. Most of our data infrastructure was there to keep our operational systems running, but data management allowed a big expansion in other ways, back to the modeling and down to the decision making. Being able to have actionable insights is key.
How do we know the model is right? Why do we choose the models? Manufacturing process and extraction sees AI/ML as having a role. It improves sensing. Predictive maintenance means shorter downtimes and less really big downtimes. Digital twin technology and the ability to simulate an entire plant has been a good deal.
How does this impact the demand for people? It’s having a big impact. AI has been around for a long time but just over the past few years it’s caused a shift in training in the IT space. Two years ago, a book “The Age of AI and Our Human Future” <== “an easy read if I read it” says Bill Yoder. Claims self regulation and that we’ll go slow, but that did not pan out. The same people now want regulation.
When you are looking at regulation, make it easy for people to get permits. We have to know what we’re doing and how to do it. Clarity, transparency, and an understandable process. You don’t want to have to employ an attorney full time to get a business started.
Historically, I’ve needed MS Data Science people, but moving forward, the skills are becoming more widespread and available up and down the workforce. For the most part, the state government has been good to work with. There’s money out there, but when you’re looking for innovation and speed, the red tape is so huge and the process so long, that business is hampered. It’s almost not worth it in some cases, despite a need for the money. AR is a wonderful place to do business, it’s just the red tape for funding and grants is the biggest issue.
There’s a lot of good things going on in AR building an ecosystem and reinforcing collaboration and innovation. There’s people looking for funding, but the feedback loop for accountability isn’t tight enough. People doing well need positive reinforcement and people doing badly need correction.
If you were advising the administration on priorities, what would you say?
History doesn’t repeat itself but it often rhymes. Having control over supply chains is a pretty good idea. Having critical inputs like lithium and steel and having access to them regardless of what’s going on in the rest of the world is important.
We see this increase of interest in building resilience in the supply chain. What should we be thinking about moving forward?
Critical minerals and other elements means you also need other equipment. Pumps, valves, etc. Lead time on PLC systems right now is 18 months. You might have to build something out of Argentina or Chile, and it might take upwards to two years. While these minerals are important, other infrastructure is required in order to get it done. Logistics and supply chain is distorted-global at this point, and clawing it back may be unnecessarily expensive or absolutely crucial, and it may be hard to tell the difference. Less reliance on single-source moving forward? Yes. Everyone is having trouble. Getting forklifts (2 year wait list) for example. If you can’t operate then you end up selling your IP. You can’t operate with a two year wait.
Training up, quickly enough, technicians from Taiwan for example, HB1 visas. Workforce for critical industry needs, what should we be doing?
You should be thinking about the talent well ahead of a plant. The people are simply not out there.
Basic English and basic math are necessary. Why are we having to teach basic math and how to talk on a radio to people? We are having to do this. You have to do this stuff before you can start your facility. Construction training so they can come work on the construction side. Operational training for the people operating the equipment. Talking about manufacturing early and often. Comparison to the steel industry in Detroit vs. the relatively new one here in AR. You have to convince people that these jobs are good, safe, and clean. It takes more convincing here. You have to start early and often to show what it looks like to work in manufacturing.
Driver attraction and retention. Average age of a driver is middle-50s. Motor freight needs drivers. Driver shortage has been ongoing for many years. Recruiting drivers takes time and effort. Expectations of LTL vs. long haul freight. Marketing the job is a big job in and of itself. What it is vs. what they think it is.
What is happening in AR to address the needs for attracting more data scientists?
Third time he’s moved back to AR (Bill Yoder), so he has an interesting perspective. There’s a lot going on in higher education. 10 years ago they’re still training on COBOL [COBOL is currently taught at UALR, for example, because there is demand for COBOL programmers to maintain financial institution mainframes that run COBOL programs. Singling out COBOL is a poor choice for both practical and theoretical reasons. Practically, because COBOL programmers are well paid, and theoretically because the lessons learned by learning that particular language are transferable to other languages and improve the software development skills of the student. -mdt] but now higher ed is moving a lot closer to relevant skills being added sooner rather than later. Data science is coming along with lots of funded majors and 10 different disciplines. There are a lot of smart people coming out of that program. And they are sharing the curriculum with 2 and other 4 year schools. We don’t need to hire professors at each institute. We can share the talent with remote access. We did hear in another panel that teachers only have so much time and online courses are difficult to teach. Mike Rogers was mentioned again (chief of workforce development) and that there is an expectation of improved outcomes. The investment in ACDS (Bill Yoder is the chair) has made a difference and he’s doing his best to step up.
Q: 16,000 applicants to ACDS. You have some demographics? What does it look like? Are they over the age of 50? If they’re not getting jobs and not getting interns, and between 20-50, then what kind of resources are being provided? They don’t have time to get the skills?
A: The average age is 26 or so of the people that apply. Not everyone is going to qualify for an IT career. What we’ve tried to do over the past 3.5 years, has been recognized, and is being expanded to other sectors. Placing people in manufacturing, engineering, and transportation. Placing more people in different sectors is going to increase the odds of success.
Q: There’s people looking for tech work that aren’t qualified. What is going to help these people?
A: First thing we do is pre-assess, screen, and interview. Pre-apprenticeship training to get them up to being able to take advantage of the apprenticeship program.
Q: I went to the UAF and work for Raytheon, and she wants to ask about higher ed and college education and engineering and they are more theoretical based, and how do you feel about the curriculum when it comes to manufacturing and data sciences, and the theory and there’s no hands-on training. Is there a curriculum that needs to be added to the program?
[UALR used to have a large engineering technology program that did exactly this sort of thing. The last UALR class that was able to sit for the state Fundamentals of Engineering exam was 1996. The loss of engineering curriculum with hands-on lab components in the majority of the coursework was a loss for the state. At the time, it was widely believed that University of Arkansas at Fayetteville opposed engineering technology students being allowed to take the FE/EIT exam, which leads to a Professional Engineering license, and also opposed the existence of any other school producing “engineers”. The perception was that UARK wanted a monopoly on engineering, and this is why the UALR program was removed and replaced with IT classes. -mdt]
A: Internships from the panelists mentioned as solutions. The lack of supervisory and management and interpersonal skills is identified as a big problem. Graduates do not have enough of these skills.
Q: Department of education person from audience: when we try and match the experiences with labor market data, we are not sure how well that matches up with places like Standard Lithium. How do we predict the sort of skills 10 years down the road?
A: Teaching into the fads is tricky. Learn how to learn and base level operator jobs. Basic computing skills.
Q: how can we get high school graduates into the workforce?
A: Big River Steel has a “signing day” for high school students, from industry to interview graduates to get them prepared and job offers straight out of high school. New facility for steel meant a kick off of high school recruiting. They went to the schools and if you were a senior and not going away to college consider Big River steel. This resulted in two hires. They had to have training at community college over the summer and started as new hires in entry level positions at 10 dollars an hour plus bonus up to 20 dollars an hour on top of that. One of these students has been promoted. This is our second year of high school recruitment, and now recruiting juniors and seniors. Where the juniors in high school get an internship, then a summer, and then come in as entry level. You can get hired in out of high school. Better chance if you go through the internship program, but there is a chance.
Closing comments from the panel.
There are a lot of good things happening in all parts of the state. Lenore Trammel Big River Steel, northeast AR. Largest steel producing county in the US. There’s a good base to start attracting people to want to come live here. “Work here, live here” Big River Steel program.
Erica says great experience the past day and a half. Great things are going on here. If there’s any hope for partnerships then please think of ArcBest.
Chad Martin of Standard Lithium says you don’t have to go out of the state to have a great career. Lots of innovative things going on here that no one seems to know about. Business diversity is high here.
Bill Yoder ACDS says it’s not a secret and everyone present should let people know.
This panel was mainly about business boosterism, but there was a lot revealed here of use to us.
“To find yourself then lose yourself in the service to others. Go IEEE!”
Mr. Francis closing remarks: Scaling up regional economies group: facilitating proposals on CHIPS act. Meet after lunch to collaborate and catch up. Otherwise, the conference closes.
This was a unique event in several ways. It focused solidly on people, and not the technology, or the business at the expense of people. The CHIPS act is about investing in people. It is an opportunity. Just put your mind to it, talk and connect, the opportunity is out there.
Venn diagrams challenge from the opening talk revisited – has everyone met someone from another sector?
Lots of good feedback to IEEE. Single biggest network of technical volunteers in the world. It’s doing good work.
Round-table for the SURGE group at 1pm. How can organizations like ORI plug in?
IWRC2023 SURGE Roundtable
About SURGE
What is SURGE? What is it not (right now)?
We will then start at the same place in terms of information.
Any tangible next steps to continue the momentum as a community?
Scaling Up the Regional Economy
Coalition of the willing, volunteer basis, Hugh McDonald originally directed most of the effort here. Surge is an initiative to build a broad network of stakeholders in a public-private partnership to ultimately make Arkansas more competitive for funding from the CHIPS act and other federal programs.
First meeting of this working group was a couple weeks after founding in March. In May, AEDC awarded a small grant to Startup Junkie to get this off the ground. All we are is a network of people passionate about getting money for this state.
Jennifer takes her role too seriously, according to her performance evaluators. She is very motivated and serious about getting the most possible use out of tax dollars and “bring them back” to AR.
This is the first time that there’s been an initiative like this (?).
Novel and meaningful partnerships have been mandated for this program, so let’s get in there and see where we can fit in. Academia, nonprofits, government, industry, state and local government, k-12 schools, etc etc etc are needed. Solicitations are dropping, and are being read. Some are only for academia. Some are only for industry. Initially, what about having a group of people that can filter out these opportunities. It’s difficult to keep track of one website, let alone 20+. Having a group that can quickly parse through them and figure out who is who at the zoo and what’s what, and bring things to the community of focus (in this case, AR).
We’re not a formal organization. The only thing changing hands here is some organizational support. When this thing is over, by May of next year, there will be a roadmap.
There is $52 billion that has been appropriated. $39 billion is going to foundries and handled by commerce. Commercial Fabrication Facilities submissions are open. When you run the NAICS codes, you get 21 businesses in Arkansas. There’s lots of targets.
Running the NAICS codes and reaching out to people is a great way to get in touch with the right sort of organizations that might be ready to move forward. Other companies that might want to relocate here are also a target of the business development group. NIST is where these awards will come from, which in this case is the Department of Commerce. You can request up to 35% for big capital stuff. That means 65% is up to you to raise. But if you’ve ever considered retooling, expanding, or going into something like this, there has never been a better time than now. We will probably never see another investment like this, again. The last time this happened, this level of money for science and technology, was after Sputnik.
Consider how rare this opportunity is.
Questions about SURGE?
Tech-based economic development.
E.g. when Wolfspeed acquired APE, the CTO at that time made a statement “us purchasing this small business has enabled us to provide the best chips on the market worldwide”. That quote alone was a great indicator that people in the space know what’s going on. But,this sort of sale and this sort of statement is not on the map of the big industry groups.
Q: We had the presentation about NSF engines and access to food and health? Connect the dots from semiconductors to food and health.
A: Jennifer: Application? Every electronic device needs semiconductors, every piece of healthcare equipment, everything needs semiconductors. This is why it’s a matter of national security. We can’t function without semiconductors and they enable every other industry. Matt Francis (Ozark Integrated Electronics) says it’s important for power transmission because there’s a lot of “smart” things and it affects absolutely everything. John V. From Michigan State, says smart agriculture is not being done in a nice way. You have to pay to play. Places with lots of smaller producers have people that are left on the sideline. Competition that already had scale on their side now has AI and other things and this will drive them into the ground. Jennifer says Michelle Shoke from hunger alliance reports that coming here was well worth it because we can’t be innovating anything if people are starving. This is how the topic for the ENGINES proposal came about. People can’t go to school if they are hungry or chronically ill. Access to medical care and food is absolutely necessary. We have to make sure that our basic human needs are addressed. You want your fancy stuff? Address the iniquity first. We can’t deliver the solutions to rural America without innovation and workforce development. I wish the larger community would realize the significance of semiconductors to everything else. We talk about AI/ML being the next technological revolution. Technology really is everywhere, and semiconductors are everywhere. Innovations and a secure supply chain is like food access. This is the basic level of technology required for every other innovation and technology.
Q: Jennifer: how do you view the importance of semiconductors?
Q: Audience: timeline? How can we respond to this? What’s the investment thesis? Expansion opportunities for existing companies? How can we market the opportunity for industry to come up with the ask? What do you need? How could access to $38 billion dollars help you?
A: Jennifer: For example, at our August event that we had on campus, we met with someone from Newport. They saw the NIST application come out, and closed the browser. It was already too much. It’s 100 pages long. It’s not light work. They were interested, they wanted to do an expansion, but it’s too cumbersome to do the paperwork. So Jennifer offered to do the paperwork if they would go for it.
Q: An audience member (Black man) who left after graduation speaks next. He worked in software but it was just dumb luck, a contract with UALR. As far as bringing his company here, there are a lot of barriers, some perceived and some real. He went to Carnegie Mellon Pittsburgh. Marketing yourself as a solution in the semiconductor space is going to be a challenge. There’s less friction in other states with established companies and a trained workforce. E.g. north Phoenix, largest fab in the world, still having trouble hiring people. Not many Americans want to go to China, even short term. They underestimated the friction. No history in this industry, convincing people to come here, is a big challenge that should not be underestimated. Grow people here instead. That’s your best bet. This means working hard to prevent the brain drain. You’re headed in the right direction.
Q: Jennifer: are there any programs in AZ that don’t exist in AR?
A: Black man in audience: yes. AZ got TSMC by competing outside the state. They have 8 fabs. Bringing in another was the goal. This means that fabs are stealing people from each other at least a little bit. There’s no good answer. Having government and industry players is key and it’s hard work.
A: Matt Francis: identifying our niche is helping. We don’t have major fabs, but we have been a powerhouse in electronic packaging, with innovations coming out of research, transferred into companies, that have then succeeded.
A: We export our workforce here. People, very well trained, leave. We keep exporting them. The fact that they are now working in elevated positions implies that we’ve made that workforce for some time.
A: Jennifer: I listened to a podcast on TSMC and how it took decades on investment and coordination. They straight up poached people to come back to Taiwan. What if we knocked on the door of these people and what would it take to get them back to AR?
A: Matt Francis: wrote many many grants over many years and finally started winning some and was able to start making chips. He had to explain that yes, this is in Arkansas. Now it’s a “fun fact” that Ozark Integrated Circuits is from AR. You build confidence by doing the work and solving the problems. People don’t know what we’re capable of.
We have companies that go back 60-70 years that do electronics manufacturing. He had professors that worked at Baldwin Organ back in the day, and that’s some good solid old-school electronics manufacturing.
We don’t all get to be in the same place for this sort of thing very often. Any feedback.
Q: money side of things: 35% coming from the government means that financing tools have to be available. There has to be something that helps fill in the other 65% semiconductor equipment that is not cheap. There has to be a mechanism for finance.
There’s strengths we can take advantage of. Packaging and equipment manufacture. And, critical minerals. That’s just inside the NIST application. Any of these other programs, and you’re wondering how you can fit in, then come to SURGE and we can let you know how you fit in.
There’s a website for SURGE https://surgeArkansas.org
With some resources and cross links to things AEDC is doing. Of special mention is the “opportunity” section.
Conference closes.
IWRC2023 Appendix: “Final Conference Schedule”
Innovation, Workforce, and Research Conference (IWRC)
13-15 September 2023
Preliminary Agenda*
*Timing and speakers may change slightly.
Wednesday, 13 September
Time (CT)
Session
5:00 PM
First bus leaves lobby @ Embassy Suites (free parking is also available at the Clinton Library)
5:30-8:30 PM
Opening Reception @ Clinton Library
Thursday, 14 September
Time (CT)
Session
Speaker
8:00 AM
Registration
8:30 AM
Welcome & Kickoff
- Matt Francis, Ozark Integrated Circuits, Inc. • Jennifer Fowler, Arkansas Economic
Development Commission - Ed Palacio, President, IEEE-USA
9:00 AM
Opening Keynote
Secretary Hugh McDonald
Arkansas Department of Commerce
9:30 AM
Building an Innovation
Ecosystem
Dr. JD Swanson, National Science Foundation
10:00 AM
Networking Break
10:30 AM
Breakout Session
Panel Discussions
1) Advanced Energy & Critical Minerals
- Becky Keogh, Arkansas Department of Finance and Administration (moderator)
- Lisa Perry, Walmart Energy Services
- Will Smith, Standard Lithium
- Dr. John Verboncoeur, Michigan State University
- Dr. Branden Bough, National Nanotechnology Coordination Office
2) Education & Workforce
- Dr. Tina Moore, Arkansas Division of Higher Education (moderator)
- Lonnie Emard, Arkansas Center for Data Sciences
- Dr. Suzan Anwar, Philander Smith University • Dr. Argelia Lorence, Arkansas State University • Amy Elrod, Acxiom
12:00 PM
Networking Lunch (provided)
1:00 PM
CHIPS+ Plenary Panel - Kathy Hayashi, Qualcomm (moderator)
Innovation, Workforce, and Research Conference (IWRC)
13-15 September 2023
Preliminary Agenda*
*Timing and speakers may change slightly.
and Q&A
- John Hardin, North Carolina Department of Commerce
- April Campbell, U.S. Economic Development Administration
- Dr. Craig Scott, Fellow, NIST Advanced Manufacturing Program Office
- Dr. Hugh Churchill, University of Arkansas
2:30 PM
Networking Break
3:00 PM
Breakout Sessions
Panel Discussions
1) Broadening Collaboration: The Good, the Bad, and the Money
- Asa Gilliland, Redstone Consulting (moderator) • Benito Lubazibwa, Remix Ideas
- Dr. Zeeshan Habeeb, University of Arkansas at Pine Bluff
- Paul Kodzwa, RTX Technology Research Center • Todd Paulsen, NeedipeDIA
2) Innovation & Intellectual Property
- Becky Taylor, Austin Technology Incubator (moderator)
- Neil Merrett, Air Force Research Lab
- Matt Schantz, Frost Brown Todd LLP
- Luna Acosta, Arkansas State University • Weston Waldo, Austin Technology Incubator
4:30 PM
Sharing Notes: Breakout Session Report Out
5:00 PM
Closing Comments
Matt Francis, President and CEO, Ozark Integrated Circuits, Inc.
5:30 PM
Adjourn
5:30 – 6:30 PM
Networking Reception
Friday, 15 September
Time (CT)
Session
Speaker
8:30 AM
Morning Keynote
Erwin Gianchandani, Assistant Director,
Technology, Innovation, and Partnerships, National Science Foundation
9:30 AM
Advancing Equitable Access to Food and Health Technologies in the Delta
Dr. Joe Thompson, President & CEO, Arkansas Center for Health Improvement; PI, NSF Regional Innovation Engines Development Award
10:00 AM
Networking Break
Innovation, Workforce, and Research Conference (IWRC)
13-15 September 2023
Preliminary Agenda*
*Timing and speakers may change slightly.
10:30 AM
Business Innovation Panel Discussion
- Jeff Amerine, Startup Junkie (Facilitator) • Erica Brigance, ArcBest Technologies
- Chad Martin, Standard Lithium
- Lenore Trammel, Big River Steel
- Bill Yoder, Arkansas Center for Data Sciences
12:00 PM
Networking Lunch (provided)
1:00 PM
Scaling Up Regional
Economies: Collaboration is Key - Matt Francis, Ozark Integrated Circuits, Inc. • Jennifer Fowler, Arkansas Economic
Development Commission
2:00 PM
Adjourn
ORI at QSO Today Academy 9-10 September 2023
Open Research Institute presents two talks and an organizational showcase at the 9-10 September QSO Today Academy this upcoming weekend. https://www.qsotodayhamexpo.com/
This online event features a broad array of amateur radio talks. The speakers are engaging and inspiring. Q&A, connection, and conversation are a priority at QSO Today.
See Dr. Daniel Marks speak about the RFBitBanger project and the SCAMP mode at 1300 US Pacific Time on 9 September. Details of the talk can be found at https://wze95h.qsotodayhamexpo.com/sessionInfo/_the_rfbitbanger_an_off_the_grid_emergency and the repository for this ORI project is https://github.com/profdc9/RFBitBanger
See Michelle Thompson speak about A Shortened HF Antenna at 0900 US Pacific Time on 9 September. Details of this talk can be found at https://wze95h.qsotodayhamexpo.com/sessionInfo/22 and the ORI repository for this project is https://github.com/OpenResearchInstitute/dumbbell
Please visit Open Research Institute’s exhibit at QSO Today Academy from the main portal.
Thank you to everyone that supports work at ORI.
Executive Board Meeting Minutes 22 August 2023
Open Research Institute, Inc
1873 3525 Del Mar Heights Road
San Diego, CA 92130
23 August 2023 1000 US Pacific
Virtual meeting, held on Zoom
Attending
Keith Wheeler
Steve Conklin
Frank Brickle
Michelle Thompson
Not present (excused)
Anshul Makkar
Approval of Previous Meeting Minutes was unanimously passed.
Motions and Votes
1) Director and Officer appointments.
Steve Conklin, Keith Wheeler, and Michelle Thompson agreed to continue as Directors. Frank Brickle was welcomed as a Director. Steve Conklin to continue as CFO. Michelle Thompson to continue as CEO. Michelle Thompson moved and Steve Conklin seconded Keith Wheeler’s appointment as Secretary. Motion passed unanimously.
2) An offered launch opportunity was discussed.
The short timeline to submit a proposal combined with three days of stabilized platform were weighed and considered. Michelle Thompson directed by the board to communicate with the individuals to thank them for extending the opportunity, decline this particular opportunity, and to identify long-term opportunities with enough lead time to leverage existing and ongoing work.
3) Liability insurance.
The insurance quote received from California Non-profits was reviewed. A motion by Steve Conklin and seconded by Frank Brickle was made to accept the quote and bind the policy. Motion passed unanimously.
4) Director and Officer reports.
A) Detailed updates were presented about Ribbit, ranging from successful DEFCON presentation to international field testing to earning the 2023 ARRL Technical Innovation award. Ribbit has a $1000 balance in a dedicated bank account and has generated $200,000 in capability return on an approximate $250 investment. Ribbit is lead by Pierre Deliou .
B) A new amateur radio club in Germany is seeking advice on low bitrate codecs. Michelle Thompson directed by the board to communicate about the decisions to go with high fidelity voice codecs as implemented in Opulent Voice.
C) RFBitBanger is a QRP HF transceiver design using Class E amplification and introduces a new digital keyboard to keyboard mode called SCAMP. RFBitBanger development team has produced Batch 1 kits, all 96 of which which were claimed by donors. The prototype cost $2,741.49 to design, document, and test. Donors have contributed $14,160.18 to produce, kit, and ship 96 transceivers. Costs are expected to be covered by the Batch 1 fundraising. Commit Change was commended for excellent performance and customer service. Batch 2 is under discussion. RFBitBanger was successfully demonstrated live and over the air at DEFCON31 in August 2023, will be presented at QSO Today Academy’s inaugural event in September 2023, and is lead by Dr. Daniel Marks.
D) ARRL’s new policy of identifying particular amateur radio educational organizations as competitors for ARRL Learning Center was discussed. ARRL’s decision to withdraw support to and drop collaboration with these particular amateur radio educational organizations was discussed. ORI disagrees with ARRL’s new policy of approaching amateur radio educational efforts as a zero sum game. Reclassifying amateur radio clubs that produce educational videos as competitors harms the amateur community and is not aligned with ARRL’s mission statement (ARRL’s Mission Statement: To advance the art, science, and enjoyment of Amateur Radio.)
E) The May 2023 custom training from Mathworks “HDL Coder for Software Defined Radio” class was a success, with excellentt demographics, high impact, very positive reviews, a significant increase in capability realized, and hard copies of class resources for ongoing reference obtained. 17 supporters donated $9,916 in a Commit Change fundraising campaign. 12 students enrolled in the class, which was delivered by MathWorks and cost $15,000.
F) Inner Circle newsletter launch was successful and contains project reports, guest editorials, outreach, and updates. Newsletter is free, friendly, and accessible. The goal is at least monthly, with special editions encouraged.
G) Next scheduled board meeting set for six months out.
Meeting Adjournment Time and Signature
Meeting adjourned at 1100 US Pacific time.
Minutes recorded by Acting Secretary Michelle Thompson
Minutes submitted to the board of directors for review 1 September 2023.
RFBitBanger DEFCON31 Show Special has Sold Out
Thank you to everyone helping spread the word about the HF QRP digital RFBitBanger kit DEFCON31 Show Special. We sold out the 99 kits with 13 hours to spare.
Here’s the geographical distribution of this version of the RFBitBanger kit.
Main boards are in process at the manufacturer with final inspection expected today, 31 August 2023.
The bandpass filter boards, which have been upgraded from “three bands included and one spare” to “nine bands included and three spares” at no additional cost, are in process and expected to be complete no earlier than 4 September 2023.
Kitting is well underway with the machining of the heat sinks completed.
This DEFCON31 version of the board is black in color to distinguish it from potential future versions. Here is a rendering of the top side of the board.
The RFBitBanger team is discussing future builds on the #rfbitbanger channel on our Slack account right now.
The next opportunity for a show special is for QSO Today Academy, 9-10 September 2023, where Dr. Daniel Marks is speaking about the RFBitBanger and SCAMP mode. Find out more about this event here: https://www.qsotodayhamexpo.com/
This project would not be successful with your support, feedback, and advice. Thank you all for making this project, one of many at ORI, a big success. There’s been a lot of interest in this project and some very nice coverage from Hackaday and QRZ blogs, with more articles expected in the future.
Getting the word out about what we do is up to people like you. Do you know of any open source digital radio projects that need a friendly and supportive home? We can help with ethical, professional, and competent research and development support.
https://www.openresearch.institute/your-project-is-welcome/
Inner Circle Newsletter – All About the RFBitBanger
Three Days Remaining for the RFBitBanger HF Radio Kit DEFCON Show Special
Be a part of the future with a prototype kit build of the RFBitBanger, a low-power high-frequency digital radio by Dr. Daniel Marks KW4TI. Presented by Open Research Institute, this kit is designed to produce 4 watts of power and opens up a new digital protocol called SCAMP. Your donation in exchange for this kit directly enables the development of an innovative Class E amplifier based radio design. It has a display, button menu navigation, and keyboard connection for keyboard modes and keyboard-enabled navigation. This radio can be taken portable or used in a case. If you have a 3d printer, then Dr. Marks has a design ready for you to print.
- Built-in digital modes: CW, RTTY, SCAMP (FSK and OOK, multiple speeds)
- Key jack supports straight keys and iambic paddles
- Open Source hardware and firmware, Arduino UNO compatible https://github.com/profdc9/RFBitBanger
- External sound-card FSK digital modes supported (including FT4/FT8)
- Experimental SSB support
- Serial port support (2400 baud) for send and receive in keyboard modes
SCAMP is a new protocol that allows keyboard-to-keyboard contacts with a digital protocol that has excellent connection performance. See Dr. Marks presentation about RFBitBanger at QSO Today Academy in September 2023 to learn more about SCAMP and the RFBitBanger project. Information about that event is here: https://www.qsotodayhamexpo.com/
All surface mount parts on the main board are pre-installed at the factory. All the through-hole parts you need to complete the radio are provided for you to solder yourself. If you don’t know how to wind toroids or solder surface mount capacitors, this is an excellent kit to learn on. There are just six toroids on the main board, and two on each band pass filter board. You can build just one band pass filter board and operate on a single band, or you can build an assortment. We provide 12 filter boards, enough toroids to build any 9 filters, and a supply of capacitors that will let you build those 9 filters for 9 different HF ham bands. These capacitors are size 1206, which is the largest common size for SMT capacitors and the easiest to solder manually. All you’ll need is a pair of tweezers and your regular soldering iron and solder. We provide detailed instructions on winding the toroids and soldering the capacitors. You get spare filter boards to experiment with.
Support is provided through a dedicated Open Research Institute Slack channel.
Instructions on how to join the ORI community are here:
https://openresearch.institute/getting-started
Delivery is no earlier than late August 2023. Will be posted here and on the ORI website at https://www.openresearch.institute/rfbitbanger-project/
If you missed this sale, check out the upcoming show special at QSO Today Academy.
Want to Learn More About RFBitBanger?
Project lead Dr. Daniel Marks will give a presentation about the RFBitBanger at QSO Today Academy 9 September 2023 1300 PDT, 0800 UTC.
Daniel Marks, KW4TI, is a Ph.D. in Electrical Engineering, having graduated from the University of Illinois at Urbana-Champaign in 2001. His fields of speciality include optical engineering, computed imaging, and signal processing. He has made dozens of open hardware projects including many for amateur radio.
https://wze95h.qsotodayhamexpo.com/sessionInfo/_the_rfbitbanger_an_off_the_grid_emergency
The recent shortage of semiconductors, parts important for electronics, shows us that supply chains can be fragile. What does this mean? It means if we have a big problem for a long time, our advanced radios might be tough to keep working, which could be a problem in an emergency.
To solve this, a new kind of radio called the RFBitBanger has been created. It’s a type of low power, long-distance radio that is easy to build from basic parts using simple tools. It uses a new digital language, called SCAMP, made specifically for this radio.
All the signal work is done by an Arduino processor. What’s cool is that the radio has a small screen and buttons or you can even attach a keyboard. It’s a full text communications system all by itself. SCAMP is pretty special too. Even though it only needs a simple 8-bit microcontroller, it can do lots of things that digital modes like FT8 can do using small bandwidth and something called forward error correction.
The RFBitBanger radio has other helpful features. It can support CW (which is Morse code), RTTY (another way of sending text), and SSB phone (voice communication).
We hope that the RFBitBanger can serve as an easy-to-build and easy-to-maintain emergency radio. It can also be a great educational kit. And, it can be a lifesaver when there’s a big shortage of parts.
Media for RFBitBanger
Thank you to Hackaday and QRZ forums for covering the RFBitBanger project. Here are the links to the articles.
RFBitBanger Kit DEFCON31 Show Special
Be a part of the future with a prototype kit build of the RFBitBanger, a low-power high-frequency digital radio by Dr. Daniel Marks KW4TI. Presented by Open Research Institute, this kit is designed to produce 4 watts of power and opens up a new digital protocol called SCAMP. Your donation in exchange for this kit directly enables the development of an innovative Class E amplifier based radio design. It has a display, button menu navigation, and keyboard connection for keyboard modes and keyboard-enabled navigation. This radio can be taken portable or used in a case. If you have a 3d printer, then Dr. Marks has a design ready for you to print.
Receive a kit for your donation here: https://us.commitchange.com/ca/san-diego/open-research-institute/campaigns/defcon31-rfbitbanger-show-specpeial
- Built-in digital modes: CW, RTTY, SCAMP (FSK and OOK, multiple speeds)
- Key jack supports straight keys and iambic paddles
- Open Source hardware and firmware, Arduino UNO compatible https://github.com/profdc9/RFBitBanger
- External sound-card FSK digital modes supported (includes FT4/FT8)
- Experimental SSB support
- Serial port support (2400 baud) for send and receive in keyboard modes
SCAMP is a new protocol that allows keyboard-to-keyboard contacts with a digital protocol that has excellent connection performance. See Dr. Marks presentation about RFBitBanger at QSO Today Academy in September 2023 to learn more about SCAMP and the RFBitBanger project. Information about that event is here: https://www.qsotodayhamexpo.com/
Surface mount parts are pre-installed. You will need to have through-hole parts installation skills to complete the kit. If you don’t know how to wind toroids, this is an excellent kit to learn on. 80, 40, and 20 meter band pass filters are included. More will be available soon.
Support is provided through a dedicated Open Research Institute Slack channel.
Instructions on how to join are here:
Delivery is no earlier than late August 2023. Updates will be shared here in the news section as well as on the RFBitBanger page at https://www.openresearch.institute/rfbitbanger-project/
Opportunities This Week at ORI
Greetings all!
What do you need help with this week?
Here’s some opportunities at ORI.
1) Pierre and Ahmet are looking for people to help with mobile app design on Ribbit.
The Ribbit Radio app is in both Android and Apple testing. The updates to Rattlegram are incorporated and the app is functional on both platforms. We have had excellent response for test teams and things are moving forward.
To make the app as great as it can be, we could use some additional human resources for UX/UI/code development. If this sounds like something you are interested in, please join #ribbit on our Slack or write to me directly and I’ll get you in touch with the team leads.
2) DEFCON volunteers for the booth/exhibit. We’ve got just enough people to cover it. It’s a great event. We have solid support from RF Village and we advertise to Ham Radio Village. If you have been sitting on the sidelines waiting for a chance to do something for ORI, this is the best event of the year.
https://defcon.org/ for details about DEFCON 10-13 August 2023
https://wirelessvillage.ninja/ for details about our Village, RF Hackers Sanctuary.
3) FPGA designs for Haifuraiya and Neptune. Want to use MATLAB/Simulink, VHDL, and Verilog to make open source digital communications designs for aerospace, terrestrial, and drones? These designs run on updated FPGA stations in ORI Remote Labs, and everything is on the microwave amateur radio bands. When you see microwave frequencies mentioned, then it’s good to also say that “we use these bands or lose them”. We’ve got plenty to do. Get in touch on #haifuraiya or #neptune on Slack or to any ORI director.
4) Meander Dipole construction phase. Project Dumbbell explores an overlooked HF antenna design. There’s been strong interest in these designs from multiple people (some of which are on this list), clubs, and organizations. We need to build the designs that MATLAB says look pretty good. Time to make it work over the air and write up some construction and measured performance articles.
As always, there’s plenty more going on, but these projects have some specific needs, today.
Thank you to everyone that supports our work. I’d like to especially thank the IEEE and ARRL for being excellent partners to ORI.
-Michelle Thompson
Open Source Digital Radio IEEE Group Announcement
A new #opensource group for #digital #communications has formed in #IEEE. This looks to be the first dedicated Open Source #hamradio friendly group in largest engineering professional society in the world. ORI will be sponsoring activities and supporting volunteers.
You do not need to be a member of #IEEE to join the Collabratec workspace linked below.
Project Neptune
Neptune is an open source implementation of an open protocol for high-throughput multimedia drone communications from Open Research Institute. This protocol directly competes against the proprietary designs from DJI.
Implementation prototypes use the Xilinx Ultrascale+ and Analog Devices 9002 RFSOC. These development boards are accessible at no cost through ORI Remote Labs West. Amateur radio bands will be used to the fullest extent. Full Vivado and MATLAB licenses are included.
A review of the OFDM-based physical layer draft specification will happen shortly and invitations are going out now. Participants must be proficient with the design review process, understand OFDM, accept our developer and participant code of conduct, and support open source work.
To join as a participant please visit https://openresearch.institute/getting-started
Join the #neptune channel on ORI Slack.
To keep informed about our work you should know about our newsletter at https://www.openresearch.institute/newsletter-subscription/
Thank you to everyone that has made this innovative and groundbreaking project possible. We deeply appreciate your support and we will be successful with this design.
Inner Circle Newsletter April 2023
Welcome to our newsletter for April 2023!
Inner Circle is your update on what’s happening at and adjacent to Open Research Institute. We’re a non-profit dedicated to open source digital radio work. We support technical and regulatory efforts. A major beneficiary of this work is the amateur radio services. Sign up at this link http://eepurl.com/h_hYzL
Contents:
- Guest Editorial by Dr. Daniel Estévez Amaranth in Practice
- Federal Communications Commission Technological Advisory Council resumes!
- HDL Coder for Software Defined Radio Class May 2023
- FPGA Workshop Cruise with ORI?
Amaranth in practice: a case study with Maia SDR
Maia SDR is a new open-source FPGA-based SDR project focusing on the ADALM Pluto. The longer term goals of the project are to foster open-source development of SDR applications on FPGA and to promote the collaboration between the open-source SDR and FPGA communities. For the time being, focusing on developing a firmware image for the ADALM Pluto that uses the FPGA for most of the signal processing provides realistic goals and a product based on readily available hardware that people can already try and use during early stages of development.
The first version of Maia SDR was released on Februrary 2023, though its development started in September 2022. This version has a WebSDR-like web interface that displays a realtime waterfall with a sample rate of up to 61.44Msps and is able to make IQ recordings at that rate to the Pluto DDR (up to a maximum size of 400MiB per recording). These recordings can then be downloaded in SigMF format.
Exploring the RF world in the field with a portable device is one of the goals of Maia SDR, so its web UI is developed having in mind the usage from a smartphone and fully supports touch gestures to zoom and scroll the waterfall. A Pluto connected by USB Ethernet to a smartphone already give a quite capable and portable tool to discover and record signals.
The following figure shows a screenshot of the Maia SDR web user
interface. More information about the project can be found in
https://maia-sdr.net
Amaranth
Amaranth is an open-source HDL based in Python. The project is led by Catherine “whitequark”, who is one of the most active and prolific developers in the open-source FPGA community. Amaranth was previously called nMigen, as it was initially developed as an evolution of the Migen FHDL by M-Labs.
I cannot introduce Amaranth any better than Catherine, so I will just cite her words from the README and documentation.
The Amaranth project provides an open-source toolchain for developing hardware based on synchronous digital logic using the Python programming language, as well as evaluation board definitions, a System on Chip toolkit, and more. It aims to be easy to learn and use, reduce or eliminate common coding mistakes, and simplify the design of complex hardware with reusable components.
The Amaranth toolchain consists of the Amaranth hardware definition language, the standard library, the simulator, and the build system, covering all steps of a typical FPGA development workflow. At the same time, it does not restrict the designer’s choice of tools: existing industry-standard (System)Verilog or VHDL code can be integrated into an Amaranth-based design flow, or, conversely, Amaranth code can be integrated into an existing Verilog-based design flow.
The Amaranth documentation gives a tutorial for the language and includes as a first example the following counter with a fixed limit.
from amaranth import *
class UpCounter(Elaboratable):
"""
A 16-bit up counter with a fixed limit.
Parameters
----------
limit : int
The value at which the counter overflows.
Attributes
----------
en : Signal, in
The counter is incremented if ``en`` is asserted, and retains
its value otherwise.
ovf : Signal, out
``ovf`` is asserted when the counter reaches its limit.
"""
def __init__(self, limit):
self.limit = limit
# Ports
self.en = Signal()
self.ovf = Signal()
# State
self.count = Signal(16)
def elaborate(self, platform):
m = Module()
m.d.comb += self.ovf.eq(self.count == self.limit)
with m.If(self.en):
with m.If(self.ovf):
m.d.sync += self.count.eq(0)
with m.Else():
m.d.sync += self.count.eq(self.count + 1)
return m
Amaranth Elaboratable
‘s are akin to Verilog
module
‘s (and in fact get synthesized to
module
‘s if we convert Amaranth to Verilog). IO ports for
the module are created in the __init__()
method. The
elaborate()
method can create additional logic elements
besides those created in __init__()
by instantiating more
Signal
‘s (this example does not do this). It also describes
the logical relationships between all these Signals
by
means of a Module()
instance usually called m
.
Essentially, at some point in time, the value of a Signal
changes depending on the values of some Signal
‘s and
potentially on some conditions. Such point in time can be either
continuously, which is described by the m.d.comb
combinational domain, or at the next rising clock edge, which
is described by the m.d.sync
synchronous domain (which is,
roughly speaking, the “default” or “main” clock domain of the module),
or by another clock domain. Conditions are expressed using
with
statements, such as with m.If(self.en)
,
in a way that feels quite similar to writing Python code.
For me, one of the fundamental concepts of Amaranth is the division
between what gets run by Python at synthesis time, and what gets run by
the hardware when our design eventually comes to life in an FPGA. In the
elaborate()
method we have a combination of “regular”
Python code, which will get run in our machine when we convert the
Amaranth design to Verilog or generate a bitstream directly from it, as
well as code that describes what the hardware does. The latter is also
Python code, but we should think that the effects of running it are only
injecting that description into the list of things that Amaranth knows
about our hardware design.
Code describing the hardware appears mainly in two cases: First, when
we operate with the values of signals. For instance,
self.count + 1
does not take the value of
self.count
and add one to it when the Python code is run.
It merely describes that the hardware should somehow obtain the sum of
the value of the register corresponding to self.count
and
the constant one. This expression is in effect describing a hardware
adder, and it will cause an adder to appear in our FPGA design. This
behaviour is reminiscent of how Dask and other packages based on lazy
evaluation work (in Dask, operations with dataframes only describe
computations; the actual work is only done eventually, when the
compute()
method is called). I want to stress that the
expression self.count + 1
might as well appear in
elaborate()
only after a series of fairly complicated
if
and else
statements using regular Python
code. These statements will be evaluated at synthesis time, and our
hardware design will end up having an adder or not depending on these
conditions. Similarly, instead of the constant 1
in the
+ 1
operation, we could have a Python variable that is
evaluated in synthesis time, perhaps as the result of running fairly
complicated code. This will also affect what constant the hardware adder
that we have in our design adds to the value of the
self.count
register.
Secondly, we have the control structures: m.If
,
m.Else
, and a few more. These also describe hardware.
Whether the condition is satisfied is not evaluated when the Python
script runs. What these conditionals do is to modify the hardware
description formed by the assignments to m.d.sync
and
m.d.comb
that they enclose so that these assignments are
only effective (or active) in the moments in which the condition is
satisfied. In practice, these statements do two things in the resulting
hardware: They multiplex between several intermediate results depending
on some conditions, in a way that is usually more readable than using
the Mux()
operator that Amaranth also provides. They also
control what logic function gets wired to the clock enable of
flip-flops. Indeed, in some conditions a synchronous
Signal()
may have no active statements, in which case it
should hold its current value. This behaviour can be implemented in
hardware either by deasserting the clock enable of the flip-flops or by
feeding back the output of the flip-flops to their input through a
multiplexer. What is done depends mainly on choices done by the
synthesis tool when mapping the RTL to FPGA elements. As before, we can
have “regular” Python code that is run at synthesis time modifying how
these m.If
control structures look like, or even whether
they appear in the design at all.
In a sense, the regular Python code that gets run at synthesis time
is similar to Verilog and VHDL generate
blocks. However,
this is extremely more powerful, because we have all the expressiveness
and power of Python at our disposal to influence how we build our design
at synthesis time. Hopefully the following examples from Maia SDR can
illustrate how useful this can be.
maia-hdl
maia-hdl is the FPGA design of Maia SDR. It is bundled as a Python
package, with the intention to make easy to reuse the modules in third
party designs. The top level of the design is an Amaranth
Elaboratable
that gets synthesized to Verilog and packaged
as a Vivado IP core. As shown below, the IP core has re_in
and im_in
ports for the IQ data of the ADC, an AXI4-Lite
subordinate interface to allow the ARM processor to control the core
through memory-mapped registers, AXI3 manager interfaces for the DMAs of
the spectrometer (waterfall) and IQ recorder, and ports for clocking and
reset.
The IP core is instantiated in the block design of a Vivado project that gets created and implemented using a TCL script. This is based on the build system used by Analog Devices for the default Pluto FPGA bitstream. In this respect, Maia SDR gives a good example of how Amaranth can be integrated in a typical flow using the Xilinx tools.
There are two classes of unit tests in maia-hdl. The first are Amaranth simulations. These use the Amaranth simulator, which is a Python simulator than can only simulate Amaranth designs. These tests give a simple but efficient and powerful way of testing Amaranth-only modules. The second are cocotb simulations. Cocotb is an open-source cosimulation testbench environment for verifying VHDL and Verilog designs using Python. Briefly speaking, it drives an HDL simulator using Python to control the inputs and check the outputs of the device under test. Cocotb has rich environment that includes Python classes that implement AXI devices. In maia-hdl, cocotb is used together with Icarus Verilog for the simulation of designs that involve Verilog modules (which happens in the cases in which we are instantiating from Amaranth a Xilinx primitive that is simulated with the Unisim library), and for those simulations in which the cocotb library is specially useful (such as for example, when using the cocotb AXI4-Lite Manager class to test our AXI4-Lite registers).
One of the driving features of Maia SDR is to optimize the FPGA resource utilization. This is important, because the Pluto Zynq-7010 FPGA is not so large, specially compared with other Xilinx FPGAs. To this end, Amaranth gives a good control about how the FPGA design will look like in terms of LUTs, registers, etc. The example with the counter has perhaps already shown that Amaranth is a low-level language, in the same sense that Verilog and VHDL are, and nothing comparable to HLS (where regular C code is translated to an FPGA design).
FFT
The main protagonist of the Maia SDR FPGA design is a custom pipelined FFT core that focuses on low resource utilization. In the Maia SDR Pluto firmware it is used as a radix-2² single-delay-feedback decimation-in-frequency 4096-point FFT with a Blackman-harris window. It can run at up to 62.5 Msps and uses only around 2.2 kLUTs, 1.4 kregisters, 9.5 BRAMs, and 6 DSPs. One of the tricks that allows to save a lot of DSPs is to use a single DSP for each complex multiplication, by performing the three required real products sequentially with a 187.5 MHz clock. A description of the design of the FFT core is out of the scope of this article, but I want to show a few features that showcase the strengths of Amaranth.
The first is the FFTControl
module. The job of this
module is to generate the control signals for all the elements of the
FFT pipeline. In each clock cycle, it selects which operation each
butterfly should do, which twiddle factor should be used by each
multiplier, as well as the read and write addresses to use for the delay
lines that are implemented with BRAMs (these are used for the first
stages of the pipeline, which require large delay lines). As one can
imagine, these control outputs are greatly dependent on the
synchronization of all the elements. For example, if we introduce an
extra delay of one cycle in one of the elements, perhaps because we
register the data to satisfy timing constraints, all the elements
following this in the pipeline will need their control inputs to be
offset in time by one cycle.
It is really difficult to implement something like this in Verilog or VHDL. Changing these aspects of the synchronization of the design usually requires rethinking and rewriting parts of the control logic. In Amaranth, our modules are Python classes. We can have them “talk to each other” at synthesis time and agree on how the control should be set up, in such a way that the result will still work if we change the synchronization parameters.
For example, all the classes that are FFT pipeline elements implement
a delay
Python @property
that states what is
the input to output delay of the module measured in clock cycles. For
some simple modules this is always the same constant, but for a
single-delay-feedback butterfly it depends on the length of the delay
line of the butterfly, and for a twiddle factor multiplier it depends on
whether the multiplier is implemented with one or three DSPs. These are
choices that are done at synthesis time based on parameters that are
passed to the __init__()
method of these modules.
The FFTControl
module can ask at synthesis time to all
the elements that form the FFT pipeline what are their delays, and
figure out the reset values of some counters and the lengths of some
delay lines accordingly. This makes the control logic work correctly,
regardless what these delays are. For instance, the following method of
FFTControl
computes the delay between the input of the FFT
and the input of each butterfly by summing up the delays of all the
preceding elements.
def delay_butterflies_input(self):
"""Gives the delay from the FFT input to the input of each of the
butterflies"""
return [
self.delay_window
+ sum([butterfly.delay for butterfly in self.butterflies[:j]])
+ sum([twiddle.delay for twiddle in self.twiddles[:j]])
for j in range(self.stages)
]
This is then used in the calculation of the length of some delay lines that supply the control signals to the butterflies. The code is slightly convoluted, but accounts for all possible cases. I don’t think it would be reasonable to do this kind of thing in Verilog or VHDL.
mux_bfly_delay = [
[Signal(2 if isinstance(self.butterflies[j], R22SDF) else 1,
name=f'mux_bfly{j}_delay{k}', reset_less=True)
for k in range(0,
delay_butterflies_input[j]
- delay_twiddles_input[j-1]
+ self.twiddles[j-1].twiddle_index_advance)]
for j in range(1, self.stages)]
Another important aspect facilitated by Amaranth is the construction
of a model. We need a bit-exact model of our FFT core in order to be
able to test it in different situations and to validate simulations of
the Amaranth design against the model. Each of the modules that form the
pipeline has a model()
method that uses NumPy to calculate
the output of that module given some inputs expressed as NumPy arrays.
Here is the model for a radix-2 decimation-in-frequency
single-delay-feedback butterfly. Perhaps it looks somewhat reasonable if
we remember that such a butterfly basically computes first
x[n] + x[n+v//2]
, for n = 0, 1, ..., v//2-1
,
and then x[n] - x[n+v//2]
for
n = 0, 1, ..., v//2-1
.
[class R2SDF(Elaboratable):]
[...]
def model(self, re_in, im_in):
v = self.model_vlen
re_in, im_in = (np.array(x, 'int').reshape(-1, 2, v // 2)
for x in [re_in, im_in])
re_out, im_out = [
clamp_nbits(
np.concatenate(
(x[:, 0] + x[:, 1], x[:, 0] - x[:, 1]),
axis=-1).ravel() >> self.trunc,
self.w_out)
for x in [re_in, im_in]]
return re_out, im_out
The interesting thing is that, since each of the FFT pipeline modules
has its individual model, it is easy to verify the simulation of each
module against its model separately. The model of the FFT
module, which represents the whole FFT core, simply puts everything
together by calling the model()
methods of each of the
elements in the pipeline in sequence. An important detail here is that
the arrays self._butterflies
and
self._twiddles
are the same ones that are used to
instantiate and connect together the pipeline modules, in terms of the
hardware design. By having these synergies between the model and the
hardware design, we reduce the chances of them getting out of sync due
to code changes.
[class FFT(Elaboratable):]
[...]
def model(self, re_in, im_in):
v = self.model_vlen
re = re_in
im = im_in
if self._window is not None:
re, im = self._window.model(re, im)
for j in range(self.nstages):
re, im = self._butterflies[j].model(re, im)
if j != self.nstages - 1:
re, im = self._twiddles[j].model(re, im)
return re, im
Instantiating Verilog modules and primitives
A question that often comes up is how to instantiate Verilog modules,
VHDL entities or FPGA primitives in an Amaranth design. Kate Temkin has
a short blog
post about it. In maia-hdl this is used in in several cases, such as
to implement clock domain crossing with the Xilinx FIFO18E1 primitive.
The most interesting example is however the Cmult3x
module,
which implements complex multiplication with a single DSP48E1 that runs
at three clock cycles per input sample (some simple algebra shows that a
complex multiplication can be written with only three real
multiplications).
When designing modules with DSPs, I prefer to write HDL code that will make Vivado infer the DSPs I want. This is possible in simple cases, but in more complicated situations it is not possible to make Vivado understand exactly what we want, so we need to instantiate the DSP48 primitives by hand.
The drawback of having an Amaranth design that contains instances of Verilog modules, VHDL entities or primitives is that we can no longer simulate our design with the Amaranth simulator. If our instances have a Verilog model (such as is the case with Xilinx primitives via the Unisim library), we can still convert the Amaranth design to Verilog and use a Verilog simulator. This is done in maia-hdl using Icarus Verilog and cocotb. However, this can be somewhat inconvenient.
There is another possibility, which is to write different implementations of the same Amaranth module. One of them can be pure Amaranth code, which we will use for simulation, and another can use Verilog modules or primitives. The two implementations need to be functionally equivalent, but we can check this through testing.
The way to acomplish this is through Amaranth’s concept of platform.
The platform is a Python object that gets passed to the
elaborate()
methods of the modules in the design. The
elaborate methods can then ask the platform for some objects that are
usually dependent on the FPGA family, such as flip-flop synchronizers.
This is a way of building designs that are more portable to different
families. The platform objects are also instrumental in the process of
building the bitstream completely within Amaranth, which is possible for
some FPGA families that have an open-source toolchain.
In the case of the maia-hdl Cmult3x
we simply check
whether the platform we’ve been passed is an instance of
XilinxPlatform
and depending on this we have the
elaborate()
method either describe a pure Amaranth design
that models the DSP48 functionality that we need, or instantiate a
DSP48E1 primitive. Note that in the case of the pure Amaranth design we
do not model the full functionality of the DSP48. Only that which is
applicable to this use case.
[class Cmult3x(Elaboratable):]
[...]
def elaborate(self, platform):
if isinstance(platform, XilinxPlatform):
return self.elaborate_xilinx(platform)
# Amaranth design. Vivado doesn't infer a single DSP48E1 as we want.
[ ... here a pure amaranth design follows ... ]
def elaborate_xilinx(self, platform):
# Design with an instantiated DSP48E1
[...]
m.submodules.dsp = dsp = Instance(
'DSP48E1',
[...]
Registers
Another aspect where the flexibility of Amaranth shines is in the
creation of register banks. In maia-hdl, the module
Register
corresponds to a single 32-bit wide register and
the module Registers
forms a register bank by putting
together several of these registers, each with their corresponding
address. The registers support a simple bus for reads and writes, and an
Axi4LiteRegisterBridge
module is provided to translate
between AXI4-Lite and this bus, allowing the ARM CPU to access the
registers.
Registers and register banks are created with Python code that
describes the fields of the registers. The basic ingredient is the
Field
named tuple:
Field = collections.namedtuple('RegisterField',
['name', 'access', 'width', 'reset'])
We describe a register by giving it a name, an access mode (which can be read-only, write-only, read-write, or some other more specialized modes that we will describe below), a width, and a reset or default value.
The best way to understand how to work with these registers is to see how they are used in the Maia SDR top-level design.
self.control_registers = Registers(
'control',
{
0b00: Register(
'product_id', [
Field('product_id', Access.R, 32, 0x6169616d)
]),
0b01: Register('version', [
Field('bugfix', Access.R, 8,
int(_version.split('.')[2])),
Field('minor', Access.R, 8,
int(_version.split('.')[1])),
Field('major', Access.R, 8,
int(_version.split('.')[0])),
Field('platform', Access.R, 8, 0),
]),
0b10: Register('control', [
Field('sdr_reset', Access.RW, 1, 1),
]),
0b11: Register('interrupts', [
Field('spectrometer', Access.Rsticky, 1, 0),
Field('recorder', Access.Rsticky, 1, 0),
], interrupt=True),
},
2)
self.recorder_registers = Registers(
'recorder',
{
0b0: Register('recorder_control', [
Field('start', Access.Wpulse, 1, 0),
Field('stop', Access.Wpulse, 1, 0),
Field('mode_8bit', Access.RW, 1, 0),
Field('dropped_samples', Access.R, 1, 0),
]),
0b1: Register('recorder_next_address', [
Field('next_address', Access.R, 32, 0),
]),
},
1)
Here we show two register banks: one for the control of the IP core and another for the control of the IQ recorder. There is a similar third register bank for the control of the spectrometer (waterfall).
The parameters of the Registers
constructor are a name,
a dictionary that contains the registers in the bank (the keys of the
dictionary are the addresses, and the values are the
Register
objects), and the width of the address bus. Note
that these addresses correspond to the addressing of the native register
bus. When we convert to AXI4-Lite, the addresses get shifted by two bits
to the left because each register is 4 bytes wide.
The parameters of the Register
constructor are a name
and a list of Field
‘s describing the fields of the
register. Fields are allocated into the 32-bit register according to
their order in the list, starting by the LSB. For instance, in the
interrupts
register, the spectrometer
field
occupies the LSB and the recorder
field occupies the next
bit.
If we look at the control
registers, we can see that the
registers for product_id
and version
have
access type R
, which means read-only. These registers are
never wired in the design to other signals that would override their
default values, so they are in fact constants that the CPU can read to
check that the IP core is present and find its version number.
Next we have a control
register, which has an
sdr_reset
field. This is wired internally to a bunch of
reset signals in the IP core. It has a default value of 1, which means
that most of the IP core starts in reset. The CPU can write a 0 to this
field to take the IP core out of reset before using it. Accessing this
sdr_reset
field within the design is very simple, because
the Registers
and Register
implement
__getitem__()
, allowing us to access them as if they were
dictionaries. This example shows how it works. Here we are connecting
the field sdr_reset
to the reset input of something called
rxiq_cdc
(which implements clock domain crossing between
the ADC sampling clock and the internal clock used in the IP core).
m.d.comb += rxiq_cdc.reset.eq(
self.control_registers['control']['sdr_reset'])
If we look at the interrupts
register, we can see an
example of the Rsticky
access mode. This means read-only
sticky. A field of this type will be set to 1 when its input (which is
wired internally in the IP core) has the value 1. It will keep the value
1 even if the input goes back to 0. The field is cleared and set to 0
when it is read. The intended use for this access mode is interrupts. A
module can pulse the input of the field to notify an interrupt, and the
field will hold a 1 until the CPU reads the register, clearing the
interrupts. The interrupts
register even has an
interrupt=True
option that provides an interrupt output
that can be connected directly to the F2P interrupt port of the Zynq.
This interrupt output will be high whenever any Rsticky
field in the register is non-zero.
Finally, the recorder_control
field gives some examples
of the Wpulse
access type. This is a write-only field with
pulsed output. Writing a 1 to this field causes a one-cycle pulse at its
output. This is ideal for controlling modules that require a pulse to
indicate some event or command. For example, this is the case with the
start and stop commands of the IQ recorder.
The Amaranth code that makes all of this work is not so complicated.
You can take a look at the register.py
file in maia-hdl to
see for yourself.
Another interesting feature of this register system is that it can write an SVD file describing the register map. CMSIS-SVD is an XML format that is often used to describe the register maps of microcontrollers and SoCs. Maia SDR uses svd2rust to generate a nice Rust API for register access.
The Registers
and Register
classes have
svd()
methods that generate the SVD XML using Python’s
xml.etree.ElementTree
. This is relatively simple, because
the classes already have all the information about these registers. It
is, after all, the same information that they use to describe the
hardware implementation of the registers. This is another example of how
by using synergies between the code that describes the hardware design
and code that does something related to that hardware design (in this
case, writing SVD), we make it harder for changes in the code base to
cause inconsistencies.
Conclusions
In this article we have gone from a “hello world” type counter in Amaranth to some rather intricate code from the inner workings of an FFT core. My intention with giving these code examples is not to expect the reader to understand all the code, but rather to give a feeling for how using Amaranth in complex projects can look like. Perhaps by now I have managed to convince you that Amaranth is a powerful and flexible alternative to HDLs such as Verilog and VHDL, or at least to get you interested in learning more about Amaranth and the world of open-source FPGA and silicon design.
Federal Communications Commission Technological Advisory Council resumes!
Want someone on your side at the FCC? We have good news. The FCC TAC is going to resume work. The previous term ended in December 2022 with an in-person meeting in Washington, DC. ORI was a member of the AI/ML Working Group and served as a co-chair of the “Safe Uses of AI/ML” sub-working group. The next term will be for two years. The appointment will require another round of nominations and vetting. An invitation to ORI has been made. ORI will speak up for open source digital radio work and the amateur radio services. Thank you to everyone that made the 2022 FCC TAC term productive and beneficial. Join the #ai channel on ORI Slack to get more involved. Not part of Slack? Visit https://openresearch.institute/getting-started to Get Started.
HDL Coder for Software Defined Radio Class May 2023
Sign-ups are live at https://us.commitchange.com/ca/san-diego/open-research-institute/campaigns/hdl-coder-for-software-defined-radio
Advanced training for Digital Communications, Software Defined Radio, and FPGAs will be held 1-5 May 2023. Do you know someone that can benefit from customized and focused training? Please forward this email to them. Designed to benefit open source digital radio, this course also benefits the amateur radio services.
Presented by ORI and taught by Mathworks, this class will cover the following topics.
COURSE OUTLINE
Day 1 – Generating HDL Code from Simulink & DSP for FPGAs
Preparing Simulink Models for HDL Code Generation (1.0 hrs)
Prepare a Simulink model for HDL code generation. Generate HDL code and testbench for simple models requiring no optimization.
- Preparing Simulink models for HDL code generation
- Generating HDL code
- Generating a test bench
- Verifying generated HDL code with an HDL simulator
Fixed-Point Precision Control (2.0 hrs)
Establish correspondence between generated HDL code and specific Simulink blocks in the model. Use Fixed-Point Tool to finalize fixed point architecture of the model.
- Fixed-point scaling and inheritance
- Fixed-Point Designer workflow
- Fixed-Point Tool
- Fundamental adders and multiplier arrays
- Division and square root arrays
- Wordlength issues and Fixed-point arithmetic
- Saturate and wraparound.
- Overflow and underflow
Optimizing Generated HDL Code (4 hrs)
Use pipelines to meet design timing requirements. Use specific hardware implementations and share resources for area optimization.
- Generating HDL code with the HDL Workflow Advisor
- Meeting timing requirements via pipelining
- Choosing specific hardware implementations for compatible Simulink blocks
- Sharing FPGA/ASIC resources in subsystems
- Verifying that the optimized HDL code is bit-true cycle-accurate
- Mapping Simulink blocks to dedicated hardware resources on FPGA
Day 2 – DSP for FPGAs
Signal Flow Graph (SFG) Techniques (SFG) Techniques and high-speed FIR design (2.0 hrs)
Review the representation of DSP algorithms using signal flow graph. Use the Cut Set method to improve timing performance. Implement parallel and serial FIR filters.
- DSP/Digital Filter Signal Flow Graphs
- Latency, delays and “anti-delays”!
- Re-timing: Cut-set and delay scaling
- The transpose FIR
- Pipelining and multichannel architectures
- SFG topologies for FPGAs
- FIR filter structures for FPGAs
Multirate Signal Processing for FPGAs (4.0 hrs)
Develop polyphase structure for efficient implementation of multirate filters. Use CIC filter for interpolation and decimation.
- Upsampling and interpolation filters
- Downsampling and decimation filters
- Efficient arithmetic for FIR implementation
- Integrators and differentiators
- Half-band, moving average and comb filters
- Cascade Integrator Comb (CIC) Filters (Hogenauer)
- Efficient arithmetic for IIR Filtering
CORDIC Techniques AND channelizers (2.0 hrs)
Introduce CORDIC algorithm for calculation of various trigonometric functions.
- CORDIC rotation mode and vector mode
- Compute cosine and sine function
- Compute vector magnitude and angle
- Architecture for FPGA implementation
- Channelizer
Day 3 – Programming Xilinx Zynq SoCs with MATLAB and Simulink & Software-Defined Radio with Zynq using Simulink
IP Core Generation and Deployment (2.0 hrs)
Use HDL Workflow Advisor to configure a Simulink model, generate and build both HDL and C code, and deploy to Zynq platform.
- Configuring a subsystem for programmable logic
- Configuring the target interface and peripherals
- Generating the IP core and integrating with SDK
- Building and deploying the FPGA bitstream
- Generating and deploying a software interface model
- Tuning parameters with External Mode
Model Communications System using Simulink (1.5 hrs)
Model and simulate RF signal chain and communications algorithms.
- Overview of software-defined radio concepts and workflows
- Model and understand AD9361 RF Agile Transceiver using Simulink
- Simulate a communications system that includes a transmitter, AD9361 Transceiver, channel and Receiver (RF test environment)
Implement Radio I/O with ADI RF SOM and Simulink (1.5 hrs)
Verify the operation of baseband transceiver algorithm using real data streamed from the AD9361 into MATLAB and Simulink.
- Overview of System object and hardware platform
- Set up ADI RF SOM as RF front-end for over-the-air signal capture or transmission
- Perform baseband processing in MATLAB and Simulink on captured receive signal
- Configure AD9361 registers and filters via System object
- Verify algorithm performance for real data versus simulated data
Prototype Deployment with Real-Time Data via HW/SW Co-Design (2.0 hrs)
Generate HDL and C code targeting the programmable logic (PL) and processing system (PS) on the Zynq SoC to implement TX/RX.
- Overview of Zynq HW/SW co-design workflow
- Implement Transmitter and Receiver on PL/PS using HW/SW co-design workflow
- Configure software interface model
- Download generated code to the ARM processor and tune system parameters in real-time operation via Simulink
- Deploy a stand-alone system
FPGA Workshop Cruise with ORI?
Want to learn more about open source FPGA development from experts in the field? Ready to capitalize on the HDL Coder for Software Defined Radio Class happening in May 2023? Want to get away? How about something that can give you both? We are looking at organizing an FPGA Workshop Adventure Cruise. Be part of the planning and write fpga@openresearch.institute
Are you interested in supporting work at ORI?
Consider being part of the board. We’d like to expand from 5 to 7 members in order to better serve our projects and community.
We’ve got lots going on with Opulent Voice, Haifuraiya, AmbaSat Respin, and regulatory work.
Thank you from everyone at ORI for your continued support and interest!
Want to be a part of the fun? Get in touch at ori@openresearch.institute
Class Announcement: HDL Coder for Software Defined Radio
Open Research Institute (https://openresearch.institute) has negotiated a customized class for advanced digital radio work. Content was chosen to directly benefit open source workers in the amateur radio service.
Registration link is below. A heavily subsidized link is offered. Class runs 1-5 May 2023 and is entirely virtual. Theoretical and practical content is offered. Class is taught by Mathworks instructors and uses their training platform.
The goal of this class is to expand the technical volunteer corps in amateur radio and amateur satellite services. Radio work accomplished on FPGAs and complex RFICs is the primary focus.
Updating the Opulent Voice Interleaver
The interleaver for Opulent Voice needs to be updated because the frame size has increased. We are incorporating RTP, UDP, and IP layers into the existing OPUS and 4-ary MFSK layers and now have what we think may be the final frame size.
Since convolutional encoding is used for Opulent Voice payload, an interleaver is necessary to get the best bit error rate performance out of the convolutional encoder. The interleaver is used over both the physical layer header (Golay encoded) and the data payload (a 1/2 rate Convolutional code). Opulent Voice is an open protocol that we use for our HEO/GEO uplink. It can also be used terrestrially on the #hamradio bands at 70cm and above. Find out more at https://www.openresearch.institute/2022/07/30/opulent-voice-digital-voice-and-data-protocol-update/
The distance that an interleaver spreads out bits in a frame is the most familiar performance measurement. It’s commonly called “spread” or “minimum interleaved distance”. However, we learned about another metric that is important in Turbo codes. Several papers refer to the measure of randomness of the mixture of bit position reassignments as “dispersion” (for example, see https://cgi.tu-harburg.de/~c00e8lit/cgi-bin/ivpub/download.php?file=kb-wpmc2008.pdf). That particular paper cited another paper (reference [6]) as defining dispersion.
Following that citation lead to a paper but this paper didn’t mention dispersion or explain the equation. Going back to the original paper, we started working with the definition for dispersion that we had. This used the cardinality of the set of indices of original bit positions vs. permuted bit positions. This seemed straightforward enough. But, after trying this in MATLAB, we always got the minimum dispersion value, so there must be something wrong with our interpretation.
Volunteers then spent time trying to figure out if dispersion is important enough metric for a single convolutional code, like we have in #OpulentVoice. In other words, should we simply not simply choose the polynomials that result in the largest minimum interleaved distance? Selecting the right interleaver based on a balance between how far apart it spreads the bits vs. how randomly the bits are distributed is a useful selection methodology for Turbo codes, but may not be strictly necessary for a single convolutional code used with 40 mS frames.
Everyone is welcome to join in the discussion and work to create quality #OpenSource work for #digital communications at ORI. Please see https://openresearch.institute/getting-started to be welcomed to our community.
Inner Circle Newsletter March 2023
March 2023 Inner Circle
Welcome to our newsletter for March 2023!
Inner Circle is a non-technical update on everything that is happening at ORI. Sign up at this link http://eepurl.com/h_hYzL
Contents:
FPGA Workshop Cruise with ORI?
ORI’s Birthday 6 March – Celebrate With Pins!
RFBitBanger Prototypes
Announcing the ORI App Stores
QSO Today Ham Expo Spotlight
Jay Francis in QEX
Pierre W4CKX Declares Candidacy for ORI Board of Directors
FPGA Workshop Cruise with ORI?
Want to learn more about open source FPGA development from experts in the field? Want to get away? How about something that can give you both? We are looking at organizing an FPGA Workshop Adventure Cruise. Be part of the planning and write fpga@openresearch.institute
ORI’s Birthday – Celebrate With Pins!
We celebrate our 4th birthday on 6 March 2023. Thank you to everyone that has helped ORI grow and succeed in so many different ways. To commemorate our anniversary, we have a limited edition acrylic logo pin. They will be available for a small donation at all upcoming in-person events. Where will be be? We’ll be at DEFCON 31 and IEEE IWRC in Little Rock, AR, USA 13-14 September 2023. Want to include us at your event before then? Let us know at hello@openresearch.institute
RFBitBanger Prototypes
Interested in high frequency amateur (HF) bands? Want to learn about Class E amplification? Excited about open HF digital protocols that aren’t just signal reports? Well, we have a kit for you. Here’s a walk-through by Paul KB5MU of all RFBitBanger modes. This project is lead by Dr. Daniel Marks, is enthusiastically supported by ORI, and will be demonstrated at DEFCON in August 2023. We are doing all we can to have kits available for sale by DEFCON, or sooner.
Announcing the ORI App Stores
Open Research Institute can be found in the Google Play Store and the Apple App Store. That’s right – we are in both app stores delivering open source mobile apps. Thank you to everyone that has helped make this possible. The Ribbit app will be available on both platforms as our initial release. Do you know of an open source application that needs a home? Get in touch at hello@openresearch.institute and let’s talk. We want to share our platform and support applications that help open source and amateur radio.
QSO Today Ham Expo Spotlight
We hope to see you again at QSO Today Ham Expo, 25-26 March 2023. If you haven’t gotten a ticket yet, please visit https://www.qsotodayhamexpo.com/
This is a wonderful event that showcases the best parts of amateur radio. The theme for this Ham Expo is “New License – Now What?” Recordings will be available on the Ham Expo platform for a month, and then will be available on YouTube for anyone to view. ORI will volunteer at the March 2023 QSO Ham Expo session and will have technical presentations, a booth, and poster sessions at the Autumn 2023 QSO Today Ham Expo.
Jay Francis in QEX
Please see page 20 of the March/April 2023 issue of QEX magazine for an article co-authored by Jay Francis, our AmbaSat Re-Spin team lead. Excellent job, Jay!
Pierre W4CKX has declared his candidacy for ORI Board of Directors
We welcome Pierre’s interest in being a member of the board. Pierre is the Ribbit project lead. He brings broad industry knowledge, experience in Agile project management, a commitment to ethical leadership, and innovative energy. Learn about all our directors at https://www.openresearch.institute/board-of-directors/
Are you interested in supporting work at ORI? Consider being part of the board. We’d like to expand from 5 to 7 members in order to better serve our projects and community.
We’ve got lots going on with Opulent Voice, Haifuraiya, AmbaSat Respin, and regulatory work. We support IEEE in many ways, one of which is logistics support with technical presentations such as “Advances in AI for Web Integrity, Ethics, and Well Being” by Srijan Kumar PhD. Video recording of his talk can be found here.
Thank you from everyone at ORI for your continued support and interest!
Whatever will be do for our April 1st newsletter?
Want to be a part of the fun? Get in touch at ori@openresearch.institute
Inner Circle Newsletter February 2023
Greetings all! Welcome to the February 2023 issue of the Inner Circle Newsletter from Open Research Institute.
Join the Inner Circle
Sign up for this newsletter at http://eepurl.com/h_hYzL
Thank you so much for your time, attention, and support. We appreciate you, we welcome your feedback, and we are dedicated to serving the community to the best of our abilities. You can get in touch with the ORI board of directors directly at hello@operesearch.institute.
A Puzzle Just For Fun
Here’s a puzzle. Chicken Nuggets have been on the menu at the international fast food chain McDonald’s since 1983.
If Chicken McNuggets are sold in packs of 6, 9, or 20, then what is the largest number of nuggets that cannot be ordered?
Answer is at the end of this newsletter!
Projects
Our volunteer teams have been busy and successful, and our project lineup has grown.
Regulatory Efforts: ORI works hard to promote and defend open source digital radio work. We do all we can to help move technology from proprietary and controlled to open and free. Our work on ITAR, EAR, Debris Mitigation, and AI/ML are where we have spent most of our time over the past two years. We were a member of the Technological Advisory Committee for the US Federal Communications Commission in 2022, and co-chaired the Safe Uses of AI/ML Subworking Group. We have received consistently positive reviews for all of our work, and there has been increasing use of the results.
Ribbit: this open source communications protocol uses the highest performance error correction and modern techniques available to turn any analog radio into an efficient and useful digital text terminal. No wires, no extra equipment. The only thing you’ll need to use it is the free open source Android or IoS app on your phone. Learn how to use this communications system and get involved in building a truly innovative open source tactical radio service by visiting https://ribbitradio.org
Join Ribbit mailing lists at: https://www.openresearch.institute/mailing-lists/
Amateur Satellite: ORI has the world’s first and only open source HEO/GEO communications satellite program, called Haifuraiya. We will demonstrate all working parts of the transponder project at DEFCON 31, where broadband digital communications and open source electric propulsion will be featured. Find out how to support or join this and other teams at https://openresearch.institute/getting-started
AmbaSat for 70 cm: We’ve redesigned the AmbaSat board to move it from 915 MHz to 70 cm and it will be flown on a sounding rocket this year. With increasing interest in LoRa for both space and terrestrial use, this has proven to be a popular and useful project. The design has been adapted for applications in India and Japan.
Opulent Voice: a digital protocol that seamlessly combines high fidelity voice and data, using modern forward error correction, authentication and authorization, and efficient minimum frequency shift keying modulation. Opulent Voice will be flown on a sounding rocket this year and it is the native digital uplink protocol for Haifuraiya. Completely open with the high quality voice we deserve to hear. Due to the bandwidth requirements of the 16kHz OPUS codec, Opulent Voice can be used on 70cm and above ham bands, or anywhere else where the modest bandwidth requirements can be met.
Remote Labs: We have two remotely accessible workbenches for FPGA development, with Xilinx 7000 and Xilinx Ultrascale+ development boards as the focus. We also have several SDRs and radio utility devices available through virtual machine access. The 7000 series development board has an Analog Devices ADRV9371 radio system attached, and that has enabled a number of open source FPGA products to be published. This is a unique resource that has produced a lot of good work and is constantly being improved and updated. In addition to the development boards, the laboratory has a network accessible spectrum analyzer, an oscilloscope with logic analyzer extension, power supplies, frequency and power counters, and dedicated human resources available to help students, volunteers, or professionals contribute to open source work. Help it be more useful by spreading the word about ORI Remote Labs.
Equipment available: https://github.com/phase4ground/documents/tree/master/Remote_Labs/Test_Equipment
How to get an account: https://github.com/phase4ground/documents/blob/master/Remote_Labs/ORI-New-User-Setup.md
Using FPGA Development Stations: https://github.com/phase4ground/documents/blob/master/Remote_Labs/Working-With-FPGAs.md
Versatune: amateur digital television next generation hardware and software product. It is open source and affordable. We have committed engineering resources to support Versatune and are very excited about how things are going. Some of the Versatune team will be at Hamvention 2023 in Xenia, OH, USA, and it will be represented at DEFCON in August 2023.
HF antennas: We have a novel foldable antenna design for space and terrestrial use. The hardware prototype will be demonstrated at DEFCON. This design manipulates radiation resistance to produce best-of-class results. Think you can’t do 160m without an enormous antenna? Think again.
HF QRP: Coming soon, an exciting HF QRP digital radio board and protocol. The hardware prototypes will be demonstrated at DEFCON. What might happen when we combine the HF digital radio with the novel foldable antenna? We think you’ll be delighted.
Battery Matching Curves: are you available to mentor a college student interested in learning how to match up charge and discharge curves from NiCd cells in order to create battery packs? These packs would then be tested and/or deployed in the field. Our student volunteer has collected the data and is looking to learn how to use Jupyter Notebooks to select the cells to create battery packs.
Logistics
We’re growing and adapting!
We will be changing our GitHub project name from Phase4Ground to Open Research Institute very soon. Phase4Space GitHub project will change to Haifuraiya, which is the program name for our HEO/GEO design. These changes better reflect the content and purpose of the 64 repositories that span everything from important historical archives to open source music to the most modern open source encoders available.
We have a very well-qualified applicant for our open board of directors position. We would like to invite interested community members to consider applying to ORI in order to expand the board beyond this filled position in order to take us from our current five members to seven. Given our continuing growth, a larger leadership team would ensure continued smooth operations. These positions are unpaid, engaging, and can be demanding. The most important skill set is a strong sense of ethics and service.
Fundraising and Grants
We’ve applied for the GitHub Accelerator Program (Remote Labs) and the IEEE Innovation Fund (Polar Codes in Ribbit). If you have a recommendation for ORI in terms of partnerships or collaboration, please let us know at hello@openresearch.institute
Support ORI financially directly through the website https://openresearch.institute. There is a PayPal donation widget at the bottom of almost every page. Donations can be directed to any project, or to general operations. ORI has a very low overhead, with most projects coming in under 5%.
Support our open source propulsion work and get a cool desk toy at https://us.commitchange.com/ca/san-diego/open-research-institute/campaigns/where-will-we-go-next
We’ve raised enough money to cover materials for machining the engine parts. The next step is to raise enough money to pay for the electronics. Please help spread the word!
Thanks to our wonderful community, we have employee matching in place at Microsoft and Qualcomm. If you have an employee matching program at your work, and you think ORI would fit in, please consider nominating us. Our EIN is EIN: 82-3945232
Events
Where can you meet up with ORI people?
QSO Today Ham Expo
We support and attend QSO Today Ham Expo, held online 25-26 March 2023. The theme of this event is “New License, Now What?” and focuses on people new to amateur radio.
Our page for QSO Today Ham Expo content is https://www.openresearch.institute/qso-today-ham-expo-technical-demonstrations/
IMS2023
Join us at the amateur radio social at the International Microwave Symposium (IMS2023) on Tuesday 13 June 2023 in San Diego, CA, USA at 6pm. It will be held in a beautiful outdoor venue with food and drink provided. The easiest way to register for this event is to purchase an exhibition badge and then sign up for the social. https://ims-ieee.org/ is the event website.
DEFCON
We are getting ready for our biggest event of the year. We have proposed an in-person Open Source Showcase to RF Village for DEFCON 31 in Las Vegas, Nevada, USA from 10 – 13 August 2023.
Our page for the event, with all the latest and greatest details, can be found at https://www.openresearch.institute/defcon/
Want to help at DEFCON? Please visit https://openresearch.institute/getting-started and let us know!
IWRC 2023
IEEE wants to bring together all participants to take full advantage of CHIPS Act funding. IEEE will have an Innovative Workforce Resources Conference in Little Rock, AR 13-14 September. There will be a reception at the Clinton Presidential Library, and attendees will enjoy the best BBQ in the country. The National Science Foundation requires that a certain percentage of funding has to be spent in states that don’t get their fair share of research money. The goal of this conference is to pull together small researchers from small business like ORI and do research, with Arkansas as a focus.
We couldn’t agree more. After all, we are putting a lot of time and energy into Remote Labs South, located just outside Little Rock, AR. Bringing innovative open source digital radio work to students, workers, and volunteers that need it the most simply makes sense. If you can attend IWRC 2023 and help represent ORI please get in touch. We will be reaching out to IEEE chapters in Arkansas as well.
Read about the CHIPS and Science Act here: https://en.wikipedia.org/wiki/CHIPS_and_Science_Act
Puzzle Solution
43 is the largest number of nuggets that cannot be ordered.
What is the largest number of McNuggets that you can’t buy with packs of 6, 9 and 20? After putting in their blood, sweat, and tears, the mathematicians found that the answer is 43. You cannot buy 43 nuggets with packs of 6, 9 and 20, but you can buy any amount larger than 43.
Please see Mike Beneshan’s excellent blog about this type of problem at https://mikebeneschan.medium.com/the-chicken-mcnugget-theorem-explained-2daca6fbbe1e
The other Non-McNugget numbers are 1,2,3,4,5,7,8,10,11,13,14,16,17,19,22,23,25,28,31,34, and 37.
Trivia: You can get 47 in two ways: 36+19+120 or 06+39+120.
We’ve used the McDonald’s version of the chicken nugget to present and frame this mathematical puzzle. Here’s a link about the history of this menu item: https://www.thrillist.com/news/nation/history-of-chicken-mcnuggets
Robert C. Baker invented the chicken nugget, among many other things. He was a true innovator of what can be fairly called “modern foods”. A brief wikipedia article about him can be found here: https://en.wikipedia.org/wiki/Robert_C._Baker
A song written about this remarkable inventor can be enjoyed at this link: https://youtu.be/OEa8wqv4QM0
Do you have an idea for an interdisciplinary puzzle for our next newsletter? We’d love to hear about it. Write ori@openresearch.institute
Until Next Time
Thank you so much for being part of our Inner Circle! You are the motivation for all of this work, provided to the general public for free. We believe it makes the world a better place.
HamCation 2023: Call for Open Research Institute Volunteers (booth/housing provided)
Greetings all!
If you are not familiar with the US amateur radio vendor fair HamCation, then please visit https://www.hamcation.com/
ORI has a booth in a very nice location right in front of the prize drawing area.
We have shown at HamCation for many years. In the past, we’ve collaborated with and supported exhibits and presentations from Society of Amateur Radio Astronomy (SARA), Tucson Amateur Packet Radio (TAPR), M17, DEFCON, GNU Radio, SBMS Beacon Project, and more.
We’ve organized four all-day forum sessions, recruited talks from all over the world, and welcomed people and projects that needed space to present their efforts to the large crowd in Orlando, FL. We’ve done a lot of demos, given out thousands of dollars of prizes and swag, and hosted several contests. The organizers have been deeply appreciative and delight to work with.
Aside from ARRL, ORI has fielded the most diverse and successful set of exhibits at HamCation in recent history.
It’s not a bad hamfest, as ham events go. Out of all of the ones in the US, this has been the best one for us.
Our plans were to show the Versatune project, which is a fantastic upgrade to a beloved ham DVB product, show Ribbit and Rattlegram, demonstrate Haifuraiya satellite work, introduce our sounding rocket work, and more.
Ribbit project team members cannot attend due to work and time conflicts. We’ll show through IEEE and potentially at Ham Expo.
Versatune has run into insurmountable delays and supply chain issues with Raspberry Pis. We looked at every possible alternative to get Versatune done faster with alternate parts, including rewriting the codebase for some very different off-the-reel parts that were available. We decided this was not a reasonable or achievable course of action. The original design is excellent and making progress – just not fast enough to show at HamCation in February 2023.
Haifuraiya (Open source HEO/GEO satellite) will show at QSO Today Ham Expo in March and through IEEE.
Sounding Rocket students cannot afford to come to HamCation, and we have similar supply chain problems there with Opulent Voice.
So – What do we have at HamCation?
We have a four-bedroom AirBNB very close to the fairgrounds reserved. Each room has a king sized bed. It has a large kitchen and very nice living room.
We have a booth at HamCation that is now completely open for anyone from ORI to use. I will do anything I can to help you showcase our work at HamCation. Do a shift at the booth, enjoy the very nice house, and promote our work.
More about this will be on Slack in the HamCation2023 channel.
Get in touch with me (cell phone number below) to take advantage. Deadline is 1 February.
If we have no staff, then we cancel and attempt to get the money back or donate the housing and booth space to a worthy group.
Please forward to anyone you think might be interested. What sort of work do we support? It’s outlined here:
https://www.openresearch.institute/your-project-is-welcome/
-Michelle Thompson
(858) 229 3399
Open Source COBS Protocol Design Document
Aside from the usual clk and rst signals, the only input to the entity is an AXI-Stream with a width of one byte. The data stream consists of frames encoded according to the rules described in Consistent Overhead Byte Stuffing by Stuart Cheshire and Mary Baker. These rules convert a known-length stream of bytes (a “frame”) with all values 0-255 into a slightly longer stream of bytes containing only values 1-255, allowing a byte with value 0 to be used unambiguously as a separator. It does this by dividing the stream into sequences of bytes. Each sequence must consist of zero to 253 non-zero bytes followed by a 0 byte or the end of stream, or 254 non-zero bytes. It is then encoded as the sequence length (1 to 254) followed by the non-zero bytes.
Read the rest at:
https://github.com/phase4ground/adi_adrv9371_zc706/blob/adrv9371-zc706-dvbs2-integ/design_docs/cobs_decoder/COBS_dec-Entity-Design.md
QoS: Call for Input
We’re moving into the challenge of multiplexing on the transponder with a goal of delivering Quality of Service (QoS) metrics and policies.
This is “how do the uplink packets get properly prioritized on the downlink, to make the most of limited resources”.
These resources are spectrum, power, and time.
QoS doesn’t make any of our communications channels go faster. This is a common misconception about QoS. Here’s some descriptions from conversations this week. I would like to hear more opinions about QoS in general, and any specific requirements that people on this list might have.
Kenneth Finnegan writes,
“In #networking it’s common to forget that QoS is mainly about deciding which packets you’d rather drop first.
If you don’t like that idea, then you just need to pony up and throw more capacity at the problem.”
Adam Thompson continues,
“In the presence of a pizza that’s not big enough for all the hungry people, QoS inhibits less-important pizza eaters. This lets more-important eaters-of-pizza get more pizza than their fair share, at the expense of the less-important eaters.
“In the presence of a pizza that’s not big enough for all the hungry people, QoS inhibits less-important pizza eaters. This lets more-important eaters-of-pizza get more pizza than their fair share, at the expense of the less-important eaters.
QoS never (ever!) makes the pizza bigger – if you need more pizza, you must still bake or buy more, or someone’s going to go hungry!
Complex QoS systems might let you differentiate between e.g. crust and topping and permit cutting the pizza into bizarre topographies/topologies, but still can’t make the pizza any bigger.
Finally, if there is enough pizza for everyone, QoS doesn’t do anything useful.”
If this last part sounds familiar, then you’re not alone. QoS often doesn’t do anything useful… in a resource rich environment. This may be the main reason that we sometimes hear that QoS is a “failure”, that it’s “never used”, or “why bother for hams since hams don’t care about this subject at all”.
It is true that most amateur communications are made with acres and acres of spectrum, with a very generous power limit (although you are supposed to use the minimum required power) and no time limits on how often you can try to make a contact.
When we talk about microwave broadband digital communications, it’s a different situation. And, with space channels, there are constraints. We have less bandwidth to work with because we’re on a sub-band. We have latency, which is non-trivial for GEO or beyond. We have power concerns and pointing requirements.
“Adaptive” QoS that does nothing until congestion forces some decisions, at which time we sort with respect to SNR, has been our baseline.
What we want to do when constraints are hit is what we need to better define. Right now, we have a whiteboard design (summarized above) and a paper about Adaptive Coding and Modulation (ACM) that was published in AMSAT-DL and AMSAT-UK Journals.
We have the implementation guidelines from GSE as well, which address QoS and show how to set up queues.
With a controllable downlink going out over the air, and a defined uplink protocol, now is the time to work on exactly how to multiplex the traffic. Evariste asked about this exact thing less than a week ago at the FPGA meetup.
Decisions about QOS heavily affect the central part of the design, so let’s get this right.
Do you have experience implementing QoS policies? Do you have experience with bad QoS policies as a consumer? Do you have an idea about what you want to see this design do?
Well, you’re in the right place, and we’d love to hear what you have to say about it.
Participate at https://openresearch.institute/getting-started
Will I Lose my Programming Job to AI/ML?
2022-12-03 Paul Williamson
There has been some fretting lately among programmers about the future of their jobs in a world where AI/ML seems capable of writing code automatically. To think about this, we need a realistic model of AI/ML capabilities. If we just assume that AI/ML can be as smart as a human programmer, maybe smarter, definitely faster, and much cheaper to reproduce and operate, then the whole game is over. In that world, humans are outcompeted by machines in every important way, and programmers will have lots of company in the unemployment lines. Humans will have bigger things to worry about than jobs. That scenario is so far “out there” that even the SF writers haven’t found a way to understand it without artificially crippling the AIs in some way. If we really believe that is coming to pass, we (humans) ought to seriously consider getting started on the Butlerian jihad against AI.
Instead, let’s think about the consequences of AI/ML as it is currently starting to exist in the programming world: as a sophisticated search engine and an improved method of facilitating code re-use. AI/ML applications like ChatGPT are (starting to be) able to find some existing code that seems responsive to a query. That’s the search engine part. Let’s assume that they are then (getting better at) combining multiple pre-existing examples in a “smart” way that seems likely to preserve the good parts of each example in such a way as to solve the requested problem. That’s the code re-use part.
Today’s programmer is very familiar with the efficiency of solving coding problems by searching Stack Overflow for related solutions. With a bit of luck, the search will yield something close enough to the required solution to be re-used in solving the problem at hand. For common well-defined problems, it might be a complete drop-in solution. For less common problems, it might just have some of the parts worked out, and we have to pick and choose and maybe write a bit of new logic to glue it all together. Only when nothing similar is found will we have to write something entirely from scratch. To programmers, this feels a lot like what we imagine that the AI does when it coughs up some mutated open-source code in response to a simple query. Because we systematically underestimate how hard it is for a computer to do the kind of logical reasoning that comes easily to human programmers, we imagine that computers are on the edge of surpassing human programmers.
Searching and code re-use have been around for a long time. A lot of computer science research has gone into looking for ways to make code re-use easier. That’s why we have high level languages, and extensive libraries of built-in functions, and Stack Overflow. These things have made it possible for humans to create more and more complex software systems, by reducing the number of details that have to be thought about all at once. So far, this has not resulted in any net loss of programming jobs. Rather the opposite, in fact.
Some kinds of jobs do seem less important now. When we think about programming jobs today, we probably aren’t thinking much about people who are skilled in writing assembly language. Those jobs still exist, though, albeit in specialized fields, such as writing compilers for higher-level languages. They are just embedded in a much larger ecosystem of programming jobs that no longer require thinking at such a low level on a routine basis.
It might be instructive to go back to one of the earliest ideas computer scientists used to think about reaching higher levels of abstraction: that computer programs are like electronic circuit designs. Computer scientists noticed that EE productivity went through the roof with the advent of the integrated circuit. That’s a module that only has to be designed once, with a well-defined documented function and well-defined documented interfaces, easy to mass produce in whatever quantity is required, all functionally identical, and relatively easy to glue together into more complex circuits. Maybe if software could be like that, it would also realize huge increases in productivity. That worked out pretty well, though a true “software IC” technology still seems elusive, and probably always will.
If you look at the job market for electrical engineers today, decades after the successful introduction of the integrated circuit, what do you see? On the digital side, you see a lot fewer listings for people who can design logic circuits out of transistors, or ALUs out of gates, or even CPUs out of ALUs and gates. The common board-level digital design engineer is more involved in picking existing devices and combining them than in actually designing circuits. Likewise, the FPGA or ASIC designer will often be able to get pretty far by integrating existing cores. The work is mostly at a higher level of abstraction. The engineer ideally needs to be aware of exactly how far they can trust the abstractions to hold, and what to do about it when the abstractions leak. Lots of adequate designs can be churned out with imperfect understanding of these issues.
If you look at the market for RF engineers, you see what’s perhaps a later stage of the same evolution. Not only are most RF designs done by using off-the-shelf RF modules, but it is getting very hard to find qualified RF designers at all. As the cohort of RF engineers who had to learn component-level design age out and retire, they are followed by a group of engineers who were mostly able to avoid worrying about that. Only relatively few picked up the lowest-level circuit design skills. Those that did are highly sought-after by companies with RF design requirements.
This trajectory for hardware engineers corresponds to the trend in software engineering toward use of higher level languages and environments and away from programming down to the metal. We can expect this trend to continue. Programmers with deep expertise at any level of abstraction will still be needed and employable. The fraction of jobs at the lower layers of abstraction will decrease, but so will the fraction of programmers with extensive lower layer skills.
This is a problem for the companies that need to hire engineers to work on projects requiring lower-layer expertise, but it’s a boon for those who are able to use higher-layer skills to turn reusable code into useful applications for the growing market in high-complexity systems. As the scope of the software we can re-use without much thought grows to include bigger chunks of functionality, our power to create highly functional systems increases. When the job is to deploy a system that would have been unthinkably complex just a few years ago, the availability of larger re-usable components can make it possible.
These new higher-layer jobs are not easier. They may be a better match for the kind of intelligence that human programmers have, so that they seem easy and pleasant to work on. That probably makes them a worse match for AI/ML capabilities. There’s no current reason to believe that AI/ML technology is on the verge of making a bot that’s able to understand how things need to fit together in the same way as a human. It seems clear that the current generation of AI/ML experiments is not a giant step in that direction. As an improvement over simple search-engine technology, they have potential to make it easier to collect the background knowledge we need to have at our fingertips. To the extent they’re able to turn a vague query into concrete code, they have potential to reduce the amount of rote typing we have to do.
But these robots are not on the verge of being able to do the whole job, working as a programmer without human intervention. As a programmer, you are not about to lose your job creating computer programs. Instead, your job is about to get easier and more fun, as the AI/ML takes on the more tedious parts. The main thing you have to worry about today is that this transformation is still going to take a long time to arrive.
Paul Williamson
AI vs. Human: ChatGPT vs. ORI Open Source Designers
Greetings all,
You know that ORI has been active in a variety of regulatory work for several years now. One of those areas has been in AI/ML and the effect on communications. We served on the US FCC TAC in 2022, have presented and written on the subject, and are working towards an AI/ML Handbook for Amateur Radio.
You may have seen news about OpenAI GPT, or ChatGPT.
https://openai.com/api/
There’s a lot of people testing this chatbot out for reverse engineering and in writing software. There’s been some successes in cases where the model would have had access to code or documentation about protocols, observations, or technical behavior in order to train, and requests match up well with the models.
For example, a friend asked the chatbot to create a Python script to access the webcam on their computer, and they shared a still image from the resulting feed. Another example from another friend resulted in better reverse engineering results than they had gotten with either IDA or Ghidra over many weeks.
So, how does ChatGPT handle VHDL?
We have something specific to compare against, since we just completed a COBS decoder in VHDL for our open source HEO/GEO transponder work for #Haifuraiya.
Let’s start off simple. Here’s the first dialogue with the chatbot, and the results.
-=-=-=-=-=-=-=-=-=-=-=-=-=-
Abraxas3d: Design a COBS decoder in VHDL
Sure, here’s an example of a COBS decoder in VHDL:
library IEEE;
use IEEE.STD_LOGIC_1164.ALL;entity COBS_decoder is
Port (
input_data : in std_logic_vector;
decoded_data : out std_logic_vector
);
end COBS_decoder;architecture Behavioral of COBS_decoder is
— Declare a variable to keep track of the current index
— in the input and output data streams
variable current_index : integer := 1;
— Declare a variable to store the length of the
— run of zeros in the input data
variable zero_run_length : integer := 0;
begin
— Iterate over the input data
for i in input_data’range loop
— If the current input value is a zero, increment
— the zero run length variable
if input_data(i) = ‘0’ then
zero_run_length := zero_run_length + 1;
— Otherwise, the current input value is not a zero,
— so we’ve reached the end of the zero run
else
— Set the decoded value at the current index to
— the length of the zero run
decoded_data(current_index) := conv_std_logic_vector(zero_run_length, 8);
— Increment the current index and reset the zero
— run length for the next iteration
current_index := current_index + 1;
zero_run_length := 0;
end if;
end loop;
end Behavioral;
This code decodes the input data using the COBS (Consistent Overhead Byte Stuffing) algorithm, which involves replacing runs of zeros in the input data with a single byte that indicates the length of the zero run. For example, the input ‘101001000’ would be decoded as ‘103101’.
This decoder iterates over the input data and maintains a variable zero_run_length that is incremented for each zero in the input data. When a non-zero value is encountered, the length of the zero run is written to the output data and the zero_run_length variable is reset.
I hope this helps! Let me know if you have any other questions.”
-=-=-=-=-=-=-=-=-=-=-=-=-=-
It knew what COBS meant. It produced code, with comments, and a brief “design document”, with examples.
The code produced is not licensed or cited.
Our open source HEO transponder project uses AXI-based blocks in the FPGA. So, let’s add AXI to the request.
-=-=-=-=-=-=-=-=-=-=-=-=-=-
Abraxas3d: Design a COBS decoder with AXI interface in VHDL
Sure, here’s an example of a COBS decoder with an AXI interface in VHDL:
library IEEE;
use IEEE.STD_LOGIC_1164.ALL;
use IEEE.NUMERIC_STD.ALL;— AXI interface definitions
library unisim;
use unisim.vcomponents.all;entity COBS_decoder is
Port (
AXI_IN : in AXI4Stream;
AXI_OUT : out AXI4Stream
);
end COBS_decoder;architecture Behavioral of COBS_decoder is
— Declare a variable to keep track of the current index
— in the input and output data streams
variable current_index : integer := 1;
— Declare a variable to store the length of the
— run of zeros in the input data
variable zero_run_length : integer := 0;
begin
— Iterate over the input data
for i in AXI_IN.data’range loop
— If the current input value is a zero, increment
— the zero run length variable
if AXI_IN.data(i) = ‘0’ then
zero_run_length := zero_run_length + 1;
— Otherwise, the current input value is not a zero,
— so we’ve reached the end of the zero run
else
— Set the decoded value at the current index to
— the length of the zero run
AXI_OUT.data(current_index) := conv_std_logic_vector(zero_run_length, 8);
— Increment the current index and reset the zero
— run length for the next iteration
current_index := current_index + 1;
zero_run_length := 0;
end if;
end loop;
— Set the valid and last flags in the output AXI stream
AXI_OUT.valid <= ‘1’;
AXI_OUT.last <= ‘1’;
end Behavioral;
This code is similar to the previous example, but it uses an AXI (Advanced eXtensible Interface) interface for the input and output data. The AXI interface is a standard interface used in many FPGA designs, and it provides a way to stream data into and out of the decoder.
In this code, the input data is read from the AXI_IN.data port, and the decoded output is written to the AXI_OUT.data port. The valid and last flags are also set in the output AXI stream to indicate that the data is valid and that it is the last data in the stream.
I hope this helps! Let me know if you have any other questions.
-=-=-=-=-=-=-=-=-=-=-=-=-=-
It knows about the previous request and updated the design. No license.
Here’s a review of the COBS implementation from Paul Williamson KB5MU.
“I don’t know what this is, but it isn’t a COBS decoder with AXI interfaces.
It does seem at first glance to be some sort of thing with AXI interfaces, but it does not implement an AXI interface at all. It just relies on a (possibly imaginary) library type called AXI4Stream that somehow magically does AXI interfaces, in a way that’s both implausibly smart and inexplicably dumb. I think the classic phrase “not even wrong” applies here.
The AXI4Stream object apparently has a member .data that is an array of bytes, which might make sense if the entire AXI transfer is being treated as a single entity here. The code iterates through the input .data using the ’range attribute, as if the AXI4Stream object has a defined fixed transfer length.
Which it can’t have, if it’s a general purpose AXI stream implementation.
So, if this was ever anything real, it must have been a special purpose AXI implementation with a fixed transfer length. Assuming that the AXI4Stream .data actually works that way, the entity does
do some sort of transformation on the input data to create the output data.
We asked for that to be a COBS decoder, but the function that it actually implements bears only the slightest resemblance to a COBS decoder. What it actually does is output a stream of words that are the lengths of the runs of zeroes in the input data. Nonzero data does not get passed through at all.
Instead, a run of nonzero bytes gets translated into a run of zeroes, as if two adjacent nonzero bytes meant nothing but a zero-length run of zeroes.
Here’s an example of what this code seems to do:
Input .data: 1 2 3 4 0 0 0 0 1 2 3 4
Output .data: 0 0 0 0 4 0 0 0
That’s certainly not a COBS decoder, or even anything useful at all.
Note that the output is variable length, but never longer than the input.
We had to assume that the AXI4Stream object had a fixed .data size to get this far, but now it has to have a variable data size for the output.
Supposing we had successfully suspended disbelief up to here, we now examine the final two lines of code in the Behavioral architecture. It sets the .valid and .last members of the AXI_OUT port to ‘1’.
That makes absolutely no sense if it’s supposed to encapsulate an entire AXI stream transfer. Those signals only make sense if we’re treating one word at a time, as you’d expect to see in a normal, general-purpose AXI stream object.
The extremely verbose commenting style in this code suggests that the original source material was from an introductory tutorial. Maybe the AI has been tuned to favor heavily commented code, and ends up picking up partially completed junk from the middle of tutorials?
Anyhow, this is not an example of automated programming in response to a high-level query. This is gibberish that succeeds only in having a superficial resemblance to the code requested.”
So, does this work?
Let’s try it out in the lab!
The first thing we notice is that there is an obvious syntax error with a missing semicolon. Aside from that, there is no AXI4Stream port type. It’s not recognized. Vivado appears to be disappointed in this file, and wants little to do with this code. This is where we should stop, but I spent some time looking to see if the ports were at least close to being declared correctly.
The model appears to have taken some custom or maybe enumerated type from somewhere, and come up with a custom AXI4Stream type. This is not recognized by the unisim library right off the bat, and that’s the sort of thing that automated code writing needs to get right.
Let’s look at the code written by humans from ORI. The decoder can be found here:
https://github.com/Abraxas3d/fpga_cores/blob/master/src/decoder.vhd
-=-=-=-=-=-=-=-=-=-=-=-=-=-
— Company: Open Research Institute, Inc.
— Engineer: Skunkwrx, Abraxas3d
— Design Name: COBS protocol decoder
— Module Name: decoder – Behavioral
— Project Name: Phase 4 “Haifuraiya”
— Target Devices: 7000 Zynq
— Tool Versions: 2021.1
— Description: COBS protocol decoder.
— Additional Comments: This work is Open Source and licensed using CERN OHL v2.0
library IEEE;
use IEEE.STD_LOGIC_1164.ALL;
use IEEE.NUMERIC_STD.ALL;
–Entity Declaration
entity decoder is
Port ( rst : in STD_LOGIC;
clk : in STD_LOGIC;
s_tdata : in STD_LOGIC_VECTOR (7 downto 0);
s_tlast : in STD_LOGIC;
s_tvalid : in STD_LOGIC;
s_tready : out STD_LOGIC;
m_tdata : out STD_LOGIC_VECTOR (7 downto 0);
m_tlast : out STD_LOGIC;
m_tvalid : out STD_LOGIC;
m_tready : in STD_LOGIC);
end decoder;
–Architecture
architecture Behavioral of decoder is
— internal copy of s_tdata
signal input_data : STD_LOGIC_VECTOR (7 downto 0);
— s_tdata delayed by one clk where s_tvalid is high
signal input_data_d : STD_LOGIC_VECTOR (7 downto 0);
— internal version of s_tlast
— not used for anything
— We create our own m_tlast from the COBS framing instead
signal s_tlast_i : STD_LOGIC;
— internal version of input handshaking signal s_tvalid
signal s_tvalid_i : STD_LOGIC;
— s_tvalid delayed by one clk
— thus, a version of s_tvalid aligned with input_data_d
signal s_tvalid_i_d : STD_LOGIC;
— s_tvalid delayed by two clks
— thus, a version of s_tvalid aligned with output_data
signal s_tvalid_i_d_d : STD_LOGIC;
— countdown of bytes in this sequence
— loads from input_data_d when it represents the frame count
— as determined by signal counter_load
— contains the count while m_tdata contains the implied 0 at
— the end of a sequence, or the next count that replaced it
— counts down thereafter, to contain 1 when the last non-zero
— byte of the sequence is on m_tdata
— allowed to count down to 0, but not beyond
signal count : STD_LOGIC_VECTOR (7 downto 0);
— enable to load count from input_data_d on this clk edge
— two cases detected:
— * first valid non-zero byte after a frame separator
— * first valid byte after count is exhausted
— allowed to be high for multiple cycles
signal counter_load : STD_LOGIC;
— counter_load delayed by one clk where s_tvalid is high
— used to identify the first valid data byte of any sequence,
— for purposes of computing m_tvalid (via pre_tvalid)
signal counter_load_d : STD_LOGIC;
— detection of a valid frame separator (zero) byte in input_data_d
signal frame_sep : STD_LOGIC;
— frame_sep delayed by one clk where s_tvalid is high
— used to compute counter_load
— used to compute rising edge of pre_tvalid
signal frame_sep_d : STD_LOGIC;
— frame_sep_d delayed by an additional clk (not depending on s_tvalid)
— used to find the first non-zero byte of the new frame
signal frame_sep_d_d : STD_LOGIC;
— move the frame_sep signal that occurred during m_tready low
— out to the first cycle when m_tready is high again
signal use_saved_frame_sep : STD_LOGIC;
— flag to remember that the frame count for this sequence was 255,
— to handle the special case that such a sequence does not have
— an implied zero byte at the end.
— set when loading count with 255
— cleared when the counter is reloaded with anything else
signal case_255 : STD_LOGIC;
— internal version of m_tdata output
signal output_data : STD_LOGIC_VECTOR (7 downto 0);
— internal version of m_tlast output
— high when the last byte of a frame is valid on m_tdata
signal m_tlast_i : STD_LOGIC;
— delayed versions of m_tlast
signal m_tlast_i_d : STD_LOGIC;
signal m_tlast_i_d_d : STD_LOGIC;
— intermediate result for m_tvalid.
— high across all data bytes of each sequence on m_tdata
— does not go low for bytes on m_tdata corresponding to
— bytes invalidated by s_tvalid.
signal pre_tvalid : STD_LOGIC;
— internal version of m_tvalid output.
— pre_tvalid with periods of low s_tvalid_d_d punched out
signal m_tvalid_i : STD_LOGIC;
— internal version of m_tready input
— also the internal version of s_tready output
— passes through m_tready to s_tready with no clk delays
signal m_tready_i : STD_LOGIC;
— constant byte value 0xFF, for comparison purposes
signal all_ones : STD_LOGIC_VECTOR(input_data’range) := (others => ‘1’);
— constant byte value 0x00, for comparison purposes
signal all_zeros : STD_LOGIC_VECTOR(input_data’range) := (others => ‘0’);
begin
— asynchronous assignments
frame_sep <= ‘1’ when input_data_d = all_zeros and s_tvalid_i_d = ‘1’
else ‘0’;
m_tlast_i <= ‘1’ when ((frame_sep = ‘1’ and m_tvalid_i = ‘1’ and m_tready = ‘1’))
else ‘0’;
counter_load <= ‘1’ when (input_data_d /= all_zeros and frame_sep_d = ‘1’ and s_tvalid_i_d = ‘1’) — start of frame
or (to_integer(unsigned(count)) = 1 and s_tvalid_i_d = ‘1’) — start of next sequence in frame
else ‘0’;
m_tvalid_i <= ‘1’ when ((pre_tvalid = ‘1’ and s_tvalid_i_d_d = ‘1’ — usual case, if input_data was valid
and not (to_integer(unsigned(count)) = 1 and s_tvalid_i_d = ‘0’)) — defer last byte; might be m_tlast
or (pre_tvalid = ‘1’ and to_integer(unsigned(count)) = 1
and s_tvalid_i_d = ‘1’ and s_tvalid_i_d_d = ‘0’)) — pick up that deferred last byte
else ‘0’;
s_tready <= m_tready_i;
m_tdata <= output_data;
input_data <= s_tdata;
s_tvalid_i <= s_tvalid;
m_tready_i <= m_tready;
m_tvalid <= m_tvalid_i;
m_tlast <= m_tlast_i;
— processes
set_case_255 : process (rst, clk)
begin
if rst = ‘1’ then
case_255 <= ‘0’;
elsif rising_edge(clk) and m_tready_i = ‘1’ then
if counter_load = ‘1’ and input_data_d = all_ones then
case_255 <= ‘1’;
elsif counter_load = ‘1’ and input_data_d /= all_ones then
case_255 <= ‘0’;
end if;
end if;
end process set_case_255;
delay_s_tvalid : process (rst, clk)
begin
if rst = ‘1’ then
s_tvalid_i_d <= ‘0’;
s_tvalid_i_d_d <= ‘0’;
elsif rising_edge(clk) and m_tready_i = ‘1’ then
s_tvalid_i_d <= s_tvalid_i;
s_tvalid_i_d_d <= s_tvalid_i_d;
end if;
end process delay_s_tvalid;
create_pre_tvalid : process (rst, clk)
begin
if rst = ‘1’ then
counter_load_d <= ‘0’;
pre_tvalid <= ‘0’;
elsif rising_edge(clk) and m_tready_i = ‘1’ then
if s_tvalid_i_d = ‘1’ then
counter_load_d <= counter_load;
if (frame_sep_d_d = ‘1’ and frame_sep_d = ‘0’) — normal last byte of frame
or (counter_load_d = ‘1’ and frame_sep_d = ‘0’) — normal first byte of a sequence
then
pre_tvalid <= ‘1’;
end if;
end if;
if frame_sep = ‘1’
then
pre_tvalid <= ‘0’;
end if;
if counter_load = ‘1’ and case_255 = ‘1’ then
pre_tvalid <= ‘0’;
end if;
end if;
end process create_pre_tvalid;
delay_m_tlast_i : process (rst, clk)
begin
if rst = ‘1’ then
m_tlast_i_d <= ‘0’;
m_tlast_i_d_d <= ‘0’;
elsif rising_edge(clk) and m_tready_i = ‘1’ then
m_tlast_i_d <= m_tlast_i;
m_tlast_i_d_d <= m_tlast_i_d;
end if;
end process delay_m_tlast_i;
set_counter : process (rst,clk)
begin
if rst = ‘1’ then
count <= (others => ‘0’);
frame_sep_d <= ‘0’; frame_sep_d_d <= ‘0’; elsif rising_edge(clk) and m_tready_i = ‘1’ then frame_sep_d_d <= frame_sep_d; if s_tvalid_i_d = ‘1’ then frame_sep_d <= frame_sep; if counter_load = ‘1’ then count <= input_data_d; elsif count /= all_zeros then count <= STD_LOGIC_VECTOR(unsigned(count) – 1); end if; end if; end if; end process set_counter; create_output : process (rst, clk) begin if rst = ‘1’ then output_data <= (others => ‘0’);
elsif rising_edge(clk) and m_tready_i = ‘1’ then
if counter_load = ‘1’
then
output_data <= all_zeros;
elsif s_tvalid_i_d = ‘1’ then
output_data <= input_data_d;
end if;
end if;
end process create_output;
selective_delay_of_input_data : process (rst,clk)
begin
if rst = ‘1’ then
input_data_d <= all_zeros;
elsif rising_edge(clk) and m_tready_i = ‘1’ then
if s_tvalid_i = ‘1’ then
input_data_d <= input_data;
end if;
end if;
end process selective_delay_of_input_data;
end Behavioral;
-=-=-=-=-=-=-=-=-=-=-=-=-=-
This codebase doesn’t include just the source code, but also a testbench file, a design document, timing diagrams, a Python notebook that creates test vectors, and Python code that compares results produced by the testbench that uses the test vectors.
None of this sort of thing is produced by ChatGPT.
There is code in some languages for some functions that can be correctly written by AI at this point.
This is a situation similar to algorithmic musical composition. Algorithms can come up with useful ideas, motifs, sketches, or traverse a search space more quickly than a human. They can help a composer, but do not replace one. Algorithms can produce some sparkling gems of ideas. These are fresh cuts and views. This is mixed in with a lot of music that is just plain wrong.
If your programming job happens to be in a well-defined area that is easily automated, then you do have something to worry about today.
All jobs are a target for eventual automation with AI/ML. Yes, all of them. As AI/ML becomes more capable, it will automate even things like testbench writing (HDL Coder already does something like this) and support code (like a Python notebook that creates a solid set of test vectors for a testbench) and design documents. All of us should be aware of what we do being replaced by an algorithm some number of tomorrows in the future.
That day is not yet “today” with Chat GPT, when it comes to writing #VHDL.
What do you think? We’re interested in your experience and opinions with AI/ML writing code.
Federal Communications Commission Technological Advisory Committee Meeting 8 December 2022
Greetings all,
The final Technological Advisory Committee Meeting of 2022 for the Federal Communications Commission will be held 8 December.
ORI was a member of the TAC for 2022, contributed to several reports, and will be represented in person at the closing meeting.
I’ve represented Open Source and Amateur Radio concerns over the past year on the Artificial Intelligence/Machine Learning (AI/ML) working group of TAC. I co-chaired the sub-working group about “Safe Uses of AI/ML” with Paul Steinberg of Motorola, invited and organized a variety of speakers to present to the working groups, and had the opportunity to work on “how AI/ML is affecting bandwidth and throughput” paper with excellent FCC staffers. The amateur radio service is highlighted in this report.
The work consisted of two meetings a week and a lot of time in between to prepare, organize speakers, and manage deliberative discussions.
The final meeting in DC summarizes work for the year and sets out an agenda for next year. This year was a very difficult “rebuilding” year for TAC, as it had been shut down at the beginning of COVID. I am honored to be a part of getting TAC back up and running.
Thank you to everyone that has supported ORI participating at this level of US government. It’s been very successful.
Karen Rucker (ORI Secretary Emeritus) was instrumental in the application process, and I’d like to recognize her service to ORI and the FCC.
Paul Williamson, with experience on standards committees, has been invaluable in terms of providing advice for deliberations and decisions.
A special thanks to Marty Woll of YASME Foundation for his guidance and advice, and to ARRL counsel for coordinating and cooperating with ORI on a wide variety of issues we’ve taken to the FCC over the past year. ARRL is ably represented at FCC TAC by Greg Lapin.
If you are interested in “sticking up for amateur radio and open source at the FCC”, then you can make a positive difference in the US regulatory process. This is much more involved than filing a comment or complaining on social media. It is a significant commitment of time and effort.
Please get in touch and I will do all I can to support your application to groups like the FCC TAC. There are many ways to participate, and all of them affect the future success of open source and the amateur radio services that we care so much about.
-Michelle Thompson CEO ORI
Inner Circle – September 2022
Greetings from Open Research Institute!
We hope to see you again at QSO Today Ham Expo this weekend, 17-18 September 2022. We have a booth, five talks, three project exhibits, and a lounge space for meet and greet.
To find out more about Ham Expo, visit https://www.qsotodayhamexpo.com/
Since the last Ham Expo, we’ve integrated the DVB-S2/X encoder into the downlink reference design for our open source broadband microwave transponder. We have started on the uplink receiver. We have published a specification for our high bitrate digital voice and data uplink protocol. It’s called Opulent Voice and it will be introduced and described at the Expo. Find the source code for a C++ implementation at https://github.com/phase4ground/opv-cxx-demod
We have two sounding rocket projects, an open source propulsion project, successful regulatory work, and we represent open source and amateur radio interests on the US FCC Technological Advisory Committee. We co-chair the “Safe Uses of AI/ML” subworking group.
Our open source HEO proposal Haifuraiya will be presented at the Expo this weekend and details will be in an upcoming JAMSAT Journal.
We do terrestrial communications as well! Ribbit is a digital emergency communications mode for VHF/UHF. No extra equipment or cables required. We have a poster about the project in the exhibit hall and a presentation. Get the free Android application at https://play.google.com/store/apps/details?id=com.aicodix.rattlegram
All video presentations will be available at our YouTube channel after the Ham Expo platform has closed in 30 days.
We have a mailing list for updates and discussion, a Slack account for engineering work, and all work is published as it is created to our GitHub account.
To join any of these resources at ORI, please visit https://www.openresearch.institute/getting-started/
If you’d like to get monthly newsletters like this one, then do nothing. You’re already part of the inner circle!
Our volunteers could not accomplish all of this wonderful work without your interest and support.
Thank you from everyone at ORI. We value your comment, critique, and feedback, and look forward to hearing from you. If you use social media, then a lot of what we do is published through the channels linked below.
Thank you from all of us at ORI!
September 2022 QSO Today Ham Expo – ORI’s Open Source Technical Presentations
These are our technical talks from the September 2022 QSO Today Ham Expo.
Thank you to everyone that supports our work ❤️
Deviation Limits of the MD-380
Not enough deviation for Opulent Voice
We measured the deviation limits on the MD-380 with firmware from OpenRTX. Thank you to Redman for help with modifying the firmware to make this test as easy as possible.
The transmitted signal is about 10 dB down at 3000 Hz and almost gone at 4200 Hz. Therefore, there is not enough deviation for Opulent Voice.
The part of the radio under test was the HR_C5000. This is a part from Hong Rui and is a DMR digital communications chip. The chip handles 4FSK modulation and demodulation, among other functions.
According to a translated datasheet for the HR C5000, adjustment of the frequency offset range not possible. It appears to be designed only for +/- 3 kHz. Unless there’s an undocumented feature, or gain is added after the HR C5000, then +/- 3 kHz is the maximum deviation for this radio.
The HR C5000 puts out two analog signals MOD1 and MOD2, which are combined and then drive a varactor diode. The varactor might well have more range. Or it could be replaced with one that has more range.
Below is a photo essay of the testing and screenshots of results.
Test Results
Subscribe to ORI’s “Inner Circle” Newsletter
Join the Inner Circle at ORI.
ORI publishes a lot of technical reports. There’s over 30 repositories, 10 projects, and well – that’s a lot to digest. People asked for something easier to read that came less often so we did just that.
The link is http://eepurl.com/h_hYzL and the QR Code is below.
The response to the newsletter has been really nice with over 2000 subscribers in the first two weeks. Please consider yourself invited!
ORI is a non-profit all-volunteer group that donates all of its work to the amateur radio and amateur radio satellite services. Subscriber information is private and will not ever be sold.
How Can Open Research Institute Help *You*?
Thank you so much for visiting with us at QSO Today Ham Expo! We hope you found it as enjoyable, vibrant, and inspiring as we did.
We presented five talks, had three project exhibits, and a booth. You can find a summary below.
Your interest in our work is appreciated. We want you to enjoy open source non-profit digital radio and amateur radio to the fullest. How can we help?
Here is how to get involved with what we do:
https://www.openresearch.institute/getting-started/
Here’s a roundup of what we brought to Ham Expo. All of what we do is published as it is created. Our work is free to the general public at no cost.
-=-=-=-=-=-=-=-=-=-
Ribbit, a new digital text messaging mode for UHF/VHF emergency communications
Presentors: Pierre Deliou W4CKX, Ahmet Inan
Level: General Audience Category: Emergency Communications Time:
PDT: September 18, 2022, 10:00 am UTC: September 18, 2022, 5:00 pm
Ribbit is a novel digital text messaging mode for VHF/UHF communications for recreational and emergency use which radically increases the density of information transmitted by spectrum used. It leverages the computing power of the modern smartphone to increase the capabilities of any Handy Talkie without requiring any additional hardware. Its redundant distributed nature allows it to function even when connectivity to the internet is lost during emergencies. Ribbit is open source and currently in its early stages of development. Get the free Android app here: https://play.google.com/store/apps/details?id=com.aicodix.rattlegram
Artificial Intelligence and Machine Learning and the Future of Amateur Radio
Level: Intermediate Category: DSP and Software Design, Future of Amateur Radio, SDR Software Defined Radio, Software and Services Time:
PDT: September 17, 2022, 1:00 pm UTC: September 17, 2022, 8:00 pm
Artificial Intelligence and Machine Learning are all over the news, taking over academia, getting billions of dollars of commercial investment, and will change both computer networking and wireless communications in fundamental ways. What does the future of amateur radio look like when radios use machine learning to operate? How does our relationship to the bands change with cognitive radio? Where are we in this transformation? What will happen next?A working group to produce an AI/ML Handbook for Amateur Radio is forming now. Register your interest here: https://forms.gle/4dZsLkmyxCkp8JiF6
Truly Excellent Digital Voice Quality: Opulent Voice
Presentors: Paul Williamson KB5MU
Level: General Audience Category: Digital Voice Mode, DSP and Software Design, Software and Satellites, Space and Satellites Time:
PDT: September 17, 2022, 9:00 am UTC: September 17, 2022, 4:00 pm
Digital voice on amateur radio to date has generally had terrible voice quality, due to both a perception of limited available bandwidth and the convenience (to manufacturers) of repurposing commercial protocols with their older, proprietary, low-bitrate voice codecs. We present and demonstrate a modern digital voice design that can be used on 222 MHz and above with truly excellent voice quality. Source code here: https://github.com/phase4ground/opv-cxx-demod
Haifuraiya – Open Source HEO Satellite Project Proposal
Presentors: Michelle Thompson W5NYV
Level: General Audience Category: Space and Satellites Time:
PDT: September 18, 2022, 9:00 am UTC: September 18, 2022, 4:00 pm
Haifuraiya is an open source highly elliptical orbit amateur satellite project proposal. This presentation will walk through the high-level project proposal. The project features a digital microwave multiplexing transceiver with a failover transponder mode, has an international volunteer team open to community participants, and complies with debris mitigation guidance from the United States Federal Communications Commission. Repository here: https://github.com/phase4ground/documents/blob/master/Papers_Articles_Presentations/Slide_Presentations/haifuraiya/README.md
User Authentication for Amateur Satellites
Presentors: Paul Williamson KB5MU
Level: General Audience Category: DSP and Software Design, Software and Satellites, Space and Satellites Time:
PDT: September 17, 2022, 8:00 am UTC: September 17, 2022, 3:00 pm
After a brief discussion of the reasons why user authentication is needed on an amateur satellite service system, we’ll cover a proposed system to implement reasonably secure user authentication on a P4XT digital multiplexing satellite transponder, within the bounds of the (United States) rules.
We had three project showcases in the Project Gallery
Each Gallery had a Q&A tab, a poster or document, links to any papers, and a link to any associated video presentations.
1) Ribbit, a distributed digital messaging platform
2) Opulent Voice – High Bitrate Digital Voice and Data
3) Open Source Satellite Work is Free of ITAR/EAR
Kumospace Lounge
Thank you to Ham Expo for providing fun and effective Lounges for interaction at the conference. We truly enjoyed visiting with everyone that dropped by! We hope you enjoyed our themed events and the extended Q&A in the Lounges.
-=-=-=-=-=-=-=-=-=-
Open Source represented at the Quarterly FCC TAC Meeting
Open Research Institute is a member of the AI/ML Working Group and co-chairs the “Safe Uses” of AI/ML Sub-working Group.
ORI advocates for open source and amateur radio on the TAC.
ORI Brochure
Please take one.
DEFCON 30 Activity Report
Open Research Institute’s amateur radio open source showcase at the annual hacker convention DEFCON was located in RF Village (RF Hackers Sanctuary) in The Flamingo Hotel. A volunteer crew of seven people from three US states staffed the exhibit that ran from Friday 12 August to Sunday 14 August 2022.
RF Village hosts a very popular wireless Capture the Flag (CTF) event. It is a top tier contest at DEFCON and the winners are recognized at closing ceremonies. RF Village also has a peer-reviewed speaking track. See previous talks in the YouTube playlists here: https://www.youtube.com/c/RFHackersSanctuary
RF Village generously offers space for exhibits from the community. For 2022, the exhibits included Open Research Institute, Kent Britain PCB Antennas, Alexander Zakharov (ALFTEL Systems Ltd.), and Starlink (SpaceX). Starlink brought two stations and allowed visitors to experiment with network and physical security.
Total attendance at DEFCON 30 was estimated at 27,000. Conference events were held in the new Caesar’s Forum + Flamingo, Harrah’s, and Linq convention centers.
Open Research Institute’s exhibit had multiple parts. The entry to the exhibit was a poster session. Posters presented were ITAR/EAR Regulatory Relief for Amateur Satellite Service, Libre Space Foundation’s Manifesto, Authentication and Authorization Protocol for Amateur Satellites, and the Ribbit Project Introduction and Architecture. Ribbit allows an amateur operator to type in SMS messages on an Android app. Each SMS message is converted to digital audio tones. The tones are played out the phone’s speaker into the microphone of an amateur radio handheld or mobile rig. This can turn any analog HT into part of a digital messaging network. The app can do point-to-point communications and also has a repeater mode. More open source implementations are planned.
All posters were enthusiastically well-received. Specific technical feedback was received on the Authorization protocol that will improve the design. There will be a presentation about the Authorization and Authentication protocol at the September 2022 QSO Today Ham Expo.
Visitors understood the purpose and potential of Ribbit and could download the free open source Android app from a QR code on the poster. The code was also on the Ribbit stickers handed out at the booth. All 300 of the Ribbit stickers were handed out by Sunday morning.
Find the Ribbit “Rattlegram” application here: https://play.google.com/store/apps/details?id=com.aicodix.rattlegram
There will be a Ribbit presentation at the September 2022 QSO Today Ham Expo.
The ITAR/EAR Open Source amateur satellite regulatory relief poster garnered a lot of attention. A very large fraction of DEFCON attendees are familiar with ITAR/EAR, which are a set of regulations that govern the way we design communications satellites in the USA. People that read the poster at DEFCON understood and appreciated the value of the work, which provides long-awaited regulatory relief for the amateur satellite service. The poster presentation led to an invitation to Policy Village Sunday afternoon for a panel session hosted by the Office of the National Cyber Director. Summary of that session can be found in ORI’s 19 August 2022 project report. The ITAR/EAR poster will be part of the Projects Exhibits at the September 2022 QSO Today Ham Expo.
Foot traffic flowed past the posters and into the live demonstrations.
The first live demonstration visitors encountered was from OpenRTX (https://openrtx.org). This demonstration used a tablet computer running OpenWebRX to display modified MD-380 transmissions. Visitors could use headphones to hear live transmitted signals. Posters at the table explained the modifications required to implement the M17 protocol on the MD-380 and described the motivation and value of the work, with an emphasis on the use of the free and open CODEC2 voice codec. The use of CODEC2 in M17 replaces the proprietary AMBE codec found in every other digital voice protocol for VHF/UHF ham radio. There was strong interest in both the M17 and the DMR work from OpenRTX, broad understanding of why proprietary codecs are not ideal, and consistently positive feedback. 500 OpenRTX business cards were printed with QR codes for the OpenRTX website and nearly all of them were handed out.
The second demonstration was Opulent Voice. This is a high bitrate open source voice and data protocol. It’s designed as the uplink protocol for ORI’s amateur satellite program. The Authentication and Authorization fields are built in and sending data does not require a separate packet mode. The baseline voice codec for Opulent Voice is OPUS at 16 kbps. Higher bitrates are a build-time option. For the DEFCON demonstration, Opulent Voice was transmitted from an Analog Devices PLUTO SDR and received on an RTL-SDR/Raspberry Pi. Visitors could use headphones to listen to the received audio. The modulator and demodulator code can be found at https://github.com/phase4ground/opv-cxx-demod. 300 custom art stickers for Opulent Voice were ordered and all were handed out.
The two demonstrations compared and contrasted voice quality (3.2 kbps vs 16+ kbps), regulatory limitations (VHF/UHF vs. microwave), and approach to framing (P25 style vs. COBS/UDP/RTP).
The next station had stickers, buttons, patches, ORI’s Tiny CTF, Haifuraiya proposal printouts, and a Trans-Ionospheric badge display.
ORI’s “Tiny CTF” was a hidden web server, accessible from the wifi access point located at the OpenRTX demonstration. The access point allowed people to view the OpenWebRX display directly on their connected devices. Participants that found the hidden web server and then blinked the LEDs on a certain piece of equipment at the booth received a prize.
Haifuraiya (High Flyer) is an open source highly elliptical orbit communications satellite proposal. Microwave amateur band digital communications at 5, 10, and 24 GHz are proposed. Transmissions are frequency division multiple access Opulent Voice up, and DVB-S2/X time division multiplexed down. A presentation about this proposal will be at the September 2022 QSO Today Ham Expo.
Based on the feedback about the amateur radio themed Trans-Ionospheric badge, ORI will update and build another round of these badges. Round one of the Trans-Ionospheric badge was a very successful open source project fundraiser. The badges have been enduringly popular in the community, and they can serve as radio peripherals that display radio link and payload health over bluetooth. The artistic design of the badge is based on the front panel of the Zenith Trans-Oceanic radio. Find out more about the Trans-Ionospheric badge here: https://www.openresearch.institute/badge/
There were very high levels of interest, enthusiasm, and positive feedback throughout the weekend. Friends from Ham Radio Village and Aerospace Village visited the exhibit and shared their experiences. The organizational support from RF Village leads was excellent. ORI will return to DEFCON in 2023 with another round of open source digital radio demonstrations.
Amateur radio experimenters and their projects are welcome at Open Research Institute. Individuals can join for free at https://www.openresearch.institute/getting-started/. Projects can apply at https://www.openresearch.institute/your-project-is-welcome/
AquaPhage Lab at Remote Lab South
Bacteriophage work will be carried out at Remote Lab South, where an existing building is being converted to house laboratory space. Roof and interior work was required.
Spring 2022 Meeting Minutes
Recent Business:
Opulent Voice educational effort w/ University of Puerto Rico and University of San Diego
Goal is to develop curriculum using open source protocols
Rocket Desk Toy Fundraiser campaign via CommitChange
Supports open source electric engine synchronization that benefits high-speed digital communications mission integration
Morehead State University ASTROBi “Cost Sensitive KA-band LNA using COTS MMIC devices and novel coding” proposal
Deep space project that is interested in leveraging ORI’s work
AmbaSat sounding rocket work ongoing
Aeva Black of Open Source Initiative (OSI) nominated to the FCC Technological Advisory Board
FCC working group activity and participation continues with sub-working group “Safe Uses” co-chair service provided by ORI for 2022.
P4DX downlink encoder demonstration and code release at Ham Radio
Friedrichshafen 2022.
Report received
Code published (Pluto SDR with DVB-S2/X Encoder)
OpenRTX+M17 visit to Ham Radio Friedrichshafen 2022
Report received
Fiscal Sponsorship of Project Skylark
2021 tax return completed and filed
Grant proposals to ARDC for #104 “Douglas Qugaliana Contract Proposal” project and #106 “Transition from Remote Labs East to Remote Labs South”, both rewritten by ARDC, then declined by ARDC.
Both projects funded from alternate sources
Legal consult regarding a variety of ARDC behavior completed
Grant proposal to ARDC for “#272 A Low-Cost Open-Source Universal Radio Test Instrument” with Great Scott Gadgets deleted before the ARDC review committee saw it.
Government grants pursued as an alternative
Ongoing Issues:
M17 Project discussion of communication, expectations, and reimbursement
Items to Discuss:
Defcon “Retail Hacking Village” request to join Open Research Institute
Minutes approved 22 August 2023
Opulent Voice – digital voice and data protocol update
Opulent Voice is an open source high bitrate digital voice (and data) protocol. It’s what we are using for our native digital uplink protocol for ORI’s transponder project. Opulent Voice is also looking pretty darn good for terrestrial.
Here is an audible example of the Opulent Voice audio quality under ideal conditions. Each file is about 37 seconds long. It starts with a short musical intro, and the rest is the beginning of the audio track from one of Michelle’s conference talks. These were originally recorded with mid-range podcasting studio gear. The recording was converted to a signed 16-bit PCM raw file, which has been re-converted to a standard WAV file so you can play it easily, MDT-short.wav
This file was then run through opv-mod to create a file of baseband samples, which was then piped to opv-demod, which created an output file of signed 16-bit PCM. That file was converted to WAV file MDT-short.demod.wav
We expect to present a nice demo at DEFCON in August 2022 and at the QSO Today Ham Expo in September 2022.
We’ll be using COBS protocol within Opulent Voice. If you’re unfamiliar with COBS, please read about it here:
https://en.wikipedia.org/wiki/Consistent_Overhead_Byte_Stuffing
Authentication and authorization is built in and optional. There is no separate “packet mode”. Things are designed to “just work” and get out of your way whether or not you’re sending voice or data.
Opulent Voice is designed to where you can use even higher bitrate OPUS codecs if you wish. This will most likely be a build option and not a run-time option, but if a run-time option is something you want to work on, speak up! Let’s see what we can accomplish.
Originally based on Mobilinkd codebase that implements M17, the Opulent Voice development implementation can be found here:
https://github.com/phase4ground/opv-cxx-demod
Initial demos will be on a HackRF/PortaPack on the 1.2 GHz ham bands.
Thank you to OpenRTX for help with troubleshooting the audio quality on the PortaPack. In order to have a good demo, basic FM transmit from the microphone needs to work. The audio quality is pretty bad (this was a surprise) with the stock application, so we’ve been spending some time with the Mayhem codebase, the microphone transmit app, and the driver for the audio codec in order to get it sounding like it should. This needs to happen before we publish an app for the PortaPack.
Synthesized audio from the HackRF/PortaPack sounds clear and wonderful. It’s just the microphone that is splattery and overdriven.
ORI’s Slack channel can be found at https://phase4ground.slack.com/
The authentication and authorization work is in #aaaaa
Opulent Voice work is in #opulent-voice
Thank you to everyone supporting the work!
-Michelle Thompson
Summer Fundraising: Rocket Desk Toys Available Now
Help spread the word about our summer fundraiser. These are cute mini-puzzle desk toys in custom packaging. They are shaped like a rocket ship and are made out of laser-cut orange acrylic. Campaign runs through 1 September 2022. More items will be added throughout the summer.
https://us.commitchange.com/ca/san-diego/open-research-institute/campaigns/where-will-we-go-next
Countdown to NASA SBIR/STTR Solicitations Announcement
It is 5 days until the next SBIR/STTR NASA solicitation round.
Let’s take some time and sort through the solicitations and see what we qualify for.
We have a fantastic community and volunteers that would like to do meaningful work.
Applying for SBIR/STTRs as the research institute or non-profit is one way to accomplish this goal.
I’ll post the announced solicitations, but if you want to keep track, then the webpage to go to is here:
https://sbir.nasa.gov/solicitations
If you would like to be part of ORI, please visit:
https://www.openresearch.institute/getting-started/
Poster Presentation ITAR/EAR
Video of Working Meeting on Higher Bitrate M17
Specification of M17:
P4DX architecture document:
https://github.com/phase4ground/docum…
M17 is P4DX native digital uplink protocol.
There are at least three use cases of M17.
One, 9600 bps voice for VHF/UHF.
Two, the idea of 9600 bps data or packet mode, also VHF/UHF.
Three, higher bitrate mode for microwave.
There is a data type specifier in the current specification. Reserved protocol types are RAW, AX.25, APRS, 6LoWPAN, IPv4, SMS, and Winlink.
What we’re talking about today is what, if anything, needs to be added to the specification in order to enable high bitrate operation for microwave, and also to figure out if anything needs to be done for IP over M17 or M17 over IP.
From Slack:
Ron
What needs to be defined is how to do IP over M17. In the M17 specification, there’s a protocol identifier for IPv4, but that’s it.
And here is a review of the conversation from 2021. This was the starting point for the conversation in this video recording.
Ron
M17 supports IPv4, but I’m not exactly sure how. The M17 specification seems pretty vague on that particular point
Howie
Assume we consider M17 stream mode operating in an FDM manner with a receiver for each uplink channel. Each channel can be given a GSE label that could map to an uplink center freq. The 4FSK modulated data is demodulated but not decoded. Instead, the data streams are clocked into individual buffers and used to generate the GRE frames. The idea is to keep the M17 frames intact so that on the ground earth station the demodulated data is identical to the uplinked frame which can be processed by the existing M17 decoder software. You listen to a channel by selecting the label for the stream you want to listen to. The limiting factor becomes how fast you can assemble the uplink channels into GRE frames.
I don’t think there is any need or desire to use anything other than native M17 on the uplink. While GSE is normally used for IP transport I think we could put the M17 frames into the GSE data field. At that point the only overhead is on the downlink with the addition of the GSE headers and LSF management. I have not looked closely at the sizes of the required fields are or how much processing it would take to multiplex multiple uplink streams into a composite downlink. At this point I am just brainstorming.
Anshul
looks like we don’t need IP as an intermediate step. I agree with @ab2s that there is no need to use anything other than native M17 on the uplink. GSE should encapsulate M17 frames and produce BBFRAME as it normally does for IP packet.
It implies we will be not using any IP stream/packets on uplink. Everything uplink will be M17 based.
Do you see any concerns here . Else, I will proceed with implementation of GSE block in firmware keeping this decision in mind.
Consensus on:
- Validity of use case for higher bitrate M17 for P4DX uplink.
- IP over M17 could use an example (as could all the types in this field), but the type field indicating IPv4 is sufficient for carrying IPv4 within M17. M17 packet is small enough to where IP fragmentation will probably occur.
- M17 over IP is defined in the appendix, it works as implemented in the reflector network, and did not appear to need any additional work.
- P4DX could provide a spigot of M17 uplinks over IP, using the protocol in the appendix, as a Groundsat feature. This would not affect the air interface.
- We discussed the XOR with random data aspect (covert SPARROW channel here? Yes/maybe if there’s a known message)
- Discussed asking for a P4 Type Field Indicator. Smart receivers won’t need this, but it would allow people to move between 9600 bps M17 and higher bitrate M17.
17 March 2022: International Standardization of the M17 Protocol
Interested in M17 Project? IEEE and ORI are co-hosting a presentation about International Standardization of the M17 Protocol.
Even if you can’t make the live meeting, please register. Registrants get a link to the recording sent to them after the event. And, good attendance numbers will help get future amateur radio events cross-listed with IEEE.
Have You Heard The Good News?
Updated one-sheet and brochure for 2022.
Take one today!
HamCation 2022 Report
HamCation 2022 Report
Paul Williamson (Remote Labs), Douglas Quagliana (P4DX), Michelle Thompson (ORI), Ed Wilson (M17), and Steve Miller (M17) represented the breadth of projects from Open Research Institute at HamCation 2022.
ORI’s “Tonight’s The Night: SDRs are HOT” booth made its first appearance in nearly two years. Available at the booth were stickers, pins, patches, shirts, consulting, and project updates. ORI’s “extra chair” seating area was appreciated by volunteers and visitors alike. Booth visitors heard about the successful DVB-S2X modem work from ORI and progress on the end-to-end demo of the entire satellite transponder chain. At Open Research Institute, it doesn’t work until it works over the air. Due to the efforts of a truly wonderful international open source team, the custom FPGA code is coming together very well, and Remote Labs continues to evolve. The Phase 4 Digital Multiplexing Transceiver project is on budget, on track, and highly likely to succeed. The return on investment is high. The team isn’t anywhere near done innovating, publishing, and enabling high-tech space aand terrestrial amateur radio work. If you want to be a part of this, or just follow along, visit https://openresearch.institute, go to “Getting Started”, and sign up for the Phase 4 Ground mailing list. This is “home base” for announcements from ORI.
Right beside ORI’s booth was the “future of amateur radio”, the M17 Project. Ed and Steve from M17 brought working hardware, firmware updates, and also demonstrated several different software implementations throughout the weekend. M17 held their weekly net on Friday live from the booth, gave away stickers, magnets, and pins, and captured the hearts of all who visited. You can get involved with this project at https://m17project.org
AmbaSat re-spin was a frequent topic of conversation. The five AmbaSat boards from ORI, which operate at 70cm, have been distributed to the firmware team, and they have begun development and are seeing success in university and hobbyist labs. The goal is to create a compelling application, put the hardware on a sounding rocket, apply for a launch license, and send this project to space in a way that makes the amateur community proud. While “AmbaSat Inspired Sensors” is ORI’s smallest received grant, it has by far the highest capability return on investment of any ORI project.
ORI and M17 booths were located in the North Hall. While the other buildings are larger and many consider them to be higher profile, booths in the North building are what you must walk by to get to the Information Booth and Prize Booth. Since the vast majority of participants visit this part of the show, it is, in our humble opinion, the best possible location.
Michelle Thompson (W5NYV) presented about Digital Communications Technology at the ARRL Expo Technology Track held on Thursday at a conference center near Seaworld. There were four tracks of presentations at the Expo: Contesting, Handbook, Technology, and Emergency Communications.
Michelle reported a positive, enthusiastic, and engaged audience for her ARRL Technology Track talk, and has high hopes that ARRL will continue doing events like this moving forward. She discussed ORI’s Polar Code initiative, successful regulatory and legal work, why open source LDPC work is so important to amateur radio, the four fundamental components to digital communications, and why the M17 protocol was selected as ORI’s satellite uplink protocol for the P4DX transponder project. Michelle invited M17 principals to speak about their work, and opened the floor for questions and comments from the many highly competent and curious technical hams that were in attendance. Subjects covered ranged from asynchronous computing to concatenated coding. The rumors about toilet paper being a fundamentally important part of this presentation are entirely true.
ORI organized a Friday forum track for Clearspan Tent #1 that ran from 11:15am until closing. HamCation was extremely generous in giving us time to present work from a wide variety of people. Here’s our lineup for 2022.
11:15 am
Understanding and Changing Amateur Radio Regulation / Open Source Digital HTs are Real! by Bruce Perens (K6BP)
12:30 pm TAPR – TangerineSDR Update, or How to build an SDR without any parts by
Scotty Cowling (WA2DFI)
1:45 pm M17 Project by Ed Wilson, Steve Miller (N2XDD, KC1AWV)
3:00 pm GNU Radio work at ORI / FreeDV HF Voice Update 2022 by Douglas Quagliana, Mel Whitten (KA2UPW, K0PFX)
3:00 pm Society of Amateur Radio Astronomy SARA by Tom Crowley (KT4XN)
At both the Expo and HamCation, ARRL set the pace this year for satellite talks and satellite demonstrations, with a video (please see https://www.youtube.com/watch?v=fhyUbC_o1JM&ab_channel=ARRLHQ) providing practical examples of amateur satellite operations. Patrick Stoddard (WD9EWK) gave a tutorial on satellite operations at the ARRL Expo in the Handbook Track. Amateur satellite was very well supported from ARRL this year, and we have heard this will continue to strengthen going forward.
With some optimism, ORI looks forward to returning to in-person events. The next planned in-person event is DEFCON (https://defcon.org/). Last year, DEFCON was held in person. Proof of vaccination was required. Masks were required. It was a highly successful and enjoyable event. This year, for 2022, ORI will be represented in DEFCON villages and activities. We are looking at applying for M17 to be part of Demo Labs, multiple radio links between villages to demonstrate a wide variety of technology, and presentations about the R&D that we do.
If you would like to be a part of this, and we do need you, then please join the Slack channel for DEFCON planning. Quite a bit of work is underway already. The goal for DEFCON 2022 is over the air demonstrations, outreach, fun, swag, and supporting our friends at all the villages we’ve been involved with over the years.
DEFCON is run very differently from traditional amateur radio conventions. The most significant practical difference is that DEFCON has a written code of conduct, and those written community standards and policies are enforced. It has a very diverse and very interdisciplinary attendance. Unlike many technical or hobby conferences, participation in the DEFCON community is possible year-round through participation in local groups that meet monthly.
DEFCON is a very large event, with attendance of over 30,000.
DEFCON is devoted to a very broad spectrum of experimental, commercial, and open source work. Participation by the government, industrial, information security, hacker, hobbyist, and scientific communities has steadily grown over the past 30 years.
The next virtual event for Open Research Institute is Ham Expo, 12-13 March 2022. Andre Suoto will have an excellent talk about our open source LDPC encoder for FPGAs and ASICs. This is in the main track. We will have a wide variety of work and projects represented at our booth, which is in the vendor hall. Open Research Institute is a non-profit sponsor of Ham Expo. We’ll have friendly and accessible “office hours” during the event.
Quarterly Technical Advisory Committee Meeting 5 February 2022
HamCation 2022
This post will be updated with information leading up to and throughout the event. Thank you to HamCation for the support and opportunity.
Tucson Amateur Packet Radio
Booth, prototypes, forum presentation, give-aways, and more!
Society of Amateur Radio Astronomers
Forum presentation.
M17 Project
Booth, forum presentations, give-aways, and more!
Open Research Institute
Booth, demonstration reports, give-aways, sales, and more!
ARRL Technology Track
Talk by Michelle Thompson W5NYV.
Abstract:
Digital communications technology is large interdisciplinary field that incorporates some of the most fundamental scientific advancements of the past 120 years.
From the first spark gap transmitters, to telegraph, to the transistor, to the fast fourier transform, to the tape drive, to telnet, to touchscreens and trace routes, trackballs and telecommunications of all sorts, digital transmission of everyday information has revolutionized the way we communicate with each other, the way we store data, and the way we process that data to create things of greater and greater value.
This talk is about how information travels over the air in ways relevant to motivated amateur radio enthusiasts.
Digital communications is a difficult subject. This talk is simplified, but definitely not dumbed down. You will leave this session with a greater intuitive understanding of how digital communications works.
There’s a vibrant community and growing body of work in open source amateur radio digital communications for space and terrestrial work. The talk will close with a brief summary of open source digital communications work at Open Research Institute, Inc., a 501(c)(3) dedicated to open source work for amateur radio and beyond.
2021 Retrospective
Greeting all, and welcome to the close of 2021 at ORI.
For a high-level summary of what Open Research Institute is and what we have been up to, please watch the very short video presented at Open Source Cubesat Workshop 2021. The recording of the talk is here: https://youtu.be/VG9-Mc1Hn4A
If you would like to keep up with what we do, then subscribing to our mailing list and YouTube channel helps in several ways. More people find out about what we do because our work will get recommended more often to new people, and you get notifications of new content when it’s published.
Please visit https://www.youtube.com/c/OpenResearchInstituteInc/featured and subscribe to YouTube.
Please visit https://www.openresearch.institute/getting-started/ for information on joining the mailing list and Slack.
Join Phase 4 Ground Trello board:
https://trello.com/invite/b/REasyYiZ/8de4c059e252c7c435a1dafa25f655a8/phase-4-ground
Join Phase 4 Space Trello board:
https://trello.com/invite/b/GRBWasqW/1336a1fa5b88b380c27ccf95d21fec79/phase-4-space
We have other social media accounts as well (Twitter, Instagram, FaceBook) and we gratefully accept help and support there too. Want to be part of the social media team? Write ori at openresearch dot institute to apply.
https://twitter.com/OpenResearchIns
https://www.facebook.com/openresearchinstitute
https://www.instagram.com/open_research_institute/
Here are our challenges and successes from the past year and what we’re looking forward to in 2022. There’s a lot going on here and some of the things we are facing are not fun. Some of the discussion is political and tedious. We have some decisions that have been made and some big ones to make for 2022 and beyond. Your opinions matter. Comment and critique welcome and encouraged.
First and foremost, we thank the individuals and organizations that have made our work possible. Funding comes from YASME Foundation, ARRL Foundation, ARDC Foundation, Free Software Foundation, our Trans-Ionospheric and JoCo Badge projects, proceeds from the Gold Medal Ideas ORI store, and people like you.
2021 Retrospective
We are a research institution. We are not a ham radio club. Our primary focus is to carry out open source work for the amateur radio space and terrestrial bands. We expect this work to be used by amateur radio groups that execute and operate designs in space and on earth. This expectation has not been met in some of the ways we anticipated, but we have a broad path forward, a lot of things going very well, and we are going to take full advantage of all the positive developments over the past year in every way we can.
This next part is not the most fun story to write or read, but there’s a lot of very good lessons learned here, and it needs to be put in one place so that our amateur satellite volunteers know about it and can find it.
When we say we expected our work to be used by amateur satellite groups, we assumed this meant AMSAT. Primarily AMSAT-NA, but we are also here to serve AMSAT-DL, AMSAT-UK, and so on. ORI is an AMSAT Member Society, and has showed preparation, enthusiasm, and experience through continued contributions to the amateur satellite community. ORI volunteers have professional, academic, and amateur experience with collectively at least a couple dozen payloads in orbit, ranging from GEO commercial to LEO amateur. A very large fraction of our volunteers are new to amateur radio. They have never volunteered for AMSAT or any other legacy satellite group before. Other volunteers have experience with AMSAT but no current role because of the politics of AMSAT-NA GOLF. I can say without any reservation that there is no loss of capability to any AMSAT organization from ORI activity. We have always encouraged volunteering for and membership within whatever AMSAT organization is nearest to you. It’s not just supportive words, but actions as well. We have sold AMSAT-NA memberships at numerous events over the years. We have actively promoted TAPR, AMSAT, ARRL, and other amateur groups at every opportunity. We’ve happily worked with TAPR and ARRL to great positive effect.
We have achieved some truly significant wins in the regulatory sphere with ITAR/EAR and Debris Mitigation, have groundbreaking success in P4DX comms development, and have one of the very few functional advanced communications research remote access lab benches in existence. We have expanded the AmbaSat Inspired Sensors project to move the AmbaSat to 70cm in anticipation of sounding rocket and space tests, have fully supported M17 Development and Deployment, and have proposed an employment program to ARDC to directly confront the problem with open source burnout in DSP/FPGA open source amateur designs.
We really do not suck.
However, despite all this good work, AMSAT-NA leadership, including senior officers, have consistently and publicly described ORI as “grifters” and “thieves” and “frauds”. Officers of AMSAT-NA have said we are “undeserving of any community support” and have taken actions to try and make this opinion a reality. It hasn’t worked, but these aggressively provocative and negative public posts from AMSAT-NA officers and members about ORI are clearly intended to harm. The attacks date back to 2018. ORI has not responded to any of this. However, ignoring it doesn’t make it go away, and participants in ORI need to know what’s being said and done.
ORI has had work censored from AMSAT publications and events. An ITAR/EAR update article submitted in October 2021 was removed before publication. According to the editor, this was the first time ever an article had been censored in the AMSAT Journal. The article had been requested by the editor and is in the draft of that issue of the Journal. It was personally squashed by the AMSAT President after the draft Journal was sent out. Several presentations and some papers were ordered to be eliminated at the last minute from 2020 AMSAT Symposium. The work had been welcomed by the submissions chair. This exclusion was unprecedented as well.
This sort of bizarre censorship has no place in amateur radio. Our disappointment with these decisions has been communicated to the editor of AMSAT Journal and the submissions chair for AMSAT Symposium.
For 2021, ORI co-hosted a half-day conference in collaboration with IEEE. This Information Theory Space and Satellite Symposium was successful, got great reviews, and IEEE has asked several times if ORI would be willing to organize something like this again. This gave us a chance to present some of the sort of work that we think should be part of AMSAT Symposium.
You can find the event recordings here: https://www.youtube.com/playlist?list=PLSfJ4B57S8DnhlrRya50IxGP90_uGpiho
Why do we care about any of this grumpy opposition? Why be concerned about censorship from a relatively small event or newsletter?
Because AMSAT-NA is presumed to be the primary advocacy group for amateur satellite activity in the United States. Because we want all AMSAT organizations to be successful. Because AMSAT and ARISS-USA have claimed that they are gatekeepers for amateur radio access to NASA. Because AMSAT-NA currently controls access to things like IARU committees for Region 2. Because AMSAT-NA gets irate when anyone else meets with the FCC on behalf of the amateur satellite service, but will not present anything outside of internal AMSAT-NA interests.
We care about this because ORI showed up and contributed within the AMSAT framework in good faith.
AMSAT-NA is, to be blunt, supposed to help us do exactly what we are doing. We are not a “threat”. We are not “thieves”. We are not “grifters”. We are not “frauds”. We don’t “siphon technical members away”. We are not “an embarrassment”. We deserve absolutely none of this sort of thing. We have invited AMSAT-NA to participate in every single major endeavor that we have carried out and accomplished. This inclusive and cooperative spirit has not been reciprocated.
Tacit acceptance of this sort of behavior is the real embarrassment.
For 2022, we will (of course) continue to utilize the amateur radio bands. All radio work will directly benefit amateur radio terrestrial and space. There will be no loss of opportunities or restrictions of goals for technical work. However, our associations and attention moving forward will focus on communities and organizations that share basic values with ORI. There will be some changes as we adapt, evolve, and grow. We can’t afford to spend time trying to work with organizations completely out of step with open source amateur satellite work, no matter how famous, wealthy, or historical they happen to be.
Successes in 2021
There is a lot of good news here.
Both the San Diego Microwave Group and the San Bernardino Microwave Society have been actively supportive and provided material assistance, volunteer time, and expert advice that we simply would not have received anywhere else. We would not have had a successful meeting with the FCC about Debris Mitigation without the support from members of these two radio clubs. Members generously offered their time, input, and guidance. All the regulatory work can be found here: https://github.com/phase4ground/documents/tree/master/Regulatory
Based on this meeting, we had a series of Orbit Workshops in November 2021. Recordings posted to the debris mitigation channel on our Slack.
The ITAR CJ Request work was funded through a grant from ARDC. The EAR Classification, successful Advisory Opinion Letter from Commerce, FAQ, and “How to use this work” flow graph were paid for with a loan to ORI. The process to fundraise to pay back this loan is underway. The final amount for EAR/Advisory Opinion/FAQ/Flowgraph is $14,425.00 Similar to the ITAR CJ Request work, this amount is substantially less than initial estimates. Credit goes to excellent counsel at Thomsen and Burke LLP and a motivated volunteer team at ORI that handled as many of the preparations as possible. Active sustained involvement reduced costs and increased competence and awareness of the many legal issues we were dealing with.
For 2022, we have two legal efforts that we are considering becoming involved with. Fundraising for those efforts will happen in advance of the work. This is a change from how we did the ITAR/EAR legal work, where fundraising was done after the legal work was completed.
We would not have had a successful multi-media beacon demonstration without support and advice from Kerry Banke and Ron Economos. A video presentation of this work can be found at https://youtu.be/vjfRI1w_dSs?t=609 and documentation can be found here: https://github.com/phase4ground/documents/tree/master/Engineering/Transmitters/DVB-S2-Multimedia-Beacon
This work is presented as a terrestrial beacon, but is also the default digital download for the P4DX transponder payload.
The payload work is currently focused on producing an FGPA-based end-to-end over-the-air demonstration. There are multiple repositories. The best way to get an overview of this work is either through the README.md files in the repos at https://github.com/phase4ground and https://github.com/phase4space.
If reviewing source code and block diagrams is not your thing, then watch the introduction of this video: https://youtu.be/fCmzS6jBhHg followed by the most recent Technical Advisory Committee meeting here: https://youtu.be/V2BlIp7XYMM
Thomas Parry is the Primary Investigator and lead the TAC meeting. Wally Ritchie (SK) was the previous and founding Primary Investigator, and he presented the overview in the design review linked above.
P4DX is our digital multiplexing microwave amateur band transverter. The native digital uplink is M17 FDMA and the downlink is TDM DVB-S2/X. A high-level architectural paper can be found here: https://github.com/phase4ground/documents/tree/master/Engineering/Requirements/Architecture
One of the current roadblocks with the end-to-end demo is a necessary expansion of capability in Remote Labs West. In order to use the Analog Devices ADRV9371 RFIC development board, we can get by with using an SD card image in the FPGA development station. However, this requires a lot of manual intervention, so booting the filesystem over NFS is an obvious improvement. This turned out to be impossible because the kernel from Analog Devices does not appear to support NFS. So, we’re fixing it and will (assuming success) submit whatever capabilities we add to the kernel back to Analog Devices. In the meantime, integration of the various bodies of FGPA code continues. Immediately following the NFS boot addition is DVB-S2/X verification station bring-up, in anticipation of being able to test what comes out of the ADRV9371. That’s just one example of the type of work that has had to happen all year in order to get things done.
Remote Labs have become much more than a “wear item” along the way. Once it became clear that the internet-accessible lab benches had potential to support a much wider variety of projects than just P4DX, volunteers started putting time into making sure they were as easy to use as possible. You can find out more about what Remote Labs are and how they work by going here: https://github.com/phase4ground/documents/tree/master/Remote_Labs
Remote Labs East (Florida) equipment has been moved to Remote Labs South (Arkansas). The move was necessary due to the untimely death of Wally Ritchie in July 2021. The new site will need additional funding to complete that Florida did not require. A grant application was made to ARDC in late August 2021 for this work. Remote Labs South will also have additional capabilities for bacteriophage and interferometry work. Both are open source efforts.
There is a backup bridge funding plan to get the lab bench at Remote Lab South operational. We can temporarily divert funds allocated to P4DX for FPGA software licenses, as the floating license approach has worked out well for us. The original budget planned for 10 node-locked licenses as those were the type of licenses we have received as an organization in the past. With only 1 floating license required for work so far, this leaves some margin in the budget. This is enough margin to develop Remote Labs South infrastructure while waiting for a response about funding from ARDC, without further delaying deployment of this lab.
Remote Labs are a good example of the frugality, public science orientation, and opportunistic spirit of ORI volunteers. We look forward to many years of making the equipment available to the open source community. We could use your help in spreading the word about this asset.
HamCation and Ham Expo have been invaluable. The staff and volunteers have been friendly, supportive, and creative. We are looking forward to HamCation 2022. If all goes well this will be our first in-person event most of us have been able to attend in quite a while. We have a booth in our usual spot. M17 Project and TAPR are on either side, and the large Society for Amateur Radio Astronomy booth is on the other side of TAPR. DATV is in the same row. ARRL will have a large presence. We have a lot of forum time and plenty to talk about. Returning to in-person events is a big step and there is extra stress, risk, and planning involved. If you are willing to be part of HamCation, please get in touch and we will add you to the planning spreadsheet and discussions.
IEEE Computer Society, Information Theory Society, and Signals and Systems have been incredibly supportive. As mentioned above, in 2021, ORI co-hosted a half-day conference in collaboration with IEEE. This Information Theory Space and Satellite Symposium was successful, got great reviews, and IEEE has asked several times if ORI would be willing to organize something like this again.
You can find the event recordings here: https://www.youtube.com/playlist?list=PLSfJ4B57S8DnhlrRya50IxGP90_uGpiho
We have received a lot of positive feedback from IEEE section, region, and national executive teams. The biggest challenge with IEEE is that they are not the best or easiest way to publish open source or open access work. They are honestly not set up for public access papers. IEEE is split between academia and industry members, and that’s the constituencies more or less served. Despite the big differences between a tiny open source non-profit and a gigantic professional development organization, there is a substantial amount of interaction and genuine mutual support. IEEE does not exist without volunteers. Therefore, what we are doing is recognizable as a thing of value by everyone in any role any of us comes into contact with. We also benefited from having access to the salary survey results, anonymized membership statistics, and a targeted member survey in order to help construct the Engineers General grant proposals to ARDC. Is there a possibility of funding through IEEE? Yes, although there are a lot of limitations.
We have solid relationships with a number of Universities. Working with academic institutions is not simple as a non-profit, but we have transcended these difficulties several times and are part of the process of getting space “done better” for students wherever we can. Our most recent involvement is getting AmbaSat at 70cm, the DVB-S2/X microwave band work, and M17 equipment on board sounding rockets and in the running on several LEO platforms. Is there a possibility of funding through Universities? Honestly, no. They expect funding from us, in order to do anything with us. That is just the way the current engineering academy operates. Students are not “free labor” now and never really have been in the past.
We have brought a small grant to a University, with the professor as the Primary Investigator (AmbaSat Inspired Sensors). We would be willing to do that again, if we were fortunate enough to get a professor of the same motivation, experience, and availability, and fortunate enough to get enough grant money to ensure student time. In general, the overhead customarily demanded at a University, and the costs of getting significant seat time from enough students, require much larger grants than we have pursued to date. If you know of an opportunity or have an idea, get in touch with ORI board and let’s see what we can achieve.
AmbaSat Inspired Sensors has redesigned the AmbaSat board to move from 915 MHz ISM LoRaWan to 70cm amateur radio satellite band. Thank you to Vidya Gopalakrishna and Jay Francis for making this happen. LoRa with integration to both SatNOGS and The Things Network through bridging is prototyping now. The first hardware with the 70cm part has been received and works. There were other changes to improve power and ground and routing. All of the details can be found in the kicad-conversion branch at https://github.com/phase4space/AmbaSat-1/tree/kicad_conversion/Release
This past year has been a significant step forward for the M17 Project. The protocol has been strengthened, the number of development boards in the community has increased, the amount of hardware that M17 can work on has increased, and the lab on the East Coast of the US is moving forward. There have been numerous successful public outreach efforts resulting in a steady increase in name recognition, awareness of the communications mode, and participation on the M17 Discord. A large amount of lab equipment has been earmarked by ORI for M17. This purchase opportunity came from Open Lunar Foundation and will put M17 lab into a highly capable category from the start. All of us associated with M17 would like to recognize the OpenRTX project. This team is a vital part of the M17 ecosystem and has done a significant amount of highly technical work to enable M17 on the MD-380 HT. OpenRTX has contributed a lot of engineering work, verification, validation, and lab tests for M17.
Open Lunar Foundation and ORI collaborated on an SBIR grant application for funding targeting LunaNet in January 2021. While our application for funding was not successful, the feedback from the reviewers was positive and very constructive. The process for applying was clear, the technical work in preparing the application lined up with all of ORI’s goals for P4DX, and the teamwork with OLF was excellent.
We attempted to apply for a STTR with Tek Terrain LLC for opportunistic positioning and ranging using LEO signals in mid-October 2021, but we were not able to complete the application in time. We look forward to the next opportunity to work with a for-profit on something like this, as there are dozens of opportunities through a variety of government agencies for research and development. This particular project would have put some significant work into the public domain during Phase 1 of the grant.
We have an opening on our board of directors. Our co-founder Ben Hilburn has stepped down from the board. Thank you very much to Ben for helping found and build ORI. We welcome you to a (much less demanding) senior advisor role.
If you have a recommendation for someone to invite, or you would like to volunteer for this role, then get in touch to start the process. There are a few IRS limitations on who can be on the board to prevent conflicts of interest. No relatives of current board members, for example.
Current board is listed at: https://www.openresearch.institute/board-of-directors/
Our open source workers/employment initiative is called Engineers General. Two grant proposals were made to ARDC after a series of productive meetings with their staff. The initiative got a lot of positive feedback. All of ARDC’s feedback was incorporated into a set of revised grant requests that were re-submitted in October 2021.
We have 6 additional resumes that have been submitted to us. We have received a very large amount of interest in this initiative. Information from IEEE salary surveys, informational interviews with open source workers, and combing through peer reviewed papers resulted in the hypothesis of Engineers General, and all of this information was communicated to ARDC in support of the grant requests.
ORI board has the capacity, capability, and experience to manage contracted workers, and there is a population of highly qualified people that want to work in open source.
We do not have a timeline on when we will hear back from ARDC. P4DX took 11 months to approve. The ITAR legal work funding wasn’t pressing since the funding application followed completion of the work. The AmbaSat Inspired Sensors grant application was folded into P4DX at some point during its review process.
Rent-a-GEO was submitted in October 2019, and there has not been a final answer from ARDC about that proposal as of today. Rent-a-GEO is now down to ~2.5 years left on the offer of 5 years discounted rental of the transponder. This is closer to 2 because the team assembled for Rent-a-GEO would have to be rebuilt.
For those unfamiliar with this project proposal, it would enable a variety of GEO development work over useful space channels with a footprint that covers the continental United States. We did obtain a private pledge of funding for the rental due to the urgency with the lifetime of the resource coming to an end, and we have communicated this pledge of funding to the vendor handling the transponder rental. However, there are substantial contingencies with this funding source, and the vendor has a lot of challenges that they are dealing with. Negotiations are slow. I’ll keep working on this until EchoStar9 is turned off. In the meantime, we have had a series of successful experiments in Europe.
We are headquartered in California, USA. According to Cal Non-Profits, a 501(c)(3) dedicated to helping California 501(c)(3)s, they really do not know of any other organizations like ORI (or Open Lunar Foundation). We are quite rare. The vast majority of non-profits in CA (and across the US) are devoted to health and human services. Non-profits heavily dominate “last mile” services delivery in the US, and there’s a wealth of information about them and advice on how to operate. We have taken advantage of as much as we can all the advice given by Cal Non-Profits, and will continue to rely upon them for guidelines and checklists and statistics about the non-profit sector.
Almost all of the science and technology non-profits are private foundations. Almost all of the research institutes in this category have a single very large source of money, have paid staff, and are clearly dedicated to a mutually beneficial relationship with commercial consumers. This is a very different way of operating from ORI, which is registered as a public charity.
And, the way we have been funded directly impacts this status as a public charity. 501(c)(3)s like ORI are required to have diverse funding. We have to comply with what’s called a “public support test” that kicks in after our fifth year of operation. We’ve been around three years and have two more to go before this test is applied. While we did come very close to passing this test in 2020, we will not pass it for 2021. The specific test is that 33.3% of our funding must come from what are called public sources. Technically this means at least 33.3% of donations must be given by donors who give less than 2% of the nonprofit’s overall receipts. That 2% test means that each non-profit’s donation numbers will be different, depending on the overall receipts.
With ARDC being our primary funding source, all of the other sources amounted to at most 30% in 2020. In 2021, the vast majority of funding came from ARDC, putting the percentage from other sources down much further. A quick calculation today shows other sources of funding coming in at most 24%. Given the 2% rule, that number is in reality lower.
If we had just one unusually large grant from ARDC in our financial history, then that would be ok. The IRS lets you ignore one unusually large grant. You can punch that one out of your public support test calculations.
One can argue that all of the money from ARDC should count as unusually large, and all recipients out there doing tower trailers and buying equipment for mesh networks and university club shacks shouldn’t have to worry about this at all.
The amateur community has never sourced or sunk large amounts of money like this. Hams have a reputation for being tight-fisted with money. Frugality is a virtue that we ourselves value and employ, as described earlier in this letter in the way we’ve extracted several “extra” features from the P4DX grant money that a less motivated organization would not bother to do.
A step function of money of the magnitude that ARDC has, showing up in the amateur radio community, cannot easily be matched or diluted. ARDC principals have heard this from community members with philanthropic experience from the get go.
For almost any amateur radio organization, outside of the very largest, diverse sources of money on the order of an ARDC grant simply do not exist. This means that ham non-profits can take one large grant from ARDC without much trouble or effect on their status, but that’s it. The vast majority of ham clubs and organizations file nothing more than a postcard with the IRS every year. Above $50,000 in gross receipts and then they have to file the full 990. A large influx of money on an ecosystem of organizations that have never had access to it before includes both negative and positive effects.
For organizations like ORI that fully intended to work with ARDC for the long haul, this puts a huge additional fundraising burden on the leadership. Since ORI has ruled out selling memberships, the fundraising alternatives are even more challenging in an environment where a highly successful ham club auction raises $400.
So what happens when your public charity fails the public support test? Well, actually, nothing too horrible, but only if you are prepared for it. You are, after a process that does have a subjective component, converted from a public charity to a private foundation. The downside is that you have to re-file all your taxes as a private foundation going back all five years. There are some upsides. Private foundations do not have to follow some of the rules that public charities are required to comply with.
As soon as we figured out we were well on our way to being converted into a private foundation, which was mid-May 2021, we told ARDC. This was “news to them”. After talking it over with ARDC staff, we then hired a non-profit law specialist for advice (at ORI expense), wrote everything down, and came up with a plan. ARDC could either fund ARDC service programs that ORI would execute, and it would not “count against us”, or ORI could simply plan on becoming a Private Operating Foundation associated with ARDC. These options were proposed to ARDC staff. There was email back and forth and several zoom calls. The answer was eventually “no” on ARDC running Service Programs, but “yes” on ORI becoming a Private Operating Foundation associated with ARDC.
Problem solved! We had a party to celebrate. The feelings of IRS doom are kind of a big deal for a relatively new non-profit. We viewed this as being “hired”, in a way, by ARDC.
This solution held until October 2021. It was no longer clear that ARDC wanted this type of relationship. Both the “run Service Programs that ORI executes” approach and the “Private Operating Foundation associated with ARDC” approaches require a lot of communication and work. ARDC was not set up for either of these solutions. ARDC operates very differently from ORI. It does not have the same management structure or style, and it does not communicate like we do. Despite our best efforts, we couldn’t “impedance match” to make up for these differences. It’s unreasonable to expect them to change.
So, in November of 2021, the board of ORI and other senior advisers with non-profit and foundation experience recommended reversing the “conversion plan”. This means raising enough money to bring the ratio back up above the public support test limit to stay a 501(c)(3). The fundraising goal, as of today, is $150,000. This money has to come from diverse and much smaller sources. This must be raised over the next two years. It will be substantially more administrative and executive work to remain independent, but it’s how we were founded and how we have operated all along. The path forward is clear enough. The series of decisions during this process took a large amount of time and energy from May until November, but it was well worth the effort. Decisions about what type of non-profit organization ORI is or becomes have enormous impact on what we do and how well we are able to do it.
$150,000 (or more) is a large amount of money to raise in small amounts, especially within the amateur radio community. Have some advice? Want to get involved raising the money? Have another solution? Welcome aboard.
The fact that we exist and are successful in amateur radio communications R&D is very unusual. This means that we are vulnerable and it means we have more work to do, every year, to remain operational. Your support is vital for success.
Thank you to everyone that is pulling for us to succeed! We are looking forward to 2022 and welcome your ideas, time, talent, treasure, and advice.
-Michelle W5NYV
CEO ORI
ORI participation at OSCW 2021
Recording, transcript, and slides of Open Research Institute’s presentation at Open Source Cubesat Workshop 2021.
Hello everybody! I’m Michelle Thompson W5NYV and I’m here to tell you all about what Open Research Institute is and what we have been doing.
Open Research Institute (ORI) is a non-profit research and development organization which provides all of its work to the general public under the principles of Open Source and Open Access to Research. As we all know, these mean particular things, and those things have to be defined and they have to be defended.
Open Source is type of intellectual property management where everything you need to recreate or modify a design is freely available. As a baseline, we use GPL v3.0 for software and the CERN Open Hardware License version 2.0 for hardware. All we do is open source work, primarily for amateur radio space and terrestrial, but also some other fields, as you will see.
So who are we?
Here is our current board, and our immediate past CEO Bruce Perens. We have one opening on the board, as Ben Hilburn, one of our founders, very recently retired from being an active Director at ORI. He remains as one of our senior advisors. We are looking for someone to join ORI board that supports what we do and wants to help make it happen. It’s an active role in a flat management structure. Board members are are experienced in management, engineering, operations, and technology, and three out of the current number of four are from underrepresented groups in STEM.
As a board, it is our mission to serve our participants, developers, and community members. We now have at least 535 that participate in what we call the Open Source Triad: our mailing list, Slack, and GitHub. All work is organized in independent projects or initiatives.
We have some affiliations and we proudly ascribe to the Open Space Manifesto from Libre Space Foundation. We work with radio organizations, several universities, and have worked with a variety of for-profits.
What do we do?
Here’s a visual summary of top level projects and initiatives. The vertical axis is risk. Higher risk projects are at the top, lower risk projects are at the bottom. Maturity increases left to right. Maturity may indicate schedule, but the score is also influenced by complexity or difficulty. The color of the shape indicates how much stress that project is under or what the risk level is at this time. The size of the shape is the budget estimate. By far, the largest budget, riskiest, and least mature work is in the AquaPhage project, which is open source bacteriophage research and development. Bacteriophage are viruses that attack and destroy bacteria. This is biomedical and not amateur radio. This project was halted by COVID and has not yet resumed.
Our digital multiplexing payload project is called P4DX, and it’s in the middle in green. This is a multiple access microwave digital regenerating repeater for space and terrestrial deployment.
Channels divided in frequency are the uplink. The uplink is on 5 GHz. The processor on the payload digitizes and multiplexes these signals and uses DVB-S2/X as a single time-division downlink. The downlink is on 10 GHz. The system adapts to channel conditions and handles things like quality of service decisions. For example, low and high latency digital content. The uplink is divided up using a polyphase channelizer, based on the open source work done by Theseus Cores.
For the current prototype, we are only using MPEG transport stream, but generic data is the goal. The prototype beacon signal is 5 MHz wide and we are using one modulation and one error coding (yet). We are not yet rotating through all the allowed combinations in DVB-S2 (yet).
Our prototype work can also serve as a terrestrial multimedia beacon. Work was demonstrated to groups with mountaintop spaces in October 2021, and deployment will be as soon as possible.
M17 project is an open source VHF/UHF radio protocol. Think open source digital mode HTs and repeaters. This project is only slightly more stressed than P4DX, but it’s further along in maturity because it’s narrower in scope. We believe M17 Project will be very successful from current development to scaling up to commercial product launch. The M17 protocol is the native digital uplink protocol, with some modifications for 5GHz, for P4DX. We are working hard to get M17 on and through more satellites and more sounding rocket tests today.
Engineers General is our initiative to hire highly competent open source workers to reduce burnout and increase quality in open source work important to amateur radio. We have one contractor currently, eight resumes, and have applied for funding for two more. We are actively looking for funding for the remaining five.
The “birdbath” is a large dish antenna at the Huntsville Space and Rocket Center. This was used in the past, but has been parked for decades. It took two years of negotiation, but ORI has the support of the museum and permission to begin work renovating this dish for citizen science and amateur radio educational use. Work parties from earlier this year were rescheduled due to COVID.
Upper right there are two completed projects. One is ITAR/EAR Regulatory Work. It took over a year, but we received a determination from the State Department that open source satellite work is free of ITAR, from Commerce that it is free of EAR, and we obtained an advisory opinion that publishing on the internet counts as publishing under the regulations. This is a huge step forward for not just amateur radio, but anyone that wants to contribute to open source space work.
Debris Mitigation Regulatory Work took 10 months to complete. The process culminated in a highly successful meeting with the FCC Wireless Telecommunications Board, the Office of Engineering Technology, and the Satellite Bureau in late October 2021.
Lower right is Battery Matching, a project that matches NiCd cells for very durable batteries in the style that used to be done in amateur satellites, and puts the methods and documentation in the public domain.
AmbaSat Inspired Sensors used to be on the bottom right but now it’s bumped back a bit in maturity level is higher risk. This was supposed to be a project done by students at Vanderbilt university, but no students materialized, primarily due to COVID. We had one kick-butt professional volunteer who was working on a 10GHz beacon that went into the sensor connector on the main board, but the project was moving slowly, and ORI decided to provide additional operational support. Additional volunteers joined the team, we reviewed the finances, and then took some actions. We updated the main board to move it from the illegal ISM band it was in to the legal 70cm ham band. We improved power and ground and addressed some other design concerns. The boards are back as of last week and software and firmware development is underway. The 10 GHz sensor “beacon” work is proceeding quickly as well. AmbaSat is an excellent educational platform, but the ISM band decision isn’t the only problem with it. It’s very small.
We decided to look at combining the 70cm AmbaSat with another open source satellite board to make a combined spacecraft design. I reached out to Pierros Pappadeus at Libre Space, and we are moving forward with using the SatNOGS Comms project. We look forward to contributing to the FPGA codebase and flying both AmbaSat and SatNOGS Comms designs as early and as often as possible, starting with sounding rockets and ending up in space.
All of these projects are open source and all work is published as it is created.
When?
We have timelines! We were incorporated in February of 2018, got our 501c3 in March of 2019, and we hit the ground running and haven’t stopped since.
We’ll distribute a copy of the slides so you can see our wins and losses along the along the way. There’s a lot going on in here.
Here’s what’s been going on since March, and the future plans we know about.
We use Agile framework for management, and most of us have some sort of formal certification either completed, or in process. This is the Agile manifesto and it is the foundation of how our board decides things and how it supports project leads and volunteers. Note the second item, and put in the word hardware instead of software, and that’s one of the reasons we demonstrate early and often and incorporate the feedback quickly.
Where are we?
Here’s the locations of the concentrations of current major contributors and participants. When we say international, we mean it. Our participants have a wide range of ages, are generally educated in engineering, come from a variety of backgrounds, but do tend to be relatively young and male.
We have some physical locations that are important for carrying out the work we do. Remote Labs are lab benches connected to the internet that allow direct access to advanced lab equipment and two different large Xilinx development boards and DVB-S2/X gear. We have relocated our second Remote Lab equipment from Florida to Arkansas, and have added a three-dish interferometry site for amateur radio and public science use. Remote Labs are here for you all to use. If you need large FPGA resources and test equipment up to 6 GHz, then we have your back.
We bought Open Lunar Foundation’s satellite lab. It’s in storage waiting for the M17 project lab construction to conclude, and then the equipment will go there to pack that lab full of wonderful test equipment, materials, and supplies.
Why do this?
We believe that an open source approach to things like amateur digital communications, bacteriophage research, and sticking up for the non-commercial use of space will result in the best possible outcomes for the good of humanity.
We have a lightweight agile approach to doing things. We keep our overhead very low, we are radically participant-focused, and the work must be internationally accessible.
You can see that public demonstrations and regulatory work are given a high priority. Working code and working hardware are highly valued. Working means working over the air.
Thank you to everyone at Libre Space for the support and opportunity to present here today.
https://www.openresearch.institute/wp-content/uploads/2021/12/OSCW-2021-W5NYV-ORI-1.pdf
FPGA Meeting 23 November 2021
Space and Satellite Symposium 2021 Transcript and Video Links
Welcome to the IEEE Space and Satellite Symposium: Information Theory, Amateur Radio, and Amateur Satellites.
This event is co-sponsored by the IEEE San Diego Computer Society Chapter, lead by Naveed Qazi. Please welcome him to the stage as explains what the Computer Society is all about. Naveed you have the floor.
(Naveed shared a live update with the audience about the Computer Society meetings, events, and areas of concentration.)
This event is also co-sponsored by the IEEE San Diego Information Theory Society, lead by Dr. Orlitsky and Michelle Thompson, W5NYV.
Logistics sponsor is Open Research Institute. A special thank you to Vidya Gopalakrishna, Jayala_29, Jim Tittsler, Navid Qazi, Charlie Bird, the IEEE review committee, IEEE-USA, and all our speakers.
All talks have already been published on YouTube, so if there’s something in particular you want to see and you have limited time, then please feel free to go straight to the playlist. Our goal for this event is high-tech and low-stress.
If you have questions for the speakers, please put them in chat. If the speaker is present, then they will answer there. All questions will be anonymized and sent to the speakers. A Q&A will be added to the YouTube playlist.
Information Theory is an intensely interdisciplinary field. This collection of talks demonstrates that to great effect.
The talks span a variety of subjects and are from people with a range of experience and backgrounds.
All talks will be available for free going forward and we look forward to working with IEEE on future events and workshops.
In November, Open Research Institute will have a series about mission planning for non-traditional amateur satellite orbits and we will be at HamCation in Florida in February of 2022. If you are there, please visit our booth. We’ll have a forum with TAPR and will be hosting a contest for the hamlets attendees.
We will begin with our keynote, Ugly Modern Music: An Information Theoretic View by Frank Brickle. Talks will play live from here with a brief intermission at 10am US Pacific.
It has been a great honor to work with Frank Brickle. It’s often said that music and mathematics are closely related, but relatively little published accessible and practical work. We hope this presentation is a step forward towards a goal of Information Theory Applications in Music.
Our next talk is about amateur radio as a testbed for science and high technology. Courtney Duncan has a unique viewpoint here, as he recently retired from the Jet Propulsion Laboratory and was a lead on the Mars Helicopter.
Thank you to Courtney for continuing service to both the scientific and amateur communities and for describing an interpretation of the amateur radio service, for both space and terrestrial, that provides both a practical and a theoretical role.
I think we can see how amateur radio values and practice assisted in the success of the Mars Helicopter.
Please share your questions for Courtney in the chat. He is here and can answer. If you want to send in your questions later, then send them in to the address in the Symposium email, or at w5nyv@arrl.net.
Next, is Anshul Makkar, who will speak about specific very technical work for the amateur radio satellite service. He is working on Low Density Parity Check implementation on Field Programmable Gate Arrays for any amateur satellite project that sees the value in open source work.
Thank you to Anshul Makkar. If you have questions for him please share them in chat, as he is here and can answer them live, or send them to the contact addresses in the Symposium registration email, and we will follow up.
Bringing multiple implementations of LDPC to the open source community is one of the things that Open Research institute does, and it is something that you can find an enormous number of IEEE resources about.
Next is Dr. Estevez who will be speaking about his work on a narrowband modem for the QO-100 GEO amateur radio transponder. For those of you unfamiliar with this satellite, it’s the first geosynchronous amateur radio payload. This is a remarkable achievement and a huge step forward for amateur communications. This physical platform for experimentation will give us opportunities for innovation for years to come. Dr. Estevez work is a big part of that movement. Please welcome him to the stage.
A special note, on October 24th, Dr. Estevez was awarded the G3AAJ Trophy, from AMSAT-UK, in recognition of his contributions to amateur satellite development and activity. In addition to the practical applications seen in this presentation, Dr. Estevez is also the author of GNU Radio satellites block set, which are blocks in gnu radio that allow one to much more easily receive satellite communications using GNU Radio. If you are unfamiliar with GNU Radio, a DSP framework for SDR, then please visit gnu radio dot org to learn more.
Next is a talk about a very practical and scrappy project – figuring out how to characterize channels and make circuits for a very small open source satellite platform called AmbaSat. Part of the mission of IEEE and Open Research Institute is education and professional development. If you see a way to contribute to the success of renovating and improving the AmbaSat platform, please get in touch with Vidya Gopalakrishna and Dr. Alan Johnston, the Primary investigator and advisor for this particular project, which is funded by ARDC.
Please welcome Vidya to the stage.
Thank you to Vidya Gopalakrishna. Please ask your questions for her in the chat, as she is here and can answer them live.
Part of our event was a call for musical compositions related to Space and Satellites. We are proud to premiere some original music today. The first of the two short pieces that we will play today is Space Orchestra, which is categorized as Jazz. A full information theory analysis of this piece will be done for the next San Diego Information Theory Society meeting, later this year.
The theme of this piece, is what the composer felt and decide to write, when focusing on the planets of our solar system, and our place within it. This is Space Orchestra, put into the public domain and available at no cost from Open Research Institute.
Space Orchestra
Our second music premiere is called Risk, and is in the electronic dance music category. The lyrics are from John F. Kennedy’s speech at Rice University, but are from a part of the speech that is not quoted as often as the section that includes “we choose to go to the moon, not because it is easy, but because it it hard.” Instead, we highlight the part of the speech that puts space exploration in the context of human history, and recognizes the great risk of exploration into hostile conditions for the benefit of all.
This is Risk, available from Open Research Institute for free.
Risk
Jan King
Our closing talk is from Jan King, a space industry professional and frequent contributor to amateur satellite work. He is speaking today about the very bright future for millimeter wave amateur satellites. Please welcome to the stage Jan King.
Thank you to Jan King.
This event would not be possible without a significant amount of work from our speakers, sponsors, supporters, and volunteers. Thank you all for your time and expertise.
Do you have an idea or talk that you would like to share? All of us at the chapter level in IEEE, like Naveed Qazi, Dr. Orlitzky, myself, and many others, are here to make it as easy as possible for your work to be shared. Get in touch and we’ll get you started and supported.
This transcript with the links to videos will be posted to the YouTube playlist description, and will be sent out to everyone that registered in advance, to make it easy for anyone to replay any part of this event. For this set of presentations, 104 people pre-registered and there’s a large number of views on the content in the playlist as of the close of the conference.
While the half-day conference program has concluded, the floor is open for discussion, questions, comments, and ideas for related or future work.
ITAR/EAR Regulatory Work Background and Summary
September 12, 2021
Michelle Thompson W5NYV
Export regulations divide both technical information and actual hardware into three categories. The most heavily restricted technologies fall under ITAR, the International Traffic in Arms Regulations, which are administered by the State Department. Technologies subject to more routine restrictions fall under EAR, the Export Administration Regulations, administered by the Department of Commerce. Technologies that are not subject to either set of regulations are not restricted for export.
ITAR and EAR have had a dramatic effect on both commercial and amateur satellite work since at least the mid-1990s. The regulations are blamed for a significant decline in US market share for satellite systems and halted highly successful international amateur collaborations.
There is a public-domain exception in both ITAR and EAR. Open source work that is published as it is created, and is freely available to the general public at no cost, is not subject to ITAR or EAR.
Open Research Institute (ORI) was founded in March 2018 by Bruce Perens in order to provide a formal structure for open source satellite work. Bruce invited Ben Hilburn and myself to be the founding officers. ORI is headquartered in California, USA. Participants come from all over the world.
ORI memberships would not be sold in order to not compete with amateur satellite membership organizations in any way. All work would be freely available to the general public in compliance with ITAR and EAR. ORI was set up as a project-based research institute and not as a member society.
ORI became a 501(c)(3) in March 2019 and began fundraising with the Trans-Ionospheric conference badge project. This was successful and allowed for open source satellite technical and regulatory work to proceed. While all the legal advice so far had affirmed ORI’s interpretation of ITAR and EAR public domain carve-outs, some potential funding sources wanted to see a “formal†legal opinion.
Our choices were to continue insisting we were right, or to be effective. ORI chose to be effective.
In July 2019 Bruce Perens interviewed several several law firms that were aligned with ORI goals and values. We selected one recommended by the Electronic Frontier Foundation (EFF) and began working with Thomsen & Burke LLP to form a legal strategy that would clearly and explicitly solve the “ITAR/EAR problem†for amateur satellite.
From May – September 2019, I campaigned in a contested election to the AMSAT-NA Board of Directors and won a seat. AMSAT stands for AMateur SATellite, and is composed of a number of organizations around the world that support the amateur satellite service. AMSAT-NA is the North American amateur satellite advocacy organization. The name of the North American organization is frequently shortened to AMSAT.
In November 2019, December 2019, and January 2020, ORI reached out in writing to AMSAT-DL, JAMSAT (AMSAT Japan), AMSAT-UK, AMSAT-NA, EFF, the Institute for Electrical and Electronic Engineers (IEEE), American Radio Relay League (ARRL), Open Source Initiative (OSI), and multiple Universities and individuals active in open source and amateur radio. The communication outlined the legal strategy, invited collaboration, and asked for statements of support.
The legal strategy consisted of three parts. First, a Commodity Jurisdiction Request to the US State Department asking for a Final Determination Letter that said that open source satellite work was free of ITAR. Second, a classification request to the US Commerce Department that would use the Final Determination to synchronize classification under EAR. Third, an Advisory Opinion Request to US Commerce clarifying the result from the US Commerce Department. This final step would provide needed guidance on publishing requirements and make it abundantly clear that open source satellite work was indeed free. Being free to work with others in the open is vastly superior to complying with onerous and punitive regulations designed to insure “national security”.
All organizations responded to or at least acknowledged the letter, except AMSAT.
On 20 February 2020, Open Research Institute filed a Commodity Jurisdiction Request with the US State Department, seeking to establish that key technologies for amateur radio are not subject to State Department jurisdiction. “Information and Software for a Digital Microwave Broadband Communications System for Space and Terrestrial Amateur Radio Use†was assigned the case number CJ0003120.
As encryption is allowed under Part 97 amateur satellite rules, the use of encryption was deliberately included in the request. The inclusion of encryption mandated that the Bureau of Industry and Security would have to review the request, which lengthened the schedule. The Department of Defense and the Department of Homeland Security also reviewed the work, as both departments have significant interest in regulating communications satellites and communications technology.
On 11 August 2020, The United States Department of State ruled favorably on Open Research Institute’s commodity jurisdiction request, finding that specified “Information and Software for a Digital Microwave Broadband Communications System for Space and Terrestrial Amateur Radio Use†was definitely not subject to State Department jurisdiction under ITAR.
The technology was not subject to State Department jurisdiction. This was the best possible outcome of a CJ request. The news was publicly announced.
The Final Determination letter, Commodity Jurisdiction cover letter, and the application itself can be found at:
https://github.com/phase4ground/documents/tree/master/Regulatory
A list of Commodity Jurisdiction request summaries can be found at the State Department website at:
https://www.pmddtc.state.gov/?id=ddtc_kb_article_page&sys_id=6ea6afdcdbc36300529d368d7c96194b
Under this Final Determination, the technologies were subject to the EAR. The next step was to submit a classification request to the Commerce Department. Work began on the request with Thomsen & Burke LLP.
In October 2020, the classification request was submitted to the US Commerce Department.
During the board meeting at the 2020 Symposium (October), I moved for AMSAT to adopt the regulatory results from ORI as AMSAT’s open source policy, using ORI’s participant and developer policies and open source approach as a template that would be customized for AMSAT. The motion also included a companion policy for closed-source/proprietary work, as there was no written policy for ITAR/EAR of either type. We would coordinate with both FD Associates and Thomsen & Burke LLP to write this two-pronged policy. This would completely cover AMSAT for any type of project.
The rest of the board wanted to instead establish an “Open Source Committee†that would produce a report in 90 days.
The 90 days expired without a report. The committee was renewed for another 90 days. That 90 days also expired without a report. I volunteered to participate on this committee, but was not included.
In January 2021, a classification of all the items, as requested, was received from the US Commerce Department.
Work began with Thomsen & Burke to draft an Advisory Opinion Request asking that openly published work ceases to be subject to the EAR. This established a full chain of documentation for open source amateur radio satellite service work.
On 23 February 2021, the Advisory Opinion Request was sent to the US Commerce Department.
On 2 September 2021, the US Commerce Department confirmed Thomsen & Burke LLP’s advice that posting information on the internet so that it is available to the public means it is not subject to the EAR.
Classification and Advisory Request documents can be found at: https://github.com/phase4ground/documents/tree/master/Regulatory
Many organizations have picked up the regulatory results, expressed appreciation, asked questions, and have indicated they are incorporating the results into their own work and policy documents.
The legal costs were fully reimbursed with a generous grant from Amateur Radio Digital Communications (ARDC). See https://www.ampr.org/grants/grant-open-research-institute/
ARDC and ORI share a vision of clearly establishing open source as the best and safest way to accomplish technical volunteer work in amateur radio. The regulatory work provides solid support for that vision. The path is clear for a number of interesting projects facilitating new methods for terrestrial and satellite communications, opening the door to robust global digital amateur communications.
Current work with Thomsen & Burke LLP is to write documents that explain how these results can be best used by others. This has significant relevance in industry and academia. Our goal is to make it as easy as possible to use the results.
The FAQ, optional notice, and training can be found (as soon as they are completed) at https://github.com/phase4ground/documents/tree/master/Regulatory
Will there be additional filings? The goal of any additional filings is to build a body of work that solidly support a wide variety of open source work. This is somewhat similar to the way patent portfolios work in commercial settings. It’s the sort of thing AMSAT could, and honestly should, be helping with.
This effort gives direct and large benefits to a large number of organizations, but it benefits AMSAT in particular. It allows free and open international collaboration, dramatically reduces legal risks, increases the potential volunteer corps, simplifies fundraising, and reduces management burdens.
The work applies to orbits besides GEO and technology besides DVB-S2/X. Those that “insist” on extremely narrow final determinations can write their own Commodity Jurisdictions requests and expect to get the same result because they can use this one in their request as a model and reference. As said before, additional filings would be of great benefit to the community because a population of results strengthens the case for open source work. However, additional filings are not necessary to use the results.
The key to using these regulatory results, or any like it, is that the public domain carve outs in ITAR and EAR are solid and provide a bright path out of a bad place. In order to use them, one has to commit to documented open source policies and follow the law with regard to what constitutes publishing. According to the Advisory Opinion Letter, if it is published, it must be free.
Publishing work as it is created, freely available to the general public, is the way to use the public domain carve-outs in the law. Publishing designs and data that allow the recreation of a work of software or hardware means publishing schematics, Gerber files, bills of materials, source code, tools required, test data, test plans, and the license that that work uses.
This last part is often overlooked but is a necessary part of a compliant open source policy. ORI recommends the CERN open hardware license or the TAPR open hardware license for hardware. ORI recommends GPL version 3.0 for software. Any license recognized by Open Source Initiative is an excellent starting point. Providing regular copies of work to a public library, whether in print or on DVD, is a baseline approach for a publishing policy. Using GitHub or GitLab is another recommended baseline policy.
ORI recommends the CERN Open Hardware License v2 because of the way it enables a useful open source hardware definition in a world dominated by a wide variety of proprietary tools. For example, FPGA design is a large and growing part of our world in advanced open source digital communications, and is the central service provided by ORI’s Remote Labs. Find more information about Remote Labs here: https://github.com/phase4ground/documents/tree/master/Remote_Labs
Since open source tools for FPGA are currently not capable of executing some of the required designs, as long as the tool or component meets the definition of “available componentâ€, then the use of things like proprietary tools are allowed in the production of an open source design.
Following the example of FPGA work, this means that the VHDL source code is available for free to the general public. The FPGA is listed in the bill of materials and can be purchased. The version of Xilinx Vivado is listed, and can be obtained.
ORI’s developer and participant policies can be found here:
https://openresearch.institute/developer-and-participant-policies/
This regulatory work is a significant and positive result for the commercial and industrial world as well as in amateur and academic circles. Goals for the amateur radio satellite service should be the absolute minimum regulatory fear and risk for amateur volunteers, and a maximum amount of free and open international technical cooperation.
Thank you! Contact ORI with questions about the legal work at ori at openresearch dot institute
Wojciech Kaczmarski SP5WWP wins 2021 ARRL Technical Innovation Award
The ARRL Board of Directors, with the recommendation of the Programs and Services Committee, has awarded the 2021 ARRL Technical Innovation Awards to Steve Haynal, KF7O, Wojciech Kaczmarski, SP5WWP (from the M17 Project), and Roger Clark, VK3KYY.
Congratulations SP5WWP!
ORI is the fiscal sponsor for M17 Project. Funding provided by ARDC.
Successful Regulatory Results for Open Source Amateur Satellite Work
On 2 September, 2021, Open Research Institute (ORI) received an advisory opinion from US Commerce Department BIS.
The letter confirmed that posting information on the internet so that it is available to the public means that open source amateur satellite communications work is not subject to the Export Administration Regulation (EAR). Prior work established that open source amateur satellite communications work was free of International Traffic in Arms Regulations (ITAR).
This is a significant regulatory success for open source amateur satellite work and open source in general.
Work was funded by ARDC and executed by Open Research Institute. Legal assistance was provided by Thomsen and Burke LLP.
All documents and links to presentations about the work are freely available at https://github.com/phase4ground/documents/tree/master/Regulatory
Thank you to those who have supported and assisted ORI during the many stages of this successful regulatory endeavor. Making a successful argument requires competence, persistence, and patience. ORI will build upon this work moving forward in order to advance the aims and purposes of open source amateur radio work.
Visit https://www.openresearch.institute/getting-started/ to get involved.
Executive Board Meeting Minutes August 2021
Attending:
Steve Conklin (CFO), Rose Easton (guest), Keith Wheeler (Director), James Wheeler (Acting Secretary), Michael Easton (guest), Paul Williamson (Master at Arms), Michelle Thompson (CEO)
Location:
Koi Restaurant, Planet Hollywood, Las Vegas, Nevada, USA (DEFCON)
Minutes:
-Opening Remarks
–Motion passed to maintain current group of Directors (Bill and Karen in absentia)
-Previous minutes edits approved
-Open Lunar Business lab equipment obtained due to running under budget on equipment
-ARDC and ORI remote lab talks continue
-Plans on movement of Remote Lab East to Remote Lab South
–Motion Passed Remote Lab South to be established on the property of Keith Wheeler, in Little Rock, AR
–Shipping costs of equipment will likely push over grant budget
—Some amount of leeway needed to adjust budgeting to cover shipping
Recess
-ERR request being considered up to $10k
-Discuss to go beyond the budget originally allocated to make up for the sudden need to shut down Remote Lab East
-Additional discussion made to take from the M17 account to make up for additional cost
-Discussion conducted on determining how far over budget lab project can go before additional meetings must be conducted
-Pertinent Budget Information:
–Currently, under budget by $2k
–Lab equipment in bay area costs $500 a month
-Motion Passed: Proposal to allow for a $20k overage on the lab budget, to account for movement of equipment to Remote Lab South, and M17, used at the discretion of M approved. In the event that additional cost beyond this limit is reached, another meeting will be held
-Progress with discussions with M17 and FCC discussed
–Future discussion with International Satellite Bureau and OET planned after meeting with the FCC
-Plans to discuss successes with the FCC and defeating ITAR at upcoming HAM Expo
-Regulatory meddling in Texas successful
–space industry people happy with meddling due to discussing debris mitigation and FCC jurisdiction
-AMSAT maintains that debris mitigation rules should not be enforced on HAM radio, believe it will destroy space based HAM radio
–AMSAT invited to meetings and to be part of the planning committee but declined
-FCC seems to be leaning more towards ORI beliefs on debris mitigation
-Possibility of LEO being one of few exceptions to debris mitigation rules
-End goal of FCC discussion is to allow for ambitious missions, including graveyard orbits
–Possibility of third graveyard orbit
-The meetings will continue until morale improves
-Note of moving of satellite antennas to Remote Lab South, due to increased space
-Discussion of grant being written by Keith to get a salary for engineers on a contract basis from ARDC, and for payment for Lab Director to maintain lab equipment on Remote Lab South, no motion to be made at time, but grant will be applied for
-Closing Remarks
-Motion to adjourn
Space and Satellite Symposium: Information Theory, Amateur Radio, and Amateur Satellite
30 October 2021, 8am – 12pm US Pacific
Spirit Wear Store Promotion
Thanks to a generous donor you get a Free Book with your order of Open Research Institute Spirit Wear. Proceeds benefit ORI, an open source 501(c)(3).
Visit https://stores.goldmedalideas.com/ori/shop/home and spend $30 US or more. While supplies last.
Demonstration: FreeRTOS Task Upload
This is a Scheduler for Dynamic Patching of FreeRTOS Tasks. It’s based on FreeRTOS and it helps the user to dynamically update and patch the task without the need for system reboot.
Weekly Engineering Report 10 August 2021
Greetings all!
1) OpenRotor will have a Ham Expo workshop from 12:00pm – 2:00pm in the Chat. Direct link is: https://ori.whereby.com/open-research-institute
Get there by clicking “Chat” in the booth at Ham Expo.
2) Planning spreadsheet for ORI at Ham Expo has been started and the editable version is linked in the Slack.
Please add yourself if you have something to present on any open source amateur radio or amateur radio satellite service subject. Coordinate through Slack. We have excellent resources and support from Ham Expo this year. The goal is to provide a low-stress enjoyable venue to speak with attendees about the things we do and the things we want to see succeed.
I need videos of demos or time commitments for live demos. Don’t be shy – your work is of great interest at the Expo.
3) If you are not on our Slack, or haven’t visited lately, please do – this is where daily engineering and planning happens.
https://phase4ground.slack.com/
If you need an invite, please send me a request directly.
4) FPGA Standup meeting was today and the team will have a lot to show off at Ham Expo and for Google Skywater in October. Most recent recording of the weekly standup is:
5) DEFCON was a big success. We had our first in-person board meeting in nearly two years. A lot of networking and discussion and learning happened. There are several projects that we might want to consider supporting or assisting. More about those projects in the #defcon channel in Slack.
6) ORI Store (https://stores.goldmedalideas.com/ori/shop/home) will have a promotion. We have a supply of the 2019 printed paper versions of the AMSAT Getting Started With Amateur Satellites Guide and will include one in every order over $30 starting at Ham Expo and lasting until supplies are gone.
7) Open Lunar Foundation lab purchase is complete and the lease for storage of that equipment is being transferred from Open Lunar to ORI this week. The lab equipment will move to primarily M17 Lab on the East Coast and some will go to Remote Lab South in Arkansas this autumn. If you can help reduce shipping costs then get in touch.
8) FCC has agreed to meet with us and will arrange for both OET and the International Satellite Bureau to attend. The agenda is how open source can successfully address Debris Mitigation regulatory requirements for the amateur radio satellite service, and specific microwave band spectrum defense for the amateur radio satellite service. A summary of the content for this meeting will be presented at Ham Expo. There will be a breakout session and Q&A.
9) Work session at Huntsville Space and Rocket Center for the Birdbath Big Dish renovation has been postponed due to covid. Originally scheduled for immediately following Huntsville Hamfest, the work session will happen when it’s safe to invite volunteers to work together on site. This project renovates a 20 foot dish for open source amateur and citizen space science use.
-Michelle W5NYV
Weekly Engineering Meeting of FPGA Team
OpenRTX Firmware Measured in Remote Lab West
Wally Ritchie WU1Y – SK
It’s never easy to share bad news about a significant loss.
Wally Ritchie WU1Y passed away in Florida on 1 July 2021 from heart failure.
We have lost a big part of our team. I, and I know many of you, join his friends and family in mourning his passing.
While he defeated cancer with the same energy and style that he overcame so many other daunting challenges in his life, he was unable to recover from a series of setbacks that began in late May and worsened in late June.
Wally was our Primary Investigator for the Phase 4 transponder project, is a primary contributor to the documentation, design, fundraising, and grant process for the transponder, and was responsible for the specification and vision of Remote Labs. He defended, mentored, and supported the team and Open Research Institute work on numerous occasions. He was a true subject matter expert in space and terrestrial digital communications, was an experienced manager, and a talented entrepreneur. He lived and traveled internationally, was well read, and never failed to provide real backbone exactly when and where it was needed.
Professionally, Wally was a Principal Engineer. He had extensive experience in systems engineering and firmware development. He was an expert in Field-Programmable Gate Arrays (FPGA). He held several high-level manufacturing and management positions during his career, and knew digital signal processing in depth. He was devoted to education and improving student accessibility to high technology.
I met Wally through Jonathan Brandenburg at the 2016 TAPR DCC. We hit it off instantly. We had a lot in common. Wally had repeatedly attempted to volunteer through AMSAT and had not gotten a positive response. He was thrilled to find out that people were working on the problems that he thought were important for amateur satellites, and he dug in and selflessly volunteered from that day forward. Our collaboration extended to open source medical devices, regulatory work, a variety of grant applications, and some attempts at some really fun proprietary ventures. I met his wife Debbie and his son Keegan.
He did presentations, volunteered at the HamCation booth, and organized several workshops. He lead design reviews and wrote papers whenever they were needed. He did whatever I asked and always let me know when I was doing a good job, or where I could improve.
I learned so much from him and will miss him very much.
While it’s not possible to “replace” someone like Wally, we will keep going with the same spirit. He had great confidence in our ability to achieve our goals. I’m not inclined to let him down.
-Michelle W5NYV
NiCd Battery Analysis: Historical and Modern
Greetings all!
I’d like to tell you all about a project going on to revive/document Larry Keyser’s engineering on matched NiCd cells that made up the batteries for UO-11 and other amateur payloads from that era. This would be up to four of the AO-teens payloads, and at least one other smallsat. The batteries were very reliable, exceeding amateur and professional expectations.
Selecting cells for a battery takes testing and an understanding of the basics of the underlying chemistry and physics. Early amateur payloads got a great deal here with some surplus cells from avionics and/or medical surplus. These cells were high quality to begin with, but that’s not enough by itself to ensure a lengthy lifespan in space.
Larry Keyser knew how to match the cells to make batteries that would last a long time. The overall strategy was to select batteries that were similar. Not necessarily the best performers in the batch, but the best matched cells.
Temperature performance and curve matching were both considered critical. Furthermore, the batteries were scanned to eliminate those with internal structural anomalies and faults.
Several of us at ORI are preserving, publishing, and extending this work. We have some advantages, in that modern battery analysis equipment is much easier to use and more capable than what previous volunteers had to work with. ORI has a modern battery analyzer, capable of working up to 44 volts, available for community use.
Modern test equipment produces much higher resolution charge/discharge curves, and temperature monitoring is incorporated automatically. Measurements can be automated in ways that Larry didn’t really have available at the time he was working on this for AMSAT and other missions.
We have software tools and languages (Python, MATLAB) that make curve matching easier. There’s never been a better time to save and publish a summary article about Larry’s achievements and what we, as modern hams, can do to improve upon it.
This is all open source work through Open Research Institute. It’s offered for free to anyone or any organization that wants to use it. NiCd batteries aren’t as hip or cool as Lithium Ion, but they are reliable in space, and this ongoing battery project will produce both data and actual physical battery packs that amateur/educational missions may want to consider using.
The battery analysis equipment is capable of doing any battery chemistry, so if you have an open source amateur satellite project in mind that needs battery analysis support, ORI is here to help out with that.
Want to get involved?
Ground-based DVB-S2 Repeater for GEO Satellites by Wally Ritchie.
In case you missed it when it was published by AMSAT-UK, you can download the paper here.
Radio-Free RFC Podcast – All Episodes
Please visit https://www.openresearch.institute/radio-free-rfc-podcast/ for the episodes of the Radio-Free RFC Podcast.
The revival of this collection came about due to some Twitter banter on 1 April 2021.
This podcast was originally published beginning in January 2005. It’s a light-hearted and humorous view of Internet “Request for Comments” or RFCs.
Dual-Band Feeds Update
My background is baseband and algorithm development, but the RF side is where the signals meet and exceed the sky. I have only the deepest respect for those that are talented here and give generously of their time for amateur satellite project success. We owe so much to Kent Britain, Paul Wade, and many others.
There are two designs for Phase 4 dual band feeds in the repository linked here. They are dual-band feeds, best used in dishes.
https://github.com/phase4ground/documents/tree/master/Engineering/Antennas_and_Feeds
The first one I want to introduce you to is the 5 GHz up, 10 GHz down. This feed was designed by Paul Wade W1GHZ, has lab results, has been manufactured in amateur machine shops, and has been 3d printed/metallized. This feed was demonstrated at amateur and IEEE conferences.
The second is 10 GHz up, 24 GHz down. Paul fabricated a number of feeds for us to distribute. The design is by Gary K6MG and Lars AD6IW. Their paper can be found at https://dokumen.tips/documents/dual-band-1024-ghz-feedhorns-for-shallow-ad6fp-aa6iw-dualfinalpdfdual-band-1024.html?page=1.
Preliminary lab results are in progress and published in the repository. More to come! ORI bought 15 of them and is interested in putting them into the hands of amateurs that will use them and report back. Three have been sent out so far, and we are looking to send out more.
While the baseline Phase 4 design is “five and dime”, the goal of ORI is to use any and all microwave bands that we can. I think we are all aware of how much pressure our microwave bands are under from commercial interests.
The system design is extensible to 10/24, so we needed a feed for this.
If you want to contribute or participate, then please visit
https://www.openresearch.institute/getting-started/
Thank you to all that have helped make this possible!
-Michelle W5NYV
26 March 2021 Engineering Report
Here is a visual walkthrough of the features on the TEBF0808 UltraITX+ Baseboard for Trenz Electronic TE080X UltraSOM+, presented by Paul KB5MU and Michelle W5NYV.
These stations are available to the community from Open Research Institute’s Remote Labs. We currently have two sets of gear and are procuring two more.
The Trenz platform allows for full access to the FPGA, power reduction work, and thermal modeling. All are extremely important for space applications.
We also have the Xilinx development board for the Ultrascale, for preliminary work.
The FPGA module goes in the lower left empty square with the high-density connectors.
The FPGA module has a heat sink, called a heatspreader, that is a machined metal plate. It attaches to the FPGA module with screws. However, it needs an intermediate layer to conduct the heat from the FPGA to the metal plate. The plate is designed to fit many different modules, and there’s a gap between the metal plate and the top of the components on the FPGA module.
This gap is usually filled with a specific gap-filling thermal paste.
Which happens to be out of stock, all over the world.
So, of the four stations we’re settting up, one will be fitted with a thermal adhesive film. This comes in sheets and can be cut to size. It can be used for space, so as we dial down the power consumption with code adjustments, we can measure the thermal results with something that is appropriate for the space mission.
The other three will get gap-filling goo directly from Trenz. This is the only way to preserve the warranty on these expensive modules, so it’s not a bad choice. And, this gives us something to compare the sheet against. We’ll test both in thermal modeling and chamber.
-Michelle W5NYV
How To Leverage Amateur Radio In Space
Compiled by Michelle Thompson W5NYV, Patrick Stoddard WD9EWK, Douglas Quagliana KA2UPW, and Pierros Papadeas SV1QVE Director of Operations at Libre Space. Please contact any of us with questions, comments, additions, and corrections.
w5nyv@arrl.net
wd9ewk@amsat.org
dquagliana@gmail.com
pierros@libre.space
Version: March 22, 2021
Introduction
Who is this document for? You may belong to one or more of the following categories.
You want to deploy an amateur radio spacecraft.
You want to include amateur radio operators.
You want to use amateur radio frequencies.
You are interested in using SatNOGS.
Amateur radio is about the operators. The licensees in the amateur radio satellite service are individual people. They have a license not just to use communications resources in space, but they are also licensed to control spacecraft, with the permission of the spacecraft license holder.
The Amateur Radio Satellite Service is a non-commercial communications service available worldwide. It is dedicated to education, experimentation, and the amateur use of space.
The VHF international amateur satellite frequency allocation is 144.000 MHz – 146.000 MHz with 145.800 MHz – 146.000 MHz being recommended and preferred. The UHF international amateur satellite frequency allocation is 435.000 MHz – 438.000 MHz. There are other allocations on other bands, but these are the most heavily used at this time.
Providing a spacecraft that is useful to the amateur radio satellite service is not difficult, but there are aspects that may be non-intuitive coming from a commercial or academic background. There are expectations from the amateur radio community of spacecraft that operate on amateur radio bands.
The starting point is https://www.iaru.org/reference/satellites/
This site contains a wealth of information about Amateur Radio in Space. Carefully reviewing the entire site will put your project and your team in the best possible place to leverage the global amateur radio satellite service.
Once this set of documentation has been read, then community standards can be adopted.
Community Standards
The advice following about community standards is hard-won. If this advice is followed, the amateur radio aspects of your project have a much better chance of being successful.
1) Use forward error correction for digital downlinks. Use open protocols and open source.
2) Test over the air, as soon as possible, in the lab, on the ground, well before launch.
3) Clearly describe how amateur radio operators will receive your signal. Operators of satellites in the amateur-satellite service must publish full details of their modulation, encoding and telemetry formats and equations before launch. Publish details long enough in advance so that amateur radio operators can implement and test receiver designs. Use Science-Technology-Engineering-Math (STEM) educational organizations to get the word out. Use your local AMSAT Societies and related groups to get the word out. Describe the air interface as early as possible, even if this is before any software is ready.
4) Make and publish a recording of your telemetry signal to allow amateurs to test demodulation and decoding of your signal.
5) What’s in this for amateur radio operators? What is the added value of the project for the ham radio community? Is there an amateur radio transponder available for general use? If not, then support from the amateur community may be very low.
6) Incorporate SatNOGS.
SatNOGS has a very useful guide for satellite builders that want to use amateur radio.
Thank You
If you are reading this, you know that forward error correction or changing frequencies can’t be done at the last minute. The amateur satellite community can be highly valuable active participants in your satellite mission, if they have the information they need about the project.
If the project provides useful communications services and engaging opportunities to amateur operators, then the benefits are plentiful and powerful. Announcing amateur radio plans early enough to get engagement and quality feedback, and publishing all the details, are the key concepts.
Do you know of a team that is starting to look at using amateur radio on their spacecraft? Please pass this along to them.
Amateur Space Radio Exhibit to host ORI Technical Demos at Ham Expo March 2021
Please visit the Amateur Space Radio exhibit at the upcoming Ham Expo, 12-14 March 2021.
https://www.qsotodayhamexpo.com/
Amateur Space Radio is any amateur radio activity that has to do with space. It could be satellites, ionospheric sounding, ground stations, any AMSAT activity, schools, citizen science, radio astronomy, and more.
Exhibit support website is located at https://amateurspace.radio/
Space Radio is fun and accessible. There is room for people that want to operate satellites. There is room for advanced experimenters improving the technology. There is room for people that buy commercial equipment. There is room for DIY and open source. And, there is room for you!
Saturday’s Space and Satellite Track features eight talks that cover all aspects of Space Radio. How to get started with equipment you already own, an introductory talk that opens up all of the magic of satellite operations, a deep dive into current microwave band digital transponder technology, a history of GEO projects at AMSAT, an explanation of what is required to support an international volunteer team working on FPGA development for amateur satellite work, some very good regulatory news for the United States, how we are engaging students in amateur satellite, and what we need to do about space junk.
All of the talks will be available after Ham Expo, but at the event you will get to interact with the presenters directly, asking them questions, live. Many of these speakers will be at the Amateur Space Radio booth for breakout sessions.
The breakout session schedule includes Getting Started, Roving Operations, JAMSAT, Tech Talk, Tech Demos with Open Research Institute and others, ARDC, Space Weather with TAPR, and an Antenna Session with Kent Britain. We have a couple of open tables and if you want to see something discussed, then please come by and we will set something up.
The Amateur Space Radio exhibit in the Expo doesn’t just have breakout sessions with subject matter experts. It also has nine hours of video content from around the world. These videos include highlight reels, tutorials, and presentations. They cover activity ranging from FM satellite operations to antenna design to advanced propulsion experiments and more. We are playing the world class GNU Radio workshop from Dr. Estevez about decoding satellite transmissions on Sunday with all of the resources needed to participate, linked at the booth.
Our video playlist is available on YouTube from a link at front of the booth. This allows on demand viewing. The schedule for when they will be shown during the Expo is at the booth.
We have two social events this year. Friday night is a custom electronic dance set from John Brier. The recording will also be available through a link at the booth. John Brier is an active satellite operator and educator and is also an electronic dance music musician.
Our second social event is an online scavenger hunt with an Around the World Theme. The event starts at 7pm US Pacific tonight, Saturday, the 13 of March, and will be conducted through Zoom by Watson’s Adventures. If you want a ticket, come to Amateur Space Radio and find the Watson table. First come first serve. If you cannot use your ticket please return it or find someone who can. The adventure will start at 7pm US Pacific time sharp, so make sure to join ahead of time so you won’t be left out. We will close the table when we have given all tickets out.
If you want to learn more about Amateur Space Radio, and stay in touch, please use the Register Interest on our main banner at Ham Expo. We think space is the most exciting part of the amateur radio hobby and we want to hear from you on how to best support it moving forward.
Thank you to Ham Expo and the satellite community for making this exhibit such a success. Please welcome our speakers, and see you at the booth!
Open Research Institute “Spirit Wear” Store
US shipping only at this time.
Store will premier on 12 March 2021 at Ham Expo.
10% of every purchase goes towards ORI!
https://stores.goldmedalideas.com/ori/
Welcome to Ham Expo March 2021
Here is the Schedule for the Space and Satellite PresentationTrack in Space Radio Auditorium. ORI is proud to have such good representation at this event. Please visit the Amateur Space Radio booth at QSO Today Virtual Ham Expo for our technical demonstrations, watch video presentations, and to visit with other amateur satellite enthusiasts. This event will be a big highlight of the year for amateur radio!
Watch the Track Intro Video below:
Please visit the Ham Expo website to register for the event.
Space and Satellite Content from ORI at HamCation 2021
Want to hear the rest? Come to the TAPR/ORI forum at HamCation 2021! https://www.hamcation.com/
Excess Equipment For Sale
We have excess lab equipment that is now for sale!
— OpenResearchInstitute (@OpenResearchIns) January 27, 2021
All proceeds go directly back to the Phase 4 project. Learn more about that at https://t.co/ReSTT6mOfT
Analog Devices ADRV9371-W/PCBZ evaluation board listing is here:https://t.co/rI2Et3pnqv
Remote Labs Report for January 2021
HamCation 2021 – Special Edition
TAPR and ORI will have a joint forum at HamCation Special Edition 2021.
Attending HamCation Is Now Easier Than Ever!
At this virtual event, you can attend from anywhere you have an internet connection. Attend great webinars, join the HamCation QSO party, and put in your ticket for some truly great prizes.
At this year’s forum, ORI and TAPR focus on use cases for our open source hardware projects, celebrate the very bright present and future of amateur radio, and explain why open source is such a powerfully positive concept for the Amateur Radio Service as well as the Amateur Radio Satellite Service.
Join us Saturday February 13, 2021 at 12:00 PM US Eastern Time. Here’s what ORI and TAPR have in store for you!
12:00 – 12:05 The Spirit of Amateur Radio Experimentation
An inspiring and accessible introduction to the state of the art in amateur radio, this short video showcases the heart and soul of open source amateur radio hardware design, featuring TAPR and ORI. Exciting developments are happening in terrestrial microwave, aerospace, machine learning, contesting, education, and much more. There has never been a better time to be involved in amateur radio. You belong, no matter your level of technical expertise.
12:05 – 12:25 TAPR
Please join us as Scotty Cowling explains the TangerineSDR ecosystem, describes how much fun it will be to use this innovative software-defined radio, and how it stacks up against other radio systems. Then, learn about the Clock Module (CKM) from John Ackermann. This flexible module provides high-accuracy clock signals to your future favorite radio, the TangerineSDR. It can also be used in its own carrier board to provide a GPS Disciplined Oscillator (GPSDO) instrument, permitting near-laboratory grade time and frequency standard measurements in your ham shack. The modular and useful approach guides all of TAPR’s work.
TAPR is central to amateur radio culture. TAPR hosts the annual Digital Communications Conference, publishes a widely-read technical conference proceeding, and sends out an informative newsletter to members. TAPR sustains an enduring community of volunteers that consistently produce fast, flexible, and truly useful open source designs for the discerning amateur experimenter.
Panelists are Scotty Cowling and John Ackermann.
12:25-12:45 Open Research Institute
Space is beautiful, dangerous, challenging, and rewarding. Best of all, amateur radio operators worldwide have access to it! Open Research Institute (ORI) builds digital multiplexing transponders in the microwave bands. Intended for spacecraft at HEO, GEO, and beyond, these powerful transponders use state-of-the art error correction to provide world class reliability that adapts to the signal environment.
But, all statistics and no play makes for a dull radio. This system lets you send any data type you want, even through extremely difficult signal-to-noise conditions. Want to leave someone a voice message? No problem. Impromptu voice meetup? Yes! Set an alert for when a friend is on the air? Sure. Post a photo album of your antenna project with a voice memo to answer another ham’s question? You bet. All over the air and independent of the Internet. These systems can also be deployed terrestrially to provide modern amateur digital communications networks.
Open Research Institute is a 501(c)(3) that does open source research and development for amateur radio and beyond. ORI provides a wealth of community resources and learning opportunities for the experimental amateur radio community. Two well-stocked Remotely Accessible Lab Benches for advanced digital communications work, a full floating Vivado license, field-programmable gate array (FPGA) stations, and most crucially, ORI offers community, expert advice, and support to go from “curious” to “crack shot” in a wide variety of high-tech skillsets. Ready to take advantage of the rapidly growing world of open source hardware? Bring your time and attention and become part of it.
Participants are Michelle Thompson, Paul Williamson, Wally Ritchie, Anshul Makkar, and more.
Engineering Report 11 December 2020
Content:
## Phase 4 Weekly Report for 11 December 2020
#### Architecture 9 December 2020
Progress this week on detailed architecture for the exciter. The short term goal is to be able to write base-band frames (BBFRAMES) to the buffer and send them out. BBFRAMES are connected to ethernet on the A53 side. This will achieve our original Phase I goals. Wally Ritchie leading efforts on the modulator and the interfaces so we can integrate the existing FEC code.
#### Remote Labs 9 December 2020
Video report from Remote Lab West available here: https://youtu.be/z0d1vvbX_LU
Video shows unpacking and deployment of the logic analyzer accessory for the mixed-signal oscilloscope. Device under test is an RC2014 and the signal inspected was RS232. Some concern here because we can get single characters and short bursts perfectly, but longer bursts of RS232 are not successfully decoded. Nick and others have given advice and it will be followed up on.
Signal generator for Remote Lab West expected Friday 11 December 2020. Remote Lab East has their signal generator with the upgraded clock already.
Trenz gear delayed, date TBD.
#### 9 December 2020 Meeting Notes – Open Lunar Foundation Use of ORI Radio Designs
Participated in a working meeting on how to use ORI’s transponder work in the NASA grant ecosystem. Answered questions, shared documents, and took some action items from Open Lunar Foundation.
#### 8 December 2020 Meeting Notes – Open Lunar Foundation Donor Summit
Attended a donor summit held by Open Lunar Foundation. Answered questions about ORI, P4XT, open source licensing, and how best to use the ORI transponder and ground equipment as a base design for Open Lunar Foundation’s efforts to provide solutions for LunaNet and beyond.
Learn more about Open Lunar Foundation at:
#### 8 December 2020 Meeting Notes – Debris Mitigation, GMAT, and Orbits
Wally Ritchie
Anshul Makkar
Michelle Thompson
**AI:** = Action Items
GMAT stands for General Mission Analysis Tool. This is an open source framework from NASA that allows high-fidelity mission planning. Find more information about this tool here:
https://opensource.gsfc.nasa.gov/projects/GMAT/index.php
Our LEO-to-GEO GMAT models by Achim Vollhardt can be found here:
The LEO-to-GEO GMAT models shows what we need to do to get to GEO on our own. They allow us to do a trade study between motoring to GEO from LEO vs. paying for a launch to GEO. In both cases, we need to model the GEO-to-disposal orbit, which is one of the things Anshul Makkar is working on.
There are multiple variables to consider when comparing LEO-to-GEO against straight-to-GEO, including:
1) debris mitigation concerns because spiraling up through what may be very large LEO constellation may raise objections, where straight-to-GEO does not, at increased launch expense.
2) the capability cost to LEO-to-GEO due to the larger amount of space required for fuel.
3) increased radiation exposure of a LEO-to-GEO spiral, which drives up cost and potentially capability.
Anshul is creating a GMAT mission to model desired orbits for P4XT. He had some questions about Debris Mitigation, GMAT, and the impact on orbits. Here is a summary of the discussion and the resulting action items and goals.
Anshul has been working through some examples to learn GMAT and has had success. He came to the point where he needed to know more about the parameters.
For Anshul’s initial round of work, we will model from GEO delivery to disposal orbit.
We currently refer to this as “Straight to Graveyard”.
The disposal orbits are 250 km above and below GEO.
The upper stage of the launches we expect to be able to take advantage of deliver payloads 50 km above or below GEO. The final maneuvering is typically done by the primary payload after separation from the final stage. This orbit, 50 km out, is called the “maneuvering zone”.
While we would like an equatorial disposal orbit, we can handle inclinations.
Wally shared some paper about some stable orbits available in disposal.
**AI:** Wally to send Anshul an edition of a good book resource on orbital mechanics.
With this GMAT mission creation, we will have three line elements (TLEs) that will enable ground station tracking modeling in currently available software.
**AI:** GMAT animations will be created to show a train of 4 payloads for global coverage.
The advantages to Straight to Graveyard are significant.
1) With a GEO-to-dispoal, we do not have to have the estimated 2 lbs of Iodine thruster fuel for a LEO to GEO orbit, modeled previously by Achim.
2) We do not suffer the wear and tear a LEO to GEO mission incurs.
3) We can use the saved space for more and better batteries, which increases mission life.
Given the reduced stationkeeping requirements of disposal orbits, we may be able to use open source thruster technology such as AIS work to maintain attitude.
The disposal orbit does require some tracking. However, it is slow. It also provides additional DX opportunities for operators. Path loss will vary more. Anything below 20 to 15 degrees elevation is challenging.
**AI:** Anshul to use existing GEO orbits and modify this mission with a burn to disposal to achieve the simplest Straight to Graveyard mission presentation.
**AI:** Anshul to present his work.
debris_mitigation Slack channel created for discussion, and relevant foundational documents have been shared there.
#### Virginia Tech Industrial Advisory Board Meeting Report
Open Research Institute attended our first Virginia Tech Industrial Advisory Board Meeting on 20 November 2020. The meeting was attended by over 40 representatives from industrial, academic, amateur, and open source communities. The goal of the Industrial Advisory Board is to improve Virginia Tech’s ability to educate students for roles in space exploration, science, technology, regulation, and management.
**Action items:** prepare 2-3 slides about ORI and our mission on the Industrial Advisory Board. Open source regulatory advancements, positive effect on commerce when used appropriately, and the improvement in educational outcomes are the communications goals for the slide deck.
#### High-Level Discussion on Thermal and Radiation
Action Item closed: Thermal Desktop license successfully installed on a FlexLM server donated to the cause by the power of KN6NK.
Current status: having trouble getting the license from the server to the local installation.
**New Action Item:** Tutorials completed using this software.
Mike Murphree requested a mission plan and expectations on the radiation environment as soon as possible.
Mike Murpree requested resource utilization of the Xilinx parts in order to compare against other potentially more radiation tolerant families of parts.
Michelle to provide documentation on the block diagrams and architecture documentation.
#### Trello Boards up and running
We are using Trello for task management. Plenty going on!
Join Phase 4 Ground Trello board:
https://trello.com/invite/b/REasyYiZ/8de4c059e252c7c435a1dafa25f655a8/phase-4-ground
Join Phase 4 Space Trello board:
https://trello.com/invite/b/GRBWasqW/1336a1fa5b88b380c27ccf95d21fec79/phase-4-space
#### AmbaSat Inspired Sensors
Account at Wells Fargo set up and dedicated funds from ARDC deposited.
#### Ham Expo 2021 Participation
ORI will present at and be part of an exhibit at the Ham Expo 2021. Details about the event here: https://www.qsotodayhamexpo.com/
**We will be using this event as a deadline for transponder work.** We will demonstrate functionality complete by March 2021 at the show.
#### HamCation 2021 Participation
We will participate in HamCation 2021. This is a virtual event. We have 45 minutes available for presentations. HamCation wants unique, fun, engaging, interactive events. This is a wonderful opportunity for us. Message from organizers after we committed: “We don’t have a schedule yet. Plan on 45 minutes for the webinar with a 15 minute break between. Please provide a topic for the presentation with short description that will be posted. Thank you for offering.”
Topics for presentation and short descriptions need to be drawn up. We could do a competition, quiz bowl, live demo, technical presentation, contest, or anything of the sort.
#### Regulatory Presentation
The report is called “Minimum Viable Product” and the Debris Mitigation activities fold into this presentation. Version 1.2 received from Jan King on 7 December 2020.
Engineering Report 20 November 2020
## Phase 4 Weekly Report for 20 November 2020
#### Virginia Tech Industrial Advisory Board Meeting Report
Open Research Institute attended our first Virginia Tech Industrial Advisory Board Meeting on 20 November 2020. The meeting was attended by over 40 representatives from industrial, academic, amateur, and open source communities. The goal of the Industrial Advisory Board is to improve Virginia Tech’s ability to educate students for roles in space exploration, science, technology, regulation, and management.
The first part of the meeting was a description and orientation of the re-dedication of the Industrial Advisory Board lead by Scott Bailey. The second part of the meeting was a curriculum review lead by Dr. Jonathan Black. The next meeting will be in the Spring.
**Action items:** prepare 2-3 slides about ORI and our mission on the Industrial Advisory Board. Open source regulatory advancements, positive effect on commerce when used appropriately, and the improvement in educational outcomes are the communications goals for the slide deck.
#### High-Level Discussion on Thermal and Radiation
We had a high-level discussion about thermal and radiation requirements and work on 19 November 2020. The goals of the meeting were to introduce volunteers with experience in these areas to each other, and to generate any action items necessary to clear roadblocks for future work. Initial list of action items:
**Meeting Minutes**
Attending were Michelle Thompson, Mike Murphree, Thomas Savarino, Alan Rich, and Nick KN6NK.
We use FlexLM for our Vivado license server, generously donated by KN6NK, and we will be able to use this server for Thermal Desktop. This is limited to one user, Thomas Savarino, but we are satisfied with this work plan. Thomas will also need Parallels and Autodesk. Invoices requested.
Alan Rich provided valuable advice about thermal engineering. Junction temperature and thermal cycling are of primary interest. We need to expect to do a layer analysis and treat the board like a structure. Concerns for radiation were discussed which align with previous work by Wally Ritchie, Thomas Parry, and Suoto.
Mike Murphree requested a mission plan and expectations on the radiation environment as soon as possible.
Mike Murpree requested resource utilization of the Xilinx parts in order to compare against other potentially more radiation tolerant families of parts.
Michelle to provide documentation on the block diagrams and architecture documentation.
*Priorities? Get the Thermal Desktop software up and running so Thomas Savarino can train on it and then start characterizing the 1U circuit cards for the communications payload.*
###### Open Research Institute sponsors the M17 Project
Open Research Institute is proud to sponsor M17, an open source digital radio protocol, code, voice codec, and hardware project.
Learn about and get involved at
https://m17project.org/
M17 has been added to the list of Open Research Institute Projects at
#### Trello Boards up and running
We are using Trello for task management. Plenty going on!
Join Phase 4 Ground Trello board:
https://trello.com/invite/b/REasyYiZ/8de4c059e252c7c435a1dafa25f655a8/phase-4-ground
Join Phase 4 Space Trello board:
https://trello.com/invite/b/GRBWasqW/1336a1fa5b88b380c27ccf95d21fec79/phase-4-space
#### AmbaSat Inspired Sensors
Phone conference with Dr. Alan Johnston on 2 November 2020 to answer questions and set up a tentative schedule. Work is expected to commence December 2020 through May 2021. This work is funded by an ORI grant. Project kickoff report here: https://www.openresearch.institute/2020/11/12/ambasat-inspired-sensors-project-kick-off-in-december-2020/
#### Remote Labs
Equipment has begun to arrive for the Remote Labs project. Access protocols have been drafted and tested. Feedback has been received and incorporated. Report and link to overview video here: https://www.openresearch.institute/2020/10/24/remote-labs-equipment-review/
Tracking document will be moved to the GitHub Wiki, but the current draft is here: https://docs.google.com/document/d/1EG_anaUNWxluriktrDBUa1MnIdIlOe9_hMCkNFj3Tc4/edit?usp=sharing
#### Ham Expo 2021 Participation
ORI will present at and be part of an exhibit at the Ham Expo 2021. Details about the event here: https://www.qsotodayhamexpo.com/
**We will be using this event as a deadline for transponder work.** We will demonstrate functionality complete by March 2021 at the show.
#### HamCation 2021 Participation
We will participate in HamCation 2021. This is a virtual event. We have 45 minutes available for presentations. HamCation wants unique, fun, engaging, interactive events. This is a wonderful opportunity for us. Message from organizers after we committed: “We don’t have a schedule yet. Plan on 45 minutes for the webinar with a 15 minute break between. Please provide a topic for the presentation with short description that will be posted. Thank you for offering.”
Topics for presentation and short descriptions need to be drawn up. We could do a competition, quiz bowl, live demo, technical presentation, contest, or anything of the sort.
#### Regulatory Presentation
We will present to the FCC, accompanied by ARRL counsel, in the next small number of months. This presentation will emphasize how open source technologies and policies strengthen the Amateur Radio Satellite Service. The presentation will show how the Amateur Radio Satellite Service can fully comply with Debris Mitigation, how it can and will continue a rich history of providing quality public service communications, and how it will be a full participant in the New Space Age.
#### Ed Friesma Needs Help
One of our volunteers, Ed Friesma, writes
“We’re submitting a proposal here at UNLV to get a Cubesat off the ground and I’m in charge of the communications team (both hardware and software) We are submitting our base proposal for review but I will have to get a team of students together. A mentor would really help here. Especially when it comes to building the ground station. but also testing the comms link and the ground station software.
Do you know anyone
a) with some good experience setting up communications with Satellites and also boradcasting to satellites over UHF.
b) who would be interested in occasionally speaking with and answering questions from our team.
They don’t necessarily have to be in the area but at least be open to using Zoom or Discord to chat with us.”
Ed has the right experience to put this team together, but would like to run things by someone that’s been there before. It would really help to sort out what must happen over the next few months.
Are you willing and able to mentor Ed’s team? Get in touch with me at w5nyv@arrl.net and I’ll get you in touch with Ed if you don’t already have his email.
As published in The AMSAT Journal, Volume 43, Number 5
[Published under the US doctrine of fair use. This is an excerpt of a publication, used for commentary to advance public discourse regarding a subject of great interest and importance to the amateur radio satellite community.]
September/October 2020
Engineering Update
Jerry Buxton, N0JY
Vice President, Engineering
Open source, Open mind
“Open-Source†is a hot topic for many in discussions about AMSAT, as you may well know. While my go-to, good old fat Webster’s Third New International Dictionary does not have an entry for “open-source,†it does have an entry for “open-mind.†You can find any number of definitions for open-source in an online search. I will go with what turned up first on my search, annotated “Definitions from Oxford Languagesâ€:
adjective [COMPUTING] “denoting software for which the original source code is made freely available and may be redistributed and modified.
A handful of others I looked at to be somewhat certain in what I say here were all essentially the same, and specified software as part of the definition of open-source. That is interesting in that some comments directed at me in the argument for open-source seemed to use the term to include not just software, but hardware as well.
“You cannot reason someone out of something he or she was not reasoned into†(Jonathan Swift, 1721). The quote of Jonathan Swift seems to apply to the current situation because of discussions calling for AMSAT to adopt “open-source†as our means of doing business with satellite projects, lest AMSAT die off as an ineffective organization. Hence, the subtitle refers to what seems to be rare in the age of polarized tweets and blogs and unfortunately, amateur radio email lists, having an “open mind.â€
My trusty old Webster’s says about “open mind†(actual entry is “open-mindedâ€):
adjective: “receptive of arguments or ideas: free from rigidly fixed preconceptions: UNPREJUDICED (an open-minded curiosity that made him receptive to new ideas – V.L.Parrington)
To me, being open-minded is a natural part of the general fraternity of amateur radio, and it takes place every day in everything from tower parties to satellite QSOs. I’m baffled that the concept seems to be left behind as you look at leadership levels of amateur radio affinity groups where one might think being open-minded is a required “skill.†Yet here we have some of the most highly polarized and divided groups of hams who are the functioning antithesis of the openminded definition, especially “free from rigidly fixed preconceptions.†There appears to be no reasoning behind the highly polarized championing of a dire need for AMSAT to “be†open-source. On the flip side, there is no apparent reasoning by anyone who summarily says “no.â€
Fear not. My subject here is not who said what or how AMSAT is run. My director hat is on the tree, and I wear my “VPE MAGA†hat (Moving AMSAT GOLF Ahead) for this. With the scenario set, I will look at how open-source may already exist in AMSAT Engineering, and share some open-minded questions and curiosity in how open-source fits what we do.
There are surely high levels of disagreement already with what I have written this far. Whatever your opinion on my being openminded, please do the same, and perhaps we can think beyond the existing “must†and “no,†which don’t really facilitate any discussion.
To my knowledge, which only goes back just shy of a decade as far as being in a position to know, AMSAT Engineering has never had a policy that specifically ruled out open-source. Obviously, some things would need to be carefully considered before a change is made. I cannot speak for my predecessor as far as the choice to handle documents the way we do right now. It was in place and would make no sense to have tried to change it in the middle of the Fox program.
When I “went to work†for AMSAT in August (or so) 2011 as Systems Engineer, I was tasked with putting together all of the Fox-1 engineering documents that we had at that point for publication in the 2011 Proceedings of the AMSAT Space Symposium. That was the first AMSAT Space Symposium I attended in my then 37 years of fun using amateur radio satellites. I believe, from looking at the 2010 Proceedings, book that 2011 was the first year that Fox-1 was fully documented in that way. In writing the introduction used in those Proceedings, Tony Monteiro (AA2TX), who was VPE at the time, wanted to include the following:
We would also like to be able to discuss our satellite projects with our own members, [emphasis added] some of whom are not “US-persons” per ITAR. These AMSAT Space Symposium proceedings provide a convenient mechanism for the needed publication to make this information public domain and allow us to communicate with our members. The engineering documents published in these proceedings are what was available at the time needed for inclusion, and we hope you find them interesting and informative. AMSAT intends to continue to make the majority of the final technical documents, exclusive of satellite control information, available in future publications.
Those same points were included in what became the yearly publication and sharing of the development of the Fox-1 satellites, and I carried that on when I was voted VPE upon Tony’s passing in 2014. Especially as the Fox-1 platform quickly became popular with partners and prospective partners in flying on our “experiment bay†platform, I took a bit different view of the reason for publication in the Proceedings. I reworded the introduction to better reflect the popularity and the intent of making the designs for Fox-1 CubeSats available to any interested parties, including foreign organizations interested in building their first CubeSats. It stated in part:
AMSAT, in consideration of the educational component of our organization, would like to release the majority of our design documentation to the public as a learning tool to anyone interested in satellite development. [emphasis added]
Since hardware and hardware designs are not included in the definitions of open-source that I mentioned, could you still call our publication of documents “open-source?†It is certainly intended to be accessible to all (purchasing a copy of the proceedings book was not a requirement, as I shared directly as well). It allowed changes for your own use without restriction. In fact, it was about as open as you might get as far as giving stuff to the public.
Incidentally, in the open-source sense, we recently entered into an agreement for an educational program in which students will rework the LTM design to require only two PCBs instead of our design of three. We will benefit from that as the re-design is shared back with us to help improve the LTM package.
The point in the Proceedings introduction that “a majority of the final technical documents†was made available refers to the omission of command and control hardware, and includes software functions regarding such. That point in the sense of “open-ness†is just reasonable security in the operation of the satellites because of licensing, certain government authorizations, and to keep from having the whistler and jammer crowd from also maliciously commanding a bird and ruining the fun for the users. In that, I do not include that omitted piece in this discussion. I expect to make it available after the Fox-1 satellites are no longer operational so it is shall we say, “pending open-ness.”
Let’s look at some of the things that I believe would need to be considered and clarified in “taking Engineering open-source.” One of the points would be whether there is any requirement to put everything on GitHub.com. That is consistently stated or implied in the argument for open-source, but I honestly do not know if that is simply because of general usage or there is something about it in the “compliance†with open-source. The answer to that leads to the obvious question of how doing so makes anything more opensource or officially open-source.
Another point of discussion that flows from that would be the control of information that is restricted by export regulations. Whether you believe that there is no need for concern because the fact that something is open-source makes it impossible for it to be a weapon, what really counts is the government and how the corporation sees it best to comply with those regulations. Certain things that are deemed exports cannot be shared with “non-US Persons,†so how might one secure that information yet still allow some to see it, and all to see whatever other bits are not restricted? There is also the issue of certain blacklisted countries that cannot have access to even something that has an export license, and the internet generally makes it difficult to determine where any interested individuals are from if they hit our GitHub.com page.
For a third point, we do have some volunteers who do not wish to share some or all of the details of their work and that is their right, which is addressed in our IP policy. That work is shared with AMSAT to use in any projects we have, but AMSAT cannot share it, and rightfully so. Do we then have to exclude any volunteers, no matter their capability or desire, if they do not wish to make all that they do open-source? That may be easily dismissed as it has been in some arguments I have seen, but it is an interesting contrast to our current policy that lets anyone participate, whether or not you wish your work to be open-source. In the specific terms of that argument, what we do now is certainly inclusive of all volunteers.
My fourth point in this exploration of the suitability of open-source is something that probably comes only from experience as a volunteer in our all-volunteer organization. It is my understanding that the point of opensource is to allow creativity and input from a larger number of volunteers with the ultimate outcome of essentially, “building better satellites, faster.” In that, I see a situation that we encounter all of the time and for all of the 6+ years I have been VPE.
With any new project, many wish to contribute their ideas in the design and execution of the project, and that is of course a good thing, to some extent. It does present some challenges in areas such as involving numbers of individuals in discussion and demonstration of ideas through documents or prototypes, even existing widgets. I wonder how that would be structured to play out in a reasonable timeframe without the time creep that inevitably comes with lots of individuals pitching lots of ideas.
Also, a pattern of unbridled enthusiasm appears at the start of something new that tends to die rapidly once ideas are pitched and production of those ideas begins. Many are not quite as willing to spend further time making the idea a reality, properly so in some cases, but unfortunately somewhat easily passed on as “and somebody can build it.†If the originator goes silent as is often the case in terms of percentage (recall that this is said from experience), then whoever might have taken up the reins to start making the idea a reality is often put in a position of finding the need for changes in prototyping or further down with PDR and so forth. If they did not originate the idea, while they have done their part of open-source in making the prototype happen, the widget now relies on input from the originator or others in the open-source world to solve the issues found and advance the project.
This is where things get tougher, and while this exists to an extent in our current process, it is more easily solved because it is likely that the originator of the idea is the one pursuing their dream and therefore has the ability (as well as desire) to see it completed. What might be expected in an open-source execution of a project in this regard, if the ideas and designs come from those other than the “construction crew†(for lack of a better term)? I do not necessarily doubt that people will not jump in on GitHub some of the time but you again have the situation of viable contribution if they are not intimately familiar with the stage of the development and willing to spend time with the team working on that widget to find a solution and move forward. Anything less creates delay, and, believe me, we can create that just fine already — and that is the nature of all volunteer projects.
My last thought for this article is that of who is in charge of such a project. Again, I have not contributed to any open-source projects other than AMSAT’s own, so I do not have any idea how they are organized in terms of responsibility. You have to have a boss and some sub-bosses I would think, else you wind up with chaos? At the very least, the systems engineering of any satellite project on GitHub as open-source would be a must and perhaps, a nightmare. That is one more of the items that would need discussion and clarification in consideration of “going open-source†that has not been touched upon in the “on/off †arguments.
My point is not to list all of these things I think of, I simply believe that if there is any serious intent in the arguments regarding open-source I do not see a simple turnkey solution. Whether commercial (do they use open-source?) or amateur radio satellites, some processes are similar and some, perhaps many, are different because of the extreme difference between a paid workforce and a team of enthusiasts who share a common interest. I also do not expect that the arguments being made are with a full understanding of how AMSAT does satellites.
In my tenure, we have seen opportunities and ideas come out from our Engineering Team that can be at least related to open-source, such as standardizing on KiCad. This was an idea put forth and convincingly shown through documentation and use as a great idea, and it is, by a couple of kids who designed and built the Fox-1 MPPT as well as keeping me up late at night for “10 PM Pacific Time†meetings about the MPPT. Bryce and Brent Salmi were all in and one would regularly call or we would meet (can’t remember which, they kinda start to look alike on GTM at 1 AM) which led to the suggestion. With some frustration from the variety of a few other “free†versions of schematic software that had been used by whoever liked which best at the start of the Fox-1 project, they made the push for KiCad. They also turned me on to Kerbal Space Program through which I got my not-a-real Aerospace Engineer Degree usually after one of their calls since I was no longer sleepy.
I do not recall any suggestions about doing our work as open-source, perhaps it has been mentioned but there has been no momentum behind it, so one might take that as an indication that the team is happy with what we have now (SVN complaints aside). Nonetheless, I do believe that I am 98.9% open-minded and the team might support that statement although most people usually only remember the 1.1% of the times I told them no. All of our satellites are testament though, since I neither designed nor created any of it (that I recall) and always give credit to our Engineering Team for their hard work. They are also my real teachers and tutors by which I earned my status as a Real Engineer. (Who needs a piece of paper nobody sees anyway.) I appreciate your reading this with an open mind and ask you to consider the points not as a rejection of open-source, but as valid points of discussion in the consideration of implementing open-source in AMSAT Engineering. Next Journal issue: NDAs and open-source. Exciting!
Open Source and Space: Everybody But AMSAT Came To The Party!
Bruce Perens K6BP, AMSAT member; Michelle Thompson W5NYV, AMSAT Director
Open Source is big in space! Just ask NASA, which operates code.nasa.gov, containing millions of lines of Open Source software created by NASA itself, including Open Mission Control Technologies, Core Flight System: NASA’s spacecraft firmware system, and the General Mission Analysis Tool. With such a complete Open Source toolkit for all aspects of its missions, we can confidently say NASA has gone Open Source. ESA has also come to the Open Source party, releasing lots of code, including their own nanosat firmware, a plate solver that tells you where your telescope is pointed by looking at the photo it takes, and a directory of Open Source Space software that they recommend. SpaceX, which launches more rockets to orbit today than any nation or company, and owns the largest satellite fleet, uses Linux as the brain of its rockets and open source software with SDRs for communications
And Open Source is big in Amateur Space! Ask Librespace, creator of UPSat, a fully-Open-Source cubesat and SatNOGS, a vast ground-station network built of Open Source software and Open Hardware. Fossa came to the party with an Open Source satellite, and has two more in development. Even AMSAT-EA, the European affiliate of AMSAT, has two satellites containing Open Source electric thrusters developed by Applied Ion Systems. And Open Research Institute has received a half-million-dollar grant to develop a 10 GHz digital ground-station as Open Source.
Why is Open Source important to Amateur Space? Let’s start with money: ARDC is providing five Million dollars per year in grants to non-profit organizations to do work important to Amateur Radio, but requires that the technology created be Open Source. Why is Open Source so important that ARDC insists on it? It is software that is free to use, modify, and redistribute, and comes with source code. So, once written, Open Source software tends to be adopted by programmers who keep it alive, improve it, make it run on more and different sorts of computers, etc. Open Source also gets lots of users, who are attracted by the power, versatility, and the zero cost. ARDC obviously wants their grants to be as effective as possible, and for the result to be available to everyone. So, they insist on Open Source.
But Open Source was already popular long before ARDC started making grants. GNU Radio is probably the most powerful software in the Amateur world, allowing programmers to implement many different kinds of transmitters and receivers in software, without picking up a soldering iron! That Open Source SDR software became so powerful that even the United States Government started supporting its development, so that their intelligence agencies could rapidly write new receivers to eavesdrop on the bad guys. The Government had paid a Billion dollars for commercial software like it that never worked. This was just the latest in a long list of disappointments with proprietary software. After a thorough study, they turned to Open Source. Open Source has similarly taken over the computer industry: The largest companies today, Amazon, Google, Facebook, aerospace giants like SpaceX all have in common: their software infrastructure is built on Open Source.
It turns out that sharing your software development with the general public is a really good idea. It allows collaboration easily, something companies previously had a hard time doing without lots of lawyers and conflicting agendas. It produces measurably better code, because people naturally write better when the whole world is looking over their shoulder, and because two developers (or 1000) are better than one. The superior quality of open source software has been repeatedly confirmed, most notably by Harvard Business Review.
And, everybody benefits because they get great software that they can use, extend, and share for any purpose. It became clear when I spent time with NASA engineers that the decision to Open Source was driven by the engineers and researchers themselves: It’s just considered the best way to make software these days. Open Source is especially important for science: being able to duplicate an experiment to corroborate its results, and being able to read the code to see if an experimenter made a mistake, are critical to establishing truth.
A version of Open Source called Open Hardware is used to share hardware designs rather than computer software. The CERN Open Hardware License and the TAPR Open Hardware License are both excellent examples of widely-adopted and battle-tested open source licenses that enable high quality and productive open source work. If you, as an AMSAT volunteer, want to reserve the right to make money off your code or hardware design, then go into business for yourself. There’s nothing wrong with wanting to be paid for your product. But, please! Do not encumber an educational organization with proprietary intellectual property for personal pecuniary gain to the exclusion of the non-profit mission of AMSAT!
There are so many other options available to you if making money is your priority. Amateur radio is a special case. We need to be sharing our knowledge for the benefit of all, whenever we can.
Open Source is the only viable strategy an Amateur organization has to work with ITAR and EAR. These are the United States technology export laws that would otherwise hinder any US-based satellite organization. Satellites are part of a large body of technology that the government considers to be “munitions”, and doesn’t wish to have exported. It happens that ITAR and EAR both have clearly written exceptions regarding Open Source. These exceptions allow an Open Source development paradigm to be used without the export restrictions we would otherwise face when working with volunteer collaborators. Without Open Source, we would be required to carry out our development in secret – with all of the logistical complications of developing technology in secret – using only volunteers who are US Residents, and we would face serious penalties for leaks of our technology. This is very expensive and requires volunteers that do nothing more than monitor other volunteers. Is this what you want your AMSAT dues to pay for?
When our amateur satellite projects are Open Source we can operate in public. We can use collaborators from all over the world without restrictions. As of August 2020, the Department of Defense confirmed that for ORI.
So, we can share our amateur satellite developments with Libre Space Foundation, which is in Greece; AMSAT-EA, in Europe; and other organizations that we would have to lock out otherwise. We can directly use the Open Source they, NASA, and ESA have already developed.
So, why won’t AMSAT come to the party?
AMSAT isn’t getting funding like the half-million recently allocated to ORI, an amount which could easily also go to AMSAT if they were willing to work on Open Source.
Incredibly, ORI offered to share the granted funds with AMSAT/AREx, and AMSAT/AREx declined.
In 2020, AMSAT borrowed money from the Federal Government so that AMSAT could continue to pay salaries, closed their office permanently, and permanently ended printing of the AMSAT Journal. It sounds like they need money. For years, at every Hamvention and every AMSAT Symposium, the news has been negative. The potential of getting a piece of that five Million per year, every year, should attract them. Over time that would be many Millions of dollars to fund AMSAT projects.
But today AMSAT is even more hostile to Open Source! In the September 2020 issue of AMSAT Journal, available only to members, AMSAT Vice President of Engineering Jerry Buxton published the most odd column in which he – there’ss no other way to explain it – deliberately paraded his ignorance of Open Source software.
That this flaunt was obviously meant to annoy people was made even more clear because Jerry also included a MAGA reference in the article. This is what’s known as a dog-whistle: speech that has a hidden meaning to your target audience. Whatever your politics is, you should know that responsible corporate officers, which Jerry is supposed to be, don’t mix issues in their corporate communications. Doing so invariably alienates part of their audience to no purpose, and to the detriment of the organization because it harms the organization’s relationships.
In his column, Jerry expresses that he is mystified about what Open Source is, because he can’t find it in his dictionary. Jerry would not have had far to go if he’d really wanted to know about Open Source, since there is considerable overlap between AMSAT’s membership and the ORI and GNU Radio communities, both of which deal with Open Source exclusively. The co-founder of ORI is a current AMSAT Board of Directors member and presented at length about this very subject at the October 2020 AMSAT annual board meeting. Was Jerry not present at this meeting?
And we wonder about the many talks about Open Source at AMSAT Symposium 2019: Jerry was in the audience, perhaps his mind was elsewhere? By AMSAT Symposium 2020, 60% of the Proceedings were about open source projects and policies. Has Jerry not leafed through the 2020 Proceedings yet? Was he absent from the Symposium stream, where AIS presented an update on open source thruster designs? The level of interest in open source from volunteer engineers and contributors is clearly present. Yet, Jerry Buxton claims there is no interest in open source, at all.
There are many AMSAT members known to have a deep knowledge of Open Source that Jerry could have turned to, although I fear that not all of them will be renewing their membership this year. We need volunteers that are competent and comfortable with open source technologies. How else can AMSAT compete?
There is more in Jerry’s discussion which I shall not amplify. Because he chose to base his thesis on ignorance, repeating it would not contribute to your knowledge.
We should consider the cost to AMSAT of Jerry’s professed ignorance. It is completely absurd for any organization that develops software and electronics to have a head of engineering who does not have a significant understanding of Open Source. No other organization would tolerate it today. Any that did would be wasting money and time reinventing what is publicly available for free. In AMSAT’s case, this article is an admission that some Directors and Officers are deliberately passing up on opportunities to financially support the organization.
ARDC isn’t the only grantor that would want to see work made Open Source, many corporate and non-profit grantors expect the same. The amounts of money available dwarf any previous donations and fundraising.
Fortunately, ORI, Libre Space Foundation, and many other organizations carry on the development of Amateur Space. If AMSAT won’t join the party, the party will go on happily without AMSAT.
Is this what you, as a member or amateur space enthusiast, want?
-73-
AmbaSat Inspired Sensors Project Kick-Off In December 2020
We are pleased to announce AmbaSat Inspired Sensors as a formal ORI project.
Please visit https://www.openresearch.institute/wp-content/uploads/2019/11/Ambasat-Inspired-Custom-Sensors.pdf to read the proposal document.
Unboxing photographs of flight and lab hardware, with UV sensor included, can be seen here: https://www.flickr.com/photos/w5nyv/albums/72157716833127913
First work session expected December 2020 – May 2021 centered at Villanova University. Principal Investigator is Dr. Alan Johnston.
Autumn Schedule
Open Research Institute will be open for the autumn and winter holidays with a reduced schedule through 6 January 2021.
Happy Halloween!
Remote Labs Equipment Review
Transcript of Introductory Remarks
Greetings all,
Welcome to the Open Research Institute Remote Labs Equipment Review.
Open Research Institute (ORI) is a non-profit research and development organization which provides all of its work to the general public under the principles of Open Source and Open Access to Research.
Remote Labs are two physical lab benches. They have equipment for advanced digital communications design work. This equipment will be accessible online to anyone, anywhere that wants to work on open source amateur radio satellite service or open source amateur radio terrestrial engineering development.
The primary focus of the equipment list reviewed today is to support the design, verification, and test of the DVB family of links. DVB-S2, S2X, and T2 are all commonly found in amateur radio. DVB-S2X is the protocol family used by Phase 4 Ground and Space.
Remote Labs is a part of an extremely important process of re-establishing free and open international collaboration with groups such as AMSAT-DL, JAMSAT, and AMSAT-UK, and to increase and amplify collaboration with Libre Space and other open source groups. This is possible for ORI to do by using the open source carve-outs in the US export control regulatory framework. These controls have impeded international cooperation on amateur satellite work for a long time.
A significant amount of regulatory relief was achieved over the summer by ORI for amateur radio satellite work, and more work is going on right now to build upon this success. Please see the Open Research Website news section for more details on that. Today’s discussion is not about satellite technology, but about the equipment and resources required.
We are fortunate to have the advice and input of people that make a living by using remote labs at work. The advice received so far has been heard and acted upon. Python, HTML5 plus Javascript, and command line access will be the initial methods upon to provide secure access to the equipment.
We will not be writing or using a heavy or complex software framework for the Remote Lab. We will be authorizing and authenticating users. It is highly likely that we will use the same authentication and authorization approach that we intend to use for payload communications access, in order to get more experience with that design. In other words, you may be authenticated and authorized for Remote Labs the same way that you will be authenticated and authorized for the payload communications system.
We will definitely be documenting how to use the lab. We will be responsive to feedback about accessibility and ease of use.
There will be someone physically present at the Remote Labs. The equipment is not installed in racks at an unattended site. If a function needs on-site setup, or a test plan can only be done with someone physically at the bench, then that’s how the work will be done.
Remote Labs is offered as a community resource. Therefore, the review process must include community feedback. Thank you for your time here today to discuss and review the equipment list.
As an example, Thomas Parry has provided the following feedback.
1) The initial list had no power supply listed.
2) A computer controlled coax switch matrix would be very useful to control where the signals are going between test gear, DUT, etc. without physical intervention
3) Some form of general purpose digital/low frequency IO device like an analog discovery would be pretty useful for controlling things remotely
4) A way to get arbitrary RF in and out of the PC, ie. an SDR, would be very useful
5) And please remember cabling.
Wally Ritchie responded with an updated list that includes coax relays controlled from a USB relay board(s), and the other items.
Our practice will be validate and measure any cables we make in-house, buy, or obtain as surplus or donations.
I can answer your questions about budget, operation, and policy at the close of the review, or via email.
Please welcome Wally Ritchie who will lead todays Remote Labs Equipment Review.
AMSAT Symposium 2020 Video Submission and Paper
Open Source Satellite Work Has Been Determined to be Free of ITAR by the US State Department.
Free and open international collaboration can be restored.
FCC Comments Filed
Open Research Institute Comments on Further Notice of Proposed Rulemaking for Mitigation of Orbital Debris in the New Space Age, IB Docket No. 18-313
Executive Board Meeting Minutes September 2020
Attendees: Michelle Thompson, Karen Rucker, Ben Hilburn, Steve Conklin, Keith Wheeler
Date: 9/24/2020, 9 AM PT/10 AM MT
Approved minutes from last meeting in February – unanimous
Status on grants and fundraising:
Received grant money of $511,220,000 – deposited by Michelle at Wells Fargo
Took 14 months to obtain
Budget and proposal is still good
Actually 2 grants won in a single payment
3rd grant still in front of ARDC $140,000 (rent-a-geo)
Vision was to get more people to build microwave rx equipment for space
Board decided to hold on future fundraising efforts and concentrate on technical deliverables
Discussion of D&O insurance and legal considerations as a non-profit; might need to consider the legalities of having minor participants
Regulatory Updates:
ITAR/EAR:
Major win this summer with ITAR restrictions
Michelle has commissioned CCR for under EAR
Request board to authorize amount for commission and lawyers
Got a grant from ARDC to pay for CJ request (ITAR)
Ben made a motion to approve up to $10k for Dept of Commerce, Steve seconds, motion passes
Debris mitigation rules proposed to FCC
Rules will affect ORI’s spacecraft and potentially up cost of rideshares
Michelle proposes that we should file a comment – will send drafts ASAP
Expectation that we will indemnify
Other:
Paid for a booth at hamcation in Florida in February 2021
Steve proposes a motion to withdraw and ask for a refund due to ongoing COVID-19 complications, Karen seconds, motion passes
The technical meeting for FPGA team went well
Discussion of ORI board members’ involvement in GR Con 2020
Michelle proposes discussion on how we can improve our code of conduct
Action Items:
Need to update participant policies to reflect final determination with ITAR
Michelle to look into transferring the website over
CJ Determination: Open Source Satellite Work is Free of ITAR
CJ Determination: Open Source Satellite Work is Free of ITAR
The United States Department of State has ruled favorably on Open Research Institute’s commodity jurisdiction request, finding that specified “Information and Software for a Digital Microwave Broadband Communications System for Space and Terrestrial Amateur Radio Use” is definitely not subject to State Department jurisdiction under ITAR, the International Traffic in Arms Regulations. This is an important step toward reducing the burden of regulations restricting international cooperation on amateur satellite projects, which have impeded engineering work by amateurs in the United States for decades.
Export regulations divide both technical information and actual hardware into three categories. The most heavily restricted technologies fall under ITAR, which is administered by the State Department. Technologies subject to more routine restrictions fall under EAR, the Export Administration Regulations, administered by the Department of Commerce. Technologies that are not subject to either set of regulations are not restricted for export.
On 20 February 2020, Open Research Institute (ORI) filed a Commodity Jurisdiction (CJ) Request with the US State Department, seeking to establish that key technologies for amateur radio are not subject to State Department jurisdiction. “Information and Software for a Digital Microwave Broadband Communications System for Space and Terrestrial Amateur Radio Use” was assigned the case number CJ0003120. On 11 August 2020, the case received a successful final determination: the technology is not subject to State Department jurisdiction. This is the best possible outcome of a CJ request.
The Final Determination letter can be found at
https://www.openresearch.institute/wp-content/uploads/2020/08/CJ-0003120-Final-Determination-Letter.pdf
Under this determination, the technologies are subject to the EAR. The next step is to submit a classification request to the Commerce Department. ORI anticipates that the Commerce Department will find that these technologies are unrestricted under the carve-out for open source in the EAR.
Open Research Institute (ORI) is a non-profit research and development organization which provides all of its work to the general public under the principles of Open Source and Open Access to Research.
This work was accomplished by a team of dedicated and competent open source volunteers. The effort was initiated by Bruce Perens K6BP and lead by Michelle Thompson W5NYV.
Open Research Institute developed the ideas behind the Commodity Jurisdiction request, hired Thomsen and Burke LLP (https://t-b.com/) for expert legal advice, organized the revisions of the document, and invited organizations and individuals with amateur satellite service interests to join or support the request.
ORI thanks Libre Space Foundation and Dr. Daniel Estevez for providing their subject matter expertise and written testimony, and JAMSAT for helpful encouragement and support.
The legal costs were fully reimbursed with a generous grant from Amateur Radio Digital Communications (ARDC). See https://www.ampr.org/grants/grant-open-research-institute/.
ARDC and ORI share a vision of clearly establishing open source as the best and safest way to accomplish technical volunteer work in amateur radio. This final determination letter provides solid support for that vision. The determination enables the development of implementation guidelines that will allow free international collaboration.
This clears the path for a number of interesting projects facilitating new methods for terrestrial and satellite communications, opening the door to robust global digital amateur communications.
Questions and inquiries to ori at open research dot institute.