Identify capabilities in artificial intelligence (AI) and advanced signal processing technologies to enhance spectrum sensing and situational awareness for a chance to win part of the $125,000 prize pool.

Overview

The National Security Innovation Network (NSIN), in partnership with the Air Force Research Lab (AFRL), will conduct a pitch event in December 2024 to identify capabilities in Artificial Intelligence (AI) and advanced signal processing technologies to enhance spectrum sensing and situational awareness for the United States Air Force (USAF) and United States Space Force (USSF).

Submissions will undergo evaluation by government subject matter experts (SMEs), with up to the top 15 qualified applicants selected to receive a portion of the $75,000 prize pot. Selected participants will advance to the second and third rounds, undergoing algorithm training and testing within a 45-day training period before receiving challenge data. This will be followed by four weeks of intensive testing. From these rounds, up to five finalists will emerge, progressing to the final round of the competition, all within the same timeline. The final stage will culminate in a hybrid pitch event during the week of January 27, 2025, where up to five finalists will present their solutions. Subject to availability of funds, the winner/winners from the pitch event may receive a prize of up to $50,000.

Background

Spectrum congestion is a critical obstacle for both military and civilian operations due to restrictive static spectrum policies. Dynamic Spectrum Sharing offers a solution by managing conflicts through varying user access rights. Rapid and precise spectrum sensing is imperative. The RF Spectrum Sharing Challenge is a pivotal initiative, aimed at fostering innovation in automatic RF signal detection, characterization, and recognition. It accelerates advancements in machine learning and signal processing for RF signals, while facilitating the transition of top algorithms to vital DoD programs and stakeholders. The Spectrum Sharing Challenge addresses the complexities of Dynamic Spectrum Access (DSA), spectrum coexistence, and sharing, demanding a profound understanding of other spectrum users and precise waveform characterization to mitigate mutual RF spectrum interference effectively. In essence, this challenge serves as a catalyst for transformative advancements in spectrum management, shaping the future of military and civilian spectrum sharing by accelerating innovation in machine learning and signal processing for RF signals.

Problem Statement

The Air Force Research Lab (AFRL) is launching the RF Spectrum Sharing Challenge, aimed at fostering innovation in spectrum management. This challenge focuses on the rapid and precise sensing of shared RF spectrum segments to optimize their utilization across diverse user categories. The spectrum-sharing regulations are forward-looking, encompassing emerging user types and a wide range of signal characteristics. Successful participants in this challenge will devise innovative techniques for detecting, recognizing, characterizing, and monitoring signals within the shared spectrum. The challenge welcomes various signal processing approaches, including spectrogram-based, cyclostationary signal processing, and IQ-based deep neural networks. Selected participants will have access to extensive simulated and/or captured over-the-air (OTA) data for the development, training, and testing of their solutions.

Key Dates

Round 1: Submission Period

  • May 30, 2024: Solicitation Release
  • June 17, 2024: AMA “Ask Me Anything” Session
  • July 8, 2024: Solicitation Closes & Down-selection Begins
  • July 26, 2024: Semi-finalists Announced (15)

Round 2: Algorithm Training

  • August 5 - September 27, 2024: Algorithm Training
  • September 13, 2024: Exemplar 1 Deliverable Due
  • September 18, 2024: Exemplar 2 Deliverable Due
  • September 24, 2024 Exemplar 3 Deliverable Due

Round 3: Algorithm Testing 1

  • September 30 - October 24, 2024 Algorithm Testing 1
  • October 25, 2024: Deliverable Due
  • November 8, 2024: Semifinals Closes & Finalists Announced (5)

Round 4: Algorithm Testing 2

  • November 9 - November 22, 2024: Training Period
  • November 25 - December 29, 2024: Algorithm Testing 2
  • January 6, 2024: Deliverable Due
  • January 15, 2024: Evaluations Completed

Round 5: Pitch Event

  • Week of January 27, 2025: Hybrid Pitch Event & Winner Announced

Benefits of Participating

  • Up to $125,000 in awards available to the top participants
  • Access to AFRL spectrum challenge data
  • Opportunities for collaboration with industry leaders
  • Potential for follow-on activities, such as Other Transaction Authority (OTAs), Cooperative Research and Development Agreements (CRADAs), and others
  • Exposure to leaders across multiple branches of the U. S. Department of Defense (DoD)

Eligibility

  • U.S. owned and operated companies (to include those with non-U.S. citizens)
  • Early to mid-stage ventures OR non-traditional defense contractors, as defined in the 2023 DoD Other Transactions Guide
  • University Affiliated Research Centers (UARCs)
  • University faculty, researchers and students at accredited institutions of higher education (U.S. citizenship required, 18 years of age or older)
  • Applicants may submit individually or as teams
  • Demonstrate solution capabilities by December 2024
  • CAGE code required for company submissions

Submit Now

Participants must submit solutions for the RF Spectrum Sharing Challenge via the Ideascale link below.

Submit Now

Judging Criteria:

Each phase will be evaluated based on the corresponding criteria outlined below.

Round 1 White Paper Submissions:

  • Technical Soundness: Technical merit, innovation & feasibility of proposed solution
  • Creativity & Novelty: Originality and innovative aspects of proposed solution
  • Clarity: How clearly proposed solution and its components are presented and understood

Round 2-4 Algorithm Training & Testing Submissions: Ability to Transmit Metric

  • Ability-to-transmit value: Analysis of the participant’s ability to generate accurate ability-to-transmit values for both Primary and Secondary users based on modulation-type decisions and signal-parameter estimates.
  • Comparison with Organizer’s truth vectors: Comparison of participant-submitted sharing vectors with the Organizer’s truth vectors to determine alignment and accuracy.

Round 5 Pitch Event: This is a full day event, with a private government meeting with each individual finalist team/company in the first half of the day, followed by the pitches in the afternoon. The pitch format will be public and include a 5-minute presentation followed by 5 minutes for questions and answers from the judging panel.

  • Technical Soundness: Technical merit, innovation & feasibility of proposed solution
  • Team: Qualifications of proposed principals, support staff, and consultants
  • Commercialization: Proposed solution is viable in non-defense markets
  • Quality of Pitch: Team presents a clear and concise overview of its company/team members and technology, demonstrates how its technology solves one or more of the defined problem areas, and effectively answers questions from strategic advisors
  • Operational Alignment: Proposed solution aligns with listed technical requirements

Technical Requirements:

For technical details, refer to the RFSSC Participant Guide.

1) Possess suitable computational resources to process RF scenes, which comprise 10-second I/Q data files sampled at 50 MHz.

2) Each RF scene file will be associated with a particular instantiation of the RFSSC spectrum-sharing parameters, which in part specifies how the time-frequency plan (10 seconds by 50 MHz) is broken into small time-frequency cells. These cells then define a gridding of the plane so that it can be represented by a matrix. For example, the frequency axis might be broken into segments with length 1 kHz and the time axis might be broken into segments with length 1 ms. Then the matrices defined in the following items would have dimension (10000 x 50000).

3) Provide, for each supplied RF scene file, Ability-to-Transmit matrices for primary and secondary user classes.

  • Blindly determine the time-frequency bounding box for each signal in the scene
  • Blindly determine the user class of each signal in the scene, that is, classify each detected signal as belonging to one of the three user classes of primary, secondary, and urgent.
  • Apply the provided spectrum-sharing-system rules and parameters to determine, for each cell of the RF scene matrix, whether or not a primary user is permitted to transmit on that cell. Repeat for secondary users.
  • If a member of a user class is allowed to transmit on a time-frequency cell, the corresponding matrix value is one, else it is zero.

4) Provide, for each supplied RF scene file, Spectral Occupancy (SO) matrices, which are binary-valued matrices. A matrix entry equal to one means that that time-frequency cell is occupied (signal plus noise), a value of zero means it is not occupied (noise only).

  • SO matrix for primary user class
  • SO matrix for secondary user class
  • SO matrix for urgent user class
  • SO matrix for all users

Round 1 Submission Deliverable: Participants must submit the following by 23:59 Eastern Time on the designated submission day:

  • White Paper
    • PDF File
    • Max 4 pages
    • 10 pt, standard 1-inch margins
    • Cover page, resumes, biographies, and reference list shall not count against the page limit

Round 2-4 Deliverable: Excel spreadsheet with result, format TBD

Round 5 Pitch Event Deliverable: Finalists will deliver pitch presentations by 23:59 Eastern Time on the designated submission day. The pitch format will include a 5-minute public presentation followed by 5 minutes for questions and answers from the judging panel.

  • Pitch Presentation
    • Sized 16:9 (1920x1080 pixels)
    • Horizontal presentation
    • PDF file

About National Security Innovation Network

NSIN is a program office in the U.S. Department of Defense (DoD), nested within the Defense Innovation Unit (DIU). We are set up to collaborate with a wide variety of innovators to include universities, researchers, students, entrepreneurs and start-ups. We create opportunities for collaboration across communities and connect those that might not traditionally work in national security. Together, we help drive national security innovation and develop technologies that directly support the individuals responsible for protecting our country.

For more information or interview requests with Team NSIN, please contact us at [email protected].

About Air Force Research Laboratory

AFRL is the primary scientific research and development center for the Department of the Air Force. AFRL plays an integral role in leading the discovery, development, and integration of affordable warfighting technologies for our air, space, and cyberspace force. With a workforce of more than 12,500 across nine technology areas and 40 other operations across the globe, AFRL provides a diverse portfolio of science and technology ranging from fundamental to advanced research and technology development.

Intellectual Property Considerations: Participants retain ownership of existing Intellectual Property (IP) submitted under this Challenge and agree that their submissions are their original work. Participants are presumed to have sufficient rights to submit the submission. For any submission made to the Challenge, you grant NSIN and AFRL RYWE a limited license to use this IP for testing and evaluation for efforts specifically related to the Challenge. NSIN and AFRL RYWE will negotiate with individual competitors in the event additional usage, integration, or development is contemplated.


Other Transaction Authority: This NSIN Challenge public announcement is an open call to small businesses and non-traditional defense contractors seeking innovative, commercial technologies proposed to create new DoD solutions or potential new capabilities fulfilling requirements, closing capability gaps, or providing potential technological advancements, technologies fueled by commercial or strategic investment, but also concept demonstrations, pilots, and agile development activities improving commercial technologies, existing Government-owned capabilities, or concepts for broad Defense application(s). As such, the Government reserves the right to award a contract or an Other Transaction for any purpose, to include a prototype or research, under this public announcement. The Federal Government is not responsible for any monies expended by the applicant before award and is under no obligation to pursue such Other Transactions.


Satisfying Competition Requirements: This NSIN Challenge Open Call Announcement is considered to have potential for further efforts that may be accomplished via FAR-based contracting instruments, Other Transaction Authority (OTA) for Prototype Projects 10 USC 4022 and Research 10 USC 4021, Prizes for advanced technology achievements 10 USC 4025, and/or Prize Competitions 15 USC 3719. The public open call announcement made on the IdeaScale website is considered to satisfy the reasonable effort to obtain competition in accordance with 10 USC 4025(b), 15 USC 3719 (e) and 10 USC 4022 (b)(2). Accordingly, FAR-based actions will follow announcement procedures per FAR 5.201(b).