Graph Neural Networks (GNN) for UxS Collaborative Agent Control

DEPARTMENT OF THE ARMY SMALL BUSINESS INNOVATION RESEARCH (SBIR) PROGRAM SBIR 21.4 Broad Agency Announcement (BAA) Army Applied SBIR Opportunity (ASO) Announcement November 16, 2021: ASO issued for pre-release November 30, 2021: Army begins accepting proposals January 4, 2022: Deadline for receipt of proposals no later than 12:00 p.m. ET IMPORTANT Deadline for Receipt : Proposals must be completely submitted no later than 12:00 p.m. ET, January 4, 2022. Proposals submitted after 12:00 p.m. will not be evaluated. The final proposal submission includes successful completion of all firm level forms, all required volumes, and electronic corporate official certification. Classified proposals will not be accepted under the DoD SBIR Program. This BAA and the Defense SBIR/STTR Innovation Portal (DSIP) sites are designed to reduce the time and cost required to prepare a formal proposal. The DSIP is the official portal for DoD SBIR/STTR proposal submission. Proposers are required to submit proposals via DSIP; proposals submitted by any other means will be disregarded. Proposers submitting through this site for the first time will be asked to register. Effective with this announcement, firms are required to register for a login.gov account and link it to their DSIP account. See section 4.14 for more information regarding registration. The Small Business Administration, through its SBIR/STTR Policy Directive, purposely departs from normal Government solicitation formats and requirements and authorizes agencies to simplify the SBIR/STTR award process and minimize the regulatory burden on small business. Therefore, consistent with the SBA SBIR/STTR Policy Directive, the Department of Defense is soliciting proposals as a Broad Agency Announcement. SBIR/STTR Updates and Notices: To be notified of SBIR/STTR opportunities and to receive e-mail updates on the DoD SBIR and STTR Programs, you are invited to subscribe to our Listserv by emailing [email protected]. Help Desk: If you have questions about the Defense Department's SBIR or STTR Programs, please call the DoD SBIR/STTR Help Desk at 1-703-214-1333, or email to [email protected]. Topic Q&A : The Topic Q&A for this BAA opens on November 16, 2021 and closes to new questions on December 21, 2021 at 12:00 PM ET. Proposers may submit written questions through Topic Q&A at https://www.dodsbirsttr.mil/submissions/login or through the SBIR Mailbox at usarmy.pentagon.hqda-asa-alt.mbx.army-applied-sbir-program@mail.mil. In Topic Q&A, the questioner and respondent remain anonymous and all questions and answers are posted electronically for general viewing. Once the BAA closes to proposal submission, no communication of any kind with the topic author or through Topic Q&A regarding your submitted proposal is allowed. Questions should be limited to specific information related to improving the understanding of a particular topic’s requirements. Proposing firms may not ask for advice or guidance on solution approach and you may not submit additional material to the topic author. If information provided during an exchange with the topic author is deemed necessary for proposal preparation, that information will be made available to all parties through Topic Q&A. Proposing firms are advised to monitor Topic Q&A during the BAA period for questions and answers. Proposing firms should also frequently monitor DSIP for updates and amendments to the topics. This Army Applied SBIR Opportunity (ASO) is issued under the Army Broad Agency Announcement (BAA) for SBIR/STTR 21.4. All proposals in response to the technical area(s) described herein will be submitted in accordance with the instructions provided under 21.4, found here: https://beta.sam.gov/opp/b79ded14dcf54451bcfb11bddf5cd259/view?keywords=%22army%20sbir%22&sort=-relevance&index=opp&is_active=true&page=1. a. Eligibility The eligibility requirements for the SBIR/STTR programs are unique and do not correspond to those of other small business programs. Please refer to Section 3.1, Eligible Applicants, of BAA 21.4 for full eligibility requirements. b. Anticipated Structure/Award Information Phase I Please refer to Section 1, Funding Opportunity Description, provided in BAA 21.4 for detailed information regarding SBIR/STTR phase structure and flexibility. For this BAA, the Department of the Army will accept Phase I proposals for the cost of up to $250,000 for a 6-month period of performance. Proposers should refer to Section 4, Application and Submission information, of BAA 21.4 for detailed proposal preparation instructions. Proposals that do not comply with the requirements detailed in BAA 21.4 and the research objectives of this ASO are considered non-conforming and therefore are not evaluated nor considered for award. Phase I proposals shall not exceed 5 pages. Phase I commercialization strategy shall not exceed 10 slides. This should be the last section of the Technical Volume and will not count against the 5-page limit. Please refer to Appendix A of BAA 21.4 for detailed instructions on Phase I proposal preparation. Phase II Please refer to Section 1, Funding Opportunity Description, provided in BAA 21.4 for detailed information regarding SBIR/STTR phase structure and flexibility. For this BAA, Department of the Army will accept Phase II proposals for the cost of up to $1,700,000 for an 18-month period of performance. Proposers should refer to Section 4, Application and Submission information, of BAA 21.4 for detailed proposal preparation instructions. Proposals that do not comply with the requirements detailed in BAA 21.4 and the research objectives of this ASO are considered non-conforming and therefore are not evaluated nor considered for award. Phase II proposals shall not exceed 10 pages. Phase II commercialization strategy shall not exceed 10 slides. This should be the last section of the Technical Volume and will not count against the 10-page limit. Please refer to Appendix A of BAA 21.4 for detailed instructions on Phase II proposal preparation. c. Evaluation of Proposals Section 5, Evaluation of Proposals, in BAA 21.4 provides detailed information on proposal evaluation and the selection process for this ASO. d . Discretionary Technical and Business Assistance (TABA) Participation in the Army applied SBIR TABA program is voluntary for each Army Applied SBIR awardee. Services provided to Army Applied SBIR firms under the auspices of the TABA program may include, but are not limited to: Access to a network of scientists, engineers, and technologists focused on commercialization and transition considerations such as protected supply chain management, advanced manufacturing, process/product/production scaling, etc; Assistance with intellectual property protections, such as legal considerations, intellectual property rights, patent filing, patent fees, licensing considerations, etc; Commercialization and technology transition support such as market research, market validation, development of regulatory or manufacturing plans, brand development; Regulatory support such as product domain regulatory considerations, regulatory planning, and regulatory strategy development. Vendors. The Army will select a preferred vendor for the Army Applied SBIR TABA program through a competitive process. Alternately, a small business concern may, by contract or otherwise, select one or more vendors to assist the firm in meeting the goals listed above. The Applicant must request the authority to select its own TABA provider in the Applied SBIR proposal, demonstrating that the vendor is uniquely postured to provide the specific technical and business services required. Participation. Participation in the Army Applied SBIR TABA program is voluntary for each Army Applied SBIR awardee. If a small business concern selects their own vendor, they must include the request in the Applied SBIR proposal. If a small business concern opts to use the Army preferred vendor, the firm may opt into the program at any time during execution of the SBIR project. Resources. The Applied SBIR program sponsors participation in the TABA program. The resource limitation for each firm is: Phase I Firms: Up to $6,500 per project per year (in addition to the base SBIR award amount); Phase II Firms: Up to $50,000 per project; Army-Preferred Vendor: In addition to the base SBIR award amount; Firm-Selected Vendor: Included in the base SBIR award amount and must be included in Phase II proposal. e. Due Date/Time Full proposal packages (Proposal Cover Sheet, Technical Volume, Price/Cost Volume, and Company Commercialization Report inclusive of supporting documentation) must be submitted via the DoD SBIR/STTR Proposal Submission website per the instructions outlined in BAA 21.4 Section 4.3 Electronic Submission no later than 12:00 p.m. ET, January 4, 2022. Army SBIR 21.4 Topic Index A214-045 Graph Neural Networks (GNN) for UxS Collaborative Agent Control A214-045 TITLE: Graph Neural Networks (GNN) for UxS Collaborative Agent Control OBJECTIVE: The purpose of this topic is to use recent advancements in Artificial Intelligence, specifically, GNN to be able to collaborate between different AI agents, Unmanned Aerial/Ground Systems (UxS). Such collaboration must be demonstrated in Airsim due to its large adaptation; however, other game engines can also be utilized. DESCRIPTION: The purpose of this topic is to create an AI GNN framework for collaboration between swarming agents. Currently, collaboration is done using Laplacian matrices which can be used to find useful properties of a graph but it has to be hard coded and thus will be not be robust, since many lines of codes are need to program the behavior of each agent/graph. Current methods limit the behavior changes if a team member is added or lost. Since the hard coded method is used, when a new member is added, the user must account for it, which makes it harder to add new member, the same goes for losing a member, thus a new matrix will be needed to be added or the formation will not be robust. Having AI for each member will make the collaboration faster, more robust and will take the need for pre-determined behaviors. Communication, control and collaboration must be dynamic for large numbers of graph. Adjusting intelligently for unforeseen circumstances i.e adding/loosing members. Swarming for defensive and offensive fires will be able to utilize such Artificial Intelligence. This technology can also be utilized by Ballistic Low Drone Engagement (BLADE) and other C-UAS systems where they can communicate with each other and give suggestions to the user. C-swarming will also benefit from this research as it will give a testbed as to how the swarms of the future will look like and what it takes to counter them. If successful, the GNN will be easier to implement thus will make scaling up very easy and efficient thus will reduce the time it takes for the user to pre-program each new agent. It will also reduce the communication time between agents thus making it faster. If successful, having this assessed will also help in defending against future swarms. PHASE I: Phase I will consist of the demoing of communication for graphs/agents and creating the foundation of GNN in Python. It should also include the demoing of swarm control in a game engine of choice for UxVs where they dynamically change behaviors due to obstacles and/or mission goals. PHASE II: Phase II should consist of a continuation of Phase I as well as a GNN for large number of graphs (200+) in a game engine, approximately. This GNN should be implemented on NVIDIA Jetson platforms for a small number of graphs (20+); it could be a mix of ugv/uavs. PHASE III: Phase III will cotinue off of Phase I and Phase II work while proceeding into commercialization. This final software should be one that can be implemented to any device on edge where communication, control and collaboration between agents can be achieved for UxVs KEYWORDS: Collaboration; swarming agents; coding; AI; Automated intelligence; Machine learning; C-UAS REFERENCES: Tolstaya, E., Gama, F., Paulos, J., Pappas, G., Kumar, V., & Ribeiro, A. (2021, March 24). Learning decentralized controllers for robot swarms with graph neural networks. arXiv.org. https://arxiv.org/abs/1903.10527. Kallenborn, Z. (2018, October). The Era of the Drone Swarm Is Coming, and We Need to Be Ready for It. Modern War Institute at West Point. Retrieved from https://mwi.usma.edu/era-drone-swarm-coming-need-read Anh-Duc Dang and Hung M. La and Thang Nguyen and Joachim Horn “Distributed Formation Control for Autonomous Robots in Dynamic Environments” arXiv: preprint arXiv:1705.02017 (2017) T. Nguyen, and H. M. La. "Distributed Formation Control of Nonlonolomic Mobile Robots by Bounded Feedback in the Presence of Obstacles." arXiv preprint arXiv:1704.04566 (2017). Makiko Okamoto and Maruthi R. Akella. Avoiding the local-minimum problem in multi-agent systems with limited sensing and communication. International Journal of Systems Science, pp 1-10, Oct. 2014. H. Yang and F. Zhang, “Geometric formation control for autonomous underwater vehicles”, IEEE Intl. Conf. on Robotics and Automation, pp. 4288-4293, May, 2010.