Personnel Recovery Search and Evasion Guidance Planning Artificial Intelligence / Machine Learning Model Development

TECH FOCUS AREAS: Autonomy; Artificial Intelligence/Machine Learning; General Warfighting Requirements (GWR) TECHNOLOGY AREAS: Information Systems OBJECTIVE: The objective of this topic is to research, develop, integrate, and test various models/algorithms for personnel recovery and/or isolated personnel evasion. Personnel recovery goal given a last known location or area of interest, reduce the search space to find an isolated person. Evasion goal given warfighter position and potentially a target evacuation zone (or zones), plan a route that allows the warfighter to evade capture and get to a safe area. The solutions sought should: take into consideration additional information, attempt to model personnel under different circumstances (injured, elderly, etc.), or be created with unique/novel Artificial Intelligence and/or Machine Learning-based approaches. The technology can be applicable to military environments as well as civilian search and rescue. DESCRIPTION: Currently, the Joint Personnel Recovery Agency utilizes various tools (LandSAR, OSPPRE, FINDER) to 1) narrow a search space to find lost/isolated personnel and 2) allow isolated personnel to plan evasion routes. These technologies utilize terrain data, land cover data, points of interest, etc. to determine the best route for evasion or the most likely area that a lost person may be located. Each of these tools could be supplemented with additional models/approaches. The framework for integrating these approaches is under ongoing development; the main request is to integrate new approaches into that framework. PHASE I: Conduct a study to understand personnel actions in various settings when lost AND/OR how they should best act when evading hostile forces, ensuring developed algorithms will accurately align with what can be expected in a real-life scenario. Survey the types and formats of data available for use for these algorithms including terrain, land cover, watershed data, etc. Develop a plan with the Technical Point of Contact (TPOC) for the environment to be used for testing and simulation. Develop a roadmap for phase II work. PHASE II: Implement the roadmap developed in Phase I. Collect additional data if necessary. Develop the system and implement on relevant hardware (if applicable). Demonstrate capability and gather feedback from relevant end-users. Develop a plan for Phase III and dual use. PHASE III DUAL USE APPLICATIONS: Successful/promising evasion algorithms could lead to additional Phase III work with the DoD or law-enforcement agencies to expand models to various situations and environments. For search and rescue algorithms, there is vast commercialization potential. Various humanitarian groups would utilize the technology for their search and rescue missions. NOTES: The technology within this topic is restricted under the International Traffic in Arms Regulation (ITAR), 22 CFR Parts 120-130, which controls the export and import of defense-related material and services, including export of sensitive technical data, or the Export Administration Regulation (EAR), 15 CFR Parts 730-774, which controls dual use items. Offerors must disclose any proposed use of foreign nationals (FNs), their country(ies) of origin, the type of visa or work permit possessed, and the proposed tasks intended for accomplishment by the FN(s) in accordance with section 5.4.c.(8) of the Announcement and within the AF Component-specific instructions. Offerors are advised foreign nationals proposed to perform on this topic may be restricted due to the technical data under US Export Control Laws. Please direct questions to the Air Force SBIR/STTR Help Desk: usaf.team@afsbirsttr.us REFERENCES: https://www.sciencedirect.com/science/article/abs/pii/S0957417420305224 https://dl.acm.org/doi/abs/10.3233/978-1-61499-672-9-1777 https://www.rand.org/content/dam/rand/pubs/rgs_dissertations/RGSD300/RGSD382/RAND_RGSD382.pdf www.cofiretech.org/feature-projects-2/team-awareness-kit-tak https://arc.aiaa.org/doi/abs/10.2514/6.2020-0879; https://www.mdpi.com/2072-4292/13/1/27 https://www.inderscienceonline.com/doi/abs/10.1504/IJBIC.2020.112339 https://www.nap.edu/read/25156/chapter/1 KEYWORDS: Evasion; Personnel Recovery; Algorithms; Artificial Intelligence; Search and Rescue; Optimization; Planning