Space-Based Sensing at the Tactical Edge

TECH FOCUS AREAS: Artificial Intelligence/Machine Learning TECHNOLOGY AREAS: Space Platform; Information Systems; Battlespace OBJECTIVE: This topic seeks to build a cloud-based ecosystem continuously pulling multi-INT satellite sensor data, fuses and processes it through artificial intelligence (AI) to track vehicles and distributes actionable intelligence to mobile devices and analysts worldwide. DESCRIPTION: Through the proliferation of commercial and military satellites populating Low Earth Orbit (LEO), it will soon be possible to perform certain time-critical sensing missions from space. To advance the state of the art, new methods are needed to exploit the increased availability of space imagery, to predict and to track vehicle movement robustly over tactical time scales, and to make this service accessible to a broad set of decision makers. The use of space-based sensors for procuring intelligence, surveillance, and reconnaissance (ISR) on tactically relevant timelines is expected to be a key enabling capability for the Air Force. Potential end-users for such a capability include pilots engaged in mission preparation, special-ops airmen active in the field, intelligence analysts searching for enemy launch sites, and base commanders monitoring threats to facilities. The goal of this effort is to develop an end-to-end software tool that aggregates opportunistic space-based capabilities and enables an efficient and reliable ecosystem for the request and delivery of data products. The focus is on space-to-ground based tracking of vehicles (cars, trucks, military vehicles, mobile equipment, ships, maritime military assets, etc). The main deliverable will be a cloud based software app that incorporates full satellite tasking and access; builds artificial intelligence (AI) enabled automated target recognition (ATR) and processing, exploitation, and dissemination (PED) tools; extracts patterns and trends; simultaneously tracks multiple targets; merges space based sensor data with tracking tips from other sources; leverages the latest in human-machine interfaces; and an establishes a link to secure data distribution networks. PHASE I: This topic is intended for technology proven ready to move directly into Phase II. Therefore, a Phase I award is not required. The offeror is required to provide detail and documentation in the Direct to Phase II proposal which demonstrates accomplishment of a Phase I-like effort, including a feasibility study. This includes determining, insofar as possible, the scientific and technical merit and feasibility of ideas appearing to have commercial potential. It must have validated the product-market fit between the proposed solution and a potential AF stakeholder. The offeror should have defined a clear, immediately actionable plan with the proposed solution and the AF customer. Relevant areas of demonstrated experience and success include: cloud-based data flows, AI for data curation, parsing and exploiting satellite imagery, effective operator interfaces, systems integration and test, etc. PHASE II: Eligibility for D2P2 is predicated on the offeror having performed a Phase I-like effort predominantly separate from the SBIR/STTR Programs. These efforts will include a working software prototype to include integration of features to aggregate space-based ISR collections, such as satellite tasking, automated target recognition (ATR), and tracking metrics. The prototype should additionally include analytics to recognize Pattern of Life (PoL) behavior, extract patterns and trends, predict vehicle position probabilities, and queue sensor collects. The prototype should feature an intuitive user interface (UI) amenable to use on a web browser or mobile device. The demonstration should use commercial space imagery, while later investments may involve both military and commercial imagery. PHASE III DUAL USE APPLICATIONS: Phase III should include upgrades to the tool built in Phase II, accounting for user feedback and results from test and evaluation. This phase should have a strong cyber security focus and allow for the distribution of actionable information from the cloud-based software tool out to the tactical edge for users to navigate, collaborate, and coordinate real-time mission planning and execution. Phase III could also address commercial applications, like global tracking of maritime and overland shipping. REFERENCES: [1] A. Savakis, N. Nagananda, J. Kerekes, E. Ientillucci, R. Blue, W. Hicks, T. Rovito and E. Blasch, "Change Detection in Satellite Imagery with Region Proposal Networks," DSIAC Journal, vol. 6, no. 4, pp. 22-28, 2019. ; [2] E. Blasch, R. Cruise, A. Aved, U. Majumder and T. Rovito, "Methods of AI for Multimodal Sensing and Action for Complex Situations," AI Magazine, vol. 40, no. 4, pp. 50-65, 2019. ; [3] "The Space Force considers a new mission: tactical satellite imagery," 3 February 2021. [Online]. Available: https://www.c4isrnet.com/battlefield-tech/space/2021/02/03/the-space-force-is-considering-adopting-a-tactical-geoint-mission/?utm_source=Sailthru&utm_medium=email&utm_campaign=EBB%2002.04.21&utm_term=Editorial%20-%20Military%20-%20Early%20Bird%20Brief. KEYWORDS: space-based sensing; machine learning; automated target recognition; data fusion; tracking