The Department of Defense (DOD) is seeking proposals for evaluating data strategies in training AI solutions for space command and control (C2). The objective is to assess the consequences of employing different data strategies in training autonomous systems, specifically artificial intelligence and deep learning algorithms. The research aims to demonstrate the importance of sufficiently trained AI for space superiority and how space domain awareness data can support this training.
Autonomous space command and control systems are already being deployed within mega-constellations and other space systems. As the use of autonomy increases, there is a need to train algorithms for decision-making. This effort seeks to evaluate the performance of these algorithms when trained with space domain awareness data of varying quality, density, geometric diversity, precision, and timeliness.
The research will involve designing a digital training environment for modeling and simulation using digital representations of space systems and data-driven reconstructions of real-world operations informed by space domain awareness data. In Phase II, a prototype digital training environment will be developed to train AI algorithms for space command and control and demonstrate the relative performance of these agents based on different data strategies. Phase III will involve integrating the prototype solution into operational environments for evaluation and feedback.
The research falls under the OUSD (R&E) Critical Technology Area of Trusted AI and Autonomy. The topic is restricted under the International Traffic in Arms Regulation (ITAR) or the Export Administration Regulation (EAR) due to its sensitivity. Offerors must disclose any proposed use of foreign nationals and comply with US Export Control Laws.
The solicitation was released on November 29, 2023, and closed on February 21, 2024. More information can be found on the grants.gov website or the DOD SBIR/STTR Opportunities page.