Trusted Automated Satellite Operations for Mission Life

In response to the DoD SBIR 2024.1 Solicitation for the Space Force Phase I Program, topic SF241-0020 ōTrusted Automated Satellite Operations for Mission Lifeö, Advanced Space, LLC (Advanced Space) proposes a comprehensive feasibility study that encapsulates recent advances in machine learning (ML)-based approaches for spacecraft subsystems as well as overall mission management and operations. The proposed integration methods will be used to yield increased human user assurance within that framework. A crucial component to achieving this goal is implementing properly formulated artificial intelligence (AI) agent(s) that can assess real-time data; make informed decisions in the presence of dynamic environments and multiple objectives/priorities; take proper minimal, self-preserving actions in the absence of immediate human assistance; and define constraints to recommend a human userÆs best course of action when one is available in near-real time. Should the executing control authority be provided to the autonomous agent for certain tasks, the system itself will be able to implement the suggested action independently. Advanced Space will leverage its recent work for government customers (NASA, IARPA, AFRL) in advances in ML applied to autonomous spacecraft operations as well as pathfinding missions in the xGEO domain (CAPSTONE and Oracle-P) where Advanced Space is the mission operations manager and prime contractor.Ā Ms. Kanak Parmar will be the Principal Investigator (PI) for the proposed project. She has an extensive background in strategic applications of AI/ML algorithms for various phases of standard space mission operations. Ms. Parmar is a Staff Astrodynamics, Satellite Navigation (ASN) and ML Engineer at Advanced Space. Through various projects and prior research, she has experience applying ML to trajectory station keeping and path planning; robust autonomous optical navigation; soft data characterization schemes; trusted autonomy and incorporation of cognitive science theory and neuroscience into spaceflight AI; custom loss function design and analysis; and human-AI cooperative/interactive learning approaches in multi-objective, contextualized, and priority-based situations. For this proposed effort, she will be supported by Dr. Nathan Rķ, Principal ASN Engineer, who is a subject matter expert (SME) in low-thrust trajectory optimization and the use of neural networks (NNs) for autonomous spacecraft operations.Ā