Satellite Collision and Risk Assessment using Machine learning (SCRAM)

In response to the 2023 NASA SBIR Phase II solicitation subtopic Z8.13, ldquo;Space Debris Prevention for Small Spacecraft,rdquo; Advanced Space, LLC proposes to mature Machine Learning (ML) techniques to reduce and subsequently remove the ldquo;human-in-the-looprdquo; bottleneck exhibited by the Collision Avoidance (COLA) Concept of Operations (ConOps). The proposed solution is named SCRAM or Satellite Collision and Risk Assessment using Machine learning. In Phase I, SCRAM featured a trade study of Recurrent and Transformer Neural Networks (NNs) to develop autonomous risk analysis for spacecraft collision avoidance. These new applications of ML provide early predictions of future collision risk trends (Collision Risk Prediction Tool) and validation of collision avoidance maneuvers (Debris Catalog Screening Tool). The autonomous conjunction assessment highlights specific information for early collision risk prediction, while the dynamic space debris catalog builds on historical Conjunction Data Messages (CDMs) to incorporate uncertainty in real time. ML models can be inferenced orders of magnitude faster than traditional methods, significantly reducing both the computational and human hours required to perform collision avoidance operations. By identifying conjunction events early and automating the validation of collision avoidance maneuvers, the strain on COLA operators is reduced. SCRAM will be further developed with the goal of future implementation into current COLA ConOps for space agencies such as the NASA Conjunction Assessment Risk Analysis (CARA) team. This framework has similar applications for mega-constellations and private Space Domain Awareness (SDA) providers. Mr. Matthew Popplewell will be the Principal Investigator (PI) for the proposed project. Mr. Popplewell has experience leveraging ML to alleviate human-in-the-loop bottlenecks for a variety of autonomous spacecraft operations.nbsp;