Satellite Collision and Risk Assessment using Machine learning (SCRAM)

In response to the 2023 NASA SBIR Phase II solicitation subtopic Z8.13, Space Debris Prevention for Small Spacecraft, Advanced Space, LLC proposes to mature Machine Learning (ML) techniques to reduce and subsequently remove the human-in-the-loop 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. Satellite operators and space agencies rely on the 19th Space Defense Squadron (19th SDS) to monitor space objects and generate close approach data (as CDMs) detailing the characteristics of conjunction. Following the identification of a conjunction event by the 19th SDS, SCRAM uses machine learning to extract key information from the related CDMs to enhance the conjunction classification and determine if the conjunction event is high-risk or low-risk. In the event of a high-risk event, spacecraft operators design a collision avoidance maneuver. SCRAM then rapidly validates the maneuver against the space debris catalog to ensure the maneuver does not create additional downstream conjunctions. In the traditional ConOps, CDMs are generated every ~8 hours leading up to the conjunction event, requiring continuous monitoring by COLA personnel and spacecraft operators. SCRAM 1) digests the first several CDMs and delivers a metric quantifying the collision risk at the Time of Closest Approach and 2) rapidly screens the debris catalog following the design of a collision avoidance maneuver.  The primary goal of the Phase II project is to mature the developed algorithms for the tools that comprise SCRAM and demonstrate them in prototype ground software. The tools that comprise SCRAM include the 1. Collision Risk Prediction Tool and 2. Debris Catalog Screening Tool. Following the Phase II effort, the prototype ground software and supporting analysis will be provided to NASA for assessment.   In the Phase II effort, the Advanced Space team plans to:  Objective 1: Develop and Mature the Collision Risk Prediction Tool  Objective 2: Develop and Mature the Debris Catalog Screening Tool  Objective 3: Develop, Demonstrate, and Validate Prototype Ground Software    Proposed Deliverables   Advanced Space will deliver the following items as corresponding deliverables during the Phase II effort:  Kickoff Meeting with all team members.   Quarterly Reports submitted every quarter through the Phase II effort will document technical progress and provide quantifiable details to determine quarterly success toward overall objectives.  A Final Report submitted after Phase II includes a summary of analyses conducted, supporting documentation, documented evidence of delivered TRL, and a high-level design summary for the proposed innovation.  A prototype ground software demonstration of the proposed innovation. 

There is direct applicability to enhance NASA’s Conjunction Assessment and Risk Analysis (CARA) operations with incorporation into the CARA ConOps. Since this technology is reliant on CDMs that were initially developed for CARA, it could seamlessly integrate within CARA and reduce the number of conjunctions considered in operations. This autonomous step screens trajectories, resulting in fewer CDMs flagged for further monitoring and less human-in-the-loop effort for operators.   Commercially, SCRAM will be adapted for cooperative space traffic management needs at the Dept. Of Commerce (TraCCS) and mega-constellations (e.g., OneWeb). For national security, SCRAM will reduce overhead expenses and be used for space situational awareness of adversarial satellites. Lastly, SCRAM will be applied to data curation and validation of state estimates for space objects in a catalog. 

This is early/mid-stage (TRL 3) — the most realistic path in is NASA SBIR/STTR, which funds small businesses and research institutions to develop technology aligned with NASA's needs (equity-free, phased funding). Check whether a current SBIR/STTR solicitation topic overlaps with this project's technology area, or contact the project directly (above) to ask.

None of these are guaranteed paths for this specific project — TechPort itself doesn't have an "apply" button. Reaching out to the contact(s) above with a specific question is usually the fastest way to find out what's actually open.