Path to Flight Development Unit Hardware in the Loop Testing for Machine Learning Based Orbit Propagation

For decades, space grade hardware has always been the determining factor in what we can truly design, develop, and deploy for space missions. Space grade hardware not only has to withstand the harsh elements of space but also needs to be low Size, Weight and Power (SWaP). Those guidelines and requirements dictate the types of techniques, methods, and approaches that can be developed for space applications. Space grade hardware is very expensive and limited in the evaluation kits that are created which leads to the need for a low-cost path to flight development unit for space missions. In recent years Artificial Intelligence and Machine Learning (AI/ML) has skyrocketed in the advancements of what can truly be accomplished. AI/ML is being used to autonomously drive vehicles, track wildfires and help cure diseases. The algorithms created need high performance computing to execute and flourish. In this paper, we present a hardware in the loop implementation for trajectory generation on an AI/ML path to flight development unit. The AI/ML path to flight development unit allows for a common architecture and infrastructure to be used when researching, designing, and developing onboard space AI/ML applications. To aide in the synergy, the Space Common Compute Plug-in Interface (SCCPI) is also presented as a common design interface that allows the deployment of AI/ML applications on space grade hardware. Evaluation of the AI/ML path to flight development unit and leveraging SCCPI is done with several orbital propagation problems running in a variety of power profiles designed to mimic small/cube satellites, spacecraft, and instruments.