Autonomy is increasingly crucial in space missions due to several factors driving the exploration and utilization of space. In the meanwhile, Artificial Intelligence (AI) methods begin to play a crucial role in addressing the challenges associated with and enhancing autonomy in space missions.
The proposed work develops a closed-loop simulator for proximity operations scenarios, particularly for the inspection of an unknown and uncooperative target object, with a fully AI-based closed-loop image processing (IP) and Guidance Navigation & Control (GNC) chain. This tool is based on four main blocks: image generation, CNN-based image processing, navigation filter, and DRL-based guidance and control blocks.
The proposed AI-based architecture is first trained and tuned to investigate the interface problems between each GNC block. Afterwards, the architecture is deployed in an Montecarlo testing campaign to verify and validate the performance of the proposed IP-GNC loop.