AI Space Cortex: An Experimental System for Space Exploration, Capable of Fault Detection, Self-repair, and Autonomous, Personality-Driven Scientific Discovery

Our Robust, Explainable Autonomy for Scien- tific Icy Moon Operations (REASIMO) effort contributes to NASA’s COLDTech program, which explores science platform technologies for icy worlds such as Europa and Enceladus. Icy world missions pose significant operational challenges – long communications lags, limited power, and lifetime limi- tations caused by radiation damage and hostile conditions. Onboard autonomy will be vital for future missions operat- ing under these constraints. Our effort focuses on advancing autonomous behaviors for robotic sampling systems that collect and transfer material samples to in-situ scientific instruments and communicate results back to Earth – all in environments whose conditions are poorly understood in advance. A further challenge for their autonomy is to react appropriately in the event of anomalies (faults or unanticipated circumstances). Traditional spacecraft rely on a transition into ’safe-mode’ in which non-essential components and subsystems are powered off to preserve safety and maintain communication with Earth. For a severely time-limited icy world mission, its significant delays from communication limitations would cause waiting for Earth-in-the-loop resolutions to drastically reduce its science effectiveness. REASIMO aims to demonstrate a flight-qualifiable level of autonomy for such missions, including the ability to detect and recover from anomalies autonomously. To address these challenges, our REASIMO effort developed an intelligent framework for control of an icy-world mission, combining a mix of advanced technologies and demonstrating them both in software simulation, and on a robotic arm in a laboratory testbed approximating possible surface conditions such a mission might encounter.