Benefits of FPGAs for Deep Learning Acceleration in Spacecraft Systems

Giovanni Maria Capuano, Salvatore Capuozzo, Antonio G. M. Strollo, Nicola Petra

Abstract: Artificial Intelligence (AI)-driven autonomous on-board data processing is essential for future space missions, enabling timely decision-making in scenarios like planetary exploration, in-orbit servicing, and Earth Observation (EO). To overcome latency and reliance on ground control, AI models must run directly onboard. While edge AI and low-power accelerators have improved deep learning (DL) deployment on embedded systems, most commercial hardware lacks the radiation tolerance needed for deep-space missions. Space-qualified Field-Programmable Gate Arrays (FPGAs) offer a robust solution, combining energy efficiency, fault tolerance, and in-flight reconfigurability. This adaptability allows spacecraft to update AI models during missions without hardware changes. This paper reviews DL acceleration strategies for space applications, focusing on image processing, and presents a case study using the ANHEO platform, developed by TSD-Space and co-funded by the Italian Space Agency (ASI), demonstrating the benefits of FPGA reconfiguration in spaceborne AI systems.

External IDs:dblp:conf/prime/CapuanoCSP25