Radiation-Aware Edge AI for Future Space Nuclear and Surface Autonomy Systems: Inference Fidelity Characterization on Rad-Tolerant FPGA Platforms

To quantify how Machine Learning (ML) inference accuracy degrades under cumulative radiation dose (TID) on NASA’s next-generation edge computing platforms — RTG4 rad-tolerant FPGA, PIC64-HPSC, and EdgeCortix SAKURA-II — to enable trustworthy onboard autonomy.

Measured dose margins for trusting onboard AI: informs FDIR design and platform selection for nuclear and surface autonomy missions; First inference fidelity data on NASA's next flight computing, ahead of 2027 HPSC flight silicon

This is a mature technology (TRL 7+) — the realistic path in is usually NASA's Technology Transfer Program: licensing an existing NASA patent, or a Space Act Agreement to use NASA facilities/expertise directly. NASA also runs a startup licensing program with no upfront fee for companies formed to commercialize a specific NASA technology.

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.