Artificial Intelligent Co-Processor Slice With Google Coral TPU For Automated Onboard Data-Product Generation

Objective of this proposal is to enable the use of state-of-the-art, experimental, artificial-intelligent (AI) microchip architectures such as the Google Coral TPU (Tensor Processing Unit) on a SmallSat platform. This capability will be accomplished by designing a 1U CubeSat AI accelerator card is compatible with the NASA reliable MARES architecture and SpaceCube. The supporting circuity and components around the AI microchip will be reliable, qualified spaceflight components, built to NASA standards, and the card will be designed to be monitored by C&DH slices of the MARES system and powering on/off individual AI accelerator cards.

Using machine learning and artificial intelligence frameworks on-board spacecraft is a challenging endeavor because common spacecraft processors cannot provide comparable performance to the clusters and datacenters of contemporary CPUs and GPUS available to terrestrial applications and advanced deep-learning networks. This limitation makes small, low-power AI microchip architectures attractive for space deployment, since the design of these devices is specific and efficient for AI applications. AI applications have been theorized and considered for calibration of sensors in spacecraft buses (e.g. calibration of magnetometers), and for processing of onboard image data (e.g. cloud screening).

This is early/mid-stage (TRL 4) — the most realistic path in is NASA SBIR/STTR, which funds small businesses and research institutions to develop technology aligned with NASA's needs (equity-free, phased funding). Check whether a current SBIR/STTR solicitation topic overlaps with this project's technology area, or contact the project directly (above) to ask.

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.