EVA Machine Learning Prototype

This project will work with Google to use state of the art trained Artificial Intelligence (AI) models and the scalable infrastructure of the Google Cloud Platform (GCP) to ingest, manage and analyze complex mission data. This activity will develop key IoT services for managing EVA or other sensor information, and develop techniques for integrating machine learning models with a variety of control center data sets. The project will determine baseline capabilities for off the shelf Google AI models when applied to complex EVA audio and video datasets. Quantifying specific areas where additional model training is required. Upon completion, the project will demonstrate deploying reusable IoT and Machine Learning (ML) services to the MCC lunar control center prototype. This will help define requirements for ML, and the software and container services to verify deployment to MCCx JSC Machine Learning Prototype with Google and LaRC to ingest/stream and analyze complex telemetry using APPDAT and AutoML on the Google Cloud Platform. Additionally provide complex data sets for a CoICE challenge to agency AI test teams.

Developing techniques for autonomous operations is a primary driver to “Accelerate Human Lunar Exploration”. How to do this has been ill defined. This approach will provide a pragmatic approach to define sensor management, AI integration and roadmaps for future ML activities.

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.