← Back to NASA Technology Projects
Completed TRL 3 (started at 2, targeting 3)
Human space exploration requires advanced robotic systems working together with humans. Successful collaboration within human-robot teams requires each member of the team to be able to predict the actions of every other member. Robots that cannot predict the actions of their human teammates can cause dangerous collisions or otherwise hinder team task completion. To avoid such problems, robots acting around humans must be able to predict the immediate future and change their actions based on these predictions. I propose a hierarchical predictive planner for robots in human-robot teams, which provides interpretable reasoning about decisions to human operators. Using a learned attentional model for action selection, this predictive planner can visually display reasoning about the salient data used to make decisions. Initial development focuses on the Astrobee platform aboard the International Space Station, and on conditioned path planning to avoid collisions with astronauts and other moving obstacles. This work is directly applicable to Technology 4.4.3.2: Intent Recognition and Reaction.
This work is directly applicable to Technology 4.4.3.2: Intent Recognition and Reaction.
Listed on TechPort itself — the most direct way to ask about this specific project.
This is early/mid-stage (TRL 3) — 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.