← Back to NASA Technology Projects
Active TRL 2 (started at 2, targeting 3)
When robots are sent to the surface of Mars or space stations like the ISS or Gateway, they will need to act autonomously for long durations of time and be exposed to challenging environments. In these conditions, robots have a high likelihood of experiencing some form of system failure. Presently, most robotic missions require engineers to develop pre-designed failure responses, significantly increasing the preparation time and decreasing the robot’s ability to continue operating if it fails in an unforeseen way. This current approach does not offer the scalability needed for large-scale robot deployments to happen--deployments that NASA will need to pave the way for humans to go back to the Moon and eventually Mars. To enable mass robotic systems to accompany and lead long-term space missions, my research will develop a unified system that utilizes redundant actuation to creatively adapt a robot’s actions in real-time in the event of one or multiple faults. Autonomous robots using this system will have greater flexibility than with classic control loops alone. This will increase the time between catastrophic failures, decrease the cost of robot deployment, and improve mission longevity. This research will present a controller-based Fault Detection, Isolation, and Recovery (CFDIR) method to adapt control systems to novel major fault types using null space manifolds. It will then utilize reinforcement learning(RL) to analyze variations in the control system due to prolonged wear and tear and adapt the control parameters to the robot’s condition. CFDIR and RL will be combined to create a task completion probability analysis system(TCAP) that will analyze tasks in a task queue and balance the task’s priority with the probability of completion. This TCAP system will present the factors decreasing the likelihood of completion and suggest ways humans or other robots can assist and increase the probability of completing the task.
Listed on TechPort itself — the most direct way to ask about this specific project.
This is early/mid-stage (TRL 2) — 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.