Autonomous Fault Detection, Recovery, and Avoidance during Robotic In-Space Assembly

As more ambitious missions in Earth-orbit, cis-lunar space, and lunar surface are pursued, the demand for autonomous robotic in-space assembly (ISA) grows. ISA enables future missions such as Artemis Base Camp and assembly of great observatories by integrating individual components into a configuration that cannot be achieved with traditional deployment methods and available launch vehicles. Accordingly, NASA and the National Science and Technology Council have identified ISA as a critical capability and research priority. Autonomous robotic ISA tasks -- such as component insertion and threading -- involve repeated, deliberated, and forceful interactions under uncertainty, which are prone to faults such as misalignment, partial fits, wedging, and jamming. The likelihood of these faults is exacerbated in a space environment where factors such as differential thermal expansion, abruptly changing lighting conditions, and sensor error are prevalent. Furthermore, there is limited a priori knowledge of how the robotic system will behave and degrade in space environment. Given the likelihood and consequences of ISA faults and the dynamically changing system and environment, there is a need to autonomously detect, recover, and avoid faults in an adaptive manner. This research aims to develop a fault-adaptive system of algorithms for in-space assembly to reliably detect faults, safely recover from faults, and intelligently avoid faults. Safe and self-adaptive fault detection, recovery, and avoidance algorithms will be developed through testing on both physical and simulation testbeds emulating autonomous robotic in-space assembly of a truss-based structure. This research will use these testbeds to develop the following techniques: (1) adaptive fault detection algorithms based on recurrent neural networks, (2) adaptive fault recovery planner that plans appropriate recovery actions, and (3) adaptive fault avoidance algorithms that adapt the controller using a control barrier function-based safe learning strategy.

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.