← Back to NASA Technology Projects
Completed TRL 5 (started at 3, targeting 5)
The Regolith Advanced Surface Systems Operations Robot (RASSOR) is an advanced excavation robot designed to mine and deliver lunar regolith for In Situ Resource Utilization (ISRU) processing. RASSOR’s unique design enables it to efficiently collect regolith, excavate trenches, build landing pads and berms, return collected regolith for processing, and myriad related ISRU activities. To reliably perform these operations in the harsh lunar environment, RASSOR software and sensory systems need to be robust, adapt to uncertainty, and make informed decisions with limited sensory information. Currently, RASSOR lacks the ability to estimate collected regolith mass, and digging controllers are inefficient and not robust to variable compactness and contents of sub-surface regolith. Practically, this means that RASSOR’s autonomous digging routines need to be optimized to handle this variable compactness, infer weights from available sensor data, and optimize power savings to increase runtime. Traditional modelling and control approaches have proved challenging due to system complexity. As such, this project seeks to acquire and optimize this information through application of robust machine learning (ML) models and computer vision tools.
The ICE-RASSOR team applied ML to solve an existing technical challenge faced by ISRU researchers in Swamp Works: How to enable the RASSOR excavation robot to execute autonomous lunar ISRU missions. This project infused ML skills into the KSC technical workforce, enabling KSC engineers and scientists to use ML tools and techniques to solve extremely complex problems across the Center.
Listed on TechPort itself — the most direct way to ask about this specific project.
This is early/mid-stage (TRL 5) — 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.