Welcome to the new version of CaltechAUTHORS. Login is currently restricted to library staff. If you notice any issues, please email coda@library.caltech.edu
Published April 2022 | Accepted Version
Journal Article Open

MLNav: Learning to Safely Navigate on Martian Terrains


We present MLNav, a learning-enhanced path planning framework for safety-critical and resource-limited systems operating in complex environments, such as rovers navigating on Mars. MLNav makes judicious use of machine learning to enhance the efficiency of path planning while fully respecting safety constraints. In particular, the dominant computational cost in such safety-critical settings is running a model-based safety checker on the proposed paths. Our learned search heuristic can simultaneously predict the feasibility for all path options in a single run, and the model-based safety checker is only invoked on the top-scoring paths. We validate in high-fidelity simulations using both real Martian terrain data collected by the Perseverance rover, as well as a suite of challenging synthetic terrains. Our experiments show that: (i) compared to the baseline ENav path planner on board the Perserverance rover, MLNav can provide a significant improvement in multiple key metrics, such as a 10x reduction in collision checks when navigating real Martian terrains, despite being trained with synthetic terrains; and (ii) MLNav can successfully navigate highly challenging terrains where the baseline ENav fails to find a feasible path before timing out.

Additional Information

© 2022 IEEE. Manuscript received September 9, 2021; accepted February 13, 2022. Date of publication March 7, 2022; date of current version March 16, 2022. This letter was recommended for publication by Associate Editor Chris Paxton and Editor Stephen J. Guy upon evaluation of the reviewers' comments. This work was supported by the JPL Research and Technology Development (R&TD) program. This work was supported in-part by Raytheon. This work was supported by the Jet Propulsion Laboratory, California Institute of Technology, and California Institute of Technology under a contract with the National Aeronautics and Space Administration. The authors would like to thank Olivier Toupet, Mitch Ingham and Ravi Lanka for valuable discussions and problem formulation.

Attached Files

Accepted Version - 2203.04563.pdf


Files (4.9 MB)
Name Size Download all
4.9 MB Preview Download

Additional details

August 22, 2023
October 23, 2023