Full Stack Navigation, Mapping, and Planning for the Lunar Autonomy Challenge
This addresses the problem of autonomous navigation for lunar robotics in challenging conditions, representing a strong domain-specific application.
The authors tackled lunar surface navigation and mapping in a GNSS-denied environment by developing a modular autonomy system, achieving first place in the Lunar Autonomy Challenge with centimeter-level localization accuracy and high-fidelity map generation.
We present a modular, full-stack autonomy system for lunar surface navigation and mapping developed for the Lunar Autonomy Challenge. Operating in a GNSS-denied, visually challenging environment, our pipeline integrates semantic segmentation, stereo visual odometry, pose graph SLAM with loop closures, and layered planning and control. We leverage lightweight learning-based perception models for real-time segmentation and feature tracking and use a factor-graph backend to maintain globally consistent localization. High-level waypoint planning is designed to promote mapping coverage while encouraging frequent loop closures, and local motion planning uses arc sampling with geometric obstacle checks for efficient, reactive control. We evaluate our approach in the competition's high-fidelity lunar simulator, demonstrating centimeter-level localization accuracy, high-fidelity map generation, and strong repeatability across random seeds and rock distributions. Our solution achieved first place in the final competition evaluation.