Full Stack Navigation, Mapping, and Planning for the Lunar Autonomy Challenge

TL;DR

This paper introduces a comprehensive lunar surface navigation system that combines perception, SLAM, and planning to operate effectively in GPS-denied environments, achieving high accuracy and winning a competition.

Contribution

It presents a modular full-stack autonomy system integrating perception, SLAM, and planning specifically designed for lunar exploration in challenging conditions.

Findings

Achieved centimeter-level localization accuracy.

Generated high-fidelity lunar maps.

Secured first place in the Lunar Autonomy Challenge.

Abstract

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.