LunarLoc: Segment-Based Global Localization on the Moon

TL;DR

LunarLoc introduces a segment-based global localization method for lunar exploration that uses instance segmentation and graph matching to achieve drift-free, high-accuracy localization in visually ambiguous environments, outperforming existing methods.

Contribution

The paper presents LunarLoc, a novel approach combining instance segmentation and graph matching for accurate, drift-free lunar global localization, with publicly released datasets for further research.

Findings

Achieves sub-centimeter accuracy in lunar localization tasks.

Significantly outperforms existing lunar localization methods.

Provides publicly available datasets for future research.

Abstract

Global localization is necessary for autonomous operations on the lunar surface where traditional Earth-based navigation infrastructure, such as GPS, is unavailable. As NASA advances toward sustained lunar presence under the Artemis program, autonomous operations will be an essential component of tasks such as robotic exploration and infrastructure deployment. Tasks such as excavation and transport of regolith require precise pose estimation, but proposed approaches such as visual-inertial odometry (VIO) accumulate odometry drift over long traverses. Precise pose estimation is particularly important for upcoming missions such as the ISRU Pilot Excavator (IPEx) that rely on autonomous agents to operate over extended timescales and varied terrain. To help overcome odometry drift over long traverses, we propose LunarLoc, an approach to global localization that leverages instance segmentation for zero-shot extraction of boulder landmarks from onboard stereo imagery. Segment detections are used to construct a graph-based representation of the terrain, which is then aligned with a reference map of the environment captured during a previous session using graph-theoretic data association. This method enables accurate and drift-free global localization in visually ambiguous settings. LunarLoc achieves sub-cm level accuracy in multi-session global localization experiments, significantly outperforming the state of the art in lunar global localization. To encourage the development of further methods for global localization on the Moon, we release our datasets publicly with a playback module: https://github.com/mit-acl/lunarloc-data.