Globally Localizing Lunar Rover in Pixels via Graph Alignment

2026-06-09

AI Summary

This study addresses the challenge of achieving high-precision, drift-free global localization for lunar rovers in GNSS-denied environments. To this end, the authors propose the WARG framework, which introduces graph alignment into cross-view lunar localization for the first time. By integrating graph neural networks with reprojection-based geometric alignment, the model is pretrained on synthetic data and demonstrates zero-shot transfer to real lunar scenes without explicit supervision, spontaneously acquiring semantic segmentation and structural reasoning capabilities. Evaluated on real-world data from the Yutu-2 rover, the method achieves a localization accuracy of 1.68 meters (approximately one pixel) with only 1.56 million parameters and runs at 5.49 Hz.

Abstract

Precise rover localization is a prerequisite for autonomous lunar exploration, yet the absence of Global Navigation Satellite System (GNSS) signals and the cumulative drift of local localization methods severely constrain long-range missions. Cross-view localization provides a promising drift-free global solution by matching rover-view and satellite-view imagery. However, the lunar environment poses unique challenges for correspondence alignment, including inter-entity entanglement, inter-viewpoint divergence, and simulation-to-real domain shift. To address these challenges, we propose Warped Alignment of Reprojected Graphs (WARG), a framework that leverages unified graph learning and reprojected graph matching for robust cross-view alignment. Pretrained on the synthetic LuSNAR dataset, WARG achieves an average test error of 0.32 m and demonstrates robust zero-shot generalization to the synthetic lunar south pole region with an error of 3.63 m. More importantly, when validated on real-world data from the YuTu-2 rover, WARG achieves a localization error of 1.68 m within a 100 m x 100 m search area, corresponding to nearly one-pixel precision in low-resolution satellite imagery with a spatial resolution of 1.40 m/pixel. Beyond accuracy, WARG is computationally efficient, containing only 1.56M parameters, corresponding to 16.12% of previous lightweight models, and operating at 5.49 Hz on an NVIDIA RTX A6000 GPU, approaching GNSS-level update frequency. Finally, we observe that WARG naturally develops low-level spatial awareness, including semantic segmentation and structural reasoning, through cross-view localization learning, highlighting its potential as a promising paradigm for spatial intelligence with minimal annotation cost. The source code is available at https://github.com/maochen-casia/warg.

Problem

• lunar rover localization
• cross-view alignment
• GNSS-denied environment
• domain shift
• correspondence matching

Innovation

• cross-view localization
• graph alignment
• lunar rover
• zero-shot generalization
• spatial intelligence