LighterBEV: LiDAR Global Localization Meets Online Learning

Binhong Liu, Tao Yang, Haoji Cao, Shuqi Fu, Yangwang Fang, Zhi Yan

Abstract: LiDAR-based global localization provides accurate robot pose estimates against a prior map. Existing deep-learning methods, however, demand heavy computation and long training or inference times and degrade sharply when faced with domain shifts. This letter presents LighterBEV, a lightweight, fast, and generalizable localization method. An Informative Compression Module achieves a fourfold reduction in localfeature dimensionality while improving accuracy. We further integrate online learning to enable rapid postdeployment adaptation, mitigating degradation under distribution shift. Extensive experiments on four largescale datasets show that LighterBEV achieves stateoftheart performance with limited training data, maintains high accuracy under domain shift, and runs in real time on resourceconstrained hardware—supporting both inference and online updates. To our knowledge, LighterBEV is the first LiDAR global localization approach to incorporate online learning for automatic adaptation to new environments, thereby narrowing the domain gap.

External IDs:dblp:journals/ral/LiuYCFFY26