RING#: PR-By-PE Global Localization With Roto-Translation Equivariant Gram Learning

摘要

Global localization using onboard perception sensors, such as cameras and light detection and ranging (LiDAR) sensors, is crucial in autonomous driving and robotics applications when Global Positioning System (GPS) signals are unreliable. Most approaches achieve global localization by sequential place recognition (PR) and pose estimation (PE). Some methods train separate models for each task, while others employ a single model with dual heads, trained jointly with separate task-specific losses. However, the accuracy of localization heavily depends on the success of PR, which often fails in scenarios with significant changes in viewpoint or environmental appearance. Consequently, this renders the final PE of localization ineffective. To address this, we introduce a new paradigm, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">PR-by-PE localization</i>, which bypasses the need for separate PR by directly deriving it from PE. We propose RING#, an end-to-end <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">PR-by-PE localization</i> network that operates in the bird's-eye-view (BEV) space, compatible with both vision and LiDAR sensors. RING# incorporates a novel design that learns two equivariant representations from BEV features, enabling globally convergent and computationally efficient PE. Comprehensive experiments on the north campus long-term vision and LiDAR (NCLT) and Oxford datasets show that RING# outperforms state-of-the-art methods in both vision and LiDAR modalities, validating the effectiveness of the proposed approach.