GroundLoc: Efficient Large-Scale Outdoor LiDAR-Only Localization

Personal use of this material is permitted. Abstract--In this letter, we introduce GroundLoc, a LiDAR-only localization pipeline designed to localize a mobile robot in large-scale outdoor environments using prior maps. GroundLoc employs a Bird's-Eye View (BEV) image projection focusing on the perceived ground area and utilizes the place recognition network R2D2, or alternatively, the non-learning approach Scale-Invariant Feature Transform (SIFT), to identify and select key-points for BEV image map registration. Our results demonstrate that GroundLoc outperforms state-of-the-art methods on the SemanticKITTI and HeLiPR datasets across various sensors. In the multi-session localization evaluation, GroundLoc reaches an A verage Trajectory Error (A TE) well below 50 cm on all Ouster OS2 128 sequences while meeting online runtime requirements. The system supports various sensor models, as evidenced by evaluations conducted with V elodyne HDL-64E, Ouster OS2 128, Aeva Aeries II, and Livox A via sensors. The prior maps are stored as 2D raster image maps, which can be created from a single drive and require only 4 MB of storage per square kilometer . HE accurate self-localization in large-scale outdoor environments remains an important problem in mobile robotics. As mobile robots, such as autonomous vehicles, operate in open, large-scale areas, there is an increase in both run-time and memory requirements for visual localization systems.