BEVPlace++: Fast, Robust, and Lightweight LiDAR Global Localization for Autonomous Ground Vehicles

This article introduces BEVPlace++, a novel, fast, and robust light detection and ranging (LiDAR) global localization method for autonomous ground vehicles (AGV). It uses lightweight convolutional neural networks (CNNs) on bird’s eye view (BEV) image-like representations of LiDAR data to achieve accurate global localization through place recognition, followed by 3-degrees of freedom (DoF) pose estimation. Our detailed analyses reveal an interesting fact that CNNs are inherently effective at extracting distinctive features from LiDAR BEV images. Remarkably, keypoints of two BEV images with large translations can be effectively matched using CNN-extracted features. Building on this insight, we design a rotation equivariant module (REM) to obtain distinctive features while enhancing robustness to rotational changes. A rotation equivariant and invariant network (REIN) is then developed by cascading REM and a descriptor generator, NetVLAD, to sequentially generate rotation equivariant local features and rotation invariant global descriptors. The global descriptors are used first to achieve robust place recognition, and then local features are used for accurate pose estimation. Experimental results on seven public datasets and our AGV platform demonstrate that BEVPlace++, even when trained on a small dataset (3000 frames of KITTI) only with place labels, generalizes well to unseen environments, performs consistently across different days and years, and adapts to various types of LiDAR scanners. BEVPlace++ achieves state-of-the-art performance in multiple tasks, including place recognition, loop closure detection, and global localization. In addition, BEVPlace++ is lightweight, runs in real-time, and does not require accurate pose supervision, making it highly convenient for deployment.