CoFi: Coarse-to-Fine ICP for LiDAR Localization in an Efficient Long-lasting Point Cloud Map

TL;DR

This paper introduces CoFi, a coarse-to-fine ICP algorithm that improves LiDAR localization accuracy and robustness by multi-resolution refinement, combined with semantic feature extraction for efficient long-term mapping.

Contribution

The paper presents a novel multi-resolution ICP approach and integrates semantic features for enhanced LiDAR localization in long-lasting maps.

Findings

Achieves state-of-the-art performance on KITTI benchmark.

Significantly improves localization accuracy over existing ICP methods.

Demonstrates robustness with semantic feature integration.

Abstract

LiDAR odometry and localization has attracted increasing research interest in recent years. In the existing works, iterative closest point (ICP) is widely used since it is precise and efficient. Due to its non-convexity and its local iterative strategy, however, ICP-based method easily falls into local optima, which in turn calls for a precise initialization. In this paper, we propose CoFi, a Coarse-to-Fine ICP algorithm for LiDAR localization. Specifically, the proposed algorithm down-samples the input point sets under multiple voxel resolution, and gradually refines the transformation from the coarse point sets to the fine-grained point sets. In addition, we propose a map based LiDAR localization algorithm that extracts semantic feature points from the LiDAR frames and apply CoFi to estimate the pose on an efficient point cloud map. With the help of the Cylinder3D algorithm for LiDAR scan semantic segmentation, the proposed CoFi localization algorithm demonstrates the state-of-the-art performance on the KITTI odometry benchmark, with significant improvement over the literature.