LiDAR Road-Atlas

LiDAR Road-Atlas: An Efficient Map Representation for 3D Urban Environment

In this work, we propose the LiDAR Road-Atlas, a compactable and efficient 3D map representation, for autonomous robots or vehicle navigation in a general urban environment. The LiDAR Road-Atlas can be generated by an online mapping framework based on incrementally merging local 2D occupancy grid maps (2D-OGM). Specifically, the contributions of our LiDAR Road-Atlas representation are threefold. First, we solve the challenging problem of creating local 2D-OGM in non-structured urban scenes based on a real-time delimitation of traversable and curb regions in LiDAR point cloud. Second, we can achieve accurate 3D mapping in multiple-layer urban road scenarios by a probabilistic fusion scheme. Third, we can achieve a very efficient 3D map representation of the general environment thanks to the automatic local-OGM induced traversable-region labeling, the sparse local point-cloud encoding and effective global LiDAR-Iris descriptor.  Given the LiDAR Road-Atlas, one can achieve accurate vehicle localization, path planning and some other tasks. We compare our map representation with a couple of popular map representation methods in robotics and autonomous driving societies, and our map representation is more favorable in terms of efficiency, scalablity and compactness. 

Reference paper: Banghe Wu, Chengzhong Xu, and Hui Kong, Lidar Road-Atlas: An Efficient Map Representation for General 3d Urban Environment, Journal of Field Robotics, 2023