Obstacle Detection in Off-road Environments Based on LiDAR

Mapping off-road terrain is a challenging task, especially when compared to urban terrain. The complexity and roughness of off-road terrain make it difficult to achieve accurate mapping results. Obstacle detection in such environments is also a challenging task, as the performance of LiDAR-based methods depends on the point cloud density at the location of the obstacle. High line beam LiDAR is expensive, while low line beam LiDAR is sparse, making it difficult to obtain dense point clouds. In this paper, we propose a multi-LiDAR fusion approach that uses roof LiDAR as the primary sensor and front LiDAR as a supplement. The approach employs point cloud filtering, dedistortion, and point cloud registration to fuse data from multiple sensors. This results in a richer view of the environment and more intensive measurement data. We combine the voxel map with a twodimensional grid map and accelerate the voxel map using a GPU to generate accurate maps. Experimental results show that our proposed method achieves the highest accuracy and recall rates, improving the accuracy and robustness of obstacle detection in off-road environments.