LiDAR Ground Segmentation and Modeling for Mobile Robots in Unstructured Terrain

Abstract

Ground segmentation and modeling for point clouds generated by mobile laser scanners is an important processing step in the environment perception of mobile robots. Many methods that work well in urban areas do not work correctly in unstructured environments such as meadows or forests. We present a new method that works reliably in both structured urban areas and unstructured outdoor environments. Overall we design a three steps pipeline. First individual scattered ground base points are identified using purely geometric criteria. Based on the ground base points, the ground is then modeled as a triangle mesh in a second step. The triangle mesh is used to provide a relative height and a local slope. The effectiveness and robustness of the proposed method are confirmed and it shows promising results even under difficult conditions.