A New Accessible Area Detection Algorithm in Unstructured Environment
YAN Ming
CAI Yunfei
CHEN Meng
Abstract：A point cloud feature detection algorithm based on four-line lidar is proposed to reliably detect the travelable area in front of off-road autonomous vehicles in unstructured environments. By searching for more regular distribution point cloud bands with relative plane scanning characteristics,extracting and approximating parallel line segment sets,hypothesizing and fitting the envelope point sets of regular point clouds,smoothing and predicting the boundary according to the context relationship of vehicle running time axis,and making good use of them. Obstacles in the area are monitored by clustering features of point clouds,bound?ary and obstacle areas are fused,vehicle accessibility is considered,and finally safe accessible areas are obtained. The method ef?fectively avoids the serious defect of the calculation method based on the absolute height of the ground plane in large-scale and high-frequency unstructured vibration environment. The experimental and competition application results verify the feasibility and practicability of the algorithm.
Keywords：point-cloudunstructured environmentaccessible area
Publication Date：2019-01-01
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：10( 1652-1661 )