Small obstacle detection for autonomous land vehicle under semi-structural environments

It is very necessary for Autonomous Land Vehicle (ALV) to have a reliable ability of obstacle detection. Unlike structural highway environments, where only vehicles ahead of the ALV are needed to consider, small obstacles are more often seen in semi-structural environments. In this paper we described a small obstacle detection system for ALV under such environments. The system consists of two 2D Laser Range Finders (LRF) which are responsible for obstacle recognizing and tracking respectively. For top LRF, a D-S evidence theory based obstacle recognition algorithm is used to distinguish the obstacles from the brushwood on the roadsides. Based on that, an obstacle tracking process is started by utilizing the data from bottom LRF. Besides the obstacles, the distribution of the brushwood on roadsides, which could be used for path planning, is also obtained. The experimental results demonstrate our success.