A NEW DYNAMIC OBSTACLE COLLISION AVOIDANCE SYSTEM FOR AUTONOMOUS VEHICLES

Yu Xin, Huawei Liang, Tao Mei, Rulin Huang, Jiajia Chen, Pan Zhao, Chen Sun, and Yihua Wu

Keywords

Autonomous vehicle, dynamic obstacle detection, dynamic obstacle tracking, dynamic obstacle collision avoidance, spacetime obstacle grid map

Abstract

A new dynamic obstacle collision avoidance system for the autonomous vehicle is designed and specifically described in this paper. In the system, an obstacle grid map is built primarily based on the data obtained from a 3D laser sensor. The detection and tracking of dynamic obstacles is accomplished by the analysis of obstacle grid map of consecutive frames. The space-time obstacle grid map is used to express the collision situation of dynamic obstacles and the autonomous vehicle. Then based on the space-time obstacle grid map, the behaviour selection and path planning of the autonomous vehicle are accomplished. The system described in this paper has been applied on the two generations of autonomous vehicles, Intelligent Pioneer I and Intelligent Pioneer II, which have already completed 10,000 km actual road tests in western suburb of Hefei, and won the first prize in the “Intelligent Vehicle Future Challenge of China Competition funded by Natural Science Foundation of China.

Important Links:



Go Back