Obstacle detection and tracking method for autonomous vehicle based on three-dimensional LiDAR

The movement state of obstacle including position, velocity, and yaw angle in the real traffic scenarios has a great impact on the path planning and decision-making of autonomous vehicle. Aiming at how to get the obstacle's movement state in the real traffic scenarios, an approach is proposed to detect and track obstacle based on three-dimensional Light Detection And Ranging (LiDAR). Firstly, the point-cloud data produced by three-dimensional LiDAR after the road segmentation is rasterized, and the reuse of useful non-obstacle cells is carried out on the basis of the rasterized point-cloud data. The proposed eight-neighbor cells clustering algorithm is used to cluster the obstacle. Based on the clustering result, static obstacle detection of multi-frame fusion is worked out by combining real-time kinematic global positioning system data and inertial navigation system data of autonomous vehicle. And we further use the static obstacle detection result to detect moving obstacle located in the travelable area. After that, an improved dynamic tracking point model and Kalman filter are applied to track moving obstacle stably, and we finally get the moving obstacle's stable movement state. A large amount of experiments on the autonomous vehicle developed by us show that the method has a high degree of reliability.