Map-Based Localization Method for Autonomous Vehicles Using 3D-LIDAR

Precise and robust localization is a significant task for autonomous vehicles in complex scenarios. The accurate position of autonomous vehicles is necessary for decision making and path planning. In this paper, a novel method is proposed to precisely locate the autonomous vehicle using a 3D-LIDAR sensor. First, a curb detection algorithm is performed. Next, a beam model is utilized to extract the contour of the multi-frame curbs. Then, the iterative closest point algorithm and two Kalman filters are employed to estimate the position of autonomous vehicles based on the high-precision map. Finally, experimental results demonstrate the accuracy and robustness of the proposed method.