受限泊车通道下自动驾驶平行泊车的路径规划方法-《郑州大学学报(工学版)》

文章信息/Info

Title:: A Path Planning Method for Parallel Parking in Constrained Parking Channels

Author(s):: QIN Dongchen; ZHANG Wencan; WANG Tingting; CHEN Jiangyi; School of Mechanical and Power Engineering, Zhengzhou 450001, China

Keywords:: Automatic parking; Hybrid A * algorithm; Path planning; Quadratic programming; Automated driving

Abstract:: Aiming at the problem of long time and low success rate of automatic parking planning in restricted parking channels, an improved hybrid A * algorithm for path planning is proposed. Firstly, the parking path is divided into two parts: the forward pose adjustment section and the backward reverse parking section. Secondly, the collision risk cost is introduced into the hybrid A * algorithm, the node expansion method is improved, and the collision detection is carried out by judging whether the vehicle contour line intersects with the obstacle line, so as to improve the real-time and safety of the parking segment planning. Finally, the objective function is designed with the path length, smoothness and deviation as indexes, and the initial path is smoothed by quadratic programming to get the final path. The improved algorithm and the original algorithm are simulated by MATLAB. The results show that the improved algorithm can obtain a smooth and collision-free parking path under the constrained parking channel, and the search time is reduced by 23.8% compared with the hybrid A * algorithm, and the obtained path is safer and easier to track.