A Study of Improved Global Path Planning Algorithm for Parking Robot Based on ROS

Abstract

This paper proposes an improved global path planning algorithm to generate the optimal global path that satisfies the kinematic constraints of parking robots. The estimation function is improved through BP neural network, which improves the planning efficiency of finding the shortest path. Improve the drivability of the planned route by setting up the prohibited area and the route backtracking. A simulation platform is built based on ROS, and the path planning effect of the traditional A* algorithm is compared with the effect of the improved global path planning algorithm. The results show that the improved algorithm has a shorter path length and better drivability. The overall deviation of the simulated trajectory driving along this path is small. The improved algorithm is used to conduct multiple terminal path planning experiments. The results show that the total length of the path generated by the algorithm is close to the global optimum, the path is smooth and easy to track.