Multi-Destination Path Planning Method Research of Mobile Robots Based on Goal of Passing through the Fewest Obstacles

Abstract

In order to effectively solve the inefficient path planning problem of mobile robots traveling in multiple destinations, a multi-destination global path planning algorithm is proposed based on the optimal obstacle value. A grid map is built to simulate the real working environment of mobile robots. Based on the rules of the live chess game in Go, the grid map is optimized and reconstructed. This grid of environment and the obstacle values of grid environment between each two destination points are obtained. Using the simulated annealing strategy, the optimization of multi-destination arrival sequence for the mobile robot is implemented by combining with the obstacle value between two destination points. The optimal mobile node of path planning is gained. According to the Q-learning algorithm, the parameters of the reward function are optimized to obtain the q value of the path. The optimal path of multiple destinations is acquired when mobile robots can pass through the fewest obstacles. The multi-destination path planning simulation of the mobile robot is implemented by MATLAB software (Natick, MA, USA, R2016b) under multiple working conditions. The Pareto numerical graph is obtained. According to comparing multi-destination global planning with single-destination path planning under the multiple working conditions, the length of path in multi-destination global planning is reduced by 22% compared with the average length of the single-destination path planning algorithm. The results show that the multi-destination global path planning method of the mobile robot based on the optimal obstacle value is reasonable and effective. Multi-destination path planning method proposed in this article is conducive to improve the terrain adaptability of mobile robots.