Improved path planning algorithm for mobile robots

Path planning is an NP-hard problem in road network environments. Considering that the existing path planning algorithms mainly have the problems of low smoothness and low search efficiency in generating paths in large-scale complex environments, an improved rapidly exploring random tree (RRT) algorithm is proposed in this paper. First, the grid method is applied to model the road network environment, and the RRT algorithm based on adjacency expansion is proposed to search the initial path. Then, the strategies of identifying paths and eliminating redundant paths are adopted, respectively, to further optimize the selected paths. Experimental results show that, compared with other path planning algorithms, our algorithm can achieve faster convergence speed, shorter search path, and better smoothness in a complex map of the environment.