Path Planning Algorithm Based on Improved RRT and Artificial Potential Field
Xiaodi Du, Ping Luo, Xiafu Lv · 2024
In addressing the issues of poor goal orientation, slow convergence speed, and lengthy search times associated with the Rapidly-exploring Random Tree (RRT) algorithm in robotic path planning, we propose an improved RRT algorithm. Firstly, a goal biasing strategy is employed to guide the random tree towards the target node, enhancing the algorithm’s goal orientation. Secondly, we define a target region where sampled points must lie; if a sample point falls outside this region, resampling is performed to restrict the sampling area. Finally, we incorporate an artificial potential field approach to improve obstacle avoidance and further bias the tree towards the target node during expansion. Experimental results demonstrate that the Improved RRT algorithm outperforms the P+Bias-RRT, T-RRT, T-RRT+APF, and RRT*algorithms in terms of path length, search time, and number of paths in both sparse and dense obstacle environments within a three-dimensional space. These findings validate the feasibility and effectiveness of the proposed method. This electronic document is a “live” template. The various components of your paper [title, text, heads, etc.] are already defined on the style sheet, as illustrated by the portions given in this document.