Heuristic RRT algorithm based on collision-free channels for manipulator path planning
YAO Boliang
LIU Fang
SUN Teng
YANG Jiyi
Abstract：[Objective]Aiming at the problems of traditional rapidly-exploring random tree(RRT)algorithm in multi-degree-of-freedom manipulator path planning,such as the unguided search and the poor path quality,a heuristic RRT algorithm based on collision-free channels was proposed.[Methods]Obtaining collision-free channels in the workspace through a sphere-based wavefront expansion algorithm(Wavefront algorithm),setting up path targeting points,and utilizing the environmental information to inspire the tree growth instead of the traditional blind searching;the random point sampling function was improved,and the multi-dimensional Gaussian distribution model and Gaussian mixture model(GMM)of the path targeting points in the joint space corresponding to the joint angles were used as the heuristic terms,respectively,to guide the end-effector of the manipulator to direct the fast and stable expansion in the collision-free channel.[Results]Simulation and analysis results show that the heuristic RRT algorithm reduces the path search time and the number of iterations,and the path length is shortened by 39.32%compared with the traditional RRT algorithm.
Keywords：Path planningManipulatorRapidly-exploring random treeCollision-free channelHeuristic samplingGaussian distribution
Publication Date：2025-11-15
Online Publishing Date：2026-09-12(First online date of this platform, not the publication date of the document)
Pages：7( 57-62,95 )