随机树
随机性
路径(计算)
算法
运动规划
趋同(经济学)
树(集合论)
计算机科学
数学优化
领域(数学)
路径长度
极限(数学)
数学
人工智能
统计
数学分析
计算机网络
纯数学
程序设计语言
经济
机器人
经济增长
标识
DOI:10.1109/irce53649.2021.9570910
摘要
Aiming at the problems of random sampling and low efficiency of the path planning algorithm of rapidly-exploring random trees (RRT), an improved algorithm combined with the artificial potential field method (APF) is proposed. This method first introduces a probability value in the expansion step of the random tree in the basic RRT algorithm to speed up the convergence of the random tree to the target node and adds a gravitational component to the random tree to guide the tree to grow towards the target point to speed up the search process. Establish a repulsion field around obstacles to limit the search area between obstacles and reduce the randomness of the path. In this research, in addition to the RRT algorithm, the RRT* algorithm will also be used for improvement. The simulation experiment results show that the proposed method is significantly optimized in time, path length and the number of iterations.
科研通智能强力驱动
Strongly Powered by AbleSci AI