基于改进BIT^(*)算法的机器人路径规划研究  

Research on robot path planning based on improved BIT^(*)

作　　者：张伯泉[1] 刘嘉栋 Zhang Boquan;Liu Jiadong(College of Computer,Guangdong University of Technology,Guangzhou 510006,China)

机构地区：[1]广东工业大学计算机学院,广州510006

出　　处：《计算机应用研究》2022年第1期59-63,共5页Application Research of Computers

基　　金：国家自然科学基金资助项目(62076074)。

摘　　要：针对BIT^(*)存在小样本下路径规划成功率低、冗余大样本下路径规划效率有待提高的问题,提出基于样本增量生成和概率随机几何图的BIT^(*)-SP算法,设计了生成样本和选择样本的启发式函数。实验结果表明,BIT^(*)-SP算法在小样本下路径规划成功率大幅度提高,且能更快找到初始解;在大样本下能用更短的时间找到一条优秀的路径,规划速度显著提升。该算法鲁棒性高,在简单及复杂环境中都能适用,性能高效。Aiming at the problems that BIT^(*)has low success rate of path planning under small samples and the efficiency of path planning under redundant large samples is not high enough,this paper proposed BIT^(*)-SP algorithm.Also,this paper designed the heuristic functions of generating samples and selecting samples.The experimental results show that BIT^(*)-SP algorithm greatly improves the success rate of path planning under small samples,and can find the initial solution faster.In the case of large samples,it can find an excellent path in a shorter time,and the planning speed is significantly improved.The algorithm that can be applied in both simple and complex environments has high robustness and high performance.

关 键 词：路径规划 移动机器人 BIT^(*) 采样算法 随机几何图 

分 类 号：TP242.6[自动化与计算机技术—检测技术与自动化装置]