融合IGJO与TEB算法的移动机器人路径规划  

Path planning for mobile robot integrating IGJO and TEB algorithms

作　　者：段震[1] 袁源[2] 李原[3] 李胜利 DUAN Zhen;YUAN Yuan;LI Yuan;LI Shengli(Taiyuan Normal University,Taiyuan 030006,China;Shanxi Polytechnic College,Taiyuan 030032,China;College of Artificial Intelligence,Xi’an Jiaotong University,Xi’an 710049,China)

机构地区：[1]太原师范学院,山西太原030006 [2]山西职业技术学院,山西太原030032 [3]西安交通大学人工智能学院,陕西西安710049

出　　处：《传感器与微系统》2025年第4期132-136,共5页Transducer and Microsystem Technologies

基　　金：国家自然科学基金资助项目(61976241)。

摘　　要：针对当前移动机器人路径规划中存在规划效率低、动态性差的问题,提出了一种融合改进金豺优化(IGJO)算法和时间弹性带(TEB)法的路径规划方法。首先,在IGJO算法种群初始化中,引入了Tent映射逆向学习,从而增强算法的寻优能力;其次,引入柯西突变,对最优解进行扰动和更新,从而提升算法的寻优精度。最后,引入TEB算法作为动态规划算法,帮助移动机器人避开移动障碍,同时结合IGJO算法,提升算法的综合规划性能。仿真结果表明:在不同仿真环境中IGJO-TEB算法相较其他算法在路径距离、运行时间两方面分别减短了1.37%~2.65%和10.26%~21.77%。真实场景实验果表明:本文算法能够在各类实际场景下完成路径规划任务,较其他算法具有显著的优越性。To solve the problems of low planning efficiency and poor dynamics in current mobileation robot path planning,a path planning method fuses improved golden jackal optimization(IGJO)algorithm and time elastic band(TEB)is proposed.Firstly,the tent mapping reverse learning is introduced in the population initialization of IGJO algorithm to enhance the optimizing ability of the algorithm.Secondly,Cauchy mutation is introduced to perturb and update the optimal solution to improve the optimizing precision of the algorithm.Finally,TEB algorithm is introduced as dynamic planning algorithm to help mobile robots avoid movement obstacles,and at the same time,IGJO algorithm is combined to improve the comprehensive planning performance of the algorithm.The simulation results show that the path distance and running time of IGJO-TEB algorithm are shortened by 1.37%~2.65%and 10.26%~21.77%,respectively,in different simulation environments.The results of real-scenarios experiments show that this algorithm can complete path planning tasks in various practical scenarios and has significant advantages over other algorithms.

关 键 词：金豺优化算法 时间弹性带算法 路径规划 移动机器人 

分 类 号：TP242[自动化与计算机技术—检测技术与自动化装置]