改进瞪羚算法在机器人路径规划中的应用研究  

Research on the Application of Improved Gazelle Optimization Algorithm in Robot Path Planning

作　　者：樊康生 杨光永[1] 徐天奇[1] FAN Kangsheng;YANG Guangyong;XU Tianqi(School of Electrical and Information Technology,Yunnan Mingzu University,Kunming 650500,China)

机构地区：[1]云南民族大学电气信息工程学院,昆明650500

出　　处：《组合机床与自动化加工技术》2024年第10期50-56,62,共8页Modular Machine Tool & Automatic Manufacturing Technique

基　　金：国家自然科学基金资助项目(61761049,61261022);2023年度云南省教育厅科学研究基金项目(2023Y0502);云南民族大学2022年硕士研究生科研创新基金项目(2022SKY006)。

摘　　要：针对瞪羚优化算法(gazelle optimization algorithm, GOA)收敛速度慢和易陷入局部最优等问题,提出一种改进瞪羚优化算法(IGOA)。首先,将Logistic混沌映射用于种群初始化,增加粒子多样性以提高算法逃离局部最优能力;其次,以迭代次数t为系统参数构造正余弦扰动算子和跳跃步长权重因子用于更新粒子位置,以加快算法收敛速度;同时,改进捕食者累积效应表达式以提高算法收敛精度;最后,基于粒子上下边界改进越界粒子位置,以提高算法收敛精度。将改进算法与传统GOA算法以及4个先进算法在8个标准测试函数上进行对比实验,结果表明改进算法在收敛精度和收敛速度方面优势明显。将改进算法用于机器人路径规划,结果表明改进算法搜索效率更高、收敛速度更快和规划路径更短。To address the problems that the gazelle optimization algorithm(GOA)is slow rate of convergence and easy to fall into local optimum,this paper proposed an improved gazelle optimization algorithm(IGOA).Firstly,in order to Increase particle diversity to improve algorithm′s ability to escape local optima,the improved algorithm used the Logistic chaos mapping for population initialization.Secondly,in order to speed up the convergence of the algorithm,the improved algorithm used the t of iterations to as the system parameter to construct the sine-cosine perturbation operator and the jump step weighting factor to update the particle positions.Also,the improved algorithm improved the expression of predator cumulative effect to improve the convergence accuracy of the algorithm.And finally,in order to improve the convergence accuracy of the algorithm,the improved algorithm improved the position of out-of-bounds particles based on their upper and lower boundaries.The improved algorithm compared with the traditional GOA algorithm and four advanced algorithms on eight standard test functions.The results show that the improved algorithm has significant advantages in terms of convergence accuracy and convergence speed.Using improved algorithms for robot path planning,the results show that the improved algorithm has higher search efficiency,faster convergence and shorter planning path.

关 键 词：瞪羚优化算法 混沌映射 扰动算子 路径规划 

分 类 号：TH112[机械工程—机械设计及理论] TG659[金属学及工艺—金属切削加工及机床]