改进麻雀搜索算法的轮式机器人路径规划  

Path Planning of Wheeled Robot with Improved Sparrow Search Algorithm

作　　者：陈旭东[1,2] 杨光永 徐天奇[1,2] 蔡艳[1,2] CHEN Xudong;YANG Guangyong;XU Tianqi;CAI Yan(School of Electrical and Information Engineering,Yunnan Minzu University,Kunming 650000,China;Yunnan Key Laboratory of Unmanned Autonomous System,Yunnan Minzu University,Kunming 650000,China)

机构地区：[1]云南民族大学电气信息工程学院,昆明650000 [2]云南民族大学云南省无人自主系统重点实验室,昆明650000

出　　处：《组合机床与自动化加工技术》2024年第9期50-56,共7页Modular Machine Tool & Automatic Manufacturing Technique

基　　金：国家自然科学基金项目(61761049,61261022)。

摘　　要：针对传统麻雀搜索算法(sparrow search algorithm,SSA)在轮式机器人路径规划应用中易陷入局部最优使得规划路径较长以及算法后期容易陷入早熟等问题,提出一种改进麻雀搜索算法(improved sparrow search algorithm,ISSA)应用在轮式机器人路径规划中。首先,在算法初期初始化种群时利用Logistic混沌提高初始种群的多样性;其次,将线性动态惯性权重调整方法引入到发现者位置更新中,使得算法的全局搜索能力以及收敛速度得以提升;然后,在跟随者位置更新方法中结合中垂线算法(midperpendicular algorithm,MA)使跟随者快速精准地向种群适应度最高的个体靠拢;最后,在算法后期结合最优爆炸粒子策略与反向学习策略在最优解附近产生扰动,防止算法后期陷入局部最优解。并且在机器人路径规划应用中将全局最优解再次进行局部搜索来提高机器人的路径规划能力。仿真结果表明,ISSA应用在路径规划中,其路径长度、寻优速度以及迭代次数方面均有显著提高。Aiming at the problems such as the traditional sparrow search algorithm is easy to fall into the local optimal in the path planning application of wheeled robot,which leads to the long planned path and the algorithm is easy to fall into the precocity in the later stage,an improved sparrow search algorithm is proposed for the path planning of wheeled robot.Firstly,Logistic chaos is used to improve the diversity of initial population when initializing the initial population.Secondly,the linear dynamic inertial weight adjustment method is introduced into the discoverer position update,which improves the global search ability and convergence speed of the algorithm.Then,the midvertical algorithm is combined with the follower position updating method to make the follower get closer to the individual with the highest fitness of population quickly and accurately.Finally,in the late stage of the algorithm,the optimal explosive particle strategy and reverse learning strategy are combined to generate disturbances near the optimal solution,so as to prevent the algorithm from falling into the local optimal solution.In the application of robot path planning,the global optimal solution is searched locally again to improve the ability of robot path planning.The simulation results show that ISSA application in path planning has significantly improved the path length,optimization speed and iteration times.

关 键 词：路径规划 Logistic混沌 中垂线算法 爆炸粒子 反向学习 全局最优解局部搜索 

分 类 号：TH165[机械工程—机械制造及自动化] TG659[金属学及工艺—金属切削加工及机床]