基于改进狼群算法的AGV路径规划  

AGV path planning based on improved wolf pack algorithm

作　　者：程俊[1,2] 董学平 张志军[1,2] CHENG Jun;DONG Xueping;ZHANG Zhijun(School of Electrical Engineering and Automation,Hefei University of Technology,Hefei 230009,China;Engineering Technology Research Center of Industrial Automation of Anhui Province,Hefei 230009,China)

机构地区：[1]合肥工业大学电气与自动化工程学院,安徽合肥230009 [2]工业自动化安徽省工程技术研究中心,安徽合肥230009

出　　处：《合肥工业大学学报（自然科学版）》2023年第7期879-885,共7页Journal of Hefei University of Technology：Natural Science

基　　金：安徽省自然科学基金资助项目(2108085MF221)。

摘　　要：针对自动引导小车(automated guided vehicle,AGV)全局最优路径的求解问题,文章利用栅格法对环境进行建模,提出一种基于改进狼群算法(improved wolf pack algorithm,IWPA)的AGV路径规划方法。该算法采用混沌映射形成初始种群,增加种群多样性;对探狼游走行为引入随机策略,扩大搜索范围;对头狼的选择引入Metropolis准则,增强算法跳出局部最优能力;改进猛狼奔袭策略,提高算法后期寻优效率。通过8个典型测试函数的仿真实验结果表明,改进的算法在寻优速度和精度上均有较大的提高。将改进的算法应用于路径规划仿真实验,结果表明,相比于传统狼群算法,改进的狼群算法在解决AGV路径规划问题上更有效。In order to obtain the global optimal path of automated guided vehicle(AGV),an AGV path planning method based on improved wolf pack algorithm(IWPA)is proposed.Firstly,the raster method is used to model the environment.Then,an IWPA is proposed,which uses chaotic mapping to form the initial population to increase population diversity.The random strategy is introduced to expand the search range of scouting wolf.Metropolis criterion is introduced to select the leader wolf to enhance the ability of the algorithm to jump out of local optimum.The wolf attack strategy is improved to enhance the optimization efficiency of the algorithm.The simulation results of eight typical test functions show that the improved algorithm has better convergence speed and accuracy.Finally,the improved algorithm is applied to path planning simulation experiments,and the results show that the improved algorithm is more effective than the traditional WPA in solving AGV path planning problems.

关 键 词：狼群算法(WPA) 路径规划 自动引导小车(AGV) 混沌映射 METROPOLIS准则 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] TP242[自动化与计算机技术—控制科学与工程]