基于改进灰狼算法的物流机器人运动路径规划方法

Motion Path Planning Method for Logistics Robots Based on Improved Grey Wolf Algorithm

物联网信息技术的发展使得物流机器人在当前运动路径规划中面临局部极值陷阱、算法收敛等问题,且加之传统运动路径规划手段难以满足复杂多变的物流环境,因此探寻积极有效的运动规划手段迫在眉睫;基于此,研究借助灰狼优化算法进行全局路径规划和混合路径分析,并引入协同量子、改进人工势场进行改进,实现该算法收敛因子的更新和交叉策略的执行;对物流机器人进行仿真结果分析,结果表明,该算法在测试函数上表现出较好的收敛性,且在单个障碍物结果中的搜索路径长度减少率在5%左右,平均成本消耗为23.65,能较好检测到动态障碍物并有效跳出了局部极小值陷阱;且其在动态环境下的运行时间缩短了46.37%,寻优和避障性能较好;研究提出的路径规划算法能有效为物流业的发展以及自动化调度提供借鉴思路和价值。

The development of information technology in Internet of Things(IoT)has made logistics robots face problems such as local extreme traps and algorithm convergence in current motion path planning.In addition,traditional motion path planning methods are difficult to meet the requirements of complex and changing logistics environments.Therefore,it is urgent to explore active and effective motion planning methods.Based on this,the grey wolf optimization algorithm is used to plan the global path and analyze the mixed path,and introduces the collaborative quantum and improved artificial potential fields,achieving the update of the convergence factor of the algorithm and the execution of crossover strategies.Through simulating and analyzing logistics robots,the results show that the algorithm has a good convergence in test function,and the search path length in a single obstacle is reduced by about 5%,with an average cost consumption of 23.65,which can better detect dynamic obstacles and effectively escape local minimum traps.And its running time in dynamic environments is shortened by 46.37%,with good optimization and obstacle avoidance performance.The proposed path planning algorithm can effectively provide a reference and value for the development of logistics industry and automated scheduling.