基于改进灰狼优化算法的区域监测机器人路径规划

为了解决大任务量作业监测中机器人路径规划问题,提出了一种区域监测的机器人路径规划算法。模拟大任务量监测真实环境进行问题建模。针对传统灰狼优化算法求解模型时全局搜索能力差且易陷入局部最优解的问题,提出了一种改进的灰狼优化算法。引入Logistic混沌映射,以加强初始化种群的多样性;引入一种控制参数的自适应调整策略,以平衡灰狼优化算法的搜索能力和开发能力;引入静态加权平均权重策略,更新种群位置,加快收敛速度。将机器人载电量与路径长度短作为约束,引入K-means算法进行任务聚类,通过改进灰狼优化算法对模型进行离线求解以规划出路径,将大任务量监测作业自动转换成分时分步作业。实验结果表明:通过国际通用6个基准函数进行测试,改进的灰狼优化算法在收敛速度、搜索精度及稳定性上均有明显提高。通过50任务点与100任务点作业场景对机器人路径规划模型进行算法仿真,验证了算法的真实有效性,且任务量越大模型优越性越好,路径缩短比例越高。

Path Planning of Regional Monitoring Robot Based on Improved Grey Wolf Optimizer

n order to solve the problem of robot path planning in large task monitoring, an algorithm of robot path planning based on regional monitoring was proposed. Model for large task monitoring was established for simulate the real task environment.The improved grey wolf optimizer(IGWO) algorithm was used to solve the problem that the traditional grey wolf optimizer(GWO) algorithm has poor global search ability and is easy to fall into local optimal solution.Logistic chaotic mapping was introduced to enhance the diversity of initial population.An adaptive adjustment strategy of control parameters was introduced to balance the exploration and exploitation capabilities of grey wolf optimizer algorithm.Static weighted average strategy was introduced to update population position and accelerate convergence speed. Taking robot''s electric load and the short path length as constraint, K-means algorithm was introduced to cluster tasks, and IGWO algorithm is used to solve the model offline, to plan the route, and to automatically convert large task monitoring operations into time-division and step-by-step operations. Experiments show that the convergence speed, search accuracy and stability of IGWO algorithm are improved significantly by testing six international benchmark functions. The algorithm simulation of robot path planning model is carried out at 50 and 100 task points, which verifies the validity of the algorithm.The larger the task, the better the superiority of the model and the higher the proportion of path shortening.