改进灰狼优化算法的草坪修剪机器人路径规划

Path Planning of lawn Mowing Robot Based on Improved Grey Wolf Algorithm

为解决传统灰狼算法(GWO)用于全覆盖路径规划草坪修剪作业时易陷入局部最优、收敛速度慢、迭代次数高、除草效率低等问题,提出了启发式混沌算子灰狼优化算法(CGWO)。通过对GWO算法融入启发式思想与Tent混沌映射后,加入自适应的参数调节策略,调节加速因子及不同控制参数以增加搜索过程中的随机性,帮助算法跳出局部最优解,获得更好的全局搜索能力。仿真分析发现:改进后的灰狼优化算法即CGWO算法比GWO、PSO(粒子群算法)算法的路径成本、迭代次数、耗时更优,且路径更平滑。在3种草坪环境下,进行实车试验。结果表明:CGWO算法提高了全覆盖效率和除草效率,试验结果优于GWO和PSO算法。

To solve the problems of traditional grey wolf algorithm(GWO)being prone to local optima,slow convergence speed,high iteration times,and low weed removal efficiency when used for lawn trimming operations in full coverage path planning,a heuristic chaos operator grey wolf optimization algorithm(CGWO)is proposed.Based on the tent chaotic mapping,the CGWO is established by an adaptive parameter adjustment strategy in order to adjust the acceleration factor and various control parameters.This strategy enhances randomness in the search process,aiding the algorithm in escaping local optima and improving global search capability.Through simulation analysis,it was found that path cost,iteration times and time consumption of the CGWO algorithm is less than the GWO and particle swarm optimization(PSO)algorithms.Additionally,the generated path is smoother.Real vehicle experiments conducted in three types of lawn environments demonstrate that the CGWO algorithm is more effective than GWO and PSO algorithms.