摘要
为解决自适应遗传算法应用于机器人路径规划时存在的收敛速度慢和易陷入局部最优的问题,提出了一种改进的自适应遗传路径规划方法。该方法引入转弯角评价指标,提高了路径规划目标函数的实用性;优化交叉概率和变异概率的自适应调整策略,增加灾变操作和逆转操作,有效提升了路径规划的全局寻优能力和收敛速度。仿真实验结果表明,该算法与传统自适应遗传算法相比,全局寻优能力更强,需要更少的迭代次数,且路径规划性能优于其它改进算法。
In order to solve the problems of slow convergence and easy to fall into local optimization when adaptive genetic algorithm is applied to robot path planning,an improved adaptive genetic path planning method is proposed.This method introduces the evaluation index of turning angle,which improves the practicability of the objective function of path planning.The adaptive adjustment strategy of crossover probability and mutation probability is optimized,and catastrophe operation and reversal operation are added,which effectively improves the global optimization ability and convergence speed of path planning.Simulation results show that compared with the traditional adaptive genetic algorithm,the algorithm has stronger global optimization ability and needs less iterations.In addition,the path planning performance of the proposed method is also better than other improved algorithms.
作者
宋俊福
徐炳辉
张岩
李建华
卫永刚
SONG Jun-fu;XU Bing-hui;ZHANG Yan;LI Jian-hua;WEI Yong-gang(Guo Neng Shuo Huang Railway Development Co.,Ltd.,Xinzhou 034100,Shanxi Province,China)
出处
《信息技术》
2022年第11期49-53,60,共6页
Information Technology
基金
国家能源集团科技创新项目(SHGF1739)。
关键词
机器人
路径规划
自适应遗传算法
灾变操作
逆转操作
robot
path planning
adaptive genetic algorithm
catastrophic operation
reverse operation
