基于改进遗传算法的移动机器人路径规划  

Mobile Robot Path Planning Based on Improved Genetic Algorithms

作　　者：陈亮[1] 陈君若[1] CHEN Liang;CHEN Jun-ruo(Faculty of Mechanical and Electrical Engineering,Kunming University of Science and Technology,Kunming 650500,China)

机构地区：[1]昆明理工大学机电工程学院,云南昆明650500

出　　处：《软件导刊》2019年第4期24-27,共4页Software Guide

摘　　要：经典遗传算法的缺陷在于搜索耗时较长,容易出现局部最优解。为解决该问题,引进适应度函数,并在设计遗传算子时,重新定义适应度函数。为尽量规避出现局部最优解,在不改变种群参数的条件下,通过新算法得到最短路径为31,搜索耗时均值为20.667m/s;与之对比,经典遗传算法两项数据分别是37和24.667m/s。因此,新算法可在更短时间内给出更佳解。The disadvantage of classical genetic algorithm is that the search process is time-consuming and easy to lead to local opti. mal solution. In this paper,the fitness function is introduced to solve this problem. When designing genetic operators,we redefine the fitness function. In order to avoid the possibility of local optimal solution,the shortest path obtained by the new algorithm is 31 and the average search time is 20.667m/s without changing the population parameters,while the two data of classical genetic algorithm are 37 and 24.667m/s,respectively. By comparing the two data,we can see that the new algorithm can give a better solution in a shorter time.

关 键 词：遗传算法 移动机器人 路径规划 交叉算子 变异算子 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]