基于遗传算法的机器人路径规划的仿真研究  

Simulation Study of Robot Path Planning Based on Genetic Algorithm

作　　者：雷艳敏[1] 王帅[1] 

机构地区：[1]长春大学电子信息工程学院,长春130022

出　　处：《长春大学学报》2017年第4期1-3,32,共4页Journal of Changchun University

摘　　要：鉴于其他传统机器人路径规划算法(如栅格法、人工势场法、A*算法等)存在搜索效率低、易于陷入局部最优解的问题,提出一种新的遗传算法。本文中将最短路径、避免碰撞(安全性能)和平滑度三者相结合作为新的适应度函数进行遗传优化,并给三个要素分配一定的权值。仿真结果表明:该算法搜索效率更高且能获得更好的路径规划结果。In view of the problems in other traditional robot path planning algorithms( such as grid method,artificial potential field method and A* algorithm etc.),including that the search efficiency is low and it is easy to fall into local optimal solution,this paper presents a new genetic algorithm,which makes a genetic optimization by combining the shortest path,avoidance of collision( safety performance) and smoothness as a new fitness function,and allocates a certain weight for the three elements. Simulation results show that the proposed algorithm is more efficient and can obtain better path planning results.

关 键 词：遗传算法 适应度函数 路径规划 

分 类 号：TP24[自动化与计算机技术—检测技术与自动化装置]