改进遗传算法在移动机器人路径规划中的应用研究  

Research on Mobile Robot Path Planning by using Improved Genetic Algorithm

作　　者：王雷[1] 李明[1] 蔡劲草 刘志虎[1] 

机构地区：[1]安徽工程大学机械与汽车工程学院,安徽芜湖241000

出　　处：《机械科学与技术》2017年第5期711-716,共6页Mechanical Science and Technology for Aerospace Engineering

基　　金：国家自然科学基金项目(51305001);安徽省自然科学基金项目(1708085ME129);安徽省高校优秀青年人才支持计划重点项目(gxyqZD2016125)资助

摘　　要：针对基本遗传算法解决移动机器人路径规划问题存在收敛速度慢等不足,对遗传算法进行了改进,提出了一种改进自适应遗传算法。根据进化过程中个体适应度值的大小自动调节交叉概率和变异概率,从而使算法能够跳出局部最优解,克服早熟的缺点。同时采用栅格法对机器人工作空间进行建模。对移动机器人路径规划进行仿真实验,对比结果表明:该改进的遗传算法是有效可行的,能够有效的提高机器人路径规划的质量。In order to deal with the problem such as slow convergence speed etc. of basic genetic algorithm formobile robot path planning, an improved adaptive genetic algorithm is proposed. This algorithm can adjust thecrossover probability and mutation probability automatically according to the change of the fitness value in theevolutionary process, thus to avoid falling into local optimal solution and overcome the shortcoming of prematurity.Meanwhile, the grid method is used to model the robot working space. The simulation for mobile robot path planningis performed and the comparison results show that this method is valid and the quality of robot path planning can beimproved effectively by using the proposed genetic algorithm.

关 键 词：路径规划 移动机器人 自适应遗传算法 栅格法 

分 类 号：TP242[自动化与计算机技术—检测技术与自动化装置]