基于改进遗传算法的机器人路径规划方法  

Robot Path Planning Method Based on Improved Genetic Algorithm

作　　者：汤云峰 赵静 谢非[1,4] 李鑫煌 林智昌 刘益剑 Tang Yunfeng;Zhao Jing;Xie Fei;Li Xinhuang;Lin Zhichang;Liu Yijian(School of Electrical and Automation Engineering,Nanjing Normal University,Nanjing 210023,China;College of Automation and College of Artificial Intelligence,Nanjing University of Posts and Telecommunications,Nanjing 210023,China;Jiangsu Engineering Laboratory for Internet of Things and Intelligent Robotics,Nanjing 210023,China;Nanjing Zhongke Raycham Laser Technology Co.,Ltd.,Nanjing 210038,China)

机构地区：[1]南京师范大学电气与自动化工程学院,江苏南京210023 [2]南京邮电大学自动化学院、人工智能学院,江苏南京210023 [3]江苏省物联网智能机器人工程实验室,江苏南京210023 [4]南京中科煜宸激光技术有限公司,江苏南京210038

出　　处：《南京师范大学学报（工程技术版）》2021年第3期49-55,共7页Journal of Nanjing Normal University(Engineering and Technology Edition)

基　　金：国家重点研发计划项目(2017YFB1103200);江苏省科技成果转化项目(BA2020004);2020年江苏省省级工业和信息产业转型升级专项资金项目(JITC-2000AX0676-71);南京市优势产业关键技术突破招标项目(201803).

摘　　要：针对基本遗传算法在机器人路径规划中存在收敛速度慢、易陷入局部最优解的问题,提出一种改进的遗传算法.在适应度函数中增加带有惩罚项的平滑度函数;引入精英保留机制,保留每一代最优个体;自适应调整交叉概率和变异概率,使交叉概率和变异概率随进化次数变化而变化.利用MATLAB在两种障碍物地图中与其他两种算法进行仿真对比分析,实验结果表明,改进后的算法在路径规划的应用中有效减少了机器人的转弯次数,提高了逃离局部最优路径的能力,寻优能力更强.An improved genetic algorithm is proposed to solve the problem of slow convergence rate and easy to fall into the local optimal solution in robot path planning.The smoothness function with penalty term is added to the fitness func-tion.The elite retention mechanism is introduced to retain the optimal individual of each generation.The crossover proba-bility and mutation probability are adjusted adaptively so that they vary with the number of evolutions.MATLAB is used to simulate and compare the two obstacle maps with the other two algorithms.Experimental results show that the improved algorithm effectively reduces the number of turns of robots in path planning,improve the ability to escape from the local optimal path,and has a stronger ability to find the optimal solution.

关 键 词：机器人 遗传算法 平滑度函数 精英保留 路径规划 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] TP242[自动化与计算机技术—控制科学与工程]