基于增强型果蝇算法的智能车移动路径规划  

Path Planning of Automated Guided Vehicle Based on Improved Beetle Antennae Search

作　　者：陈中[1] 陈克伟 张前图 刘瑶华[3] CHEN Zhong;CHEN Kewei;ZHANG Qiantu;LIU Yaohua(School of Electrical Engineering,Yancheng Institute of Technology,Yancheng 224051,China;Department of Arms and Control,Army Academy of Armored Forces,Beijing 100072,China;Fifth Military Represent Office of Chongqing District,Chongqing 404000,China)

机构地区：[1]盐城工学院电气工程学院,江苏盐城224051 [2]陆军装甲兵学院兵器与控制系,北京100072 [3]中国人民解放军驻重庆地区第五军代室,重庆404000

出　　处：《兵器装备工程学报》2021年第10期199-204,共6页Journal of Ordnance Equipment Engineering

摘　　要：针对果蝇算法(FOA)存在易陷入局部最优、后期搜索精度不高等问题,提出基于增强型果蝇算法(EFOA)的智能车移动路径规划方法。相比于FOA,EFOA改变了果蝇个体的位置更新方式,即在寻找到当次迭代中最优果蝇个体所在的位置后,其余果蝇个体并不直接聚集到该位置,而是缓慢向当次迭代中最优个体所在的位置靠近,增强了果蝇种群的多样性。3种测试函数的对比分析结果表明:EFOA的寻优进度、寻优速度和寻优稳定性比FOA更优;3种智能车不同行驶环境的路径规划实例表明:EFOA在耗时较少的情况下,可获得比其他几种方法更短的移动路径。In order to improve the path planning effect of the intelligent vehicle effectively,and aiming at the problems that the Fruit Fly Optimization Algorithm(FOA)was easy to fall into local optimum and the late search accuracy is not high,a path planning method of intelligent vehicle based on Enhanced Fruit Fly Optimization Algorithm(EFOA)was proposed on the basis of the study of FOA.Compared with FOA,EFOA changed the location updating mode of fruit fly individual,that is,after finding the optimal location of fruit fly individual in this iteration,the remaining individuals did not gather directly to the location,but slowly approached the location of the optimal individual in this iteration,thus enhancing the diversity of fruit fly group.The comparative analysis results of the three test functions show that EFOA is better than FOA in the optimization progress,optimization speed and optimization stability.The path planning examples of intelligent vehicles in three different driving environments show that EFOA can obtain a shorter moving path than other methods under the condition of less time-consuming.

关 键 词：果蝇算法 增强 智能车 路径规划 

分 类 号：TH165.3[机械工程—机械制造及自动化]