求解机器人路径规划的改进萤火虫优化算法  

An Improved Glowworm Swarm Optimization for Mobile Robot Path Planning

作　　者：汤雅连 杨期江 TANG Yalian;YANG Qijiang(School of Internet Finance and Information Engineering,Guangdong University of Finance,Guangzhou 510520,China;School of Marine Engineering,Guangzhou Maritime University,Guangzhou 510725,China)

机构地区：[1]广东金融学院互联网金融与信息工程学院,广州510520 [2]广州航海学院轮机工程学院,广州510725

出　　处：《东莞理工学院学报》2019年第5期62-68,共7页Journal of Dongguan University of Technology

基　　金：国家自然科学基金资助项目(51375178);广东省教育厅项目(2017KQNCX145);广东省自然科学基金(2018A030310017);广州市科技计划(201904010133)

摘　　要：针对静态环境下的机器人路径规划问题,考虑到标准萤火虫优化算法(Glowworm Swarm Optimization,GSO)存在收敛速度较慢且收敛效果不佳的缺点,采用混沌初始化策略提高算法的寻优能力,并融合3-opt局部搜索策略以提高算法的局部搜索能力,提出了一种改进萤火虫优化算法(Improved Glowworm Swarm Optimization,IGSO),建立环境栅格图,并采用GA、GSO和IGSO对两种规模的栅格模型进行了仿真实验,仿真结果证明了IGSO算法在求解该模型时,在收敛速度和寻优结果两方面都优于GSO和GA,验证了提出算法具有极好的收敛性和可行性。Aiming at the path planning problem for robot in static environment, considering GSO(Glowworm Swarm Optimization) has the disadvantages of slow convergence speed and poor convergence effect, chaotic initialization strategy is introduced to improve the optimization ability, 3-opt is integrated to improve the local search capability, and an Improved Glowworm Swarm Optimization(IGSO) is proposed to establish environmental grid diagram. The simulation experiments of two scale grid models are carried out by using GA,GSO and IGSO.The results of simulation show that the IGSO algorithm is superior to GSO and GA in both the convergence speed and the optimization result when the model is solved by using GA, GSO and IGSO, and it is proved that the proposed algorithm has excellent convergence and feasibility.

关 键 词：路径规划 机器人 萤火虫优化算法 混沌初始化 3-opt 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]