基于混合灰狼算法的机器人路径规划  

Robot path planning using a hybrid grey wolf optimization algorithm

作　　者：王永琦[1] 江潇潇[1] WANG Yong-qi;JIANG Xiao-xiao(School of Electronic & Electrical Engineering,Shanghai University of Engineering,Shanghai 201620,China)

机构地区：[1]上海工程技术大学电子电气工程学院,上海201620

出　　处：《计算机工程与科学》2020年第7期1294-1301,共8页Computer Engineering & Science

基　　金：国家自然科学基金(61701295);上海市科委资助项目(19ZR1421700)。

摘　　要：针对传统灰狼算法GWO优化精度低、易陷入局部最优等不足,构建了混合灰狼算法HGWO,并将其应用于机器人路径规划RPP问题。HGWO算法采用反向学习方法构建初始灰狼种群,力求提升初始解的质量。同时,算法在个体位置更新方法中融入自身历史信息以指导种群进化,并借助精英反向学习策略探索当前种群优秀解的反向解空间,以增强算法的勘探能力。为确保路径规划的精度并降低求解难度,利用Spline样条插值法拟合路径曲线。最后,进行了函数优化和路径规划的对比实验,实验结果表明,HGWO算法具有良好的求解精度和稳健的鲁棒性。To overcome drawbacks of grey wolf optimization algorithm(GWO),such as low convergence accuracy and easily trapping in local optimum,this paper proposes a hybrid grey wolf optimization(HGWO)algorithm and applies it to the robot path planning(RPP)problem.Firstly,HGWO uses the opposition-based learning method to generate initial population with high qualities.Secondly,the algorithm incorporates its historical information into the individual update method,so as to guide the population evolution.Meanwhile,an elite opposition strategy is applied to explore the space of elite solutions in current population,in order to strengthen the algorithm's exploitation ability.In addition,HGWO adopts the spline interpolation technique to guarantee convergence accuracy and to reduce the optimization difficulty of RPP.Finally,a comparative experiment of function optimization and path planning is carried out.The experimental results show that HGWO has good solution accuracy and robustness.

关 键 词：机器人路径规划 灰狼算法 反向学习 粒子群算法 

分 类 号：TP318[自动化与计算机技术—计算机软件与理论]