基于自适应粒子群算法的机器人路径规划  

Robot Path Planning Based on Adaptive Particle Swarm Optimization

作　　者：高岳林[1] 武少华 GAO Yuelin;WU Shaohua(Ningxia Key Laboratory of Intelligent Information and Big Data Processing,North Minzu University,Yinchuan 750021,China;School of Mathematics and Statistics,Ningxia University,Yinchuan 750021,China)

机构地区：[1]北方民族大学宁夏智能信息与大数据处理重点实验室,宁夏银川750021 [2]宁夏大学数学统计学院,宁夏银川750021

出　　处：《郑州大学学报（工学版）》2020年第4期46-51,共6页Journal of Zhengzhou University（Engineering Science）

基　　金：国家自然科学基金资助项目(61561001);北方民族大学重大专项(2019MSP003);宁夏高等教育一流学科建设资助项目(NXYLXK2017B09)

摘　　要：针对粒子群算法在解决机器人路径规划中存在的路径易陷入局部最优、路径搜索后期收敛速度慢以及路径不平滑的问题,提出了一种基于模拟退火的改进自适应粒子群算法,该算法结合了模拟退火算法和粒子群算法的优点,路径搜索前期路径搜索速度快,路径搜索过程中路径具有概率突跳的能力,能够有效地避免陷入局部最优路径,而且利用3次样条插值使路径平滑,路径搜索后期路径收敛精度也很高。仿真结果表明,该算法在不同障碍物模型中均能够快速找到最短的平滑路径,而且效果优于传统方法。Particle swarm optimization algorithm was easy fall into local optimum,the convergence speed was slow in the late path search,and the path was not smooth in the robot path planning.An improve simulated annealing adaptive particle swarm optimization algorithm was proposed.The algorithm combined the advantages of simulated annealing and particle swarm optimization.In the early stage of the algorithm route search was fast,and the algorithm had the ability of sudden jump in the path search process,which could effectively avoid falling into the local optimal path.Using cubic spline interpolation smooth the path,and the convergence precision of the late search path was high.The simulation results showed that the algorithm could quickly find the shortest smooth path in different obstacle models,and the path effect was better than the traditional method.

关 键 词：粒子群算法 模拟退火算法 机器人路径规划 三次样条插值 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]