东北大学学报（自然科学版）

东北大学学报（自然科学版） ›› 2023, Vol. 44 ›› Issue (8): 1065-1071.DOI: 10.12068/j.issn.1005-3026.2023.08.001

• 信息与控制 •    下一篇

改进鲸鱼优化算法在机器人路径规划中的应用

赵俊涛1， 罗小川1， 刘俊秘2   

  1. (1.东北大学 信息科学与工程学院， 辽宁 沈阳110819； 2.河南城建学院 电气与控制工程学院， 河南 平顶山467000)
  • 发布日期:2023-08-15
  • 通讯作者: 赵俊涛
  • 作者简介:赵俊涛(1990-)，男，河北沧州人，东北大学博士研究生； 罗小川(1974-)，男，四川西充人，东北大学教授，博士生导师.
  • 基金资助:
    国家重点研发计划项目(2019YFB1705002)； 辽宁省“兴辽英才计划”项目(XLYC2002041).

Application of Improved Whale Optimization Algorithm in Robot Path Planning

ZHAO Jun-tao1， LUO Xiao-chuan1， LIU Jun-mi2   

  1. 1. School of Information Science & Engineering， Northeastern University， Shenyang 110819， China; 2. School of Electrical and Control Engineering， Henan University of Urban Construction， Pingdingshan 467000， China.
  • Published:2023-08-15
  • Contact: LUO Xiao-chuan
  • About author:-
  • Supported by:
    -

RichHTML

121

PDF (PC)

553

摘要： 针对使用标准鲸鱼优化算法求解机器人路径规划问题时，存在收敛速度慢且容易陷入局部最优值的问题，提出混合粒子群优化算法与自适应权重策略的改进鲸鱼优化算法(PSO-AWOA).通过在标准PSO和WOA算法中引入非线性惯性权重因子，使种群进化过程中自适应更新权重，提高了算法的全局探索能力和收敛速度，同时通过将寻优能力较强的PSO算法引入WOA算法的开发阶段，保证迭代的新解优于原始解，增强了算法跳出局部最优的能力.最后，将PSO-AWOA算法应用到的栅格地图仿真环境中进行机器人最佳路径求解.通过对比给定算法的耗时、规划路径长度以及拐点数，结果表明，提出的PSO-AWOA算法在优化精度和收敛速度上优于文中给定的其他算法，验证了改进算法的有效性.

关键词: 混合优化算法；粒子群优化；鲸鱼优化算法；自适应权重；路径规划

Abstract: To solve the problem of slow convergence and susceptibility to local optima in solving robot path planning problems using the standard whale optimization algorithm (WOA)， an improved whale optimization algorithm (PSO-AWOA) with hybrid particle swarm algorithm and adaptive weights strategy is proposed. By introducing nonlinear inertia weight factors into the standard PSO and WOA algorithms and adaptively updating the weights during the population evolution， the global exploration ability and convergence speed are improved. Meanwhile， by introducing the PSO algorithm with strong optimization-seeking ability into the exploitation stage of the WOA algorithm， the new solution of iteration is guaranteed to be better than the original solution， which enhances the ability to jump out of the local optima. Finally， the PSO-AWOA algorithm is applied to generate the optimal path for the robot in the grid map simulation environment. The results show that the proposed PSO-AWOA algorithm outperforms in terms of optimization accuracy and convergence speed by comparing the time consumption， planning path length， and the number of turning points of the algorithms given， which verifies the effectiveness of the improved algorithm.

Key words: hybrid optimization algorithm; particle swarm optimization (PSO); whale optimization algorithm (WOA); adaptive weight; path planning

中图分类号: