全文下载： 
20240613.pdf
文章编号： 1672-6987（2024）06-0101-06； DOI： 10.16351/j.1672-6987.2024.06.013
李冰鑫， 孟雨倩， 曹梦龙*(青岛科技大学 自动化与电子工程学院， 山东 青岛 266061)
摘要： 针对标准萤火虫(glowworm swarm optimization,GSO)算法进行全局路径规划易陷入局部最优、收敛速度过慢和搜索路径过长等生物智能算法的一般性问题，提出一种混沌优化自适应萤火虫(chaos-optimized adaptive glowworm swarm optimization,CAGSO)路径规划方法算法。该方法中，首先采用立方映射产生的混沌序列对萤火虫的初始位置进行初始化，提高全局路径规划的全局搜索能力；其次，在混沌优化策略的基础上，通过调节萤火虫搜索步长，提高算法的运行速度和搜索精度。最后，在MATLAB上模拟室内复杂多变的工作环境，对CAGSO算法、GSO算法和粒子群(particle swarm optimization,PSO)算法进行对比验证与算法性能分析，实验结果表明改进的算法缩短了全局路径的长度，减少了收敛时间，解决了标准萤火虫算法易陷于局部最优问题。
关键词： 萤火虫算法； 混沌优化； 调节步长； 路径规划
中图分类号： TQ 207+.2文献标志码： A
引用格式： 李冰鑫， 孟雨倩， 曹梦龙. 基于混沌优化自适应萤火虫算法的室内机器人路径规划方法［J］. 青岛科技大学学报(自然科学版), 2024, 45(6): 101-106.
LI Bingxin, MENG Yuqian, CAO Menglong. Chaos-optimized adaptive glowworm swarm optimization for indoor robot path planning［J］. Journal of Qingdao University of Science and Technology（Natural Science Edition), 2024， 45（6）： 101-106.
Chaos-Optimized Adaptive Glowworm Swarm Optimization for
Indoor Robot Path Planning
LI Bingxin, MENG Yuqian, CAO Menglong
(College of Automation and Electronic Engineering, Qingdao University of Science and Technology, Qingdao 266061, China)
Abstract: To address the general problems of biological intelligence algorithms such as the standard Glowworm Swarm Optimization (GSO) algorithm for global path planning, which tends to fall into local optimality, slow convergence and long search paths, a new method for robot path planning, the Chaos-optimized Adaptive Glowworm Swarm Optimization (CAGSO) algorithm, is proposed. In this method, firstly, the initial position of the firefly is initialized using a chaotic sequence generated by cubic mapping to improve the global search capability of global path planning; secondly, changing the firefly search step size, the algorithm's operation speed and search accuracy are enhanced based on the chaotic optimization technique. Finally, by simulating the complex and changeable working environment in the laboratory on MATLAB, the CAGSO algorithm, GSO algorithm and Particle Swarm Optimization (PSO) algorithm are compared and verified and the algorithm performance is analyzed. The experimental results show that the improved algorithm shortens the length of the global path, reduces the convergence time and solves the problem that the standard glowworm swarm optimization algorithm tends to get trapped in local optima.
Key words: glowworm swarm optimization algorithm; chaos optimization; step size adjustment; path planning
收稿日期： 2023-12-07
基金项目： 山东省重点研发计划项目（2024TSGC0278）.
作者简介： 李冰鑫(1997—),女,硕士研究生.*通信联系人.
