改进GSA算法在机器人路径规划中的应用研究  

Research on the Application of Improved GSA Algorithm in Robot Path Planning

作　　者：樊康生 杨光永[1] 徐天奇[1] FAN Kangsheng;YANG Guangyong;XU Tianqi(School of Electrical and Information Technology,Yunnan Mingzu University,Kunming 650500,China)

机构地区：[1]云南民族大学电气信息工程学院,昆明650500

出　　处：《组合机床与自动化加工技术》2024年第7期44-50,共7页Modular Machine Tool & Automatic Manufacturing Technique

基　　金：国家自然科学基金资助项目(61761049,61261022);云南省教育厅科学研究基金项目(2023Y0502);云南民族大学2022年硕士研究生科研创新基金项目(2022SKY006)。

摘　　要：针对万有引力搜索算法(GSA)收敛精度低和易陷入局部最优等问题,提出一种改进万有引力搜索算法(IGSA)。引入当前迭代次数t动态调整引力常数,以增强算法逃离局部最优能力;基于边界值改进粒子越界处理策略,以保留粒子多样性,提高算法收敛精度;同时,将中垂线算法用于游离粒子的位置更新,以加速游离粒子的收敛;为适应前述策略,提出自适应权重因子更新粒子位置策略,以提高算法的收敛速度。算法在10个基准测试函数上的结果表明,改进算法在稳定性、收敛速度和精度方面具有较大优势。最后将改进算法应用于机器人路径规划,并与其他智能仿生算法进行路径规划仿真对比实验,结果表明本文改进算法规划路径更短、拐点更少、搜索效率更高。To address the problems that the universal gravitational search algorithm(GSA)is low convergence accuracy and easy to fall into local optimum,this paper proposed an improved gravity search algorithm(IGSA).Firstly,in order to enhance the ability of the algorithm to escape from local optimum,the improved algorithm used the current iteration number t that is introduced to dynamically adjust the gravitational constant.Secondly,in order to preserve the particle diversity and improve the convergence accuracy of the algorithm,the improved algorithm based on based on the boundary value to improve the particle crossing processing strategy.Meanwhile,the improved algorithm used the mid-pipeline algorithm to update the position of the free particles to accelerate the convergence of the free particles.To adapt to the aforementioned strategy,the improved algorithm used the adaptive weight factor to update particle position strategy to improve the convergence speed.And the experimental results of the algorithm on 10 benchmark test functions show that the improved algorithm has greater advantages in terms of stability,convergence speed and accuracy.Finally,the improved algorithm is applied to robot path planning and compared with other intelligent bionic algorithm path planning through simulation experiments.The results show that the improved algorithm has shorter paths,fewer inflection points and higher search efficiency.

关 键 词：引力常数 中垂线算法 自适应权重因子 路径规划 

分 类 号：TH165[机械工程—机械制造及自动化] TG659[金属学及工艺—金属切削加工及机床]