摘要
粒子群算法由于搜索速度快、易于实现等优点,在处理环境复杂、约束条件多的无人机路径规划中,可克服传统算法寻优能力不足、计算量大、难于规划出最优路径的缺陷。但是传统粒子群算法存在早期收敛速度较快、后期易陷入局部最优等缺点,为解决此问题,本文通过设置随机惯性权重、增加扰动粒子更新机制对粒子群算法进行改进并应用于无人机路径规划。通过仿真实验证明,本文提出的改进PSO算法在算法稳定性、路径规划效果等方面均优于传统PSO算法。
Due to the complex environment of UAV path planning and many constraints,the traditional path search algorithm has insufficient optimization ability and a large amount of calculation,which makes it difficult to plan a better path.Because of the advantages of fast search speed and easy implementation,particle swarm optimization algorithm can get relatively better results when dealing with this kind of problems.However,the traditional particle swarm optimization algorithm has some shortcomings,such as fast convergence in the early stage and easy to fall into local optimum in the later stage.Therefore,the particle swarm optimization algorithm is improved by setting random inertia weight and adding disturbance particle updating mechanism and applied to UAV path planning.Simulation experiments show that the proposed improved PSO algorithm is better than the traditional PSO algorithm in terms of algorithm stability and path planning effect.
作者
叶梓菁
魏文红
李环
吴帅
YE Zijing;WEI Wenhong;LI Huan WU Shuai(School of Computer Science and Technology,Dongguan University of Technology,Dongguan 523808,China)
出处
《东莞理工学院学报》
2023年第3期18-23,共6页
Journal of Dongguan University of Technology
基金
国家科技创新2030-“新一代人工智能”重大项目(2018AAA0101301)
广东省普通高校“人工智能”重点领域专项项目(2019KZDZX1011)
东莞市社会发展科技项目(20211800904722)。
关键词
无人机
路径规划
随机惯性权重
扰动粒子
改进粒子群算法
UAV
path planning
random inertia weights
perturbed particles
improved particle swarm algorithm
