摘要
针对在无人机路径规划中粒子群算法(Particle Swarm Optimization,PSO)容易过早收敛的问题,提出了一种改进粒子群混合优化算法(Improved Particle Swarm Optimization,IPSO)。IPSO算法在考虑路径长度代价、高度代价、碰撞代价以及转弯角与爬升角代价的基础上构建适应度函数,将粒子群算法与遗传算法以及和声搜索算法相结合,同时引入引力搜索算法中的加速度思想,设置动态更新的学习因子与凹函数模型的动态惯性权重。仿真结果表明,对比传统的方法,IPSO算法在路径长度,收敛速度,平均消耗时间以及稳定性等方面都具有显著的优势。
An improved PSO algorithm was tendered to solve the problem of premature convergence of particle swarm optimization(PSO)algorithm in UAV path planning.Based on the cost of path length,height,collision,turning angle and climbing angle,the function of fitness is structured.The PSO algorithm is combined with genetic algorithm(GA)and harmonic search(HS)algorithm,and the concept of acceleration was introduced in the gravity search algorithm.And Dynamic updating learning factor and dynamic inertia weight of the concave function model are set.The simulation results indicated that compared with the traditional way,the progressed algorithm had remarkable benefits in path length,convergence speed,average consumption time and stability.
作者
唐文倩
徐海芹
刘洋
TANG Wen-qian;XU Hai-qin;LIU Yang(College of Information Sciences and Technology,Donghua University,Shanghai 201620,China)
出处
《青岛大学学报（自然科学版）》
CAS
2023年第3期57-63,共7页
Journal of Qingdao University(Natural Science Edition)
基金
国家自然科学基金(批准号:62241503)资助
上海市自然科学基金面上项目(批准号:22ZR1401400)资助。
关键词
无人机
三维路径规划
粒子群混合优化算法
适应度函数
UAV
three-dimensional path planning
particle swarm hybrid optimization algorithm
function of fitness
