基于改进粒子群算法的自动引导小车路径规划

Path Planning of Automatic Guided Vehicle Based on Improved Particle Swarm Optimization Algorithm

针对传统粒子群算法易收敛到局部最优、搜索效率低等问题,提出一种改进算法并将其运用于自动引导小车(Automated Guided Vehicle, AGV)的路径规划问题中.首先,引入非线性递减惯性权重,调节不同时期粒子自身对寻优的影响.然后,对两个学习因子进行自适应改进,增强算法的局部和全局搜索能力.最后,提出考虑路径长度和平滑度的适应度函数,并通过干扰粒子速度来摆脱局部最优区域,提高搜寻路径的质量.在地图规模和障碍复杂度均不同的四种环境中进行多次实验,仿真结果表明,改进后算法相较于原算法,搜寻的平均路径缩短7.9%,平均迭代次数减少了20.2%,体现出更优越的路径规划能力.

Aiming at the problems of traditional particle swarm optimization algorithms easily converging to local optima and low search efficiency,an improved algorithm is proposed and applied to the path planning problem of Automated Guided Vehicle(AGV).Firstly,non-linear decreasing inertia weights are introduced to adjust the influence of particles themselves on optimization at different stages.Then,adaptive improvements are made to the two learning factors to enhance the algorithm's local and global search capabilities.Finally,a fitness function considering path length and smoothness is proposed,and local optimal regions are eliminated by interfering with particle velocity to improve the quality of the search path.Multiple experiments were conducted in four environments with different map sizes and obstacle complexity.Simulation results showed that the improved algorithm reduced the average search path by 7.9%and the average iteration times by 20.2%compared to the original algorithm,demonstrating superior path planning capabilities.