基于改进动态窗口法的AGV路径规划  

AGV Path Planning Based on Improved Dynamic Window Method

作　　者：郑继强 汪伟 王汝佳 ZHENG Ji-qiang;WANG Wei;WANG Ru-jia(School of Mechanical Engineering,Jiangsu Institute of Technology,Changzhou Jiangsu 213000,China)

机构地区：[1]江苏理工学院机械工程学院,江苏常州213000

出　　处：《计算机仿真》2025年第1期167-171,286,共6页Computer Simulation

基　　金：国家自然科学基金资助项目(51805229)。

摘　　要：在复杂环境下,传统的动态窗口法(DWA)常常无法避免局部极值问题,导致生成的路径较长。因此,实现自动导航车的全局路径最优和在未知环境下实时避障的要求变得困难。为了解决上述问题,改进了传统DWA算法,将A*算法优化后的关键点作为临时目标点,并将这两种算法融合在一起,从而规划出一条基于全局最优的平滑曲线路径。在MATLAB中进行的对比仿真表明,改进后的算法能够实现全局路径最优和动态实时避障的要求,具有更加优秀的路径规划效果。In complex environments,the traditional dynamic window method(DWA)often fails to avoid local extremum problems,resulting in long resulting paths.As a result,it becomes difficult to achieve global path optimization for AGVs and real-time obstacle avoidance in unknown environments.In order to solve this problem,this paper improves the traditional DWA algorithm,takes the key point optimized by the A* algorithm as the temporary target point,and integrates the two algorithms together to plan a smooth curve path based on global optimum.Comparative simulation experiments in MATLAB show that the improved algorithm can achieve the requirements of global path optimization and dynamic real-time obstacle avoidance,and has a better path planning effect.

关 键 词：动态窗口法 路径规划 融合导航算法 

分 类 号：TP242[自动化与计算机技术—检测技术与自动化装置]