基于改进粒子群蚁群融合算法的多AGV路径规划

Multi-AGVs path planning based on improved particle colony and ant colony fusion algorithm

为确定多自动导引小车(AGV)在复杂仓库环境下最优路径,本文提出了一种改进粒子群蚁群融合算法,用于多AGV路径规划。为了最小化所有AGV到达仓库中各自目的地的时间并且无碰撞,本文建立了以每个机器人路径最短、转弯角度最小以及与障碍物保持安全距离为约束的目标函数,采用所提的混合粒子群蚁群优化算法求解。仿真结果表明,在优化路径长度、安全性以及到达时间方面都优于改进的粒子群优化算法、蚁群优化算法。

In order to determine the optimal path of multiple automated guided vehicles(AGV)in a complex warehouse environment,this paper proposes a hybridization of an improved particle swarm optimization and ant colony optimization algorithm for path planning of multiple AGVs.In order to minimize the time for all AGVs to reach their respective destinations in the warehouse without collision,this paper establishes an objective function that takes the shortest path of each robot,the smallest turning angle,and the safe distance to obstacles as constraints.The proposed hybrid particle colony ant optimization algorithm is used to solve the problem.The simulation results show that it is better than the improved particle swarm optimization algorithm and ant colony optimization algorithm in terms of optimizing path length,safety and arrival time.