大连民族大学学报

针对自动导引车（Automated Guided Vehicle,AGV）在工厂环境中协同作业的无碰撞路径规划需求，提出一种基于改进A*算法和时间窗检测相结合的多AGV路径规划方法。针对A*算法对启发函数选择和优化要求较高的问题，融合动态调节启发式权重与方向一致性奖励机制，为单个AGV生成一种转弯次数最优的初始路径。为有效规避多机路径冲突，提高系统协同作业效率，使用结合优先级策略的时空维度时间窗检测机制。通过python进行仿真试验，验证所提方法的有效性。结果表明，该算法解决了传统A*算法转弯次数多的问题，并能有效实现多AGV无冲突的路径规划，使多个AGV更好地协同工作，实现高效和安全的路径规划。

Aiming at the collision-free path planning needs of Automated Guided Vehicles(AGVs) coordination in factory environments, a multi-AGV path planning method based on the combination of improved A* algorithm and time window detection is proposed. Aiming at the problem that the A* algorithm has high requirements for the selection and optimization of heuristic functions, it integrates dynamically adjusted heuristic weights with a direction consistency reward mechanism to generate an initial path with the optimal number of turns for a single AGV. In order to effectively circumvent multi-machine path conflicts and improve the efficiency of cooperative operation of the system, a spatio-temporal dimension time window detection mechanism combined with a prioritization strategy is used. Finally, simulation experiments are conducted via python to verify the effectiveness of the proposed method. The results show that the algorithm solves the problem of high number of turns brought by the traditional A* algorithm and effectively realizes multi-AGV conflict-free path planning, which enables multiple AGVs to work collaboratively better and realize efficient and safe path planning.