AGV path planning algorithm based on improved Dijkstra algorithm

In intelligent warehouse management, path planning for Automatic Guided Vehicles (AGV) is a crucial technology. Traditional A* algorithms struggle to adapt to complex and dynamic warehousing environments because they use static heuristic functions. This study introduces an A* algorithm that incorporates dynamic heuristics, adjusting the heuristic function in real-time to respond to environmental changes. Experimental results demonstrate that the improved algorithm significantly outperforms traditional A* and Dijkstra algorithms in terms of path quality, search efficiency, and adaptability. The dynamic heuristic A* algorithm reduced path cost by an average of 20%, decreased the number of nodes expanded by 15%, and shortened running time by 7.5 milliseconds. This approach is particularly suited for complex warehouse environments requiring real-time path planning adjustments, substantially enhancing AGV operational efficiency and system responsiveness.