Path planning of a multiple AGV system in unmanned warehouse with bottom passable shelves

The multiple AGV (automated guided vehicle) system is prone to conflict, collision and deadlock in the process of carrying. Therefore, the A^* algorithm was improved by introducing multi-valued grid and traffic rules to solve the path planning problem for the multiple AGV system in scenarios where there was passable space beneath shelves. To improve handling efficiency of the multiple AGV system, the planned path was optimized by adding shelf recall mechanism, turning cost and heat cost. A binary heap data structure was also used to improve calculation speed of the path planning. The simulation results show that the improved A^* algorithm has the advantages of fast solution and strong deadlock resistance, and can quickly complete the path planning of multi-AGV system in this scenario.