Aiming at the problems of manual handling of printed materials in the current printing workshop,low utilization rate of AGVs,and collisions and deadlocks in multi-AGV operations,an improved genetic algorithm was proposed to optimize the task assignment of AGVs.Firstly,combined with the actual environment of the printing workshop,the minimum total time of the AGV handling task was used as the objective function for modeling.Secondly,the traditional genetic algorithm was optimized by the improved bidirectional A* algorithm with the time window model added,which has realized the path planning and scheduling management of AGV.Finally,the algorithm was simulated and verified by MATLAB simulation software.Comparing the simulation results of the traditional genetic algorithm and the improved genetic algorithm,it had been found that the improved genetic algorithm yields a better AGV scheduling result,where the moving time for the transportation tasks was 13%shorter than that of the traditional genetic algorithm,and the number of iterations was 42%fewer than that of the traditional genetic algorithm.Therefore,the improved genetic algorithm can better achieve collision-free operation,path planning,and scheduling for multiple AGVs in a printing workshop.