In order to improve the efficiency of automated warehouse system, the integrated scheduling problem was studied on the basis of a typical warehouse layout. A new multi-objective mathematical model was built with constraints. The reason that leads to automated guided vehicle (AGV) deadlock was analyzed on basis of bidirectional route of AGV. And a deadlock-free control policy named alternative path was proposed. A heuristic algorithm based on genetic algorithm was proposed to solve the problem. The rule of coding, selection, crossover and mutation was described in detail. The simulation result shows that the proposed algorithm is effective and can be used in practical.