Improving the cooperative scheduling efficiency of equipment is the key for automated container terminals to cope with the development trend of large-scale ships. In order to improve the solution efficiency of the existing spacetime network (STN) model for the cooperative scheduling problem of yard cranes (YCs) and automated guided vehicles (AGVs) and extend its application scenarios, two improved STN models are proposed. The flow balance constraints in the original model are decomposed, and the trajectory constraints of YCs and AGVs are added to acquire the model STN_A. The coupling constraint in STN_A is updated, and buffer constraints are added to STN_A so that the model STN_B is built. As the size of the problem increases, the solution speed of CPLEX becomes the bottleneck. So a heuristic method containing three groups of heuristic rules is designed to obtain a near-optimal solution quickly. Experimental results show that the computation time of STN_A is shortened by 49.47% on average and the gap is reduced by 1.69% on average compared with the original model. The gap between the solution of the heuristic rules and the solution of CPLEX is less than 3.50%, and the solution time of the heuristic rules is on average 99.85% less than the solution time of CPLEX. Compared with STN_A, the computation time for solving STN_B increases by 58.93% on average.