With the increasing integration of AGVs (Automated Guided Vehicles) and Robot Arms in manufacturing systems, traditional scheduling approaches that handle them separately often lead to inefficiencies and poor coordination. To overcome these limitations, we proposes a concise method based on temporal logic and hybrid dynamic programming to optimize the scheduling of heterogeneous agent systems. By accurately modeling the state transitions and timing constraints of both AGVs and Robot Arms, and applying a hybrid dynamic programming framework, the method achieves global optimization in task allocation. The results show significant improvements in task completion time over conventional methods, offering a streamlined solution for multi-agent scheduling in intelligent manufacturing environments.