A Details of Platform 473 A.1 Flight Dynamics Model

The frame's origin is fixed at The motion equations are derived from Newton's second law for an air vehicle, resulting in six core The inputs for the FPEs are the aircraft's attitude quaternion components along with the components The system comprising (CLMEs)-(CAMEs)-(FPEs)-(KEs), i.e., 1, 12, 15, and 16, represents The task scenarios can be categorized by objectives into Heading, Control, and Tracking . This work designs a hierarchical control algorithm for this task. RL Methods We use PPO for Heading and Control tasks in fixed-wing aircraft. The structure for hierarchical RL method is shown in Figure 10. The PPO algorithm's parameter settings are as follows: the learning rate is set to "128 128", and the recurrent hidden layer size is 128 with a single recurrent layer.