Reinforcement learning (RL) demonstrates superior potential over traditional flight control methods for fixed-wing aircraft, particularly under extreme operational conditions. However, the high demand for training samples and the lack of efficient computation in existing simulators hinder its further application. In this paper, we introduce NeuralPlane, the first benchmark platform for large-scale parallel simulations of fixed-wing aircraft. NeuralPlane significantly boosts high-fidelity simulation via GPU-accelerated Flight Dynamics Model (FDM) computation, achieving a single-step simulation time of just 0.2 seconds at a parallel scale of $10^{6}$, far exceeding current platforms. We also provide clear code templates, comprehensive evaluation/visualization tools and hierarchical frameworks for integrating RL and traditional control methods. We believe that NeuralPlane can accelerate the development of RL-based fixed-wing flight control and serve as a new challenging benchmark for the RL community.

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.

Reinforcement learning (RL) demonstrates superior potential over traditional flight control methods for fixed-wing aircraft, particularly under extreme operational conditions. However, the high demand for training samples and the lack of efficient computation in existing simulators hinder its further application. In this paper, we introduce NeuralPlane, the first benchmark platform for large-scale parallel simulations of fixed-wing aircraft. NeuralPlane significantly boosts high-fidelity simulation via GPU-accelerated Flight Dynamics Model (FDM) computation, achieving a single-step simulation time of just 0.2 seconds at a parallel scale of 10 {6}, far exceeding current platforms. We also provide clear code templates, comprehensive evaluation/visualization tools and hierarchical frameworks for integrating RL and traditional control methods. We believe that NeuralPlane can accelerate the development of RL-based fixed-wing flight control and serve as a new challenging benchmark for the RL community.