Unmanned Aerial Vehicle Pitch Control Using Deep Reinforcement Learning with Discrete Actions in Wind Tunnel Test

Deep reinforcement learning is a promising method for training a nonlinear attitude controller for fixed-wing unmanned aerial vehicles. Until now, proof-of-concept studies have demonstrated successful attitude control in simulation. However, detailed experimental investigations have not yet been conducted. This study applied deep reinforcement learning for one-degree-of-freedom pitch control in wind tunnel tests with the aim of gaining practical understandings of attitude control application. Three controllers with different discrete action choices, that is, elevator angles, were designed. The controllers with larger action rates exhibited better performance in terms of following angle-of-attack commands. The root mean square errors for tracking angle-of-attack commands decreased from 3.42 degrees to 1.99 degrees as the maximum action rate increased from 10 degrees/s to 50 degrees/s. The comparison between experimental and simulation results showed that the controller with a smaller action rate experienced the friction effect, and the controllers with larger action rates experienced fluctuating behaviors in elevator maneuvers owing to delay. The investigation of the effect of friction and delay on pitch control highlighted the importance of conducting experiments to understand actual control performances, specifically when the controllers were trained with a low-fidelity model.