Bøhn, Eivind (SINTEF, Norwegian University of Science and Technology), Coates, Erlend M. (Norwegian University of Science and Technology), Moe, Signe (Norwegian University of Science and Technology, SINTEF), Johansen, Tor Arne (Norweigian Univ. Of Sci. & Tech.)

Deep Reinforcement Learning Attitude Control of Fixed-Wing UAVs Using Proximal Policy Optimization

Scheduled for presentation during the Regular Session "Control Architectures III" (WeC4), Wednesday, June 12, 2019, 17:40−18:00, Savannah

2020 International Conference on Unmanned Aircraft Systems (ICUAS), June 11-14, 2019, Athens, Greece

This information is tentative and subject to change. Compiled on April 23, 2024

Abstract

Contemporary autopilot systems for unmanned aerial vehicles (UAVs) are far more limited in their flight envelope as compared to experienced human pilots, thereby restricting the conditions UAVs can operate in and the types of missions they can accomplish autonomously. This paper pro- poses a deep reinforcement learning (DRL) controller to handle the nonlinear attitude control problem, enabling extended flight envelopes for fixed-wing UAVs. A proof-of-concept controller using the proximal policy optimization (PPO) algorithm is developed, and is shown to be capable of stabilizing a fixed-wing UAV from a large set of initial conditions to reference roll, pitch and airspeed values. The training process is outlined and key factors for its progression rate are considered, with the most important factor found to be limiting the number of variables in the observation vector, and including values for several pre- vious time steps for these variables. The trained reinforcement learning (RL) controller is compared to a proportional-integral- derivative (PID) controller, and is found to converge in more cases than the PID controller, with comparable performance. Furthermore, the RL controller is shown to generalize well to unseen disturbances in the form of wind and turbulence, even in severe disturbance conditions.