Data-Efficient Deep Reinforcement Learning for Attitude Control of Fixed-Wing UAVs: Field Experiments

Attitude control of fixed-wing unmanned aerial vehicles (UAVs) is a difficult control problem in part due to uncertain nonlinear dynamics, actuator constraints, and coupled longitudinal and lateral motions. Current state-of-the-art autopilots are based on linear control and are thus limited in their effectiveness and performance. drl is a machine learning method to automatically discover optimal control laws through interaction with the controlled system that can handle complex nonlinear dynamics. We show in this article that deep reinforcement learning (DRL) can successfully learn to perform attitude control of a fixed-wing UAV operating directly on the original nonlinear dynamics, requiring as little as 3 min of flight data. We initially train our model in a simulation environment and then deploy the learned controller on the UAV in flight tests, demonstrating comparable performance to the state-of-the-art ArduPlane proportional-integral-derivative (PID) attitude controller with no further online learning required. Learning with significant actuation delay and diversified simulated dynamics were found to be crucial for successful transfer to control of the real UAV. In addition to a qualitative comparison with the ArduPlane autopilot, we present a quantitative assessment based on linear analysis to better understand the learning controller's behavior.

Automated summary

This article discusses the difficult problem of attitude control in fixed-wing UAVs and proposes the use of deep reinforcement learning to handle the nonlinear dynamics. The results show that DRL can successfully learn to perform attitude control with just 3 minutes of flight data. The learned controller performs comparably to the state-of-the-art PID controller without further online learning.