Attitude Control of Highly Maneuverable Aircraft Using an Improved Q-learning

TL;DR

This paper presents an improved Q-learning approach for attitude control of a highly maneuverable, low-stability aircraft, utilizing a fuzzy action assignment to generate continuous control commands and outperform PID controllers.

Contribution

The paper introduces a novel combination of Q-learning with fuzzy action assignment for aircraft attitude control, addressing state-action space limitations and enabling continuous control.

Findings

Q-learning with FAA outperforms PID control in simulations.

Accurate reward functions and state observation are crucial for success.

The method effectively tracks variable pitch angles in the aircraft.

Abstract

Attitude control of a novel regional truss-braced wing aircraft with low stability characteristics is addressed in this paper using Reinforcement Learning (RL). In recent years, RL has been increasingly employed in challenging applications, particularly, autonomous flight control. However, a significant predicament confronting discrete RL algorithms is the dimension limitation of the state-action table and difficulties in defining the elements of the RL environment. To address these issues, in this paper, a detailed mathematical model of the mentioned aircraft is first developed to shape an RL environment. Subsequently, Q-learning, the most prevalent discrete RL algorithm will be implemented in both the Markov Decision Process (MDP), and Partially Observable Markov Decision Process (POMDP) frameworks to control the longitudinal mode of the air vehicle. In order to eliminate residual fluctuations that are a consequence of discrete action selection, and simultaneously track variable pitch angles, a Fuzzy Action Assignment (FAA) method is proposed to generate continuous control commands using the trained Q-table. Accordingly, it will be proved that by defining an accurate reward function, along with observing all crucial states, the performance of the introduced control system surpasses a well-tuned PID controller.