Robust Auto-landing Control of an agile Regional Jet Using Fuzzy Q-learning

Abstract: A robust auto-landing problem of a Truss-braced Wing (TBW) regional jet aircraft with poor stability characteristics is presented in this study employing a Fuzzy Reinforcement Learning scheme. Reinforcement Learning (RL) has seen a recent surge in practical uses in control systems. In contrast to many studies implementing Deep Learning in RL algorithms to generate continuous actions, the methodology of this study is straightforward and avoids complex neural network architectures by applying Fuzzy rules. An innovative, agile civil aircraft is selected not only to meet future aviation community expectations but also to demonstrate the robustness of the suggested method. In order to create a multi-objective RL environment, a Six-degree-of-freedom (6-DoF) simulation is first developed. By transforming the auto-landing problem of the aircraft into a Markov Decision Process (MDP) formulation, the problem is solved by designing a low-level Fuzzy Q-learning (FQL) controller. More specifically, the well-known Q-learning method, which is a discrete RL algorithm, is supplemented by Fuzzy rules to provide continuous actions with no need to complex learning structures. The performance of the proposed system is then evaluated by extensive flight simulations in different flight conditions considering severe wind gusts, measurement noises, actuator faults, and model uncertainties. Besides, the controller effectiveness would be compared with existing competing techniques such as Dynamic Inversion (DI) and Q-learning. The simulation results indicate the superior performance of the proposed control system as a reliable and robust control method to be employed in real applications.