Soft Actor-Critic Deep Reinforcement Learning for Fault Tolerant Flight Control

TL;DR

This paper presents a model-free deep reinforcement learning controller using Soft Actor-Critic for fault-tolerant flight control of jet aircraft, demonstrating robustness to multiple failures and disturbances in complex maneuvers.

Contribution

It introduces a novel offline trained cascaded DRL controller capable of handling multiple failure modes in flight, improving robustness without model-based design.

Findings

Achieved a normalized MAE of 2.64% on complex maneuvers.

Successfully maintained control under six different failure scenarios.

Demonstrated robustness to sensor noise, disturbances, and varying initial conditions.

Abstract

Fault-tolerant flight control faces challenges, as developing a model-based controller for each unexpected failure is unrealistic, and online learning methods can handle limited system complexity due to their low sample efficiency. In this research, a model-free coupled-dynamics flight controller for a jet aircraft able to withstand multiple failure types is proposed. An offline trained cascaded Soft Actor-Critic Deep Reinforcement Learning controller is successful on highly coupled maneuvers, including a coordinated 40 degree bank climbing turn with a normalized Mean Absolute Error of 2.64%. The controller is robust to six failure cases, including the rudder jammed at -15 deg, the aileron effectiveness reduced by 70%, a structural failure, icing and a backward c.g. shift as the response is stable and the climbing turn is completed successfully. Robustness to biased sensor noise, atmospheric disturbances, and to varying initial flight conditions and reference signal shapes is also demonstrated.