Evolutionary Reinforcement Learning

A Hybrid Approach for Safety-informed Intelligent Fault-tolerant Flight Control

Master thesis (2023)

Authors

V. Gavra Aerospace Engineering

Contributors

E. van Kampen (supervisor 1)
Faculty
Aerospace Engineering
Copyright: © 2023 Vlad Gavra
Deep Reinforcement Learning Evolutionary Algorithms Fault-tolerant Flight Control Control Policy Smoothness Intelligent Flight Control
More Info
expand_more

Published Date

19-01-2023

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Faculty

Aerospace Engineering

Abstract

Recent research in bio-inspired artificial intelligence potentially provides solutions to the challenging problem of designing fault-tolerant and robust flight control systems. The current work proposes SERL, a novel Safety-informed Evolutionary Reinforcement Learning algorithm, which combines Deep Reinforcement Learning (DRL) and neuro-evolutionary mechanisms. This hybrid method optimises a diverse population of non-linear control policies through both evolutionary mechanisms and gradient-based updates. We apply it to solve the attitude tracking task on a high-fidelity non-linear fixed-wing aircraft model. Compared to a state-of-the-art DRL solution, SERL achieves better tracking performance in nine out of ten cases, remaining robust against faults, changes in initial conditions and external disturbances. Furthermore, the work shows how evolutionary mechanisms can balance performance with the smoothness of control actions, a feature relevant for bridging the gap between simulation and deployment on real flight hardware.