Learning-Based vs Model-Free Adaptive Control of a MAV Under Wind Gust

Thomas Chaffre, Julien Moras, Adrien Chan-Hon-Tong, Julien Marzat, Karl Sammut, Gilles Le Chenadec, Benoit Clement

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Citation (Scopus)

Abstract

Navigation problems under unknown varying conditions are among the most important and well-studied problems in the control field. Classic model-based adaptive control methods can be applied only when a convenient model of the plant or environment is provided. Recent model-free adaptive control methods aim at removing this dependency by learning the physical characteristics of the plant and/or process directly from sensor feedback. Although there have been prior attempts at improving these techniques, it remains an open question as to whether it is possible to cope with real-world uncertainties in a control system that is fully based on either paradigm. We propose a conceptually simple learning-based approach composed of a full state feedback controller, tuned robustly by a deep reinforcement learning framework based on the Soft Actor-Critic algorithm. We compare it, in realistic simulations, to a model-free controller that uses the same deep reinforcement learning framework for the control of a micro aerial vehicle under wind gust. The results indicate the great potential of learning-based adaptive control methods in modern dynamical systems.
Original languageEnglish
Title of host publicationInformatics in Control, Automation and Robotics - 17th International Conference, ICINCO 2020, Revised Selected Papers
Subtitle of host publication17th International Conference, ICINCO 2020 Lieusaint - Paris, France, July 7–9, 2020, Revised Selected Papers
EditorsOleg Gusikhin, Kurosh Madani, Janan Zaytoon
Place of PublicationSwitzerland
PublisherSpringer
Pages362-385
Number of pages24
Volume793
ISBN (Electronic)978-3-030-92442-3
ISBN (Print)978-3-030-92441-6
DOIs
Publication statusPublished - 2022
EventICINCO 2020: Informatics in Control, Automation and Robotics, 17th International Conference - Lieusaint , Paris, France
Duration: 7 Jul 20209 Jul 2020
Conference number: 17

Publication series

NameLecture Notes in Electrical Engineering
Volume793
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119

Conference

ConferenceICINCO 2020: Informatics in Control, Automation and Robotics, 17th International Conference
Country/TerritoryFrance
CityParis
Period7/07/209/07/20

Keywords

  • control field
  • navigation problems
  • adaptive control
  • Model-free control
  • sensor feedback
  • Soft Actor-Critic algorithm

Fingerprint

Dive into the research topics of 'Learning-Based vs Model-Free Adaptive Control of a MAV Under Wind Gust'. Together they form a unique fingerprint.

Cite this