Reinforcement Learning-Based Tracking Control of USVs in Varying Operational Conditions.

approximate dynamic programming (ADP) autonomous ships dynamic positioning (DP) model-based adaptive control optimal control reinforcement learning system identification trajectory tracking

Journal

Frontiers in robotics and AI
ISSN: 2296-9144
Titre abrégé: Front Robot AI
Pays: Switzerland
ID NLM: 101749350

Informations de publication

Date de publication:
2020
Historique:
received: 06 11 2019
accepted: 20 02 2020
entrez: 27 1 2021
pubmed: 28 1 2021
medline: 28 1 2021
Statut: epublish

Résumé

We present a reinforcement learning-based (RL) control scheme for trajectory tracking of fully-actuated surface vessels. The proposed method learns online both a model-based feedforward controller, as well an optimizing feedback policy in order to follow a desired trajectory under the influence of environmental forces. The method's efficiency is evaluated via simulations and sea trials, with the unmanned surface vehicle (USV)

Identifiants

pubmed: 33501200
doi: 10.3389/frobt.2020.00032
pmc: PMC7806118
doi:

Types de publication

Journal Article

Langues

eng

Pagination

32

Informations de copyright

Copyright © 2020 Martinsen, Lekkas, Gros, Glomsrud and Pedersen.

Références

Neural Comput. 2000 Jan;12(1):219-45
pubmed: 10636940
Nature. 2016 Jan 28;529(7587):484-9
pubmed: 26819042

Auteurs

Andreas B Martinsen (AB)

Department of Engineering Cybernetics, Norwegian University of Science and Technology, Trondheim, Norway.

Anastasios M Lekkas (AM)

Department of Engineering Cybernetics, Norwegian University of Science and Technology, Trondheim, Norway.
Centre for Autonomous Marine Operations and Systems, Norwegian University of Science and Technology, Trondheim, Norway.

Sébastien Gros (S)

Department of Engineering Cybernetics, Norwegian University of Science and Technology, Trondheim, Norway.

Jon Arne Glomsrud (JA)

Digital Assurance Program, Group Technology and Research, DNV GL, Trondheim, Norway.

Tom Arne Pedersen (TA)

Digital Assurance Program, Group Technology and Research, DNV GL, Trondheim, Norway.

Classifications MeSH