Cargando…

Controlling the Solo12 quadruped robot with deep reinforcement learning

Quadruped robots require robust and general locomotion skills to exploit their mobility potential in complex and challenging environments. In this work, we present an implementation of a robust end-to-end learning-based controller on the Solo12 quadruped. Our method is based on deep reinforcement le...

Descripción completa

Detalles Bibliográficos
Autores principales: Aractingi, Michel, Léziart, Pierre-Alexandre, Flayols, Thomas, Perez, Julien, Silander, Tomi, Souères, Philippe
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group UK 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10366154/
https://www.ncbi.nlm.nih.gov/pubmed/37488193
http://dx.doi.org/10.1038/s41598-023-38259-7
_version_ 1785077107812990976
author Aractingi, Michel
Léziart, Pierre-Alexandre
Flayols, Thomas
Perez, Julien
Silander, Tomi
Souères, Philippe
author_facet Aractingi, Michel
Léziart, Pierre-Alexandre
Flayols, Thomas
Perez, Julien
Silander, Tomi
Souères, Philippe
author_sort Aractingi, Michel
collection PubMed
description Quadruped robots require robust and general locomotion skills to exploit their mobility potential in complex and challenging environments. In this work, we present an implementation of a robust end-to-end learning-based controller on the Solo12 quadruped. Our method is based on deep reinforcement learning of joint impedance references. The resulting control policies follow a commanded velocity reference while being efficient in its energy consumption and easy to deploy. We detail the learning procedure and method for transfer on the real robot. We show elaborate experiments. Finally, we present experimental results of the learned locomotion on various grounds indoors and outdoors. These results show that the Solo12 robot is a suitable open-source platform for research combining learning and control because of the easiness in transferring and deploying learned controllers.
format Online
Article
Text
id pubmed-10366154
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Nature Publishing Group UK
record_format MEDLINE/PubMed
spelling pubmed-103661542023-07-26 Controlling the Solo12 quadruped robot with deep reinforcement learning Aractingi, Michel Léziart, Pierre-Alexandre Flayols, Thomas Perez, Julien Silander, Tomi Souères, Philippe Sci Rep Article Quadruped robots require robust and general locomotion skills to exploit their mobility potential in complex and challenging environments. In this work, we present an implementation of a robust end-to-end learning-based controller on the Solo12 quadruped. Our method is based on deep reinforcement learning of joint impedance references. The resulting control policies follow a commanded velocity reference while being efficient in its energy consumption and easy to deploy. We detail the learning procedure and method for transfer on the real robot. We show elaborate experiments. Finally, we present experimental results of the learned locomotion on various grounds indoors and outdoors. These results show that the Solo12 robot is a suitable open-source platform for research combining learning and control because of the easiness in transferring and deploying learned controllers. Nature Publishing Group UK 2023-07-24 /pmc/articles/PMC10366154/ /pubmed/37488193 http://dx.doi.org/10.1038/s41598-023-38259-7 Text en © The Author(s) 2023 https://creativecommons.org/licenses/by/4.0/Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) .
spellingShingle Article
Aractingi, Michel
Léziart, Pierre-Alexandre
Flayols, Thomas
Perez, Julien
Silander, Tomi
Souères, Philippe
Controlling the Solo12 quadruped robot with deep reinforcement learning
title Controlling the Solo12 quadruped robot with deep reinforcement learning
title_full Controlling the Solo12 quadruped robot with deep reinforcement learning
title_fullStr Controlling the Solo12 quadruped robot with deep reinforcement learning
title_full_unstemmed Controlling the Solo12 quadruped robot with deep reinforcement learning
title_short Controlling the Solo12 quadruped robot with deep reinforcement learning
title_sort controlling the solo12 quadruped robot with deep reinforcement learning
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10366154/
https://www.ncbi.nlm.nih.gov/pubmed/37488193
http://dx.doi.org/10.1038/s41598-023-38259-7
work_keys_str_mv AT aractingimichel controllingthesolo12quadrupedrobotwithdeepreinforcementlearning
AT leziartpierrealexandre controllingthesolo12quadrupedrobotwithdeepreinforcementlearning
AT flayolsthomas controllingthesolo12quadrupedrobotwithdeepreinforcementlearning
AT perezjulien controllingthesolo12quadrupedrobotwithdeepreinforcementlearning
AT silandertomi controllingthesolo12quadrupedrobotwithdeepreinforcementlearning
AT soueresphilippe controllingthesolo12quadrupedrobotwithdeepreinforcementlearning