Cargando…

Iterative transfer learning for automatic collective motion tuning on multiple robot platforms

This paper proposes an iterative transfer learning approach to achieve swarming collective motion in groups of mobile robots. By applying transfer learning, a deep learner capable of recognizing swarming collective motion can use its knowledge to tune stable collective motion behaviors across multip...

Descripción completa

Detalles Bibliográficos
Autores principales: Abpeikar, Shadi, Kasmarik, Kathryn, Garratt, Matt
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10060795/
https://www.ncbi.nlm.nih.gov/pubmed/37009637
http://dx.doi.org/10.3389/fnbot.2023.1113991
_version_ 1785017153177518080
author Abpeikar, Shadi
Kasmarik, Kathryn
Garratt, Matt
author_facet Abpeikar, Shadi
Kasmarik, Kathryn
Garratt, Matt
author_sort Abpeikar, Shadi
collection PubMed
description This paper proposes an iterative transfer learning approach to achieve swarming collective motion in groups of mobile robots. By applying transfer learning, a deep learner capable of recognizing swarming collective motion can use its knowledge to tune stable collective motion behaviors across multiple robot platforms. The transfer learner requires only a small set of initial training data from each robot platform, and this data can be collected from random movements. The transfer learner then progressively updates its own knowledge base with an iterative approach. This transfer learning eliminates the cost of extensive training data collection and the risk of trial-and-error learning on robot hardware. We test this approach on two robot platforms: simulated Pioneer 3DX robots and real Sphero BOLT robots. The transfer learning approach enables both platforms to automatically tune stable collective behaviors. Using the knowledge-base library the tuning procedure is fast and accurate. We demonstrate that these tuned behaviors can be used for typical multi-robot tasks such as coverage, even though they are not specifically designed for coverage tasks.
format Online
Article
Text
id pubmed-10060795
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-100607952023-03-31 Iterative transfer learning for automatic collective motion tuning on multiple robot platforms Abpeikar, Shadi Kasmarik, Kathryn Garratt, Matt Front Neurorobot Neuroscience This paper proposes an iterative transfer learning approach to achieve swarming collective motion in groups of mobile robots. By applying transfer learning, a deep learner capable of recognizing swarming collective motion can use its knowledge to tune stable collective motion behaviors across multiple robot platforms. The transfer learner requires only a small set of initial training data from each robot platform, and this data can be collected from random movements. The transfer learner then progressively updates its own knowledge base with an iterative approach. This transfer learning eliminates the cost of extensive training data collection and the risk of trial-and-error learning on robot hardware. We test this approach on two robot platforms: simulated Pioneer 3DX robots and real Sphero BOLT robots. The transfer learning approach enables both platforms to automatically tune stable collective behaviors. Using the knowledge-base library the tuning procedure is fast and accurate. We demonstrate that these tuned behaviors can be used for typical multi-robot tasks such as coverage, even though they are not specifically designed for coverage tasks. Frontiers Media S.A. 2023-03-16 /pmc/articles/PMC10060795/ /pubmed/37009637 http://dx.doi.org/10.3389/fnbot.2023.1113991 Text en Copyright © 2023 Abpeikar, Kasmarik and Garratt. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Neuroscience
Abpeikar, Shadi
Kasmarik, Kathryn
Garratt, Matt
Iterative transfer learning for automatic collective motion tuning on multiple robot platforms
title Iterative transfer learning for automatic collective motion tuning on multiple robot platforms
title_full Iterative transfer learning for automatic collective motion tuning on multiple robot platforms
title_fullStr Iterative transfer learning for automatic collective motion tuning on multiple robot platforms
title_full_unstemmed Iterative transfer learning for automatic collective motion tuning on multiple robot platforms
title_short Iterative transfer learning for automatic collective motion tuning on multiple robot platforms
title_sort iterative transfer learning for automatic collective motion tuning on multiple robot platforms
topic Neuroscience
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10060795/
https://www.ncbi.nlm.nih.gov/pubmed/37009637
http://dx.doi.org/10.3389/fnbot.2023.1113991
work_keys_str_mv AT abpeikarshadi iterativetransferlearningforautomaticcollectivemotiontuningonmultiplerobotplatforms
AT kasmarikkathryn iterativetransferlearningforautomaticcollectivemotiontuningonmultiplerobotplatforms
AT garrattmatt iterativetransferlearningforautomaticcollectivemotiontuningonmultiplerobotplatforms