Cargando…

How Active Inference Could Help Revolutionise Robotics

Recent advances in neuroscience have characterised brain function using mathematical formalisms and first principles that may be usefully applied elsewhere. In this paper, we explain how active inference—a well-known description of sentient behaviour from neuroscience—can be exploited in robotics. I...

Descripción completa

Detalles Bibliográficos
Autores principales: Da Costa, Lancelot, Lanillos, Pablo, Sajid, Noor, Friston, Karl, Khan, Shujhat
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8946999/
https://www.ncbi.nlm.nih.gov/pubmed/35327872
http://dx.doi.org/10.3390/e24030361
_version_ 1784674334238834688
author Da Costa, Lancelot
Lanillos, Pablo
Sajid, Noor
Friston, Karl
Khan, Shujhat
author_facet Da Costa, Lancelot
Lanillos, Pablo
Sajid, Noor
Friston, Karl
Khan, Shujhat
author_sort Da Costa, Lancelot
collection PubMed
description Recent advances in neuroscience have characterised brain function using mathematical formalisms and first principles that may be usefully applied elsewhere. In this paper, we explain how active inference—a well-known description of sentient behaviour from neuroscience—can be exploited in robotics. In short, active inference leverages the processes thought to underwrite human behaviour to build effective autonomous systems. These systems show state-of-the-art performance in several robotics settings; we highlight these and explain how this framework may be used to advance robotics.
format Online
Article
Text
id pubmed-8946999
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-89469992022-03-25 How Active Inference Could Help Revolutionise Robotics Da Costa, Lancelot Lanillos, Pablo Sajid, Noor Friston, Karl Khan, Shujhat Entropy (Basel) Article Recent advances in neuroscience have characterised brain function using mathematical formalisms and first principles that may be usefully applied elsewhere. In this paper, we explain how active inference—a well-known description of sentient behaviour from neuroscience—can be exploited in robotics. In short, active inference leverages the processes thought to underwrite human behaviour to build effective autonomous systems. These systems show state-of-the-art performance in several robotics settings; we highlight these and explain how this framework may be used to advance robotics. MDPI 2022-03-02 /pmc/articles/PMC8946999/ /pubmed/35327872 http://dx.doi.org/10.3390/e24030361 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Da Costa, Lancelot
Lanillos, Pablo
Sajid, Noor
Friston, Karl
Khan, Shujhat
How Active Inference Could Help Revolutionise Robotics
title How Active Inference Could Help Revolutionise Robotics
title_full How Active Inference Could Help Revolutionise Robotics
title_fullStr How Active Inference Could Help Revolutionise Robotics
title_full_unstemmed How Active Inference Could Help Revolutionise Robotics
title_short How Active Inference Could Help Revolutionise Robotics
title_sort how active inference could help revolutionise robotics
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8946999/
https://www.ncbi.nlm.nih.gov/pubmed/35327872
http://dx.doi.org/10.3390/e24030361
work_keys_str_mv AT dacostalancelot howactiveinferencecouldhelprevolutioniserobotics
AT lanillospablo howactiveinferencecouldhelprevolutioniserobotics
AT sajidnoor howactiveinferencecouldhelprevolutioniserobotics
AT fristonkarl howactiveinferencecouldhelprevolutioniserobotics
AT khanshujhat howactiveinferencecouldhelprevolutioniserobotics