How Active Inference Could Help Revolutionise Robotics.

Bayesian inference adaptive robots filtering free energy generative model model-based control neurotechnology

Journal

Entropy (Basel, Switzerland)
ISSN: 1099-4300
Titre abrégé: Entropy (Basel)
Pays: Switzerland
ID NLM: 101243874

Informations de publication

Date de publication:
02 Mar 2022
Historique:
received: 21 01 2022
revised: 24 02 2022
accepted: 28 02 2022
entrez: 25 3 2022
pubmed: 26 3 2022
medline: 26 3 2022
Statut: epublish

Résumé

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.

Identifiants

pubmed: 35327872
pii: e24030361
doi: 10.3390/e24030361
pmc: PMC8946999
pii:
doi:

Types de publication

Journal Article

Langues

eng

Subventions

Organisme : Medical Research Council
ID : MR/S502522/1
Pays : United Kingdom
Organisme : Engineering and Physical Sciences Research Council
ID : EP/S023925/1
Organisme : Wellcome Trust
ID : 205103/Z/16/Z
Pays : United Kingdom
Organisme : Fonds National de la Recherche
ID : 13568875
Organisme : Canada-UK Artificial Intelligence Initiative
ID : ES/T01279X/1

Références

Neural Comput. 2021 Mar;33(3):713-763
pubmed: 33626312
Neural Comput. 2021 Mar;33(3):674-712
pubmed: 33400903
Entropy (Basel). 2019 Mar 07;21(3):
pubmed: 33266972
Neural Netw. 2021 Dec;144:573-590
pubmed: 34634605
Neural Netw. 2021 Oct;142:192-204
pubmed: 34022669
Nat Rev Neurosci. 2010 Feb;11(2):127-38
pubmed: 20068583
Nature. 2016 Jan 28;529(7587):484-9
pubmed: 26819042
J Physiol Paris. 2006 Jul-Sep;100(1-3):70-87
pubmed: 17097864
Neuroimage. 2008 Jul 1;41(3):849-85
pubmed: 18434205
Biol Psychiatry Cogn Neurosci Neuroimaging. 2018 Sep;3(9):809-818
pubmed: 30082215
Front Robot AI. 2021 Nov 26;8:684401
pubmed: 34901166
Neural Netw. 2021 Dec;144:229-246
pubmed: 34507043
Front Comput Neurosci. 2020 May 19;14:41
pubmed: 32508611
Sci Robot. 2020 Dec 9;5(49):
pubmed: 33298517
Nature. 2019 Nov;575(7782):350-354
pubmed: 31666705
Entropy (Basel). 2021 Oct 05;23(10):
pubmed: 34682030
Netw Neurosci. 2017;1(4):381-414
pubmed: 29417960
Biol Cybern. 2010 Mar;102(3):227-60
pubmed: 20148260
Neural Comput. 2017 Jan;29(1):1-49
pubmed: 27870614
Front Comput Neurosci. 2020 Nov 16;14:574372
pubmed: 33304260
Biol Psychol. 2022 Mar;169:108266
pubmed: 35051559
Brain Commun. 2020 Oct 01;2(2):fcaa164
pubmed: 33376985
Neural Comput. 2017 Oct;29(10):2633-2683
pubmed: 28777724
J Math Psychol. 2020 Dec;99:102447
pubmed: 33343039

Auteurs

Lancelot Da Costa (L)

Department of Mathematics, Imperial College London, London SW7 2AZ, UK.
Wellcome Centre for Human Neuroimaging, University College London, London WC1N 3AR, UK.

Pablo Lanillos (P)

Department of Artificial Intelligence, Donders Institute for Brain, Cognition and Behavior, Radboud University, 6525 XZ Nijmegen, The Netherlands.

Noor Sajid (N)

Wellcome Centre for Human Neuroimaging, University College London, London WC1N 3AR, UK.

Karl Friston (K)

Wellcome Centre for Human Neuroimaging, University College London, London WC1N 3AR, UK.

Shujhat Khan (S)

Milton Keynes Hospital, Oxford Deanery, Milton Keynes MK6 5LD, UK.

Classifications MeSH