Please use this identifier to cite or link to this item: http://hdl.handle.net/1822/10953

TitleOn the development of intention understanding for joint action tasks
Author(s)Erlhagen, Wolfram
Mukovskiy, Albert
Chersi, Fabian
Bicho, E.
KeywordsAction understanding
Action sequence
Dynamic field model
Mirror neurons
Goal inference
Joint action
intention understanding
social development
joint action in autonomous robots
Issue date2007
PublisherIEEE
CitationERLHAGEN, Wolfram [et al.] - On the development of intention understanding for joint action tasks. In IEEE INTERNATIONAL CONFERENCE ON DEVELOPMENT AND LEARNING, 6, London, United Kingdom, 2007 – “ICDL 2007 : proceedings”[CD-ROM]. [S.l.] : IEEE, 2007. ISBN 1-4244-1116-5.
Abstract(s)Our everyday, common sense ability to discern the intentions of others’ from their motions is fundamental for a successful cooperation in joint action tasks. In this paper we address in a modeling study the question of how the ability to understand complex goal-directed action sequences may develop during learning and practice. The model architecture reflects recent neurophysiological findings that suggest the existence of chains of mirror neurons associated with specific goals. These chains may be activated by external events to simulate the consequences of observed actions. Using the mathematical framework of dynamical neural fields to model the dynamics of different neural populations representing goals, action means and contextual cues, we show that such chains may develop based on a local, Hebbian learning rule. We validate the functionality of the learned model in a joint action task in which an observer robot infers the intention of a partner to chose a complementary action sequence.
TypeConference paper
URIhttp://hdl.handle.net/1822/10953
ISBN1-4244-1116-5
DOI10.1109/DEVLRN.2007.4354022
Peer-Reviewedyes
AccessOpen access
Appears in Collections:Offmath - Livros de Actas

Files in This Item:
File Description SizeFormat 
ErlhagenEtAl_ICDL07_0004.pdfDocumento principal1 MBAdobe PDFView/Open

Partilhe no FacebookPartilhe no TwitterPartilhe no DeliciousPartilhe no LinkedInPartilhe no DiggAdicionar ao Google BookmarksPartilhe no MySpacePartilhe no Orkut
Exporte no formato BibTex mendeley Exporte no formato Endnote Adicione ao seu ORCID