A Developmental Approach for low-level Imitations

3343 12 2183 4 10069 document 2183 Andry.pdf application/pdf 79194 2009-12-08 20:46:25 http://cogprints.org/3343/1/Andry.pdf 3343 1 application/pdf application/pdf en public

Andry.pdf

http://eprints.org/relation/hasVolatileVersion http://cogprints.org/id/document/5741 http://eprints.org/relation/haspreviewThumbnailVersion http://cogprints.org/id/document/5741 http://eprints.org/relation/hasVersion http://cogprints.org/id/document/5741 archive 3507 disk0/00/00/33/43 2004-02-12 2011-03-11 08:55:26 2007-09-12 16:50:15 confposter show 0 Historically, a lot of authors in psychology and in robotics tend to separate "true imitation" and its related high-level mechanisms which seem to be exclusive to human adult, from low-level imitations or "mimicries" observed on babies or primates. Closely, classical researches suppose that an imitative artificial system must be able to build a model of the demonstrator's geometry, in order to reproduce finely the movements on each joints. Conversely, we will advocate that if imitation is viewed as a part of a developmental course, then (1) an artificial developing system does not need to build any internal model of the other, to perform real-time and low-level imitations of human movements despite the related correspondence problem between man and robot and, (2) a simple sensory-motor loop could be at the basis of multiples heterogeneous imitative behaviors often explained in the literature by different models. http://www.lucs.lu.se/ftp/pub/LUCS_Studies/LUCS101/Andry.pdf Andry Pierre Gaussier Philippe Nadel Jacqueline Courant Michele August 4-5, 2003 Third International Workshop on Epigenetic Robotics: Modeling Cognitive Development in Robotic Systems Boston, MA, USA Prince Christopher G. Berthouze Luc Kozima Hideki Bullock Daniel Stojanov Georgi Balkenius Christian pub imitative artificial system, developing system, self-organizing map, robotic movement control 157-158 TRUE Lund University Cognitive Studies TRUE comp-sci-mach-learn comp-sci-neural-nets comp-sci-robot A Developmental Approach for low-level Imitations 101 published 2003 public