creators_name: Weber, Cornelius creators_name: Elshaw, Mark creators_name: Zochios, Alex creators_name: Wermter, Stefan editors_name: Berthouze, Luc editors_name: Kozima, Hideki editors_name: Prince, Christopher G. editors_name: Sandini, Giulio editors_name: Stojanov, Georgi editors_name: Metta, Giorgio editors_name: Balkenius, Christian type: confpaper datestamp: 2005-04-14 lastmod: 2011-03-11 08:55:52 metadata_visibility: show title: A Multimodal Hierarchial Approach to Robot Learning by Imitation ispublished: pub subjects: comp-sci-mach-learn subjects: comp-sci-neural-nets subjects: comp-sci-robot full_text_status: public keywords: multimodal imitation learning, hierarchial neural architecture, mirror neuron system, robotic simulator, MirrorBot abstract: In this paper we propose an approach to robot learning by imitation that uses the multimodal inputs of language, vision and motor. In our approach a student robot learns from a teacher robot how to perform three separate behaviours based on these inputs. We considered two neural architectures for performing this robot learning. First, a one-step hierarchial architecture trained with two different learning approaches either based on Kohonen's self-organising map or based on the Helmholtz machine turns out to be inefficient or not capable of performing differentiated behavior. In response we produced a hierarchial architecture that combines both learning approaches to overcome these problems. In doing so the proposed robot system models specific aspects of learning using concepts of the mirror neuron system (Rizzolatti and Arbib, 1998) with regards to demonstration learning. date: 2004 date_type: published volume: 117 publisher: Lund University Cognitive Studies pagerange: 131-134 refereed: TRUE citation: Weber, Cornelius and Elshaw, Mark and Zochios, Alex and Wermter, Stefan (2004) A Multimodal Hierarchial Approach to Robot Learning by Imitation. [Conference Paper] document_url: http://cogprints.org/4148/1/weber.pdf