@misc{cogprints4148, volume = {117}, editor = {Luc Berthouze and Hideki Kozima and Christopher G. Prince and Giulio Sandini and Georgi Stojanov and Giorgio Metta and Christian Balkenius}, title = {A Multimodal Hierarchial Approach to Robot Learning by Imitation}, author = {Cornelius Weber and Mark Elshaw and Alex Zochios and Stefan Wermter}, publisher = {Lund University Cognitive Studies}, year = {2004}, pages = {131--134}, keywords = {multimodal imitation learning, hierarchial neural architecture, mirror neuron system, robotic simulator, MirrorBot}, url = {http://cogprints.org/4148/}, 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.} }