ASSOCIATIVE NEURAL MODELS FOR BIOMIMETIC MULTI-MODAL LEARNING IN A MIRROR NEURON-BASED ROBOT

By using neurocognitive evidence on mirror neuron system concepts the MirrorBot project has developed neural models for intelligent robot behaviour. These models employ diverse learning approaches such as reinforcement learning, self-organisation and associative learning to perform cognitive robotic operations such as language grounding in actions, object recognition, localisation and docking. In this paper we describe architectures based on an associative self-organising framework which were designed to combine multimodal inputs of language, vision and motor programs to produce complex robot behaviours.

[1]  David J. Foster,et al.  A model of hippocampally dependent navigation, using the temporal difference learning rule , 2000, Hippocampus.

[2]  M. Arbib,et al.  Language within our grasp , 1998, Trends in Neurosciences.

[3]  Stefan Wermter,et al.  Towards multimodal neural robot learning , 2004, Robotics Auton. Syst..

[4]  Stefan Wermter,et al.  A Multimodal Hierarchial Approach to Robot Learning by Imitation , 2004 .

[5]  Tao Xiong,et al.  A combined SVM and LDA approach for classification , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[6]  A. Goldman,et al.  Mirror neurons and the simulation theory of mind-reading , 1998, Trends in Cognitive Sciences.

[7]  Stefan Wermter,et al.  Towards Novel Neuroscience-Inspired Computing , 2001, Emergent Neural Computational Architectures Based on Neuroscience.

[8]  Friedemann Pulverm Uuml,et al.  Words in the brain's language , 1999 .

[9]  F. Pulvermüller.  Brain reflections of words and their meaning , 2001, Trends in Cognitive Sciences.

[10]  Stefan Wermter,et al.  Learning robot actions based on self-organising language memory , 2003, Neural Networks.

[11]  I. Johnsrude,et al.  Somatotopic Representation of Action Words in Human Motor and Premotor Cortex , 2004, Neuron.

[12]  G. Rizzolatti,et al.  Hearing Sounds, Understanding Actions: Action Representation in Mirror Neurons , 2002, Science.

[13]  S. Wermter,et al.  An associator network approach to robot learning by imitation through vision, motor control and language , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[14]  O. Hauk,et al.  Neurophysiological distinction of action words in the fronto‐central cortex , 2004, Human brain mapping.

[15]  Stefan Wermter,et al.  Self-organisation of language instruction for robot action control , 2003, Proceedings of the International Joint Conference on Neural Networks, 2003..

[16]  Stefan Wermter,et al.  Object Localisation Using Laterally Connected "What" and "Where" Associator Networks , 2003, ICANN.

[17]  L. Fogassi,et al.  Audiovisual mirror neurons and action recognition , 2003, Experimental Brain Research.

[18]  F. Pulvermüller,et al.  Words in the brain's language , 1999, Behavioral and Brain Sciences.

[19]  Geoffrey E. Hinton,et al.  The "wake-sleep" algorithm for unsupervised neural networks. , 1995, Science.

[20]  Stefan Wermter,et al.  Robot docking with neural vision and reinforcement , 2004, Knowl. Based Syst..

[21]  Friedemann Pulvermüller,et al.  The Neuroscience of Language: On Brain Circuits of Words and Serial Order , 2003 .