MirrorBot

Project Description

MirrorBot: Biomimetic multimodal learning in a mirror neuron-based robot

A project between the University of Sunderland, MCR at Cambridge, University of Parma, INRIA at Nancy and University of Ulm.

3 Year EU-IST-FET project Part of the EU Neuro-IT Network of Excellence

Prof. Stefan Wermter
Chair of Intelligent Systems
Hybrid Intelligent Systems
School of Computing and Technology
University of Sunderland
Prof Friedemann Pulvermüller
Medical Research Council
Cognition and Brain Sciences Unit
Cambridge
Prof. Giacomo Rizzolatti
Institute of Neurophysiology
University of Parma
Dr. Frédéric Alexandre
CORTEX team
INRIA Lorraine/LORIA-CNRS
Nancy
Prof. Guenther Palm
Neuroinformatics
University of Ulm
 

 


MIRA grasping an orange



Recently new theories and experiments in neuroscience have indicated that a biological and neuroscience-oriented approach for multimodal processing will lead to new life-like perception action systems. In particular, concepts from mirror neurons suggest that own actions, observed actions and language are very much interrelated since the same mirror neurons fire at the same time based on experiments with monkeys and humans. Mirror neuron areas correspond to cortical areas which are related to human language centres (e.g. Broca region) and could provide a cortical substrate for the integration of vision, language and action. This project MirrorBot will develop and study emerging embodied representations based on mirror neurons.We will develop new techniques including cell assemblies, associative neural networks, and Hebbian-type learning in order to associate vision, language and motor concepts. We develop biomimetic multimodal learning and language instruction in a robot to investigate the task of searching for objects.
             

MIRA Robot

MIRA Grasping an apple