A Mirror Neuron Inspired Hierarchical Network for Action Selection

In this paper we propose an approach to robot learning by imitation that uses the multimodal inputs of language instruction, vision and motor. In our approach a student robot learns from a teacher robot how to perform three separate behaviours, 'pick', 'lift' and 'go' based on these inputs. We considered two neural architectures for performing this robot learning. First, a one-step 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 behaviour. In response we produced a hierarchical 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 and the hierarchical organisation of the motor system with regards to demonstration learning.

@InProceedings{EWZW04, 
 	 author =  {Elshaw, Mark I. and Weber, Cornelius and Zochios, Alex and Wermter, Stefan},  
 	 title = {A Mirror Neuron Inspired Hierarchical Network for Action Selection}, 
 	 booktitle = {Proceedings of NeuroBotics Workshop},
 	 editors = {},
 	 number = {},
 	 volume = {},
 	 pages = {98--105},
 	 year = {2004},
 	 month = {Sep},
 	 publisher = {},
 	 doi = {}, 
 }