Cogprints

From motor babbling to hierarchical learning by imitation: a robot developmental pathway

Demiris, Yiannis and Dearden, Anthony (2005) From motor babbling to hierarchical learning by imitation: a robot developmental pathway. [Conference Paper]

Full text available as:

[img]
Preview
PDF
2967Kb

Abstract

How does an individual use the knowledge acquired through self exploration as a manipulable model through which to understand others and benefit from their knowledge? How can developmental and social learning be combined for their mutual benefit? In this paper we review a hierarchical architecture (HAMMER) which allows a principled way for combining knowledge through exploration and knowledge from others, through the creation and use of multiple inverse and forward models. We describe how Bayesian Belief Networks can be used to learn the association between a robot’s motor commands and sensory consequences (forward models), and how the inverse association can be used for imitation. Inverse models created through self exploration, as well as those from observing others can coexist and compete in a principled unified framework, that utilises the simulation theory of mind approach to mentally rehearse and understand the actions of others.

Item Type:Conference Paper
Keywords:Bayesian belief network, HAMMER architecture, hierarchial social learning, simulation theory of mind, developmental robot
Subjects:Computer Science > Machine Learning
Computer Science > Robotics
ID Code:4961
Deposited By:Prince, Dr Christopher G.
Deposited On:16 Jul 2006
Last Modified:11 Mar 2011 08:56

Metadata

Repository Staff Only: item control page