From exploration to imitation: using learnt internal models to imitate others
File(s)DeardenDemirisAISB07.pdf (1.92 MB)
Accepted version
Author(s)
Dearden, A
Demiris, Y
Type
Conference Paper
Abstract
We present an architecture that enables asocial and social learning mechanisms to be combined in a unified framework on a robot. The robot learns two kinds of internal models by interacting with the environment with no a priori knowledge of its own motor system: internal object models are learnt about how its motor system and other objects appear in its sensor data; internal control models are learnt by babbling and represent how the robot controls objects. These asocially-learnt models of the robot’s motor system are used to understand the actions of a human demonstrator on objects that they can both interact with. Knowledge acquired through self-exploration is therefore used as a bootstrapping mechanism to understand others and benefit from their knowledge.
Date Issued
2007-04
Citation
2007, pp.218-226
Publisher
AISB
Start Page
218
End Page
226
Copyright Statement
© 2007 AISB
Description
06.02.14 KB. Ok to add accepted version to Spiral, paper available on publisher website under CC license.
Identifier
http://www.aisb.org.uk/publications/proceedings/aisb2007/aisb07-body.pdf
Source
AISB'07: Artificial and Ambient Intelligence
Source Place
Newcastle, UK
Publication Status
Published
Start Date
2007-04-02
Finish Date
2007-04-04
Coverage Spatial
Newcastle, UK