On the evolution of behaviors through embodied imitation

Erbas, M. D. , Bull, L. and Winfield, A. F. (2015) On the evolution of behaviors through embodied imitation. Artificial Life, 21 (2). pp. 141-165. ISSN 1064-5462 Available from: http://eprints.uwe.ac.uk/26155

[img]
Preview
PDF
Erbas_etal_ArtLife2015_finaldraft.pdf

Download (819kB) | Preview

Abstract/Description

This paper describes research in which embodied imitation and behavioural adaptation are investigated in collective robotics. We model social learning in artificial agents with real robots. The robots are able to observe and learn each others’ movement patterns using their on-board sensors only; so that imitation is embodied. We show that the variations that arise from embodiment allow certain behaviours, that are better adapted to the process of imitation, to emerge and evolve during multiple cycles of imitation. As these behaviours are more robust to uncertainties in the real robots’ sensors and actuators, they can be learned by other members of the collective with higher fidelity. Three different types of learned-behaviour memory have been experimentally tested to investigate the effect of memory capacity on the evolution of movement patterns, and results show that as the movement patterns evolve through multiple cycles of imitation, selection and variation, the robots are able to, in a sense, agree on the structure of the behaviours that are imitated.

Item Type: Article
Uncontrolled Keywords: social learning, behavioural adaptation, embodied imitation, multi-robot systems, swarm intelligence
Faculty/Department: Faculty of Environment and Technology
Depositing User: Professor A. Winfield
Date Deposited: 07 Sep 2015 12:51
Last Modified: 18 Nov 2018 09:30
URI: http://eprints.uwe.ac.uk/id/eprint/26155

Statistics

Downloads
Activity Overview
127Downloads
256Hits
Origin of downloads

Additional statistics for this repository are available via IRStats2

Actions (login required)

View Item View Item