Erbas, M. D., Bull, L. and Winfield, A. F.
On the evolution of behaviors through embodied imitation.
Artificial Life, 21 (2).
Available from: http://eprints.uwe.ac.uk/26155
Publisher's URL: http://dx.doi.org/10.1162/ARTL_a_00164
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.
|Uncontrolled Keywords:||social learning, behavioural adaptation, embodied imitation, multi-robot systems, swarm intelligence|
|Faculty/Department:||Faculty of Environment and Technology|
Professor A. Winfield
|Deposited On:||07 Sep 2015 12:51|
|Last Modified:||18 Oct 2016 00:34|
Request a change to this item
Total Document Downloads in Past 12 Months