Affordances, development and imitation

Abstract

We present a developmental perspective of robot learning that uses affordances as the link between sensory-motor coordination and imitation. The key concept is a general model for affordances able to learn the statistical relations between actions, object properties and the effects of actions on objects. Based on the learned affordances, it is possible to perform simple imitation games providing both task interpretation and planning capabilities. To evaluate the approach, we provide results of affordance learning with a real robot and simple imitation games with people.