Anchoring by Imitation Learning in Conceptual Spaces

In order to have a robotic system able to effectively learn by imitation, and not merely reproduce the movements of a human teacher, the system should have the capabilities of deeply understanding the perceived actions to be imitated. This paper deals with the development of a cognitive architecture for learning by imitation in which a rich conceptual representation of the observed actions is built. The purpose of the following discussion is to show how the same conceptual representation can be used both in a bottom-up approach, in order to learn sequences of actions by imitation learning paradigm, and in a top-down approach, in order to anchor the symbolical representations to the perceptual activities of the robotic system. The proposed architecture has been tested on the robotic system composed of a PUMA 200 industrial manipulator and an anthropomorphic robotic hand. The system demonstrated the ability to learn and imitate a set of movement primitives acquired through the vision system for simple manipulative purposes.