Representation, Recognition and Generation of Actions in the Context of Imitation Learning

The 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. We adopt the paradigm of conceptual spaces, in which static and dynamic entities are employed to efficiently organize perceptual data, to recognize positional relations, to learn movements from human demonstration and to generate complex actions by combining and sequencing simpler ones. The aim is to have a robotic system able to effiectively learn by imitation and which has the capabilities of deeply understanding the perceived actions to be imitated. Experimentation has been performed on a robotic system composed of a PUMA 200 industrial manipulator and an anthropomorphic robotic hand.

Authors and Affiliations

1. DINFO, Dipartimento Ingengeria Informatica, Università degli Studi di Palermo, Viale delle Scienze Ed. 6,90128, Palermo, Italy

   Haris Dindo

2. ICAR, Istituto di Calcolo e Reti ad Alte Prestazioni, Consiglio Nazionale delle Ricerche, Viale delle Scienze Ed. 11, 90128 Palermo, Italy

   Ignazio Infantino

Reprints and permissions

Policies and ethics