Task learning based on the imitation of object's goal

Issue title: Personal Care Robotics

Article type: Research Article

Authors: Acosta Calderon, Carlos A. | Mohan, Rajesh E.

Affiliations: School of Electrical and Electronics Engineering, Singapore Polytechnic, Singapore | Singapore University of Technology and Design, Singapore

Note: [] Corresponding author: Carlos A. Acosta Calderon, School of Electrical and Electronics Engineering, Singapore Polytechnic, 500 Dover Road, 139651 Singapore. E-mail: CarlosAcosta@sp.edu.sg

Abstract: Learning by imitation represents a useful and promising alternative to program robots. The approach presented here is based on two functional elements used by humans to understand and perform actions. These elements are: the body schema and the body percept. The first one is a representation of the body that contains information of the body's capabilities. The body percept is a snapshot of the body and its relation with the environment at a given instant. These elements are believed to interact within humans to generate several abilities, among them the ability to imitate. This paper presents an approach to robot imitation based on these two functional elements, which approaches imitation by identifying the goals from the perceived actions.

Keywords: Robot imitation, body representation, action representation

DOI: 10.3233/ABB-120074

Journal: Applied Bionics and Biomechanics, vol. 9, no. 4, pp. 427-441, 2012