Imitation Learning and Anchoring through Conceptual Spaces

Antonio Chella, Haris Dindo, Ignazio Infantino

Risultato della ricerca: Article

11 Citazioni (Scopus)

Abstract

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 capability to deeply understand 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. Experiments concerned with the problem of teaching a humanoid robotic system simple manipulative tasks are reported.
Lingua originaleEnglish
pagine (da-a)343-359
Numero di pagine17
RivistaApplied Artificial Intelligence
Volume2007
Stato di pubblicazionePublished - 2007

Fingerprint

Robotics
Anchors
Teaching
Experiments

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence

Cita questo

Imitation Learning and Anchoring through Conceptual Spaces. / Chella, Antonio; Dindo, Haris; Infantino, Ignazio.

In: Applied Artificial Intelligence, Vol. 2007, 2007, pag. 343-359.

Risultato della ricerca: Article

@article{833d493aff544d9099baf814893ca0a2,
title = "Imitation Learning and Anchoring through Conceptual Spaces",
abstract = "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 capability to deeply understand 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. Experiments concerned with the problem of teaching a humanoid robotic system simple manipulative tasks are reported.",
keywords = "Robotics, Imitation Learning",
author = "Antonio Chella and Haris Dindo and Ignazio Infantino",
year = "2007",
language = "English",
volume = "2007",
pages = "343--359",
journal = "Applied Artificial Intelligence",
issn = "0883-9514",
publisher = "Taylor and Francis Ltd.",

}

TY - JOUR

T1 - Imitation Learning and Anchoring through Conceptual Spaces

AU - Chella, Antonio

AU - Dindo, Haris

AU - Infantino, Ignazio

PY - 2007

Y1 - 2007

N2 - 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 capability to deeply understand 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. Experiments concerned with the problem of teaching a humanoid robotic system simple manipulative tasks are reported.

AB - 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 capability to deeply understand 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. Experiments concerned with the problem of teaching a humanoid robotic system simple manipulative tasks are reported.

KW - Robotics, Imitation Learning

UR - http://hdl.handle.net/10447/48187

M3 - Article

VL - 2007

SP - 343

EP - 359

JO - Applied Artificial Intelligence

JF - Applied Artificial Intelligence

SN - 0883-9514

ER -