FONOONI, Benjamin; JEVTIC, Aleksandar; HELLSTRÖM, Thomas; JANLERT, Lars-Erik

doi:10.1016/j.robot.2014.12.001

Métadonnées

Afficher la notice complète

Licence d’utilisation du document

FONOONI, Benjamin

JEVTIC, Aleksandar
ESTIA INSTITUTE OF TECHNOLOGY

HELLSTRÖM, Thomas

Langue

Article de revue

Ce document a été publié dans

Robotics and Autonomous Systems. 2015-03, vol. 65, p. 24-39

Résumé en anglais

In domains where robots carry out human’s tasks, the ability to learn new behaviors easily and quickly plays an important role. Two major challenges with Learning from Demonstration (LfD) are to identify what information in a demonstrated behavior requires attention by the robot, and to generalize the learned behavior such that the robot is able to perform the same behavior in novel situations.The main goal of this paper is to incorporate Ant Colony Optimization (ACO) algorithms into LfD in an approach that focuses on understanding tutor’s intentions and learning conditions to exhibit a behavior. The proposed method combines ACO algorithms with semantic networks and spreading activation mechanism to reason and generalize the knowledge obtained through demonstrations. The approach also provides structures for behavior reproduction under new circumstances. Finally, applicability of the system in an object shape classification scenario is evaluated.< Réduire

Mots clés en anglais

Semantic networks

Learning from Demonstration

High-level behavior learning

Ant Colony Optimization

URI

https://oskar-bordeaux.fr/handle/20.500.12278/182648

DOI

http://dx.doi.org/10.1016/j.robot.2014.12.001

Projet Européen

INTeractive RObotics Research Network

Unités de recherche

ESTIA - Recherche