Robot Learning from Unlabelled Teaching Signals

Abstract : At home, workplaces or schools, an increasing amount of intelligent robotic systems are starting to be able to help us in our daily life. A key feature in these new domains is the close interaction between people and robots. In particular, such robotic systems need to be teachable by non-technical users, i.e. programmable for new tasks in novel environments through intuitive, flexible and personalized interactions. Specifically, the challenge we address in this work is how a robot learning a new task can be instructed by a human using its own preferred teaching signals, where the mapping between these signals and their meaning is unknown to the robot. For example, different users may use different languages, words, interjections, gestures or even brain signals to mean "good" or "bad".
Type de document :
Communication dans un congrès
HRI 2014 Pioneers Workshop, Mar 2014, Bielefeld, Germany. 2014
Liste complète des métadonnées

Littérature citée [10 références]  Voir  Masquer  Télécharger
Contributeur : Jonathan Grizou <>
Soumis le : lundi 24 mars 2014 - 18:31:30
Dernière modification le : lundi 17 décembre 2018 - 10:32:47
Document(s) archivé(s) le : mardi 24 juin 2014 - 10:58:08


Fichiers produits par l'(les) auteur(s)


  • HAL Id : hal-00963725, version 1


Jonathan Grizou, Manuel Lopes, Pierre-Yves Oudeyer. Robot Learning from Unlabelled Teaching Signals. HRI 2014 Pioneers Workshop, Mar 2014, Bielefeld, Germany. 2014. 〈hal-00963725〉



Consultations de la notice


Téléchargements de fichiers