Learning the Combinatorial Structure of Demonstrated Behaviors with Inverse Feedback Control

Olivier Mangin 1, 2 Pierre-Yves Oudeyer 1
1 Flowers - Flowing Epigenetic Robots and Systems
Inria Bordeaux - Sud-Ouest, U2IS - Unité d'Informatique et d'Ingénierie des Systèmes
Abstract : In many applications, such as virtual agents or humanoid robots, it is difficult to represent complex human behaviors and the full range of skills necessary to achieve them. Real life human behaviors are often the combination of several parts and never reproduced in the exact same way. In this work we introduce a new algorithm that is able to learn behaviors by assuming that the observed complex motions can be represented in a smaller dictionary of concurrent tasks. We present an optimization formalism and show how we can learn simultaneously the dictionary and the mixture coefficients that represent each demonstration. We present results on a idealized model where a set of potential functions represents human objectives or preferences for achieving a task.
Type de document :
Article dans une revue
Lecture notes in computer science, springer, 2012, Third International Workshop on Human Behavior Understanding, 7559
Liste complète des métadonnées

Littérature citée [20 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-00764448
Contributeur : Olivier Mangin <>
Soumis le : jeudi 13 décembre 2012 - 09:29:17
Dernière modification le : jeudi 16 novembre 2017 - 17:12:03
Document(s) archivé(s) le : jeudi 14 mars 2013 - 03:46:31

Fichier

mangin.2012.hbu.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-00764448, version 1

Collections

Citation

Olivier Mangin, Pierre-Yves Oudeyer. Learning the Combinatorial Structure of Demonstrated Behaviors with Inverse Feedback Control. Lecture notes in computer science, springer, 2012, Third International Workshop on Human Behavior Understanding, 7559. 〈hal-00764448〉

Partager

Métriques

Consultations de la notice

200

Téléchargements de fichiers

121