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.
Document type :
Journal articles
Liste complète des métadonnées

Cited literature [20 references]  Display  Hide  Download

https://hal.inria.fr/hal-00764448
Contributor : Olivier Mangin <>
Submitted on : Thursday, December 13, 2012 - 9:29:17 AM
Last modification on : Wednesday, December 19, 2018 - 1:08:13 PM
Document(s) archivé(s) le : Thursday, March 14, 2013 - 3:46:31 AM

File

mangin.2012.hbu.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00764448, version 1

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⟩

Share

Metrics

Record views

214

Files downloads

150