Learning Forward Models for the Operational Space Control of Redundant Robots - CNRS - Centre national de la recherche scientifique Accéder directement au contenu
Chapitre D'ouvrage Année : 2010

Learning Forward Models for the Operational Space Control of Redundant Robots

Résumé

We present a control approach combining model incremental learning methods with the operational space control approach. We learn the forward kinematics model of a robot and use standard algebraic methods to extract pseudo-inverses and projectors from it. This combination endows the robot with the ability to realize hierarchically organised learned tasks in parallel, using tasks null space projectors built upon the learned models. We illustrate the proposed method on a simulated 3 degrees of freedom planar robot. This system is used as a benchmark to compare our method to an alternative approach based on learning an inverse of the extended Jacobian. We show the better versatility of the retained approach with respect to the latter.
Fichier principal
Vignette du fichier
2010COS1467.pdf (401.93 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00586453 , version 1 (15-04-2011)

Identifiants

Citer

Camille Salaün, Vincent Padois, Olivier Sigaud. Learning Forward Models for the Operational Space Control of Redundant Robots. Olivier Sigaud and Jan Peters. From Motor Learning to Interaction Learning in Robots, Springer, pp.169--192, 2010, Studies in Computational Intelligence, volume 264, ⟨10.1007/978-3-642-05181-4_8⟩. ⟨hal-00586453⟩
136 Consultations
1101 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More