Learning soft task priorities for control of redundant robots - Archive ouverte HAL
Communication Dans Un Congrès Année : 2016

Learning soft task priorities for control of redundant robots

Résumé

One of the key problems in planning and control of redundant robots is the fast generation of controls when multiple tasks and constraints need to be satisfied. In the literature, this problem is classically solved by multi-task prioritized approaches, where the priority of each task is determined by a weight function, describing the task strict/soft priority. In this paper, we propose to leverage machine learning techniques to learn the temporal profiles of the task priorities, represented as parametrized weight functions: we automatically determine their parameters through a stochastic optimization procedure. We show the effectiveness of the proposed method on a simulated 7 DOF Kuka LWR and both a simulated and a real Kinova Jaco arm. We compare the performance of our approach to a state-of-the-art method based on soft task prioritization, where the task weights are typically hand-tuned.
Fichier principal
Vignette du fichier
main_revised.pdf (2.62 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01273409 , version 1 (12-02-2016)

Identifiants

  • HAL Id : hal-01273409 , version 1

Citer

Valerio Modugno, Gerard Neumann, Elmar Rueckert, Giuseppe Oriolo, Jan Peters, et al.. Learning soft task priorities for control of redundant robots. IEEE International Conference on Robotics and Automation (ICRA 2016), May 2016, Stockholm, Sweden. ⟨hal-01273409⟩
338 Consultations
556 Téléchargements

Partager

More