BCI Control of Whole-body Simulated Humanoid by Combining Motor Imagery Detection and Autonomous Motion Planning

Abstract : In this paper we demonstrate the coupling of an autonomous planning and control framework for whole-body humanoid motion, with a brain-computer interface (BCI) system in order to achieve online real-time biasing and correction of the offline planned motion. Using the contact-before-motion planning paradigm, the humanoid autonomously plans, in a first stage, its motion to reach a desired goal configuration or contact location. In the second stage of the approach, the humanoid executes the planned motion and the user can exert online some control on the motion being executed through an EEG decoding interface. The method is applied and demonstrated in a dynamics simulator with full collision-detection on a model of the humanoid robot HRP2.
Type de document :
Communication dans un congrès
ICONIP: International Conference on Neural Information Processing, Nov 2013, Daegu, South Korea. 2013, 〈http://www.iconip2013.org/〉
Liste complète des métadonnées

https://hal-lirmm.ccsd.cnrs.fr/lirmm-00863885
Contributeur : François Keith <>
Soumis le : jeudi 19 septembre 2013 - 17:34:55
Dernière modification le : jeudi 24 mai 2018 - 15:59:24

Identifiants

  • HAL Id : lirmm-00863885, version 1

Collections

Citation

Karim Bouyarmane, Joris Vaillant, Norikazu Sugimoto, François Keith, Jun-Ichiro Furukawa, et al.. BCI Control of Whole-body Simulated Humanoid by Combining Motor Imagery Detection and Autonomous Motion Planning. ICONIP: International Conference on Neural Information Processing, Nov 2013, Daegu, South Korea. 2013, 〈http://www.iconip2013.org/〉. 〈lirmm-00863885〉

Partager

Métriques

Consultations de la notice

232