Real-time gestural control of robot manipulator through Deep Learning human-pose inference

Abstract : With the raise of collaborative robots, human-robot interaction needs to be as natural as possible. In this work, we present a framework for real-time continuous motion control of a real collabora-tive robot (cobot) from gestures captured by an RGB camera. Through deep learning existing techniques, we obtain human skeletal pose information both in 2D and 3D. We use it to design a controller that makes the robot mirror in real-time the movements of a human arm or hand.
Liste complète des métadonnées

Littérature citée [10 références]  Voir  Masquer  Télécharger

https://hal-mines-paristech.archives-ouvertes.fr/hal-02276236
Contributeur : Fabien Moutarde <>
Soumis le : lundi 2 septembre 2019 - 13:58:01
Dernière modification le : jeudi 5 septembre 2019 - 01:18:00

Fichier

workshop_ICVS_final_BUJALANCE_...
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-02276236, version 1

Citation

Jesus Bujalance, Fabien Moutarde. Real-time gestural control of robot manipulator through Deep Learning human-pose inference. Int. Conf. on Computer Vision Systems, Sep 2019, Thessalonique, Greece. ⟨hal-02276236⟩

Partager

Métriques

Consultations de la notice

103

Téléchargements de fichiers

33