Tactile Classification of Object Materials for Virtual Reality based Robot Teleoperation - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Tactile Classification of Object Materials for Virtual Reality based Robot Teleoperation

Résumé

This work presents a method for tactile classification of materials for virtual reality (VR) based robot teleoperation. In our system, a human-operator uses a remotely controlled robot-manipulator with an optical fibre-based tactile and proximity sensor to scan surfaces of objects in a remote environment. Tactile and proximity data and the robot's endeffector state feedback are used for the classification of objects' materials which are then visualized in the VR reconstruction of the remote environment for each object. Machine learning techniques such as random forest, convolutional neural and multimodal convolutional neural networks were used for material classification. The proposed system and methods were tested with five different materials and classification accuracy of 90% and more was achieved. The results of material classification were successfully exploited for visualising the remote scene in the VR interface to provide more information to the humanoperator.
Fichier principal
Vignette du fichier
Tactile Classification of Object Materialsfor Virtual Reality based Robot Teleoperation.pdf (4.73 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03644224 , version 1 (19-04-2022)

Identifiants

  • HAL Id : hal-03644224 , version 1

Citer

Bukeikhan Omarali, Francesca Palermo, Kaspar Althoefer, Maurizio Valle, Ildar Farkhatdinov. Tactile Classification of Object Materials for Virtual Reality based Robot Teleoperation. 2022 IEEE International Conference on Robotics and Automation (ICRA 2022), IEEE, May 2022, Philadelphie, PA, United States. ⟨hal-03644224⟩

Collections

TDS-MACS
135 Consultations
147 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More