La vitrine de diffusion des publications et contributions des chercheurs de l'ÉTS

Grasp stability assessment through unsupervised feature learning of tactile images

Cockburn, Deen et Roberge, Jean-Philippe et Thuy-Hong-Loan, Le et Maslyczyk, Alexis et Duchaine, Vincent. 2017. « Grasp stability assessment through unsupervised feature learning of tactile images ». In 2017 IEEE International Conference on Robotics and Automation (ICRA) (Singapore, Singapore, May 29- June 03, 2017), p. 2238-2244. Piscataway, NJ, USA : IEEE.


Télécharger (1MB) | Prévisualisation


Grasping tasks have always been challenging for robots, despite recent innovations in vision-based algorithms and object-specific training. If robots are to match human abilities and learn to pick up never-before-seen objects, they must combine vision with tactile sensing. This paper present a novel way to improve robotic grasping: by using tactile sensors and an unsupervised feature-learning approach, a robot can find the common denominators behind successful and failed grasps, and use this knowledge to predict whether a grasp attempt will succeed or fail. This method is promising as it uses only high-level features from two tactile sensors to evaluate grasp quality, and works for the training set as well as for new objects. In total, using a total of 54 different objects, our system recognized grasp failure 83.70% of time.

Type de document: Compte rendu de conférence
Duchaine, Vincent
Affiliation: Génie de la production automatisée
Date de dépôt: 24 mars 2017 16:39
Dernière modification: 30 août 2017 20:43

Actions (Authentification requise)

Dernière vérification avant le dépôt Dernière vérification avant le dépôt

Statistiques de téléchargement

Plus de statistiques ...