Grasp stability assessment through unsupervised feature learning of tactile images

Cockburn, Deen, Roberge, Jean-Philippe, Thuy-Hong-Loan, Le, 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) pp. 2238-2244. Piscataway, NJ, USA : IEEE.
Compte des citations dans Scopus : 35.

Prévisualisation

PDF Grasp-Stability-Assessment-through-Unsupervised-Feature-Learning-of-Tactile-Images.pdf Télécharger (1MB) | Prévisualisation

Résumé

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
Professeur:	Professeur Roberge, Jean-Philippe Duchaine, Vincent
Affiliation:	Autres, Génie de la production automatisée
Date de dépôt:	24 mars 2017 16:39
Dernière modification:	17 avr. 2020 16:05
URI:	https://espace2.etsmtl.ca/id/eprint/14834

Actions (Authentification requise)

Dernière vérification avant le dépôt