FRANÇAIS
A showcase of ÉTS researchers’ publications and other contributions
SEARCH

Grasp stability assessment through unsupervised feature learning of tactile images

Downloads

Downloads per month over past year

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 : 14.

[thumbnail of Grasp-Stability-Assessment-through-Unsupervised-Feature-Learning-of-Tactile-Images.pdf]
Preview
PDF
Grasp-Stability-Assessment-through-Unsupervised-Feature-Learning-of-Tactile-Images.pdf

Download (1MB) | Preview

Abstract

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.

Item Type: Conference proceeding
Professor:
Professor
Roberge, Jean-Philippe
Duchaine, Vincent
Affiliation: Autres, Génie de la production automatisée
Date Deposited: 24 Mar 2017 16:39
Last Modified: 17 Apr 2020 16:05
URI: https://espace2.etsmtl.ca/id/eprint/14834

Actions (login required)

View Item View Item