Jacquard: A Large Scale Dataset for Robotic Grasp Detection - Laboratoire d’Excellence Intelligences des Mondes Urbains
Communication Dans Un Congrès Année : 2018

Jacquard: A Large Scale Dataset for Robotic Grasp Detection

Résumé

Grasping skill is a major ability that a wide number of real-life applications require for robotisation. State-of-the-art robotic grasping methods perform prediction of object grasp locations based on deep neural networks. However, such networks require huge amount of labeled data for training making this approach often impracticable in robotics. In this paper, we propose a method to generate a large scale synthetic dataset with ground truth, which we refer to as the Jacquard grasping dataset. Jacquard is built on a subset of ShapeNet, a large CAD models dataset, and contains both RGB-D images and annotations of successful grasping positions based on grasp attempts performed in a simulated environment. We carried out experiments using an off-the-shelf CNN, with three different evaluation metrics, including real grasping robot trials. The results show that Jacquard enables much better generalization skills than a human labeled dataset thanks to its diversity of objects and grasping positions. For the purpose of reproducible research in robotics, we are releasing along with the Jacquard dataset a web interface for researchers to evaluate the successfulness of their grasping position detections using our dataset.
Fichier principal
Vignette du fichier
root.pdf (2.84 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-01753862 , version 1 (29-03-2018)
hal-01753862 , version 2 (28-09-2018)

Identifiants

Citer

Amaury Depierre, Emmanuel Dellandréa, Liming Chen. Jacquard: A Large Scale Dataset for Robotic Grasp Detection. IEEE/RSJ International Conference on Intelligent Robots and Systems, Oct 2018, Madrid, Spain. ⟨hal-01753862v2⟩
980 Consultations
1674 Téléchargements

Altmetric

Partager

More