References to related material datacite.relatedItem.IsPartOf	https://arxiv.org/abs/1710.05512
References to related material datacite.relatedItem.IsPartOf	http://proceedings.mlr.press/v78/calandra17a/calandra17a.pdf
Type of the data datacite.resourceTypeGeneral	Dataset
Total size of the dataset datacite.size	110734311436
Author dc.contributor.author	Calandra, Roberto
Author dc.contributor.author	Owens, Andrew
Author dc.contributor.author	Upadhyaya, Manu
Author dc.contributor.author	Yuan, Wenzhen
Author dc.contributor.author	Lin, Justin
Author dc.contributor.author	Adelson, Edward H.
Author dc.contributor.author	Levine, Sergey
Upload date dc.date.accessioned	2025-02-16T12:25:25Z
Publication date dc.date.available	2025-02-16T12:25:25Z
Data of data creation dc.date.created	2017
Publication date dc.date.issued	2025-02-16
Abstract of the dataset dc.description.abstract	This dataset contains 9269 robotic grasps collected from 106 objects, and their corresponding outcome. The hardware used consists of a 7-DoF Sawyer arm, a Weiss WSG-50 parallel gripper, one Microsoft Kinect 2, and two GelSight sensors, one for each finger.
Public reference to this page dc.identifier.uri	https://opara.zih.tu-dresden.de/handle/123456789/1172
Publisher dc.publisher	Technische Universität Dresden
Licence dc.rights	Attribution-NonCommercial-NoDerivatives 4.0 International	en
URI of the licence text dc.rights.uri	http://creativecommons.org/licenses/by-nc-nd/4.0/
Specification of the discipline(s) dc.subject.classification	4::44::409::409-05
Title of the dataset dc.title	The Feeling of Success: Does Touch Sensing Help Predict Grasp Outcomes?
Software opara.descriptionSoftware.ResourceViewing	Python
Project abstract opara.project.description	A successful grasp requires careful balancing of the contact forces. Deducing whether a particular grasp will be successful from indirect measurements, such as vision, is therefore quite challenging, and direct sensing of contacts through touch sensing provides an appealing avenue toward more successful and consistent robotic grasping. However, in order to fully evaluate the value of touch sensing for grasp outcome prediction, we must understand how touch sensing can influence outcome prediction accuracy when combined with other modalities. Doing so using conventional model-based techniques is exceptionally difficult. In this work, we investigate the question of whether touch sensing aids in predicting grasp outcomes within a multimodal sensing framework that combines vision and touch. To that end, we collected more than 9,000 grasping trials using a two-finger gripper equipped with GelSight high-resolution tactile sensors on each finger, and evaluated visuo-tactile deep neural network models to directly predict grasp outcomes from either modality individually, and from both modalities together. Our experimental results indicate that incorporating tactile readings substantially improve grasping performance.
Public project website(s) opara.project.publicReference	https://lasr.org/research/feeling-of-success
Project title opara.project.title	The Feeling of Success: Does Touch Sensing Help Predict Grasp Outcomes?

The Feeling of Success: Does Touch Sensing Help Predict Grasp Outcomes?

Files

Original bundle

License bundle

Collections