Repository logo
Log in(current)
Repository logoMIT Open ScholarshipDSpace@MIT
  1. Home
  2. MIT Open Access Articles
  3. MIT Open Access Articles
  4. Omnipush: accurate, diverse, real-world dataset of pushing dynamics with RGB-D video

Omnipush: accurate, diverse, real-world dataset of pushing dynamics with RGB-D video

Thumbnail Image
Download
Name

1910.00618.pdf

Description
Submitted version
Size

4.64 MB

Format

Adobe PDF

Checksum (MD5)

6eddef698af0b06c77c998c9108197bc

sword-2020-08-03T13:45:09.original.xml (130 B)
Original SWORD entry document
Author(s)
Bauza Villalonga, Maria
•
Alet, Ferran
•
Yen-Chen, Lin
•
Lozano-Pérez, Tomás
•
Kaelbling, Leslie P
•
Isola, Phillip John
•
Rodriguez, Alberto
Date Issued
November 2019
Journal
IEEE International Conference on Intelligent Robots and Systems
Publisher
IEEE
Citation
Bauza, Maria et al. "Omnipush: accurate, diverse, real-world dataset of pushing dynamics with RGB-D video" IEEE International Conference on Intelligent Robots and Systems, November 2019, Macau, China, Institute of Electrical and Electronics Engineering © 2019 IEEE.
Version
Original manuscript
Abstract
Pushing is a fundamental robotic skill. Existing work has shown how to exploit models of pushing to achieve a variety of tasks, including grasping under uncertainty, in-hand manipulation and clearing clutter. Such models, however, are approximate, which limits their applicability. Learning-based methods can reason directly from raw sensory data with accuracy, and have the potential to generalize to a wider diversity of scenarios. However, developing and testing such methods requires rich-enough datasets. In this paper we introduce Omnipush, a dataset with high variety of planar pushing behavior.In particular, we provide 250 pushes for each of 250 objects, all recorded with RGB-D and a high precision tracking system. The objects are constructed so as to systematically explore key factors that affect pushing-The shape of the object and its mass distribution-which have not been broadly explored in previous datasets, and allow to study generalization in model learning. Omnipush includes a benchmark for meta-learning dynamic models, which requires algorithms that make good predictions and estimate their own uncertainty. We also provide an RGB video prediction benchmark and propose other relevant tasks that can be suited with this dataset. Data and code are available at https://web.mit.edu/mcube/omnipush-dataset/.
MIT Department
Massachusetts Institute of Technology. Department of Mechanical Engineering
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
http://creativecommons.org/licenses/by-nc-sa/4.0/
Persistent DSpace Link
https://hdl.handle.net/1721.1/129775
DOI of Published Version
https://doi.org/10.1109/IROS40897.2019.8967920
Repository logo
PrivacyPermissionsAccessibilityContact us
Repository logo
Notify us about copyright concerns.