Omnipush: accurate, diverse, real-world dataset of pushing dynamics with RGB-D video
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 met...
| Main Authors: | , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021
|
| Online Access: | https://hdl.handle.net/1721.1/129775 |
| _version_ | 1826207826216747008 |
|---|---|
| author | Bauza Villalonga, Maria Alet, Ferran Yen-Chen, Lin Lozano-Pérez, Tomás Kaelbling, Leslie P Isola, Phillip John Rodriguez, Alberto |
| author2 | Massachusetts Institute of Technology. Department of Mechanical Engineering |
| author_facet | Massachusetts Institute of Technology. Department of Mechanical Engineering Bauza Villalonga, Maria Alet, Ferran Yen-Chen, Lin Lozano-Pérez, Tomás Kaelbling, Leslie P Isola, Phillip John Rodriguez, Alberto |
| author_sort | Bauza Villalonga, Maria |
| collection | MIT |
| description | 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/. |
| first_indexed | 2024-09-23T13:55:33Z |
| format | Article |
| id | mit-1721.1/129775 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T13:55:33Z |
| publishDate | 2021 |
| publisher | IEEE |
| record_format | dspace |
| spelling | mit-1721.1/1297752022-09-28T17:07:23Z Omnipush: accurate, diverse, real-world dataset of pushing dynamics with RGB-D video Bauza Villalonga, Maria Alet, Ferran Yen-Chen, Lin Lozano-Pérez, Tomás Kaelbling, Leslie P Isola, Phillip John Rodriguez, Alberto Massachusetts Institute of Technology. Department of Mechanical Engineering Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory 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/. 2021-02-16T20:11:22Z 2021-02-16T20:11:22Z 2019-11 2019-10 2020-08-03T13:45:09Z Article http://purl.org/eprint/type/ConferencePaper 9781728140049 https://hdl.handle.net/1721.1/129775 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. en 10.1109/IROS40897.2019.8967920 IEEE International Conference on Intelligent Robots and Systems Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf IEEE arXiv |
| spellingShingle | Bauza Villalonga, Maria Alet, Ferran Yen-Chen, Lin Lozano-Pérez, Tomás Kaelbling, Leslie P Isola, Phillip John Rodriguez, Alberto Omnipush: accurate, diverse, real-world dataset of pushing dynamics with RGB-D video |
| title | Omnipush: accurate, diverse, real-world dataset of pushing dynamics with RGB-D video |
| title_full | Omnipush: accurate, diverse, real-world dataset of pushing dynamics with RGB-D video |
| title_fullStr | Omnipush: accurate, diverse, real-world dataset of pushing dynamics with RGB-D video |
| title_full_unstemmed | Omnipush: accurate, diverse, real-world dataset of pushing dynamics with RGB-D video |
| title_short | Omnipush: accurate, diverse, real-world dataset of pushing dynamics with RGB-D video |
| title_sort | omnipush accurate diverse real world dataset of pushing dynamics with rgb d video |
| url | https://hdl.handle.net/1721.1/129775 |
| work_keys_str_mv | AT bauzavillalongamaria omnipushaccuratediverserealworlddatasetofpushingdynamicswithrgbdvideo AT aletferran omnipushaccuratediverserealworlddatasetofpushingdynamicswithrgbdvideo AT yenchenlin omnipushaccuratediverserealworlddatasetofpushingdynamicswithrgbdvideo AT lozanopereztomas omnipushaccuratediverserealworlddatasetofpushingdynamicswithrgbdvideo AT kaelblinglesliep omnipushaccuratediverserealworlddatasetofpushingdynamicswithrgbdvideo AT isolaphillipjohn omnipushaccuratediverserealworlddatasetofpushingdynamicswithrgbdvideo AT rodriguezalberto omnipushaccuratediverserealworlddatasetofpushingdynamicswithrgbdvideo |