Learning to push by grasping: Using multiple tasks for effective learning
Open accessThe DOI matches its Crossref record; 5 of the 5 references it cites were found in a registry or an index.
Abstract
Recently, end-to-end learning frameworks are gaining prevalence in the field of robot control. These frameworks input states/images and directly predict the torques or the action parameters. However, these approaches are often critiqued due to their huge data requirements for learning a task. The argument of the difficulty in scalability to multiple tasks is well founded, since training these tasks often require hundreds or thousands of examples. But do end-to-end approaches need to learn a unique model for every task? Intuitively, it seems that sharing across tasks should help since all tasks require some common understanding of the environment. In this paper, we attempt to take the next step in data-driven end-to-end learning frameworks: move from the realm of task-specific models to joint learning of multiple robot tasks. In an astonishing result we show that models with multi-task learning tend to perform better than task-specific models trained with same amounts of data. For example, a deep-network learned with 2.5K grasp and 2.5K push examples performs better on grasping than a network trained on 5K grasp examples.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Levine, S., Pastor, P., Krizhevsky, A., Ibarz, J., & Quillen, D. (2018) · The International Journal of Robotics Research · doi:10.1177/0278364917710318 · Cited by 1,971
Data-Driven Grasp Synthesis—A Survey
Bohg, J., Morales, A., Asfour, T., & Kragic, D. (2014) · IEEE Transactions on Robotics · doi:10.1109/tro.2013.2289018 · Cited by 929
Kokkinos, I. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.579 · Cited by 657
Stable Pushing: Mechanics, Controllability, and Planning
Lynch, K. M., & Mason, M. T. (1996) · The International Journal of Robotics Research · doi:10.1177/027836499601500602 · Cited by 463
Deep Learning for Detecting Robotic Grasps
Lenz, I., Lee, H., & Saxena, A. (2013) · Robotics: Science and Systems IX · doi:10.15607/rss.2013.ix.012 · Cited by 126
Cited by
Andrychowicz, M., Wolski, F., Ray, A., Schneider, J., Fong, R., Welinder, P., McGrew, B., Tobin, J., Abbeel, P., & Zaremba, W. (2017) · arXiv · doi:10.48550/arxiv.1707.01495 · Cited by 1,355
Learning Synergies Between Pushing and Grasping with Self-Supervised Deep Reinforcement Learning
Zeng, A., Song, S., Welker, S., Lee, J., Rodriguez, A., & Funkhouser, T. (2018) · 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2018.8593986 · Cited by 606
Multi-task Self-Supervised Visual Learning
Doersch, C., & Zisserman, A. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.226 · Cited by 598
Multi-Task Learning with Deep Neural Networks: A Survey
Crawshaw, M. (2020) · arXiv · doi:10.48550/arxiv.2009.09796 · Cited by 428
“(Pinto and Gupta, 2017) uses a shared trunk architecture (shown in figure 9 to jointly learn robotic grasping, pushing, and poking from pixels.”
BackgroundMethodAsymmetric Actor Critic for Image-Based Robot Learning
Pinto, L., Andrychowicz, M., Welinder, P., Zaremba, W., & Abbeel, P. (2018) · Robotics: Science and Systems XIV · doi:10.15607/rss.2018.xiv.008 · Cited by 343
Self-citationGandhi, D., Pinto, L., & Gupta, A. (2017) · 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2017.8206247 · Cited by 253
Self-citationRahmatizadeh, R., Abolghasemi, P., Boloni, L., & Levine, S. (2018) · 2018 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2018.8461076 · Cited by 205
Grasping in the Wild: Learning 6DoF Closed-Loop Grasping From Low-Cost Demonstrations
Song, S., Zeng, A., Lee, J., & Funkhouser, T. (2020) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2020.3004787 · Cited by 185
“More recent data-driven methods explore the prospects of training object-agnostic grasping policies that detect grasps by exploiting learned visual features, without explicitly using object-specific knowledge [26, 23, 24, 8, 18, 37, 17, 21, 7].”
BackgroundWhere2Act: From Pixels to Actions for Articulated 3D Objects
Mo, K., Guibas, L., Mukadam, M., Gupta, A., & Tulsiani, S. (2021) · arXiv · doi:10.48550/arxiv.2101.02692 · Cited by 132
Self-citationCuriosity-Driven Experience Prioritization via Density Estimation
Zhao, R., & Tresp, V. (2019) · arXiv · doi:10.48550/arxiv.1902.08039 · Cited by 47
“There are also many other research works about multi-task RL [45, 8, 11, 23, 37, 15, 50].”
Background
Metadata
- Authors
- Pinto, L., & Gupta, A.
- Venue
- 2017 IEEE International Conference on Robotics and Automation (ICRA)
- Publisher
- IEEE
- Published
- 2017-05
- Pages
- 2161-2168
- ISSN
- 1050-4729 (ISSN-L)
- OpenAlex
- W2524545028
- Cited by
- 99
- References
- 5
- FWCI
- 22.27
- Type
- conference paper
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.