Self-Supervised Learning for Precise Pick-and-Place Without Object Model
Open accessThe DOI matches its Crossref record; 5 of the 5 references it cites were found in a registry or an index.
Abstract
Flexible pick-and-place is a fundamental yet challenging task within robotics, in particular due to the need of an object model for a simple target pose definition. In this work, the robot instead learns to pick-and-place objects using planar manipulation according to a single, demonstrated goal state. Our primary contribution lies within combining robot learning of primitives, commonly estimated by fully-convolutional neural networks, with one-shot imitation learning. Therefore, we define the place reward as a contrastive loss between real-world measurements and a task-specific noise distribution. Furthermore, we design our system to learn in a self-supervised manner, enabling real-world experiments with up to 25 000 pick-and-place actions. Then, our robot is able to place trained objects with an average placement error of (2.7 ± 0.2) mm and (2.6 ± 0.8)o. As our approach does not require an object model, the robot is able to generalize to unknown objects while keeping a precision of (5.9 ± 1.1) mm and (4.1 ± 1.2)o. We further show a range of emerging behaviors: The robot naturally learns to select the correct object in the presence of multiple object types, precisely inserts objects within a peg game, picks screws out of dense clutter, and infers multiple pick-and-place actions from a single goal state.
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
(2016) · Springer Handbooks · doi:10.1007/978-3-319-32552-1 · Cited by 2,122
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
QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation
Kalashnikov, D., Irpan, A., Pastor, P., Ibarz, J., Herzog, A., Jang, E., Quillen, D., Holly, E., Kalakrishnan, M., Vanhoucke, V., et al. (2018) · arXiv · doi:10.48550/arxiv.1806.10293 · Cited by 697
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
One-Shot Visual Imitation Learning via Meta-Learning
Finn, C., Yu, T., Zhang, T., Abbeel, P., & Levine, S. (2017) · arXiv · doi:10.48550/arxiv.1709.04905 · Cited by 341 · cited 3×
“[3], we limit our policy to a single time step and a discrete action space.”
BackgroundMethodInfluential
Cited by
Transporter Networks: Rearranging the Visual World for Robotic Manipulation
Zeng, A., Florence, P., Tompson, J., Welker, S., Chien, J., Attarian, M., Armstrong, T., Krasin, I., Duong, D., Wahid, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2010.14406 · Cited by 200
Weihs, L., Deitke, M., Kembhavi, A., & Mottaghi, R. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00586 · Cited by 98
“Some works address some of these issues, such as generalization to new objects or imperfect perception [54, 6].”
BackgroundSpeedFolding: Learning Efficient Bimanual Folding of Garments
Avigal, Y., Berscheid, L., Asfour, T., Kröger, T., & Goldberg, K. (2022) · 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros47612.2022.9981402 · Cited by 95
“We choose a U-Net architecture over fully convolutional NN used in prior robotics manipulation works [29], [30], [10], [25] as U-Nets are better suited for high-resolution inputs that we find necessary for detecting edges and wrinkles for garment smoothing.”
MethodSelf-citation
Metadata
- Authors
- Berscheid, L., Meisner, P., & Kroger, T.
- Venue
- IEEE Robotics and Automation Letters
- Published
- 2020-07
- Volume
- 5
- Issue
- 3
- Pages
- 4828-4835
- ISSN
- 2377-3766 (ISSN-L)
- 2377-3774
- OpenAlex
- W3036642894
- Cited by
- 76
- References
- 5
- FWCI
- 5.46
- Type
- journal article
- 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.