Combining imitation and reinforcement learning to fold deformable planar objects
The DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.
Abstract
Research on robotic manipulation has primarily focused on grasping rigid objects using a single manipulator. It is however evident that in order to be truly pervasive, service robots will need to handle deformable objects, possibly with two arms. In this paper we tackle the problem of using cooperative manipulators to perform towel folding tasks. Differently from other approaches, our method executes what we call a momentum fold - a swinging motion that exploits the dynamics of the object being manipulated. We propose a new learning algorithm that combines imitation and reinforcement learning. Human demonstrations are used to reduce the search space of the reinforcement learning algorithm, which then quickly converges to its final solution. The strengths of the algorithm come from its efficient processing, fast learning capabilities, absence of a deformable object model, and applicability to other problems exhibiting temporally incoherent parameter spaces. A wide range of experiments were performed on a robotic platform, demonstrating the algorithm's capability and practicality.
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
Maitin-Shepard, J., Cusumano-Towner, M., Lei, J., & Abbeel, P. (2010) · 2010 IEEE International Conference on Robotics and Automation · doi:10.1109/robot.2010.5509439 · Cited by 418 · cited 1×
“While the majority of previous works utilizing reinforcement learning bootstrap their algorithm using kinesthetic teaching (i.e. having a human perform actions directly on a gravity-compensated robotic manipulator and recording the parameters from the robot), the fact that we are dealing with two…”
Background
Cited by
Sanchez, J., Corrales, J.-A., Bouzgarrou, B.-C., & Mezouar, Y. (2018) · The International Journal of Robotics Research · doi:10.1177/0278364918779698 · Cited by 457
Modeling, learning, perception, and control methods for deformable object manipulation
Yin, H., Varava, A., & Kragic, D. (2021) · Science Robotics · doi:10.1126/scirobotics.abd8803 · Cited by 299
“This has been shown effective in dual-arm folding and flipping a clothing item (116, 117).”
Sim-to-real reinforcement learning for deformable object manipulation
Matas, J., James, S., & Davison, A. J. (2018) · arXiv · doi:10.48550/arxiv.1806.07851 · Cited by 241
Thananjeyan, B., Garg, A., Krishnan, S., Chen, C., Miller, L., & Goldberg, K. (2017) · 2017 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2017.7989275 · Cited by 144
Seita, D., Florence, P., Tompson, J., Coumans, E., Sindhwani, V., Goldberg, K., & Zeng, A. (2021) · 2021 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra48506.2021.9561391 · Cited by 130
Dynamic Cloth Manipulation with Deep Reinforcement Learning
Jangir, R., Alenya, G., & Torras, C. (2020) · 2020 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra40945.2020.9196659 · Cited by 114
FlingBot: The Unreasonable Effectiveness of Dynamic Manipulation for Cloth Unfolding
Ha, H., & Song, S. (2021) · arXiv · doi:10.48550/arxiv.2105.03655 · Cited by 93
VisuoSpatial Foresight for Multi-Step, Multi-Task Fabric Manipulation
Hoque, R., Seita, D., Balakrishna, A., Ganapathi, A., Tanwani, A., Jamali, N., Yamane, K., Iba, S., & Goldberg, K. (2020) · Robotics: Science and Systems XVI · doi:10.15607/rss.2020.xvi.034 · Cited by 74
Visuospatial foresight for physical sequential fabric manipulation
Hoque, R., Seita, D., Balakrishna, A., Ganapathi, A., Tanwani, A. K., Jamali, N., Yamane, K., Iba, S., & Goldberg, K. (2022) · Autonomous Robots · doi:10.1007/s10514-021-10001-0 · Cited by 45
“Similar work addresses both fabric smoothing and folding, such as by Balaguer and Carpin (2011) and Jia et al. (2018, 2019).”
MethodDextAIRity: Deformable Manipulation Can be a Breeze
Xu, Z., Chi, C., Burchfiel, B., Cousineau, E., Feng, S., & Song, S. (2022) · Robotics: Science and Systems XVIII · doi:10.15607/rss.2022.xviii.017 · Cited by 45
Reinforcement learning of a motor skill for wearing a T-shirt using topology coordinates
Matsubara, T., Shinohara, D., & Kidode, M. (2013) · Advanced Robotics · doi:10.1080/01691864.2013.777012 · Cited by 41
Huang, S. H., Pan, J., Mulcaire, G., & Abbeel, P. (2015) · 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2015.7353475 · Cited by 39
Koganti, N., Tamei, T., Matsubara, T., & Shibata, T. (2014) · The 23rd IEEE International Symposium on Robot and Human Interactive Communication · doi:10.1109/roman.2014.6926241 · Cited by 24
Cloth dynamics modeling in latent spaces and its application to robotic clothing assistance
Koganti, N., Ngeo, J. G., Tomoya, T., Ikeda, K., & Shibata, T. (2015) · 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2015.7353860 · Cited by 23
“[19] proposed a motorskills learning framework for a dual-arm robot to perform towel folding task where the robot learned the optimal trajectory using Imitation Learning and Reinforcement Learning.”
Method
Metadata
- Authors
- Balaguer, B., & Carpin, S.
- Venue
- 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems
- Publisher
- IEEE
- Published
- 2011-09
- Pages
- 1405-1412
- OpenAlex
- W2137549137
- Cited by
- 57
- References
- 1
- FWCI
- 3.76
- Type
- conference paper
- Language
- en
- Open access
- closed
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.