Untying cable by combining 3D deep neural network with deep reinforcement learning
Abstract
In this study, we propose a framework to solve the cable traction problem where many cables are needed, such as in factories, schools, etc. Our framework is divided into three stages: First, we use SegNet to recognize the cable in the image, build a 3D voxel model by 3D-VAE-GAN, and transform the voxel model to a 3D particle model in Unity3D by the Position-Based Dynamics method. Second, features learned by a 3D deep neural network (PointNet++) from the 3D model are fed into a deep reinforcement learning (RL) network (DQN) to get a series of actions to untie the 3D cable model in Unity3D. Finally, we input the action sequence to the robot arm to untie the cable in the real world. Experimental results show that compared with traditional methods, our method has successfully applied artificial intelligence algorithms to help the computer learn how to untie knotted cables by itself in the virtual world. The untying operations learned in the virtual world can be also used to untie the cable in the real world.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Fan et al. used DRL algorithm Deep Q-learning (DQN) that takes embedded states as input and discretised grasping points and moving directions as action, and they achieved a 54% success rate on single-arm knot untying knots on a table.
“Fan et al. (2022) [43] use DRL algorithm Deep Q-learning (DQN) [126] that takes embedded states as input and discretised grasping points and moving directions as action. They achieve a 54% success rate on single-arm knot untying knots on a table.”
From Data-Driven Robotic Manipulation of Cloth-like Deformable Objects: The Present, Challenges and Future Prospects (2023) · cites this paper as [43]
Cites
Human-level control through deep reinforcement learning
Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A. A., Veness, J., Bellemare, M. G., Graves, A., Riedmiller, M., Fidjeland, A. K., Ostrovski, G., et al. (2015) · Nature · doi:10.1038/nature14236 · Cited by 30,357 · see citing works
SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
Badrinarayanan, V., Kendall, A., & Cipolla, R. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2644615 · Cited by 19,631 · see citing works
2014 IEEE/RSJ International Conference on Intelligent Robots and Systems
(2014) · doi:10.1109/iros20755.2014 · Cited by 1,309 · see citing works
2022 International Conference on Robotics and Automation (ICRA)
(2022) · doi:10.1109/icra46639.2022 · Cited by 467 · see citing works
Unified particle physics for real-time applications
Macklin, M., Müller, M., Chentanez, N., et al. (2014) · ACM Transactions on Graphics · doi:10.1145/2601097.2601152 · Cited by 452 · see citing works
2003 IEEE/RSJ international conference on intelligent robots and systems (IROS 2003)
(2003) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2003.1248780 · Cited by 88 · see citing works
Realization of Five Types of Tabletop Knotting with Dual-Arm Robot
Katano, R., Gomi, T., Tomizawa, T., et al. (2015) · Journal of the Robotics Society of Japan · doi:10.7210/jrsj.33.505 · Cited by 11 · see citing works
Shape modeling of a string and recognition using distance sensor
Mukai, K., Matsuno, T., Yanou, A., et al. (2015) · IEEE RO-MAN · doi:10.1109/roman.2015.7333624 · Cited by 10 · see citing works
String shape recognition using enhanced matching method from 3D point cloud data
Shirakawa, T., Matsuno, T., Yanou, A., et al. (2015) · IEEE/SICE International Symposium on System Integration (SII) · doi:10.1109/sii.2015.7405021 · Cited by 7 · see citing works
Linear Object Manipulation Including Knotting/Unknotting
Wakamatsu, H., TSUMAYA, A., Arai, E., & Hirai, S. (2005) · Journal of the Robotics Society of Japan · doi:10.7210/jrsj.23.344 · Cited by 5 · see citing works
Wakamatsu, H., TSUMAYA, A., Arai, E., & Hirai, S. (2006) · Journal of the Robotics Society of Japan · doi:10.7210/jrsj.24.523 · Cited by 4 · see citing works
Deep Adversarial Reinforcement Learning for Object Disentangling
Laux, M., Arenz, O., Peters, J., & Pajarinen, J. (2020) · IEEE/RJS International Conference on Intelligent RObots and Systems · doi:10.1109/iros45743.2020.9341578 · Cited by 4 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Kadi, H. A., & Terzić, K. (2023) · Sensors · doi:10.3390/s23052389 · Cited by 19 · see citing works
“Unity with Obi [41] has been used by Weng et al. (2021) [42] for generating synthetic data for bag manipulation and it could provide a good commercial environment for rope manipulation [43].”
Method
- Authors
- Fan, Z., Shao, W., Hayashi, T., & Ohashi, T.
- Affiliations
- Kyushu Institute of Technology (JP)
- Corresponding author
- Fan, Zheming
- Venue
- Advanced Robotics
- Publisher
- Informa UK Limited
- Published
- 2022-09-26
- Volume
- 37
- Issue
- 5
- Pages
- 380-394
- ISSN
- 0169-1864 (ISSN-L)
- 1568-5535
- OpenAlex
- W4297092688
- Cited by
- 2
- References
- 12
- Citations by year
- 2023: 1 · 2022: 1
- FWCI
- 0.16
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Advanced Robotics (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
- Physical Sciences › Engineering › Control and Systems Engineering › Robot Manipulation and Learning
- Physical Sciences › Engineering › Computational Mechanics › 3D Shape Modeling and Analysis
- Keywords
- SegNet, 3D voxel model, PointNet, deep reinforcement learning, deep Q-network, position-based dynamics, Unity game engine, robotic arm control, sim-to-real transfer
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
