Modeling, learning, perception, and control methods for deformable object manipulation
Open accessThe DOI matches its Crossref record; 124 of the 124 references it cites were found in a registry or an index.
Abstract
Enabling robots to handle deformable objects requires careful integration of data-driven and analytic approaches.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
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?
In the citing paper
“However, the long-term impact of these materials on the human body remains an uncertainty limiting the actual long-term commercial application of the devices in HMI.”
From Flexible Electronics and Devices as Human–Machine Interfaces for Medical Robotics (2022) · cites this paper as [608]
In the citing paper
“IP in the context of deformable objects has mainly been considered using a static camera [7].”
From Interactive Perception for Deformable Object Manipulation (2024) · cites this paper as [7]
Citations
Cites
Trends and challenges in robot manipulation
Billard, A., & Kragic, D. (2019) · Science · doi:10.1126/science.aat8414 · Cited by 993
DynamicFusion: Reconstruction and tracking of non-rigid scenes in real-time
Newcombe, R. A., Fox, D., & Seitz, S. M. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298631 · Cited by 951 · cited 2×
“If a canonical template is not available, it can be iteratively updated (55).”
BackgroundControl Strategies for Soft Robotic Manipulators: A Survey
George Thuruthel, T., Ansari, Y., Falotico, E., & Laschi, C. (2018) · Soft Robotics · doi:10.1089/soro.2017.0007 · Cited by 645
Dual arm manipulation—A survey
Smith, C., Karayiannidis, Y., Nalpantidis, L., Gratal, X., Qi, P., Dimarogonas, D. V., & Kragic, D. (2012) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2012.07.005 · Cited by 560 · cited 1×
“Still, problems remain open on how to account for the coordination and cooperation, for instance, of a bimanual system ( 127 ).”
BackgroundSOFA: A Multi-Model Framework for Interactive Physical Simulation
Faure, F., Duriez, C., Delingette, H., Allard, J., Gilles, B., Marchesseau, S., Talbot, H., Courtecuisse, H., Bousquet, G., Peterlik, I., et al. (2012) · Studies in Mechanobiology, Tissue Engineering and Biomaterials · doi:10.1007/8415_2012_125 · Cited by 460
Sanchez, J., Corrales, J.-A., Bouzgarrou, B.-C., & Mezouar, Y. (2018) · The International Journal of Robotics Research · doi:10.1177/0278364918779698 · Cited by 457
Discovery of complex behaviors through contact-invariant optimization
Mordatch, I., Todorov, E., & Popović, Z. (2012) · ACM Transactions on Graphics · doi:10.1145/2185520.2185539 · Cited by 451 · cited 1×
“MuJoCo is a proprietary engine that has been used for modeling rigid-linked characters ( 30 ) or as the environment backend of re-inforcement learning (RL) benchmarks ( 31 ).”
MethodUnified particle physics for real-time applications
Macklin, M., Müller, M., Chentanez, N., & Kim, T.-Y. (2014) · ACM Transactions on Graphics · doi:10.1145/2601097.2601152 · Cited by 447 · cited 3×
“Ropes (13, 14, 15) Fabrics (16, 17) Simple to implement Lacking physical interpretability Sponges (17, 18) Rubber spheres (18 where k j denotes the stiffness of the j th constraint C j ( x 1 , x 2 , …, x n ) = 0, j = 1,2, ….”
BackgroundMaitin-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×
“Early works on folding detects corners for grasping (74).”
BackgroundReal-time non-rigid reconstruction using an RGB-D camera
Zollhöfer, M., Nießner, M., Izadi, S., Rehmann, C., Zach, C., Fisher, M., Wu, C., Fitzgibbon, A., Loop, C., Theobalt, C., et al. (2014) · ACM Transactions on Graphics · doi:10.1145/2601097.2601165 · Cited by 405
Research works printed but not linked: 6
- Y. Li J. Wu R. Tedrake J. B. Tenenbaum A. Torralba Learning particle dynamics for manipulating rigid bodies deformable objects and fluids in Proceedings of the International Conference on Learning Representations (ICLR) (ICLR 2019).
- P. Giiler K. Pauwels A. Pieropan H. Kjellström D. Kragic Estimating the deformability of elastic materials using optical flow and position-based dynamics in Proceedings of IEEE International Conference on Humanoid Robots (Humanoids) (IEEE 2015) pp. 965–971.
- G. Brockman V. Cheung L. Pettersson J. Schneider J. Schulman J. Tang W. Zaremba OpenAI Gym. arXiv:1606.01540 [cs.LG] (5 June 2016). · arXiv
- J. Grannen P. Sundaresan B. Thananjeyan J. Ichnowski A. Balakrishna M. Hwang V. Viswanath M. Laskey J. E. Gonzalez K. Goldberg Untangling dense knots by learning task relevant keypoints in Proceedings of the Conference on Robot Learning (CoRL) (PMLR 2020).
- D. Seita N. Jamali M. Laskey A. K. Tanwani R. Berenstein P. Baskaran S. Iba J. Canny K. Goldberg Deep transfer learning of pick points on fabric for robot bed-making in International Symposium on Robotics Research (ISRR) (2019).
- J. Liang M. Lin V. Koltun Differentiable cloth simulation for inverse problems in Advances in Neural Information Processing Systems 32 (Curran Associates Inc. 2019) pp. 771–780.
Cited by
Flexible Electronics and Devices as Human–Machine Interfaces for Medical Robotics
Heng, W., Solomon, S., & Gao, W. (2022) · Advanced Materials · doi:10.1002/adma.202107902 · Cited by 609
Challenges and Outlook in Robotic Manipulation of Deformable Objects
Zhu, J., Cherubini, A., Dune, C., Navarro-Alarcon, D., Alambeigi, F., Berenson, D., Ficuciello, F., Harada, K., Kober, J., Li, X., et al. (2022) · IEEE Robotics & Automation Magazine · doi:10.1109/mra.2022.3147415 · Cited by 265
“Lately, [11] reports most recent advances in modeling, learning, perception, and control in DOM.”
BackgroundVisualization in virtual reality: a systematic review
Korkut, E. H., & Surer, E. (2023) · Virtual Reality · doi:10.1007/s10055-023-00753-8 · Cited by 178
“To this end, researchers are still working to improve accuracy, robustness, and processing efficiency while keeping high-fidelity renderings (Yin et al. 2021).”
BackgroundData-Driven Control of Hydraulic Manipulators by Reinforcement Learning
Yao, Z., Xu, F., Jiang, G., & Yao, J. (2023) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2023.3336070 · Cited by 99
“R obotic manipulators have garnered substantial attention in both industrial and academic circles, largely driven by the pressing need to replace human labor in critical work environments [1], [2].”
BackgroundYu, M., Lv, K., Zhong, H., Song, S., & Li, X. (2022) · IEEE Transactions on Robotics · doi:10.1109/tro.2022.3200546 · Cited by 116
“Some analytical modeling methods can be used to model DLOs, such as mass–spring systems, position-based dynamics, and finite-element methods [2], [15].”
BackgroundMethodMultistage Cable Routing Through Hierarchical Imitation Learning
Luo, J., Xu, C., Geng, X., Feng, G., Fang, K., Tan, L., Schaal, S., & Levine, S. (2024) · IEEE Transactions on Robotics · doi:10.1109/tro.2024.3353075 · Cited by 138
“Deformable object manipulation: The manipulation of de-formable materials, such as cloth, rope, and liquid, presents a major challenge for robots [27], [92].”
BackgroundLearning garment manipulation policies toward robot-assisted dressing
Zhang, F., & Demiris, Y. (2022) · Science Robotics · doi:10.1126/scirobotics.abm6010 · Cited by 115
“(23) have pointed out another potential solution, which is to accurately modeling garment states in simulation by identifying the underlying physics correspondence between simulated and real observations.”
BackgroundVersatile adhesive skin enhances robotic interactions with the environment
Linghu, C., Liu, Y., Yang, X., Chen, Z., Feng, J., Zhang, Y., Li, Y., Zhao, Z., Seo, Y.-J., Li, J., et al. (2025) · Science Advances · doi:10.1126/sciadv.adt4765 · Cited by 83
Hydrogel and Machine Learning for Soft Robots’ Sensing and Signal Processing: A Review
Wang, S., & Sun, Z. (2022) · Journal of Bionic Engineering · doi:10.1007/s42235-022-00320-y · Cited by 71
“Therefore, the overlap among soft robots, hydrogel sensors, and machine learning is increasing dramatically [30], and it is worthy of more review papers to dive into the interdisciplinary field.”
BackgroundRoboCraft: Learning to See, Simulate, and Shape Elasto-Plastic Objects with Graph Networks
Shi, H., Xu, H., Huang, Z., Li, Y., & Wu, J. (2022) · Robotics: Science and Systems · doi:10.15607/rss.2022.xviii.008 · Cited by 77
Liu, F., Su, E., Lu, J., Li, M., & Yip, M. C. (2023) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2023.3264766 · Cited by 80
“M ODELING and simulation of deformable objects have recently been of considerable interest in many robotic applications [2], [3], [4].”
BackgroundDefGraspSim: Physics-Based Simulation of Grasp Outcomes for 3D Deformable Objects
Huang, I., Narang, Y., Eppner, C., Sundaralingam, B., Macklin, M., Bajcsy, R. K., Hermans, T., & Fox, D. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3158725 · Cited by 77
“For comprehensive reviews of 3D deformable modeling techniques, please refer to [26], [27].”
BackgroundVision AI-based human-robot collaborative assembly driven by autonomous robots
Liu, S., Zhang, J., Wang, L., & Gao, R. X. (2024) · CIRP Annals · doi:10.1016/j.cirp.2024.03.004 · Cited by 58
Yu, M., Zhong, H., & Li, X. (2022) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra46639.2022.9812244 · Cited by 73
Zhang, J., Zhao, H., Chen, K., Fei, G., Li, X., Wang, Y., Yang, Z., Zheng, S., Liu, S., & Ding, H. (2025) · Robotics and Computer-Integrated Manufacturing · doi:10.1016/j.rcim.2025.103021 · Cited by 66
Zhou, P., Zheng, P., Qi, J., Li, C., Lee, H.-Y., Duan, A., Lu, L., Li, Z., Hu, L., & Navarro-Alarcón, D. (2024) · Robotics and Computer-Integrated Manufacturing · doi:10.1016/j.rcim.2024.102727 · Cited by 57
Unfolding the Literature: A Review of Robotic Cloth Manipulation
Longhini, A., Wang, Y., Garcia-Camacho, I., Blanco–Mulero, D., Moletta, M., Welle, M. C., Alenyà, G., Yin, H., Erickson, Z., Held, D., et al. (2024) · Annual Review of Control Robotics and Autonomous Systems · doi:10.1146/annurev-control-022723-033252 · Cited by 73
Self-citationAirBender: Adaptive Transportation of Bendable Objects Using Dual UAVs
Xu, J., Gao, L., Fierro, R., & Saldaña, D. (2025) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2025.3536276 · Cited by 47
“While conventional studies have focused mainly on rigid bodies and point-mass models for multirotor physical interactions [1], [2], real-world scenarios often involve nonrigidity, introducing deformations and elastic properties that significantly influence interaction outcomes [3], [4].”
Humanoid electronic-skin technology for the era of Artificial Intelligence of Things
Zhang, H., Hong, J., Zhu, J., Duan, S., Xia, M., Chen, J., Sun, B., Xi, M., Gao, F., Xiao, Y., et al. (2025) · Matter · doi:10.1016/j.matt.2025.102136 · Cited by 53
Huo, S., Duan, A., Li, C., Zhou, P., Ma, W., Wang, H., & Navarro-Alarcón, D. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3154842 · Cited by 47
Jiang, C., Xu, W., Li, Y., Yu, Z., Wang, L., Hu, X., Xie, Z., Liu, Q., Yang, B., Wang, X., et al. (2024) · Nature Communications · doi:10.1038/s41467-024-53654-y · Cited by 62
“On the other hand, the tactile array should be a stretchable interface, ensuring conformal contact with deformable objects 27 .”
Among Us: Adversarially Robust Collaborative Perception by Consensus
Li, Y., Fang, Q., Bai, J., Chen, S., Juefei-Xu, F., & Feng, C. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00024 · Cited by 45
A survey on imitation learning for contact-rich tasks in robotics
Tsuji, T., Kato, Y., Solak, G., Zhang, H., Petrič, T., Nori, F., & Ajoudani, A. (2026) · The International Journal of Robotics Research · doi:10.1177/02783649261417694 · Cited by 74
A review of learning-based dynamics models for robotic manipulation
Ai, B., Tian, S., Shi, H., Wang, Y., Pfaff, T., Tan, C., Christensen, H. I., Su, H., Wu, J., & Li, Y. (2025) · Science Robotics · doi:10.1126/scirobotics.adt1497 · Cited by 91
“Although prior reviews focused on related topics, such as deformable object manipulation ( 24 , 25 ), physics-based simulation ( 26 , 27 ), and intuitive physics ( 28 ), a dedicated review of learning-based dynamics models is lacking.”
Sundaresan, P., Antonova, R., & Bohg, J. (2022) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros47612.2022.9981101 · Cited by 41
“Recent surveys have reviewed learning-based approaches for manipulation and perception of deformables [16], [17], including methods for tracking and registration.”
RoboCraft: Learning to see, simulate, and shape elasto-plastic objects in 3D with graph networks
Shi, H., Xu, H., Huang, Z., Li, Y., & Wu, J. (2023) · The International Journal of Robotics Research · doi:10.1177/02783649231219020 · Cited by 72
“Recent advances show promising results in manipulating clothes [38, 36, 60, 15, 63, 17] and ropes [62, 57], yet the manipulation of objects with high plasticity, such as dough or plasticine, poses a unique set of challenges and is currently underexplored [37], despite the ubiquity of such objects…”
Tang, C., Chang, X., Wang, J., Peng, Y., Wu, H., & Wang, H. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3343795 · Cited by 38
“Despite the extensive deployment of robotic grippers in industry, grasping and manipulating delicate and deformable objects is still challenging [3].”
BackgroundYu, M., Lv, K., Wang, C., Tomizuka, M., & Li, X. (2023) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48891.2023.10160264 · Cited by 38
“In addition to rigid objects, deformable linear objects (DLOs) are also common in human life, such as cables, wires, ropes, rods, etc [2]; however, there are new challenges coming from the deformable properties of DLOs when applying classical manipulation methods to DLO manipulation [3], [4].”
BackgroundMethodGu, F., Wang, Z., Zhu, Z., Ma, J., Zhou, Y., Jiang, S., & He, B. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.134058 · Cited by 48
Cooperative Manipulation of Deformable Objects by Single-Leader–Dual-Follower Teleoperation
Huang, D., Li, B., Li, Y., & Yang, C. (2022) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2021.3139228 · Cited by 35
“Moreover, as for manipulation of deformable objects such as organs, tissues, cables and household laundries [18]–[20], researchers presented practical methods to endow the manipulator with touching sense [21] and achieve high-precision force tracking when interacting with soft objects [22] [23].”
MethodVIRDO: Visio-tactile Implicit Representations of Deformable Objects
Wi, Y., Florence, P., Zeng, A., & Fazeli, N. (2022) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra46639.2022.9812097 · Cited by 34
Qi, J., Ran, G., Wang, B., Liu, J., Ma, W., Zhou, P., & Navarro-Alarcón, D. (2023) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2023.3346758 · Cited by 33
“To perform shape servoing tasks, a feedback controller requires a model that captures the relationship between the robot’s motions and the produced object’s deformations [14].”
Algorithms and Systems for Manipulating Multiple Objects
Pan, Z., Zeng, A., Li, Y., Yu, J., & Hauser, K. K. (2022) · IEEE Transactions on Robotics · doi:10.1109/tro.2022.3197013 · Cited by 41
“paving [64], and shaping of plastic objects [18, 85, 143].”
BackgroundDual-Arm Mobile Manipulation Planning of a Long Deformable Object in Industrial Installation
Qin, Y., Escande, A., Kanehiro, F., & Yoshida, E. (2023) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2023.3264779 · Cited by 32
“Model-based methods like mass-spring systems, finite element methods (FEMs) require accurate physical parameters of the deformable objects, which are often difficult to obtain [6].”
MethodDeng, L., Shen, Y., Fan, G., He, X., Li, Z., & Yuan, Y. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3158440 · Cited by 32
Construction Robotics in Extreme Environments: From Earth to Space
You, K., Zhou, C., Ding, L., & Wang, Y. (2025) · Engineering · doi:10.1016/j.eng.2024.11.037 · Cited by 38
Learning differentiable dynamics models for shape control of deformable linear objects
Yang, Y., Stork, J. A., & Stoyanov, T. (2022) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2022.104258 · Cited by 39
Learning to Estimate 3-D States of Deformable Linear Objects from Single-Frame Occluded Point Clouds
Lv, K., Yu, M., Pu, Y., Jiang, X., Huang, G. M., & Li, X. (2023) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48891.2023.10160784 · Cited by 30
“Robotic manipulation of deformable linear objects (DLOs), such as ropes and wires, has a wide variety of applications in industrial, service, and health-care sectors [1], [2].”
BackgroundA Robust Deformable Linear Object Perception Pipeline in 3D: From Segmentation to Reconstruction
Zhaole, S., Zhou, H., Li, N., Chen, L., Zhu, J., & Fisher, R. B. (2023) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2023.3337695 · Cited by 28
Learning-Based MPC With Safety Filter for Constrained Deformable Linear Object Manipulation
Tang, Y., Chu, X., Huang, J., & Au, K. W. S. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3362643 · Cited by 28
“MPC searches for a sequence of optimal actions by solving a multi-step decision-making problem [9] in the form of where H is the prediction horizon and q init is the initial system configuration. γ ≤ 1 is a discount factor. c and c T are the path and terminal objective functions encoding…”
BackgroundKadi, H. A., & Terzić, K. (2023) · Sensors · doi:10.3390/s23052389 · Cited by 27
“Covering modelling, perception and traditional and data-driven control approaches, Yin et al. (2021) [19] provide a similar review but broaden their lens to include the DO domain as a whole.”
BackgroundMethodZhao, Y., Qian, K., Duan, B., & Luo, S. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3396665 · Cited by 41
“However, simulating the dynamics of deformable bodies, including the motion of markers on optical tactile sensors, remains a challenging task with existing methods [24].”
BackgroundSüberkrüb, F., Laezza, R., & Karayiannidis, Y. (2022) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros47612.2022.9982065 · Cited by 27
Learning to Singulate Layers of Cloth using Tactile Feedback
Tirumala, S., Weng, T., Seita, D., Kroemer, O., Temel, Z., & Held, D. (2022) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros47612.2022.9981341 · Cited by 38
A systematic literature review of computer vision applications in robotized wire harness assembly
Wang, H., Salunkhe, O., Quadrini, W., Lämkull, D., Ore, F., Despeisse, M., Fumagalli, L., Stahre, J., & Johansson, B. (2024) · Advanced Engineering Informatics · doi:10.1016/j.aei.2024.102596 · Cited by 32
Learning Keypoints for Robotic Cloth Manipulation Using Synthetic Data
Lips, T., Gusseme, V.-L. D., & wyffels, F. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3405335 · Cited by 37
“However, due to their variety in shape and appearance, complex deformations and self-occlusions, cloth manipulation and perception are challenging [1], [2].”
BackgroundYu, M., Lv, K., Wang, C., Jiang, Y., Tomizuka, M., & Li, X. (2024) · The International Journal of Robotics Research · doi:10.1177/02783649241276886 · Cited by 34
“The fi nite-element method is a general and accurate method for modeling deformable objects with physical fi delity and interpretability, but the computation is usually too expensive for robotic applications (Reddy, 2019; Yin et al., 2021).”
Learning Physically Realizable Skills for Online Packing of General 3D Shapes
Zhao, H., Pan, Z., Yu, Y., & Xu, K. (2023) · ACM Transactions on Graphics · doi:10.1145/3603544 · Cited by 38
“Exploiting deformation during planning to achieve tighter packing [Yin et al. 2021] is also an interesting direction.”
BackgroundGraph Learning in Robotics: A Survey
Pistilli, F., & Averta, G. (2023) · IEEE Access · doi:10.1109/access.2023.3323220 · Cited by 31
“…[62], [63], in robotic grasping and manipulation several problems are still open, such as learning to interact with objects in motion or in clutter [64], [65], [66], manipulation of deformable objects [67], [68], [69], [70], [71] - for which a proper modelling is crucial as discussed in Sec.”
BackgroundLearning Graph Dynamics With External Contact for Deformable Linear Objects Shape Control
Huang, Y., Xia, C., Wang, X., & Liang, B. (2023) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2023.3264764 · Cited by 29
“Robotic manipulation of DLO has been widely studied in recent years [1], [2].”
BackgroundDo robots outperform humans in human-centered domains?
Riener, R., Rabezzana, L., & Zimmermann, Y. (2023) · Frontiers in Robotics and AI · doi:10.3389/frobt.2023.1223946 · Cited by 33
Sim2Real Neural Controllers for Physics-Based Robotic Deployment of Deformable Linear Objects
Tong, D., Choi, A., Qin, L., Huang, W., Joo, J., & Jawed, M. K. (2023) · The International Journal of Robotics Research · doi:10.1177/02783649231214553 · Cited by 24
“Multiple methods exist for modeling DLOs (Yin et al., 2021; Sanchez et al., 2018).”
Liang, X., Liu, F., Zhang, Y., Li, Y., Lin, S., & Yip, M. C. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10610263 · Cited by 22
“Extensive research has been done on modeling, motion planning, and data representations for perception perspectives [7].”
BackgroundA Bayesian Treatment of Real-to-Sim for Deformable Object Manipulation
Antonova, R., Yang, J., Sundaresan, P., Fox, D., Ramos, F. T., & Bohg, J. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3157377 · Cited by 29
Robotic co-manipulation of deformable linear objects for large deformation tasks
Almaghout, K., Cherubini, A., & Klimchik, A. S. (2024) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2024.104652 · Cited by 31
TrackDLO: Tracking Deformable Linear Objects Under Occlusion With Motion Coherence
Xiang, J., Dinkel, H., Zhao, H., Gao, N., Coltin, B., Smith, T., & Bretl, T. W. (2023) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2023.3303710 · Cited by 21
Enabling Visual Action Planning for Object Manipulation Through Latent Space Roadmap
Lippi, M., Poklukar, P., Welle, M. C., Varava, A., Yin, H., Marino, A., & Kragić, D. (2022) · IEEE Transactions on Robotics · doi:10.1109/tro.2022.3188163 · Cited by 25
“This is especially useful in complex scenarios where explicit analytical modeling of states is challenging, such as in manipulation of highly deformable objects, which is recently gaining increasing attention by the research community [2], [3].”
BackgroundSelf-citationLearning Neural Force Manifolds for Sim2Real Robotic Symmetrical Paper Folding
Choi, A., Tong, D., Terzopoulos, D., Joo, J., & Jawed, M. K. (2024) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2024.3366909 · Cited by 24
“Prior research has focused primarily on manipulating either cloth or ropes [1], [2], and, as a result, the challenge of robotically manipulating many other deformable objects still lacks robust solutions.”
Qi, J., Lu, L., Wang, F., Lee, H.-Y., Navarro-Alarcón, D., Zhang, Z., & Zhou, P. (2025) · Robotics and Computer-Integrated Manufacturing · doi:10.1016/j.rcim.2025.103096 · Cited by 22
Deformation-Aware Data-Driven Grasp Synthesis
Le, T. N., Lundell, J., Abu‐Dakka, F. J., & Kyrki, V. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3146551 · Cited by 20
“Yin et al. [31] presents three primary deformable object modelling approaches, Mass-Spring System (MSS), Position-based Dynamics (PBD), and FEM, and their limitations.”
BackgroundDesign and Experiments of a Novel Halbach-Cylinder-Based Magnetic Skin: A Preliminary Study
Gui, M.-J., Zhou, X.-H., Xie, X., Liu, S.-Q., Li, H., Xiang, T., Wang, J., & Hou, Z. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3147904 · Cited by 19
“DEVELOPMENT and implementation of robots are hampered by tactile perception technologies [1], [2].”
BackgroundCellular micromasonry: biofabrication with single cell precision
Ellison, S. T., Duraivel, S., Subramaniam, V., Hugosson, F., Yu, B., Lebowitz, J. J., Khoshbouei, H., Lele, T. P., Martindale, M. Q., & Angelini, T. E. (2022) · Soft Matter · doi:10.1039/d2sm01013e · Cited by 19
“However, we believe that all the steps in cellular micromasonry can be automated by combining a diversity of current engineering tools like 3D image segmentation, 3D cell tracking, and the control algorithms of pick-and-place robotics (27).”
BackgroundMethodRobotic Control of the Deformation of Soft Linear Objects Using Deep Reinforcement Learning
Daniel, M., Aranda, M., Lequièvre, L., Lengagne, S., Ramón, J. A. C., & Mezouar, Y. (2022) · IEEE International Conference on Automation Science and Engineering (CASE) · doi:10.1109/case49997.2022.9926667 · Cited by 23
“deformable objects are, on the one hand, only formulated for simple tasks [1] such as hanging a cloth [14], [15] or moving a rope [12].”
BackgroundMethodInfluentialTactile based robotic skills for cable routing operations
Monguzzi, A., Pelosi, M., Zanchettin, A. M., & Rocco, P. (2023) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48891.2023.10160729 · Cited by 18
“DLOs manipulation is widespread in several tasks, both industrial and not, as specified in [1], [2].”
BackgroundBimanual Deformable Bag Manipulation Using a Structure-of-Interest Based Neural Dynamics Model
Zhou, P., Zheng, P., Qi, J., Li, C., Lee, H.-Y., Pan, Y., Yang, C., Navarro-Alarcón, D., & Pan, J. (2024) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2024.3485471 · Cited by 22
“D EFORMABLE object manipulation (DOM) [1], [2], [3] is a fundamental capability for robots to meaningfully interact with the physical world and assist in various human tasks.”
Graph-based Task-specific Prediction Models for Interactions between Deformable and Rigid Objects
Weng, Z., Paus, F., Varava, A., Yin, H., Asfour, T., & Kragic, D. (2021) · 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros51168.2021.9636660 · Cited by 17
“While multiple works address rigid object manipulation, modeling and predicting the scene dynamics of highlydeformable objects such as cloth, which is essential for many real-life tasks [2], [3], remains challenging.”
BackgroundSelf-citationOnline Model Learning for Shape Control of Deformable Linear Objects
Yang, Y., Stork, J. A., & Stoyanov, T. (2022) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros47612.2022.9981080 · Cited by 17
“linear object manipulation in the field of robotics [1]–[3], like inserting and threading a needle [4], [5], surgical suturing [6], [7], or controlling the shape of a rope [8].”
BackgroundShape Control of Elastic Deformable Linear Objects for Robotic Cable Assembly
Cao, B., Zang, X., Zhang, X., Chen, Z., Li, S., & Zhao, J. (2024) · Advanced Intelligent Systems · doi:10.1002/aisy.202300835 · Cited by 17
Zhao, C., Liu, J., & Ma, D. (2024) · IEEE Transactions on Robotics · doi:10.1109/tro.2024.3502197 · Cited by 26
UnfoldIR: Tactile Robotic Unfolding of Cloth
Proesmans, R., Verleysen, A., & wyffels, F. (2023) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2023.3284382 · Cited by 21
“Cloth manipulation has emerged as a major test bench for new approaches to these issues [2], being notoriously difficult due to the great variability in textile materials and their immeasurable capability to deform.”
BackgroundAn offline geometric model for controlling the shape of elastic linear objects
Aghajanzadeh, O., Aranda, M., Nicolás, G. L., Lenain, R., & Mezouar, Y. (2022) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros47612.2022.9981466 · Cited by 17
“For this reason, this field has acquired great relevance recently [1].”
BackgroundDeep Reinforcement Learning Based on Local GNN for Goal-Conditioned Deformable Object Rearranging
Deng, Y., Xia, C., Wang, X., & Chen, L. (2022) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros47612.2022.9981669 · Cited by 21
“The first challenge lies in the high dimensionality of the configuration space [7], which makes the observation and representation of deformable”
BackgroundHuang, D., Yang, C., Li, M., Huang, H., & Li, Y. (2023) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2022.3229149 · Cited by 16
“To extend the MRS’s ability to hold and move especially volumetric deformable objects [15], different physical models of deformable objects are introduced in [22].”
BackgroundFresnillo, P. M., Vasudevan, S., Mohammed, W. M., Lastra, J. L. M., & García, J. A. P. (2023) · Mechatronics · doi:10.1016/j.mechatronics.2023.103085 · Cited by 15
General-Purpose Clothes Manipulation with Semantic Keypoints
Deng, Y., & Hsu, D. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11128573 · Cited by 20
“Clothes have high-dimensional state [3] and diverse geometric structures, which vary significantly across different categories.”
Digital Twin Integration for Active Learning in Robotic Manipulator Control Within Engineering 4.0
Pantusin, F. J., Ortiz, J. S., Carvajal, C. P., Andaluz, V. H., Yar, L. G., Robertí, F., & Gandolfo, D. C. (2025) · Symmetry · doi:10.3390/sym17101638 · Cited by 14
Visual-tactile pretraining and online multitask learning for humanlike manipulation dexterity
Ye, Q., Liu, Q., Wang, S., Chen, J., Cui, Y., Jin, K., Chen, H., Cai, X., Li, G., & Chen, J. (2026) · Science Robotics · doi:10.1126/scirobotics.ady2869 · Cited by 32
Calculation of envelope area between grinding tool and curved surface
Chen, P., Zhao, H., Li, X., & Ding, H. (2023) · International Journal of Mechanical Sciences · doi:10.1016/j.ijmecsci.2023.108680 · Cited by 14
Occlusion-Robust Autonomous Robotic Manipulation of Human Soft Tissues With 3-D Surface Feedback
Hu, J., Jones, D. A., Doğar, M. R., & Valdastri, P. (2023) · IEEE Transactions on Robotics · doi:10.1109/tro.2023.3335693 · Cited by 13
“However, acquiringandlabelinglargedatasets from real-robot interactions can be costly [10].”
BackgroundMethodInfluentialTheodoropoulos, N. G., Kampourakis, E., Andronas, D., & Makris, S. (2023) · Journal of Manufacturing Systems · doi:10.1016/j.jmsy.2023.08.022 · Cited by 13
Gu, F., Sang, H., Zhou, Y., Ma, J., Jiang, R., Wang, Z., & He, B. (2025) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2025.3530957 · Cited by 18
“Several analytical methods, including Mass-Spring Systems (MSSs), Position-Based Dynamics (PBD), and Finite-Element Methods (FEMs), can be used to model DLOs’ dynamics [4].”
SoftGrasp: Adaptive grasping for dexterous hand based on multimodal imitation learning
Li, Y., Guo, C., Ren, J., Chen, B., Cheng, C., Zhang, H., & Lu, H. (2025) · Biomimetic Intelligence and Robotics · doi:10.1016/j.birob.2025.100217 · Cited by 25
Learning Thin Deformable Object Manipulation With a Multisensory Integrated Soft Hand
Zhao, C., Jiang, C., Luo, L., Yuan, S., Chen, Q., & Yu, H. (2025) · IEEE Transactions on Robotics · doi:10.1109/tro.2025.3588448 · Cited by 13
“Concurrently, learning-based methods have prominence in deformable object manipulation [1], [26], which is largely attributed to the capability to infer action from sensory input, bypassing the complexities of direct physical modeling [27], [28], [29], [30].”
Effective grasping enables successful robot-assisted dressing
Borràs, J. (2022) · Science Robotics · doi:10.1126/scirobotics.abo7229 · Cited by 12
“Many recent reviews, such as [6, 7], point out the need to integrate model-based and data-driven approaches and the still-open challenge to find a simplified representation of cloth that not only encodes enough from the multidimensional deformation state but also allows for a high-level understanding of such deformati…”
BackgroundPerception of Static and Dynamic Forces with a Bio-inspired Tactile Fingertip
Qin, L., Shi, X., Wang, Y., & Zhou, Z. (2023) · Journal of Bionic Engineering · doi:10.1007/s42235-023-00344-y · Cited by 12
Gabellieri, C., & Franchi, A. (2023) · International Conference on Unmanned Aircraft Systems (ICUAS) · doi:10.1109/icuas57906.2023.10156297 · Cited by 12
DefGraspNets: Grasp Planning on 3D Fields with Graph Neural Nets
Huang, I., Narang, Y., Bajcsy, R. K., Ramos, F. T., Hermans, T., & Fox, D. (2023) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48891.2023.10160986 · Cited by 12
“However, such simulators rely on complex numerical models like the gold-standard 3D finite element method (FEM) [8,9].”
BackgroundLearning to Simulate Tree-Branch Dynamics for Manipulation
Jacob, J., Bandyopadhyay, T., Williams, J., Borges, P., & Ramos, F. T. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3349830 · Cited by 12
“The comprehensive surveys [9] and [10] detail established techniques to represent shapes, mange the dynamics, and apply learning strategies, all in order to perform control and planning with deformables.”
BackgroundWu, S., Zhang, J., & Wu, D. (2024) · Advanced Engineering Informatics · doi:10.1016/j.aei.2024.102874 · Cited by 13
Zhao, S., Li, Z., Xia, H., & Cui, R. (2023) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2023.3320710 · Cited by 11
“The capacity of a robotic system to perform complex and challenging tasks using two arms or grippers parallels the abilities of human beings when addressing intricate projects together, which exceeds the capacity of one single arm or gripper, as demonstrated in [3] and [4].”
Zhai, X., Jiang, L., Wu, H., Zheng, H., Liu, D., Wu, X., Xu, Z., & Zhou, X. (2024) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2024.3418018 · Cited by 10
“In conclusion, the stiffness value of the human demonstration process can be expressed as, according to Eq.10, 11: The coordinated interaction enables improving the precision of object placement and reducing energy consumption [43].”
2D/3D Image morphing technology from traditional to modern: A survey
Lin, J., Gu, Y., Du, G., Qu, G., Chen, X., Zhang, Y., Gao, S., Liu, Z., & Gunasekaran, N. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102913 · Cited by 10
Yang, X., Ji, Z., & Lai, Y. (2025) · The International Journal of Robotics Research · doi:10.1177/02783649251334661 · Cited by 10
“…applying these methods is problematic because it is extremely dif fi cult and often infeasible to accurately model and perceive real-world elastoplastic materials and measure the underlying physics parameters that govern their motions and deformations (Arriola-Rios et al., 2020; Yin et al., 2021).”
InfluentialLiu, J., Li, Z., Lin, W., Calinon, S., Tan, K. C., & Chen, F. (2023) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros55552.2023.10341846 · Cited by 10
“Compared with deformable object manipulation that has been well studied [1] [2] [3], the shape change of soft objects is not elastic deformation, which makes it more difficult to predict the shape change outcome.”
BackgroundLearning visual-based deformable object rearrangement with local graph neural networks
Deng, Y., Wang, X., & Chen, L. (2023) · Complex & Intelligent Systems · doi:10.1007/s40747-023-01048-w · Cited by 13
Deng, H., Ahmad, F., Xiong, J., & Xia, Z. (2024) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2024.3371111 · Cited by 9
“D EFORMABLE object manipulation (DOM) has given rise to an emerging set of robotic applications in recent years [1].”
Zhang, Y., Liu, F., Xiao, L., & Yip, M. C. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10611111 · Cited by 15
“Research in cloth dynamics, explored in computer graphics and robotics, encompasses various modeling techniques, from mass-spring systems to FEM continuum mechanics [17], [9], [18].”
BackgroundAn AI‐Enabled All‐In‐One Visual, Proximity, and Tactile Perception Multimodal Sensor
Pu, M., Zhao, T., Zhang, L., Han, C., Chai, Z., Zhou, Y., Ding, H., & Wu, Z. (2025) · Advanced Robotics Research · doi:10.1002/adrr.202500062 · Cited by 9
Deformable and Fragile Object Manipulation: A Review and Prospects
Zhu, Y., Yang, D., & Li, Y. (2025) · Sensors · doi:10.3390/s25175430 · Cited by 16
“Deformable object manipulation (DOM) is a pivotal and complex challenge in robotics, with extensive real-world applications in domains such as robotic surgery, agriculture, food handling, waste sorting, caregiving, and household service [1,2].”
CLTP: Contrastive Language-Tactile Pre-training for 3D contact geometry understanding
Ma, W., Cao, X., Zhang, Y., Zhang, C., Yang, S., Hao, P., Fang, B., Cai, Y., Cui, S., & Wang, S. (2026) · Biomimetic Intelligence and Robotics · doi:10.1016/j.birob.2026.100324 · Cited by 15
Metadata
- Authors
- Yin, H., Varava, A., & Kragic, D.
- Affiliations
- KTH Royal Institute of Technology (SE)
- Robotics, Perception, and Learning (RPL), School of Electrical Engineering and Computer Science, Royal Institute for Technology (KTH), Stockholm, Sweden.
- Corresponding author
- Yin, Hang
- Venue
- Science Robotics
- Published
- 2021-05-12
- Volume
- 6
- Issue
- 54
- ISSN
- 2470-9476 (ISSN-L)
- OpenAlex
- W3164946289
- Cited by
- 299
- References
- 124
- Citations by year
- 2026: 56 · 2025: 73 · 2024: 70 · 2023: 55 · 2022: 39 · 2021: 6
- FWCI
- 5.76
- Type
- journal article
- Language
- en
- Open access
- green
- urn.kb.se
- Licence
- other-oa
- Locations
- Science Robotics (publishedVersion)
- PubMed (publishedVersion)
- KTH Publication Database DiVA (KTH Royal Institute of Technology) (submittedVersion, other-oa)
- Research at the University of Copenhagen (University of Copenhagen) (submittedVersion)
- Funders
- H2020 European Research Council
- Swedish Foundation for Strategic Research
- Knut och Alice Wallenbergs Stiftelse
- Topics
- Physical Sciences › Engineering › Control and Systems Engineering › Robot Manipulation and Learning
- Physical Sciences › Engineering › Biomedical Engineering › Soft Robotics and Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
- Keywords
- deformable object manipulation, robotic manipulation, data-driven learning, model priors, simulation environment, benchmarking, food handling, planning, control
- MeSH terms
- Computer Simulation, Humans, Learning, Perception, Robotics, Physical Phenomena, Mechanical Phenomena
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.