CoChat
Sign Up
Cited by 45Robot Manipulation and LearningSoft Robotics and ApplicationsReinforcement Learning in Robotics

DextAIRity: Deformable Manipulation Can be a Breeze

Open access
Xu, Zhenjia, Chi, Cheng, Burchfiel, Benjamin, Cousineau, Eric, Feng, Siyuan, Song, Shuran·2022·Robotics: Science and Systems XVIII
DOI 10.15607/rss.2022.xviii.017
Open this paper in CoChat — free accountOpen PDF

Abstract

This paper introduces DextAIRity, an approach to manipulate deformable objects using active airflow. In contrast to conventional contact-based quasi-static manipulations, DextAIRity allows the system to apply dense forces on out-of-contact surfaces, expands the system's reach range, and provides safe high-speed interactions. These properties are particularly advantageous when manipulating under-actuated deformable objects with large surface areas or volumes. We demonstrate the effectiveness of DextAIRity through two challenging deformable object manipulation tasks: cloth unfolding and bag opening. We present a self-supervised learning framework that learns to effectively perform a target task through a sequence of grasping or air-based blowing actions. By using a closed-loop formulation for blowing, the system continuously adjusts its blowing direction based on visual feedback in a way that is robust to the highly stochastic dynamics. We deploy our algorithm on a real-world three-arm system and present evidence suggesting that DextAIRity can improve system efficiency for challenging deformable manipulation tasks, such as cloth unfolding, and enable new applications that are impractical to solve with quasi-static contact-based manipulations (e.g., bag opening). Video is available at https://youtu.be/_B0TpAa5tVo

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.15607/rss.2022.xviii.017

Cites

6 of 6 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

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?

  • Advancements in complex 3D deformable bag manipulation do not incorporate an active movable camera for task achievement.

    “Notably, advancements in complex 3D deformable bag manipulation have been presented [27], [28], [29], [30], [31]. These works have shown significant progress in the domain but do not incorporate an active movable camera for task achievement.”

    From Interactive Perception for Deformable Object Manipulation (2024) · cites this paper as [29]

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 46

  1. [1][1] Benjamin Balaguer and Stefano Carpin. Combining imitation and reinforcement learning to fold deformable planar objects. In 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems , pages 1405-1412. IEEE, 2011. 2 -
  2. [2][2] Abhishek Bamotra, Pushpinder Walia, Avataram Venkatavaradan Prituja, and Hongliang Ren. Fabrication and characterization of novel soft compliant robotic end-effectors with negative pressure and mechanical advantages. In 2018 3rd International Conference on Advanced Robotics and Mechatronics (ICARM) , pages 369-374. IEEE, 2018. 2 -
  3. [3][3] Hugo Bertiche, Meysam Madadi, and Sergio Escalera. Cloth3d: Clothed 3d humans. In European Conference on Computer Vision , pages 344-359. Springer, 2020. 5 -
  4. [4][4] David K Biegelsen, Andrew A Berlin, Patrick Cheung, Markus PJ Fromherz, David Goldberg, Warren B Jackson, Bryan Preas, James Reich, and Lars E Swartz. Airjet paper mover: An example of mesoscale mems. In Micromachined Devices and Components VI , volume 4176, pages 122-129. International Society for Optics and Photonics, 2000. URL https://doi.org/10.1117/12.395620. 3 - · DOI
  5. [5][5] Liang-Chieh Chen, George Papandreou, Florian Schroff, and Hartwig Adam. Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587 , 2017. URL https://arxiv.org/pdf/1706. 05587.pdf. 4 - · arXiv
  6. [6][6] S Davis, JO Gray, and Darwin G Caldwell. An end effector based on the bernoulli principle for handling sliced fruit and vegetables. Robotics and Computer-Integrated Manufacturing , 24(2):249-257, 2008. URL https://www.sciencedirect.com/science/article/ pii/S0736584506001347. 2 -
  7. [7][7] F Erzincanli, JM Sharp, and S Erhal. Design and operational considerations of a non-contact robotic handling system for non-rigid materials. International Journal of Machine Tools and Manufacture , 38(4):353-361, 1998. URL https://doi.org/10.1016/S0890-6955(97)00037-0. 2 - · DOI
  8. [8][8] Juan M Escano, Manuel G Ortega, and Francisco R Rubio. Position control of a pneumatic levitation system. In 2005 IEEE Conference on Emerging Technologies and Factory Automation , volume 1, pages 6-pp. IEEE, 2005. URL https://ieeexplore.ieee.org/stamp/stamp.jsp? tp=&arnumber=1612568. 3 -
  9. [9][9] Aditya Ganapathi, Priya Sundaresan, Brijen Thananjeyan, Ashwin Balakrishna, Daniel Seita, Jennifer Grannen, Minho Hwang, Ryan Hoque, Joseph E Gonzalez, Nawid Jamali, et al. Learning dense visual correspondences in simulation to smooth and fold real fabrics. In 2021 IEEE International Conference on Robotics and Automation (ICRA) , pages 11515-11522. IEEE, 2021. 2 -
  10. [10][10] Huy Ha and Shuran Song. Flingbot: The unreasonable effectiveness of dynamic manipulation for cloth unfolding. In Conference on Robotic Learning (CoRL) , 2021. URL https://arxiv.org/pdf/2105.03655.pdf. 2, 3, 4, 5, 6 - · arXiv
  11. [11][11] Huy Ha, Jingxi Xu, and Shuran Song. Learning a decentralized multi-arm motion planner. CoRL , 2020. 9 -
  12. [12][12] Ayanna M Howard and George A Bekey. Prototype system for automated sorting and removal of bags of hazardous waste. In Intelligent Robots and Computer Vision XV: Algorithms, Techniques, Active Vision, and Materials Handling , volume 2904, pages 271-277. International Society for Optics and Photonics, 1996. 2 -
  13. [13][13] Ayanna M Howard and George A Bekey. Intelligent learning for deformable object manipulation. Autonomous Robots , 9(1):51-58, 2000. 2 -
  14. [15][15] Satoshi Konishi and Hiroyuki Fujita. A conveyance system using air flow based on the concept of distributed micro motion systems. Journal of microelectromechanical systems , 3(2):54-58, 1994. 3 -
  15. [16][16] Satoshi Konishi and Hiroyuki Fujita. Two-dimensional conveyance system using cooperative motions of many microactuators. In Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems. IROS'96 , volume 2, pages 988-992. IEEE, 1996. 3 -
  16. [17][17] Satoshi Konishi, Yasushi Mizuguchi, and Kazuyuki Ohno. Development of a non-contact conveyance system composed of distributed nozzle units. In 1999 7th IEEE International Conference on Emerging Technologies and Factory Automation. Proceedings ETFA'99 (Cat. No. 99TH8467) , volume 1, pages 593-598. IEEE, 1999. URL https://ieeexplore.ieee.org/stamp/stamp.jsp? tp=&arnumber=815409. 3 -
  17. [19][19] Yunzhu Li, Jiajun Wu, Russ Tedrake, Joshua B Tenenbaum, and Antonio Torralba. Learning particle dynamics for manipulating rigid bodies, deformable objects, and fluids. In ICLR , 2019. URL http://dpi.csail.mit.edu/ dpi-paper.pdf. 3 -
  18. [20][20] Vincent Lim, Huang Huang, Lawrence Yunliang Chen, Jonathan Wang, Jeffrey Ichnowski, Daniel Seita, Michael Laskey, and Ken Goldberg. Planar robot casting with real2sim2real self-supervised learning. arXiv preprint arXiv:2111.04814 , 2021. 2 - · arXiv
  19. [21][21] Xingyu Lin, Yufei Wang, Jake Olkin, and David Held. Softgym: Benchmarking deep reinforcement learning for deformable object manipulation. CoRL , 2020. 3 -
  20. [22][22] Xingyu Lin, Yufei Wang, Zixuan Huang, and David Held. Learning visible connectivity dynamics for cloth smoothing. In Conference on Robot Learning , 2021. 2 -
  21. [24][24] Matthew T Mason and Kevin M Lynch. Dynamic manipulation. In Proceedings of 1993 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS'93) , volume 1, pages 152-159. IEEE, 1993. URL http://citeseerx.ist.psu.edu/viewdoc/download?doi= 10.1.1.15.1943&rep=rep1&type=pdf. 2 -
  22. [25][25] Paul C Nordine and Robert M Atkins. Aerodynamic levitation of laser-heated solids in gas jets. Review of Scientific Instruments , 53(9):1456-1464, 1982. URL https: //aip.scitation.org/doi/pdf/10.1063/1.1137196. 3 - · DOI
  23. [26][26] Babur Ozcelik and Fehmi Erzincanli. A non-contact end-effector for the handling of 27. [garments. Robotica , 20(4):447-450, 2002. URL https://www.cambridge.org/core/journals/robotica/article/ noncontact-endeffector-for-the-handling-of-garments/ 20711AA699FAA3665F34030BEDC95E49. 2](https://www.cambridge.org/core/journals/robotica/article/noncontact-endeffector-for-the-handling-of-garments/20711AA699FAA3665F34030BEDC95E49) -
  24. [27][27] Babur Ozcelik and Fehmi Erzincanli. Examination of the movement of a woven fabric in the horizontal direction using a non-contact end-effector. The International Journal of Advanced Manufacturing Technology , 25(5): 527-532, 2005. URL https://link.springer.com/article/10. 1007/s00170-004-2075-x. 2 -
  25. [28][28] Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems , 32: 8026-8037, 2019. URL https://arxiv.org/pdf/1912.01703. pdf. 5 - · arXiv
  26. [29][29] Kristopher SJ Pister, Ronald S Fearing, and Roger T Howe. A planar air levitated electrostatic actuator system. In IEEE Proceedings on Micro Electro Mechanical Systems, An Investigation of Micro Structures, Sensors, Actuators, Machines and Robots. , pages 67-71. IEEE, 1990. 3 -
  27. [30][30] Daniela Rus and Michael T Tolley. Design, fabrication and control of soft robots. Nature , 521(7553):467-475, 2015. 2 -
  28. [31][31] Siddharth Sanan, Justin B Moidel, and Christopher G Atkeson. Robots with inflatable links. In 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems , pages 4331-4336. IEEE, 2009. URL https://ieeexplore.ieee.org/stamp/stamp.jsp? tp=&arnumber=5354151. 2 -
  29. [32][32] Daniel Seita, Nawid Jamali, Michael Laskey, Ron Berenstein, Ajay Kumar Tanwani, Prakash Baskaran, Soshi Iba, John F. Canny, and Ken Goldberg. Robot bedmaking: Deep transfer learning using depth sensing of deformable fabric. CoRR , abs/1809.09810, 2018. URL http://arxiv.org/abs/1809.09810. 3 - · arXiv
  30. [33][33] Daniel Seita, Aditya Ganapathi, Ryan Hoque, Minho Hwang, Edward Cen, Ajay Kumar Tanwani, Ashwin Balakrishna, Brijen Thananjeyan, Jeffrey Ichnowski, Nawid Jamali, et al. Deep imitation learning of sequential fabric smoothing from an algorithmic supervisor. In 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) , pages 9651-9658. IEEE, 2020. 2 -
  31. [35][35] Daniel Seita, Justin Kerr, John Canny, and Ken Goldberg. Initial Results on Grasping and Lifting Physical Deformable Bags with a Bimanual Robot. In IROS Workshop on Robotic Manipulation of Deformable Objects in Real-world Applications , 2021. 2, 3 -
  32. [36][36] Mizuho Shibata, Tsuyoshi Ohta, and Shinichi Hirai. Robotic unfolding of hemmed fabric using pinching slip motion. In The Abstracts of the international conference on advanced mechatronics: toward evolutionary fusion of IT and mechatronics: ICAM 2010.5 , pages 392-397. The Japan Society of Mechanical Engineers, 2010. 2 -
  33. [37][37] Priya Sundaresan, Jennifer Grannen, Brijen Thananjeyan, Ashwin Balakrishna, Michael Laskey, Kevin Stone, Joseph E Gonzalez, and Ken Goldberg. Learning rope manipulation policies using dense object descriptors trained on synthetic depth data. In 2020 IEEE International Conference on Robotics and Automation (ICRA) , pages 9411-9418. IEEE, 2020. 2 -
  34. [38][38] Amirreza Tootchi, Saeed Amirkhani, and Ali Chaibakhsh. Modeling and control of an air levitation ball and pipe laboratory setup. In 2019 7th International Conference on Robotics and Mechatronics (ICRoM) , pages 29-34. IEEE, 2019. URL https://ieeexplore.ieee.org/stamp/stamp. jsp?tp=&arnumber=9071827. 3 -
  35. [39][39] Chen Wang, Shaoxiong Wang, Branden Romero, Filipe Veiga, and Edward Adelson. Swingbot: Learning physical features from in-hand tactile exploration for dynamic swing-up manipulation. In 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) , pages 5633-5640. IEEE, 2020. URL https://arxiv.org/pdf/ 2101.11812.pdf. 2 -
  36. [40][40] Faizil Wasbari, RA Bakar, Leong Ming Gan, MM Tahir, and Ahmad Anas Yusof. A review of compressed-air hybrid technology in vehicle system. Renewable and Sustainable Energy Reviews , 67:935-953, 2017. 2 -
  37. [42][42] Zehang Weng, Fabian Paus, Anastasiia Varava, Hang Yin, Tamim Asfour, and Danica Kragic. Graphbased task-specific prediction models for interactions between deformable and rigid objects. arXiv preprint arXiv:2103.02932 , 2021. 2 - · arXiv
  38. [43][43] Jimmy Wu, Xingyuan Sun, Andy Zeng, Shuran Song, Johnny Lee, Szymon Rusinkiewicz, and Thomas Funkhouser. Spatial action maps for mobile manipulation. In Proceedings of Robotics: Science and Systems (RSS) , 2020. URL https://arxiv.org/abs/2004.09141. 4 - · arXiv
  39. [44][44] Jimmy Wu, Xingyuan Sun, Andy Zeng, Shuran Song, Szymon Rusinkiewicz, and Thomas Funkhouser. Learning pneumatic non-prehensile manipulation with a mobile blower. arXiv preprint arXiv:2204.02390 , 2022. 2 - · arXiv
  40. [45][45] Yilin Wu, Wilson Yan, Thanard Kurutach, Lerrel Pinto, and Pieter Abbeel. Learning to manipulate deformable objects without demonstrations. arXiv preprint arXiv:1910.13439 , 2019. 2 - · arXiv
  41. [47][47] Zhenjia Xu, He Zhanpeng, and Shuran Song. Umpnet: Universal manipulation policy network for articulated objects. IEEE Robotics and Automation Letters , 2022. 4 -
  42. [48][48] Kengo Yamaguchi, Yasuhisa Hirata, and Kazuhiro Kosuge. Development of robot hand with suction mechanism for robust and dexterous grasping. In 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems , pages 5500-5505. IEEE, 2013. 2 -
  43. [49][49] Yuji Yamakawa, Akio Namiki, and Masatoshi Ishikawa. Dynamic manipulation of a cloth by high-speed robot system using high-speed visual feedback. IFAC Proceedings Volumes , 44(1):8076-8081, 2011. 2 -
  44. [51][51] Andy Zeng, Shuran Song, Johnny Lee, Alberto Rodriguez, and Thomas Funkhouser. Tossingbot: Learning to throw arbitrary objects with residual physics. IEEE Transactions on Robotics , 36(4):1307-1319, 2020. URL https://ieeexplore.ieee.org/stamp/stamp.jsp? arnumber=9104757. 2 -
  45. [52][52] Zhenishbek Zhakypov, Florian Heremans, Aude Billard, and Jamie Paik. An origami-inspired reconfigurable suction gripper for picking objects with variable shape and size. IEEE Robotics and Automation Letters , 3(4): 2894-2901, 2018. URL https://ieeexplore.ieee.org/stamp/ stamp.jsp?tp=&arnumber=8385192. 2 -
  46. [53][53] Harry Zhang, Jeffrey Ichnowski, Daniel Seita, Jonathan Wang, Huang Huang, and Ken Goldberg. Robots of the lost arc: Self-supervised learning to dynamically manipulate fixed-endpoint cables. In 2021 IEEE International Conference on Robotics and Automation (ICRA) , pages 4560-4567. IEEE, 2021. 2 Fig. 11: Additional cloth unfolding results. <!-- image --> Fig. 12: Additional Bag opening results. <!-- image -->

Cited by

Sorted by citations

Authors
Xu, Z., Chi, C., Burchfiel, B., Cousineau, E., Feng, S., & Song, S.
Affiliations
  • Columbia University (US)
  • Toyota Research Institute (US)
ORCID
Venue
Robotics: Science and Systems XVIII
Publisher
Robotics: Science and Systems Foundation
Published
2022-06-27
DOI
10.15607/rss.2022.xviii.017
OpenAlex
W4226098973
Cited by
45
References
6
Citations by year
2026: 2 · 2025: 11 · 2024: 13 · 2023: 17 · 2022: 2
FWCI
16.03
Type
conference paper
Language
en
Open access
Locations
  • Robotics: Science and Systems (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University)
Funders
  • National Science Foundation (2037101, 2132519)
  • Toyota Research Institute
  • Division of Civil, Mechanical and Manufacturing Innovation (2037101, CMMI-2037101)
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, self-supervised learning, grasping, visual feedback

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