Dexterous Ungrasping in Three-Dimensional Space: Stability and Planning
Source abstract
Abstract
This work examines the robotic technique of ungrasping, in which an object held by a gripper is intentionally released into the environment. The proposed method achieves controlled object release through non-static contact interactions that permit rolling and sliding. This form of dexterous manipulation is especially important for thin or slender objects, as demonstrated through physical experiments. This study first addresses how three-dimensional stability can be established using a minimal number of contacts. It then introduces a planning framework for three-dimensional ungrasping that extends our prior planar formulation. Experimental results obtained with a two-fingered gripper—the most common gripper type—validate the feasibility, effectiveness, and practicality of the presented approach.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Robot Manipulation and Learning · Soft Robotics and Applications · Modular Robots and Swarm Intelligence
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Electric and Electronic Engineering, Pusan National University, Busan 46241, Republic of Korea
Funding
BK21FOUR program · Creative HR Education and Research Programs for ICT Convergence in the 4th Industrial Revolution · Two-Year Research Grant of Pusan National University
References (28)
Show source-provided references
1. Planning for Dexterous Ungrasping: Secure Ungrasping Through Dexterous Manipulation10.1109/LRA.2022.3142892 ↗
2. Robust Ungrasping of High Aspect Ratio Objects Through Dexterous Manipulation10.1109/LRA.2022.3144494 ↗
3. Kang, T., Kim, J., Oh, S., Lim, W., Lee, J., Yi, S.J., and Seo, J. (2025, January 19–23). Dexterous Ungrasping Manipulation in Three Dimensions. Proceedings of the 2025 IEEE International Conference on Robotics and Automation (ICRA), Atlanta, GA, USA.10.1109/ICRA55743.2025.11127227 ↗
4. A Novel Robotic Multiple Peg-in-Hole Assembly Pipeline: Modeling, Strategy, and Control10.1109/TMECH.2023.3337102 ↗
5. Learning Robust Skills for Tightly Coordinated Arms in Contact-Rich Tasks10.1109/LRA.2024.3359542 ↗
6. Shome, R., Tang, W.N., Song, C., Mitash, C., Kourtev, H., and Yu, J. (2019, January 20–24). Towards Robust Product Packing with a Minimalistic End-Effector. Proceedings of the 2019 International Conference on Robotics and Automation (ICRA), Montreal, QC, Canada.10.1109/ICRA.2019.8793966 ↗
7. TossingBot: Learning to Throw Arbitrary Objects With Residual Physics10.1109/TRO.2020.2988642 ↗
8. Regrasping10.1109/ROBOT.1987.1087910 ↗
9. Planning for dexterous manipulation with sliding contacts10.1177/027836499000900302 ↗
10. Dextrous manipulation by rolling and finger gaiting
11. In-hand dexterous manipulation of piecewise-smooth 3-d objects10.1177/02783649922066268 ↗
12. Dexterous grippers: Putting nonholonomy to work for fine manipulation10.1177/027836402321261968 ↗
13. Dafle, N.C., Rodriguez, A., Paolini, R., Tang, B., Srinivasa, S.S., Erdmann, M., Mason, M.T., Lundberg, I., Staab, H., and Fuhlbrigge, T. (June, January 31). Extrinsic dexterity: In-hand manipulation with external forces. Proceedings of the 2014 IEEE International Conference on Robotics and Automation (ICRA), Hong Kong, China.10.1109/ICRA.2014.6907062 ↗
14. Chavan-Dafle, N., and Rodriguez, A. (October, January 28). Prehensile pushing: In-hand manipulation with push-primitives. Proceedings of the 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Hamburg, Germany.10.1109/IROS.2015.7354264 ↗
15. Attribute-Based Robotic Grasping With Data-Efficient Adaptation10.1109/TRO.2024.3353484 ↗
16. Multi-Stage Reinforcement Learning for Non-Prehensile Manipulation10.1109/LRA.2024.3412630 ↗
17. Open-loop precision grasping with underactuated hands inspired by a human manipulation strategy10.1109/TASE.2013.2240298 ↗
18. Matsuno, T., Kanada, K., Arai, F., Matsuura, H., and Fukuda, T. (2005, January 18–22). Strategy of picking up thin plate by robot hand using deformation of soft fingertip. Proceedings of the 2005 IEEE International Conference on Robotics and Automation, Barcelona, Spain.
19. Picking, grasping, or scooping small objects lying on flat surfaces: A design approach10.1177/0278364918802346 ↗
20. Sampling-based algorithms for optimal motion planning10.1177/0278364911406761 ↗
21. Lynch, K.M., and Park, F.C. (2017). Modern Robotics: Mechanics, Planning, and Control, Cambridge University Press.10.1017/9781316661239 ↗
22. Energy-Bounded Caging: Formal Definition and 2-D Energy Lower Bound Algorithm Based on Weighted Alpha Shapes10.1109/LRA.2016.2519145 ↗
23. Constructing stable grasps10.1177/027836498900800102 ↗
24. On computing three-finger force-closure grasps of 2-D and 3-D objects10.1109/TRA.2002.806774 ↗
25. Dynamic Self-Righting of Planar-Based Objects on Dual Supports and its Implications for Robotic Object Placement10.1109/LRA.2025.3598992 ↗
26. Murray, R., Li, Z., and Sastry, S. (1994). A Mathematical Introduction to Robotic Manipulation, CRC Press.
27. Dynamic In-Hand Sliding Manipulation10.1109/TRO.2017.2693391 ↗
28. Planar in-hand manipulation via motion cones10.1177/0278364919880257 ↗