Journal
IEEE ROBOTICS AND AUTOMATION LETTERS
Volume 7, Issue 2, Pages 5222-5229Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LRA.2022.3154842
Keywords
Action planning; deformable linear objects; hierarchical framework; robot manipulation; synthetic learning
Categories
Funding
- Key-Area Research and Development Program of Guangdong Province 2020 [2020B090928001]
- Research Grants Council of Hong Kong [14203917, 15212721]
- Jiangsu Industrial Technology Research Institute Collaborative Research Program Scheme [ZG9V]
- Hong Kong Polytechnic University [UAKU]
Ask authors/readers for more resources
This letter presents a solution to the problem of contact-based manipulation of deformable linear objects (DLOs) using a dual-arm robotic system. By modeling DLOs as kinematic multibody systems and training a keypoint encoding network, the high-dimensional continuous state-action spaces are effectively reduced. The proposed goal-conditioned policy rearranges the configuration of DLOs based on keypoints, and the hierarchical action framework solves the manipulation problem in a coarse-to-fine manner. Experimental results demonstrate the high performance of the method in state representation and shaping manipulation of DLOs under environmental constraints.
This letter addresses the problem of contact-based manipulation of deformable linear objects (DLOs) towards desired shapes with a dual-arm robotic system. To alleviate the burden of high-dimensional continuous state-action spaces, we model DLOs as kinematic multibody systems via our proposed keypoint encoding network. This novel encoding is trained on a synthetic labeled image dataset without requiring any manual annotations and can be directly transferred to real manipulation scenarios.Our goal-conditioned policy efficiently rearranges the configuration of the DLO based on the keypoints. The proposed hierarchical action framework tackles the manipulation problem in a coarse-to-fine manner (with high-level task planning and low-level motion control) by leveraging two action primitives. The identification of deformation properties is bypassed since the algorithm replans its motion after each bimanual execution. The conducted experimental results reveal that our method achieves high performance in state representation and shaping manipulation of the DLO under environmental constraints.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available