A Coarse-to-Fine Framework for Dual-Arm Manipulation of Deformable Linear Objects with Whole-Body Obstacle Avoidance

The paper has been accepted by IEEE ICRA 2023.

The paper won the best paper award at the ICRA Workshop on Representing and Manipulating Deformable Objects. [Workshop Website]

A journal version of this work is here.

[IEEE Xplore] [arXiv]

Video

Abstract

Manipulating deformable linear objects (DLOs) to achieve desired shapes in constrained environments with obstacles is a meaningful but challenging tasks. Global planning is necessary for such a highly-constrained task; however, accurate models of DLOs required by planners are difficult to obtain owing to their deformable nature, and the inevitable modeling errors significantly affect the planning results, probably result-ing in task failure if the robot simply executes the planned path in an open-loop manner. In this paper, we propose a coarse-to- fine framework to combine global planning and local control for dual-arm manipulation of DLOs, capable of precisely achieving desired configurations and avoiding potential collisions between the DLO, robot, and obstacles. Specifically, the global planner refers to a simple yet effective DLO energy model and computes a coarse path to guarantee the feasibility of the task; then the local controller follows that path as guidance and further shapes it with closed-loop feedback to compensate for the planning errors and guarantee the accuracy of the task. Both simulations and real-world experiments demonstrate that our framework can robustly achieve desired DLO configurations in constrained environments with imprecise DLO models. which may not be reliably achieved by only planning or control.

Citation

Please cite our paper if you find it helpful :)

@INPROCEEDINGS{yu2023acoarse,
  author={Yu, Mingrui and Lv, Kangchen and Wang, Changhao and Tomizuka, Masayoshi and Li, Xiang},
  booktitle={2023 IEEE International Conference on Robotics and Automation (ICRA)}, 
  title={A Coarse-to-Fine Framework for Dual-Arm Manipulation of Deformable Linear Objects with Whole-Body Obstacle Avoidance}, 
  year={2023},
  pages={10153-10159},
  doi={10.1109/ICRA48891.2023.10160264}
}

Contact

If you have any question, feel free to contact the authors: Mingrui Yu, mingruiyu98@gmail.com .

Mingrui Yu’s Homepage is at mingrui-yu.github.io.