Goal-Conditioned Action Space Reduction for Deformable Object Manipulation

Abstract

Planning for deformable object manipulation has been a challenge for a long time in robotics due to its high computational cost. In this work, we propose to reduce this cost by reducing the number of pick points on a deformable object in the action space. We do this by identifying a small number of key particles that are sufficient as pick points to reach a given goal state. We find these key particles through a geometric model simplification process, which finds the minimal geometric model that still enables a good approximation of the original model at the goal state. We present an implementation of this general approach for 1-D linear deformable objects (e.g., ropes) that uses a piece-wise line fitted model, and for 2-D flat deformable objects (e.g., cloth) that uses a mesh simplified model. We conducted simulation experiments on ropes and cloths, which demonstrate the effectiveness of the proposed method. Finally, the planned paths are executed in a real-world setting for two cloth folding tasks.

Video

Citing

If you have any questions, please feel free to drop a line. Finally, if you want to cite this work, please use the following:

@inproceedings{wang2023goal,
  title={Goal-conditioned action space reduction for deformable object manipulation},
  author={Wang, Shengyin and Papallas, Rafael and Leonetti, Matteo and Dogar, Mehmet},
  booktitle={2023 IEEE International Conference on Robotics and Automation (ICRA)},
  pages={3623--3630},
  year={2023},
  organization={IEEE}
}