English

Dynamic Manipulation of Flexible Objects with Torque Sequence Using a Deep Neural Network

Robotics 2024-03-25 v1

Abstract

For dynamic manipulation of flexible objects, we propose an acquisition method of a flexible object motion equation model using a deep neural network and a control method to realize a target state by calculating an optimized time-series joint torque command. By using the proposed method, any physics model of a target object is not needed, and the object can be controlled as intended. We applied this method to manipulations of a rigid object, a flexible object with and without environmental contact, and a cloth, and verified its effectiveness.

Keywords

Cite

@article{arxiv.1901.10142,
  title  = {Dynamic Manipulation of Flexible Objects with Torque Sequence Using a Deep Neural Network},
  author = {Kento Kawaharazuka and Toru Ogawa and Juntaro Tamura and Cota Nabeshima},
  journal= {arXiv preprint arXiv:1901.10142},
  year   = {2024}
}
R2 v1 2026-06-23T07:25:10.085Z