Offline-Online Learning of Deformation Model for Cable Manipulation With Graph Neural Networks
Changhao Wang, Yuyou Zhang, Xiang Zhang, Zheng Wu, Xinghao Zhu, Shiyu Jin, Te Tang, Masayoshi Tomizuka
Abstract
Manipulating deformable linear objects by robots has a wide range of applications, e.g., manufacturing and medical surgery. To complete such tasks, an accurate dynamics model for predicting the deformation is critical for robust control. In this letter, we deal with this challenge by proposing a hybrid offline-online method to learn the dynamics of cables in a robust and data-efficient manner. In the offline phase, we adopt Graph Neural Network (GNN) to learn the deformation dynamics purely from the simulation data. Then a linear residual model is learned in real-time to bridge the sim-to-real gap. The learned model is then utilized as the dynamics constraint of a trust region based Model Predictive Controller (MPC) to calculate the optimal robot movements. The online learning and MPC run in a closed-loop manner to robustly accomplish the task. Finally, comparative results with existing methods are provided to quantitatively show the effectiveness and robustness.
BibTeX
@inproceedings{ral2022_offlineonlinelea,
title = {Offline-Online Learning of Deformation Model for Cable Manipulation With Graph Neural Networks},
author = {Changhao Wang and Yuyou Zhang and Xiang Zhang and Zheng Wu and Xinghao Zhu and Shiyu Jin and Te Tang and Masayoshi Tomizuka},
booktitle = {RA-L 2022},
year = {2022}
}