Offline-Online Learning of Deformation Model for Cable Manipulation with Graph Neural Networks

TL;DR

This paper presents a hybrid offline-online approach using Graph Neural Networks and real-time residual modeling to accurately predict cable deformation dynamics for robotic manipulation, enhancing robustness and data efficiency.

Contribution

It introduces a novel hybrid method combining GNN-based offline learning with online residual modeling for robust cable manipulation.

Findings

The method achieves superior deformation prediction accuracy.

It demonstrates robustness in sim-to-real transfer.

The approach improves control performance in cable manipulation tasks.

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 work, 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.