Dynamic robotic cloth folding with efficient Koopman operator-based model predictive control
Abstract
Robotic cloth folding is a challenging task, particularly when considering dynamic folding tasks, which aim at folding cloth by fast motions that leverage its dynamics. When subject to such fast motions, the complexity of cloth dynamics hinders both system identification and planning of folding trajectories, resulting in a difficult simulation-to-reality transfer when using physical models of cloth. Compared to the dexterity that humans exhibit when performing folding tasks, robotic approaches usually employ small garments with quite rigid dynamics, and are either too slow, or fast but imprecise, requiring several attempts to achieve a reasonably good fold. In this paper, we tackle these challenges by generating fast folding trajectories with a novel model predictive controller, integrating physics-based simulation of cloth dynamics and efficient, kernel-based Koopman operator regression. Koopman operator regression, an increasingly popular machine learning technique for nonlinear system identification, is used to obtain a linear model for the cloth being folded. Such a surrogate model, trained with data from a high-fidelity, physics-based cloth simulator, can then be employed within a suitable model predictive control algorithm, in place of the costly, nonlinear one, to efficiently generate folding trajectories to be executed by a robotic manipulator. Both in simulated and real-robot experiments, we show how the linearization supplied by the Koopman operator-based model can be employed to efficiently generate fast folding trajectories to unseen poses, without sacrificing folding accuracy.
Versions
Related
- Harnessing human expertise for high-precision robotic assembly in industrialized construction: A sample-efficient installer-in-the-loop interactive reinforcement learning framework
- Koopman operator learning for predictive control via Khatri-Rao kernel regression
- Adaptive Model Predictive Control for Uncertain Nonaffine Nonlinear System Based on Deep Koopman Operator
- Deep operator learning for efficient sampling from invariant measures of stochastic differential equations
- Model Predictive Control for Dynamic Hydraulic Balancing in Building Radiator Heating Systems: Modeling, Design, and Experimental Validation
BibTeX
@misc{caldarelli2026dynamic,
title = {{Dynamic robotic cloth folding with efficient Koopman operator-based model predictive control}},
author = {Edoardo Caldarelli and Franco Coltraro and Adrià Colomé and Lorenzo Rosasco and Carme Torras},
howpublished = {arXiv},
year = {2026},
month = may,
doi = {10.48550/arxiv.2605.18373},
eprint = {2605.18373},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2605.18373},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Dynamic robotic cloth folding with efficient Koopman operator-based model predictive control
AU - Edoardo Caldarelli
AU - Franco Coltraro
AU - Adrià Colomé
AU - Lorenzo Rosasco
AU - Carme Torras
PY - 2026
DA - 2026/05/18
PB - arXiv
DO - 10.48550/arxiv.2605.18373
UR - https://arxiv.org/abs/2605.18373
AB - Robotic cloth folding is a challenging task, particularly when considering dynamic folding tasks, which aim at folding cloth by fast motions that leverage its dynamics. When subject to such fast motions, the complexity of cloth dynamics hinders both system identification and planning of folding trajectories, resulting in a difficult simulation-to-reality transfer when using physical models of cloth. Compared to the dexterity that humans exhibit when performing folding tasks, robotic approaches usually employ small garments with quite rigid dynamics, and are either too slow, or fast but imprecise, requiring several attempts to achieve a reasonably good fold. In this paper, we tackle these challenges by generating fast folding trajectories with a novel model predictive controller, integrating physics-based simulation of cloth dynamics and efficient, kernel-based Koopman operator regression. Koopman operator regression, an increasingly popular machine learning technique for nonlinear system identification, is used to obtain a linear model for the cloth being folded. Such a surrogate model, trained with data from a high-fidelity, physics-based cloth simulator, can then be employed within a suitable model predictive control algorithm, in place of the costly, nonlinear one, to efficiently generate folding trajectories to be executed by a robotic manipulator. Both in simulated and real-robot experiments, we show how the linearization supplied by the Koopman operator-based model can be employed to efficiently generate fast folding trajectories to unseen poses, without sacrificing folding accuracy.
ER -