Nonlinear spectral modeling and control of soft-robotic muscles from data.
4 affiliations
- 1Institute for Mechanical Systems, ETH Zurich, Zurich, Switzerland.
- 2Soft Robotics Lab, ETH Zurich, Zurich, Switzerland.
- 3Soft Robotics Lab, ETH Zurich, Zurich, Switzerland. [email protected].
- 4Institute for Mechanical Systems, ETH Zurich, Zurich, Switzerland. [email protected].
Abstract
Artificial muscles are essential for compliant musculoskeletal robotics but complicate control due to nonlinear multiphysics dynamics. Electrohydraulic actuators, a class of soft artificial muscles, offer high performance but exhibit memory effects and hysteresis. Here we present a data-driven reduction and control strategy grounded in spectral submanifold theory. In the adiabatic regime, where inputs vary slowly relative to intrinsic transients, trajectories rapidly converge to a low-dimensional slow manifold. We learn an explicit input-to-output map on this manifold directly from forced-response trajectories, eliminating the need for decay experiments generated by large step inputs, which can induce pronounced hysteretic behavior and are often unrepresentative of normal operating conditions. We deploy the spectral-submanifold-based model for real-time control of an antagonistic electrohydraulic-clutch joint. This approach yields a substantial reduction in tracking error compared to feedback-only and feedforward-only baselines under identical settings. This record-and-control workflow enables rapid characterization and high-performance control of soft muscles and muscle-driven joints without detailed physics-based modeling.
Related
- Design, modeling, and validation of a computer-vision-enabled 3D-printed soft robotic glove for stroke telerehabilitation
- Nonlinear spectral back transfer limits the temporal coherency of zonal modes
- Inscription method for chirped fiber Bragg gratings with high spectral flatness based on a nonlinear phase mask
- High-sensitivity line-field spectral-domain OCT driven by a power-scaled gain-managed nonlinear fiber source
- Modeling and compensation of periodic nonlinear error in micro-displacement measurement using a reflective-sphere-based low-finesse Fabry-Pérot cavity
BibTeX
@article{bettini2026nonlinear,
title = {{Nonlinear spectral modeling and control of soft-robotic muscles from data.}},
author = {Leonardo Bettini and Amirhossein Kazemipour and Robert K Katzschmann and George Haller},
journal = {Nature communications},
year = {2026},
month = sep,
doi = {10.1038/s41467-026-77664-0},
url = {https://europepmc.org/article/MED/42893984},
note = {CC BY},
}
RIS
TY - JOUR
TI - Nonlinear spectral modeling and control of soft-robotic muscles from data.
AU - Leonardo Bettini
AU - Amirhossein Kazemipour
AU - Robert K Katzschmann
AU - George Haller
PY - 2026
DA - 2026/09/16
JO - Nature communications
DO - 10.1038/s41467-026-77664-0
UR - https://europepmc.org/article/MED/42893984
AB - Artificial muscles are essential for compliant musculoskeletal robotics but complicate control due to nonlinear multiphysics dynamics. Electrohydraulic actuators, a class of soft artificial muscles, offer high performance but exhibit memory effects and hysteresis. Here we present a data-driven reduction and control strategy grounded in spectral submanifold theory. In the adiabatic regime, where inputs vary slowly relative to intrinsic transients, trajectories rapidly converge to a low-dimensional slow manifold. We learn an explicit input-to-output map on this manifold directly from forced-response trajectories, eliminating the need for decay experiments generated by large step inputs, which can induce pronounced hysteretic behavior and are often unrepresentative of normal operating conditions. We deploy the spectral-submanifold-based model for real-time control of an antagonistic electrohydraulic-clutch joint. This approach yields a substantial reduction in tracking error compared to feedback-only and feedforward-only baselines under identical settings. This record-and-control workflow enables rapid characterization and high-performance control of soft muscles and muscle-driven joints without detailed physics-based modeling.
SN - 2041-1723
ER -