Generalizable and Fast Surrogates
Model Predictive Control of Articulated Soft Robots using Physics-Informed Neural Networks
Abstract
Soft robots can revolutionize several applications with high demands on dexterity and safety. When operating these systems, real-time estimation and control require fast and accurate models. However, prediction with first-principles (FP) models is slow, and learned black-box models have poor generalizability. Physics-informed machine learning offers excellent advantages here, but it is currently limited to simple, often simulated systems without considering changes after training. We propose physics-informed neural networks (PINNs) for articulated soft robots (ASRs) with a focus on data efficiency. The amount of expensive real-world training data is reduced to a minimum - one dataset in one system domain. Two hours of data in different domains are used for a comparison against two gold-standard approaches: In contrast to a recurrent neural network, the PINN provides a high generalizability. The prediction speed of an accurate FP model is exceeded with the PINN by up to a factor of 467 at slightly reduced accuracy. This enables nonlinear model predictive control (MPC) of a pneumatic ASR. Accurate position tracking with the MPC running at 47 Hz is achieved in six dynamic experiments.
Details
- Organisationseinheit(en)
-
Institut für Mechatronische Systeme
- Typ
- Artikel
- Journal
- IEEE Transactions on Robotics
- Band
- 42
- Seiten
- 619 - 636
- Anzahl der Seiten
- 18
- ISSN
- 1552-3098
- Publikationsdatum
- 16.01.2026
- Publikationsstatus
- Veröffentlicht
- Peer-reviewed
- Ja
- ASJC Scopus Sachgebiete
- Steuerungs- und Systemtechnik, Angewandte Informatik, Elektrotechnik und Elektronik
- Elektronische Version(en)
-
https://doi.org/10.1109/TRO.2025.3631818 (Zugang:
Geschlossen
)
https://doi.org/10.48550/arXiv.2502.01916 (Zugang: Offen )