A physics-guided neural network framework for prediction and control of spring-mass running
Bioinspiration & Biomimetics · 31.08.2026 · 21 (4) · 046030
DOI: 10.1088/1748-3190/ae7e2d ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinspiration & Biomimetics, online erschienen am 07.08.2026. Verfasst von Ahmet Safa Ozturk und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical and Electronics Engineering, Bilkent University, Ankara, Türkiye. Hauptthemen laut MEDLINE: Neural Networks, Computer, Robotics, Running, Biomimetics. Die Arbeit nennt 66 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
The spring-mass template acts as a fundamental bridge between animal locomotion and legged robotic platforms. However, controlling spring-mass dynamics involves a persistent trade-off: numerical integration offers accuracy but high computational cost, while approximate analytical solutions provide efficiency but suffer from linearization errors. To resolve this, we propose a physics-guided hybrid neural network framework for the spring-mass running template. Unlike closed-box predictors trained end-to-end, our architecture enforces flight phase physics by embedding exact analytical solutions for the tractable ballistic dynamics directly into the network structure, and learning only the non-integrable stance dynamics. This ‘analytically augmented’ design enhances interpretability without sacrificing accuracy. For control, we introduce a mixed-objective training strategy that combines supervised imitation with goal-conditioned learning, enabling precise trajectory tracking without the computational burden of per-step optimization. We evaluated the framework’s prediction accuracy, control precision, and runtime efficiency through extensive simulations. Furthermore, we validate the robustness of the learned policies through a comprehensive basin of attraction analysis, demonstrating that the proposed networks stabilize contiguous manifolds of highly perturbed initial conditions compared to existing methods. Finally, we assessed the framework’s real-world adaptability by validating our predictor against an archival experimental dataset from a physical one-legged hopper. Our results demonstrate that this hybrid approach outperforms existing analytical and data-driven methods in accuracy and robustness while maintaining the low inference times required for real-time embedded control.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Electrical and Electronics Engineering, Bilkent University, Ankara, Türkiye.
- Department of Electrical and Electronics Engineering, Hacettepe University, Ankara, Türkiye.
ORCID-Profile: Ahmet Safa Ozturk, Ismail Uyanik, Ömer Morgül
Zitieren
APA
Safa Ozturk, A., Uyanik, I., & Morgül, Ö. (2026). A physics-guided neural network framework for prediction and control of spring-mass running. Bioinspiration & Biomimetics, 21(4), 046030. https://doi.org/10.1088/1748-3190/ae7e2d
Vancouver
Safa Ozturk A, Uyanik I, Morgül Ö. A physics-guided neural network framework for prediction and control of spring-mass running. Bioinspiration & Biomimetics. 2026;21(4):046030. doi:10.1088/1748-3190/ae7e2d
BibTeX
@article{SafaOzturk2026,
author = {Safa Ozturk, Ahmet and Uyanik, Ismail and Morgül, Ömer},
title = {A physics-guided neural network framework for prediction and control of spring-mass running},
journal = {Bioinspiration & Biomimetics},
year = {2026},
volume = {21},
number = {4},
pages = {046030},
doi = {10.1088/1748-3190/ae7e2d}
}
EUVIMED