Physics-Embedded Neural Networks for sEMG-based Continuous Motion Estimation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Heng, Wending, Liang, Chaoyuan, Zhao, Yihui, Zhang, Zhiqiang, Cooper, Glen, Li, Zhenhong
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908426724966400
author Heng, Wending
Liang, Chaoyuan
Zhao, Yihui
Zhang, Zhiqiang
Cooper, Glen
Li, Zhenhong
author_facet Heng, Wending
Liang, Chaoyuan
Zhao, Yihui
Zhang, Zhiqiang
Cooper, Glen
Li, Zhenhong
contents Accurately decoding human motion intentions from surface electromyography (sEMG) is essential for myoelectric control and has wide applications in rehabilitation robotics and assistive technologies. However, existing sEMG-based motion estimation methods often rely on subject-specific musculoskeletal (MSK) models that are difficult to calibrate, or purely data-driven models that lack physiological consistency. This paper introduces a novel Physics-Embedded Neural Network (PENN) that combines interpretable MSK forward-dynamics with data-driven residual learning, thereby preserving physiological consistency while achieving accurate motion estimation. The PENN employs a recursive temporal structure to propagate historical estimates and a lightweight convolutional neural network for residual correction, leading to robust and temporally coherent estimations. A two-phase training strategy is designed for PENN. Experimental evaluations on six healthy subjects show that PENN outperforms state-of-the-art baseline methods in both root mean square error (RMSE) and $R^2$ metrics.
format Preprint
id arxiv_https___arxiv_org_abs_2506_22459
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Physics-Embedded Neural Networks for sEMG-based Continuous Motion Estimation
Heng, Wending
Liang, Chaoyuan
Zhao, Yihui
Zhang, Zhiqiang
Cooper, Glen
Li, Zhenhong
Signal Processing
Machine Learning
Accurately decoding human motion intentions from surface electromyography (sEMG) is essential for myoelectric control and has wide applications in rehabilitation robotics and assistive technologies. However, existing sEMG-based motion estimation methods often rely on subject-specific musculoskeletal (MSK) models that are difficult to calibrate, or purely data-driven models that lack physiological consistency. This paper introduces a novel Physics-Embedded Neural Network (PENN) that combines interpretable MSK forward-dynamics with data-driven residual learning, thereby preserving physiological consistency while achieving accurate motion estimation. The PENN employs a recursive temporal structure to propagate historical estimates and a lightweight convolutional neural network for residual correction, leading to robust and temporally coherent estimations. A two-phase training strategy is designed for PENN. Experimental evaluations on six healthy subjects show that PENN outperforms state-of-the-art baseline methods in both root mean square error (RMSE) and $R^2$ metrics.
title Physics-Embedded Neural Networks for sEMG-based Continuous Motion Estimation
topic Signal Processing
Machine Learning
url https://arxiv.org/abs/2506.22459