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

TL;DR

This paper presents a Physics-Embedded Neural Network (PENN) that combines musculoskeletal models with neural networks to improve sEMG-based motion estimation, achieving physiologically consistent and accurate predictions.

Contribution

The novel PENN integrates interpretable musculoskeletal dynamics with data-driven learning, enhancing motion estimation accuracy and physiological consistency.

Findings

PENN outperforms baseline methods in RMSE and R^2 metrics.

Experimental results on six subjects demonstrate robustness and temporal coherence.

The two-phase training strategy effectively trains the model.

Abstract

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.