Physiologically Constrained Musculoskeletal Neural Network for Multi-DoF Joint Kinematics Estimation from Partially Observed sEMG

2026-06-05

AI Summary

This study addresses the challenge of inaccurate multi-degree-of-freedom joint kinematics estimation when only partial surface electromyography (sEMG) signals are observable. To this end, the authors propose a physiologically constrained musculoskeletal neural network (MSK-NN) that integrates a CNN-based muscle activation estimator with a differentiable musculoskeletal forward dynamics module. This architecture enables, for the first time, end-to-end training without requiring biomechanical labels such as muscle forces or joint torques, while ensuring anatomical plausibility through a composite physics- and physiology-informed loss. Evaluated on a two-degree-of-freedom wrist movement task, MSK-NN significantly outperforms baseline models—including CNN and Bi-LSTM—in terms of lower normalized root mean square error (NRMSE) and higher coefficient of determination (R²). Moreover, the inferred muscle activations align closely with actual sEMG signals, and the model parameters retain physiological interpretability.

Abstract

This paper investigates multi-degrees of freedom (DoF) joint kinematics estimation under partially observed surface electromyography (sEMG), where only a subset of task-relevant muscles can be measured due to anatomical inaccessibility or sensor constraints. A novel musculoskeletal neural network (MSK-NN) is proposed to estimate multi-DoF joint angles while simultaneously inferring activations for both measured and unmeasured muscles. MSK-NN consists of a CNN-based muscle activation estimator and an embedded MSK forward dynamics module, forming a fully differentiable architecture. Unlike existing hybrid neural frameworks that require additional biomechanical labels (e.g., muscle-tendon forces, joint torques), MSK-NN is trained without direct supervision of internal biomechanical variables. A composite physics-physiology loss is designed by incorporating a joint kinematics loss, a data-driven muscle synergy loss, and an anatomy-guided trend loss. The proposed method is evaluated on two-DoF wrist kinematics estimation across three rhythmic motions with unconstrained speed and amplitude, and one random motion. Compared with CNN, Bi-LSTM, CNN-LSTM, and PET baselines, MSK-NN achieves lower normalized root mean square error (NRMSE) and higher coefficient of determination (R2), especially for the random motion. More importantly, the optimized MSK parameters remain within physiological limits, and the estimated activation of an input-excluded muscle exhibits strong temporal agreement with its recorded sEMG envelope, demonstrating the capability of musculoskeletal (MSK)-NN to recover physiologically plausible activations.

Problem

• multi-DoF joint kinematics
• partially observed sEMG
• musculoskeletal modeling
• muscle activation estimation
• physiological constraints

Innovation

• musculoskeletal neural network
• multi-DoF kinematics estimation
• partially observed sEMG
• physiology-constrained learning
• differentiable biomechanics