ScholarDeck

StudyIEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society · 2026

Physics-Informed Neural Networks for Real-Time Muscle-Tendon Force Estimation from Wearable Sensors.

Halldor Karason, Pierluigi Ritrovato, Nicola Maffulli, Francesco Tortorella

Read paper

Physical Medicine & RehabilitationStudy

Physics-informed neural networks accurately estimate Achilles tendon forces from wearable sensors.

Physics-Informed Neural Networks for Real-Time Muscle-Tendon Force Estimation from Wearable Sensors.

Halldor Karason et al. · IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society · 2026

Purpose

This article presents a physics-informed neural network (PINN) framework that estimates individual muscle-tendon forces from wearable inertial measurement units (IMUs) and pressure-sensitive insoles, without requiring labeled force data or electromyo-graphy.

8.8±1.5%

Results

the small average error when estimating Achilles tendon forces

n = 16 subjects

More results

Inference times of approximately 7 ms support potential closed-loop biofeedback applications.

“

Conclusion

The proposed approach establishes a computational foundation for translating laboratory-grade biomechanical analysis to wearable systems for continuous rehabilitation monitoring.

Post

Physics-Informed Neural Networks for Real-Time Muscle-Tendon Force Estimation from Wearable Sensors.

Physics-informed neural networks accurately estimate Achilles tendon forces from wearable sensors.

Related papers