DisPad: Flexible On-Body Displacement of Fabric Sensors for Robust Joint-Motion Tracking

TL;DR

This paper introduces DisPad, a bio-compatible, stretchable wearable sensor system with a learning-based approach that maintains accurate joint motion tracking despite sensor displacement, improving robustness in real-world use.

Contribution

The work presents a novel soft sensor prototype combined with a learning method that achieves stable joint tracking across displacements and different users, advancing wearable sensor reliability.

Findings

Average tracking error of 9.82 degrees for single-user multi-motion tasks.

Transfer learning reduces errors to 10.98 and 11.81 degrees across different motions and users.

Demonstrates robustness of the sensor system against device displacement.

Abstract

The last few decades have witnessed an emerging trend of wearable soft sensors; however, there are important signal-processing challenges for soft sensors that still limit their practical deployment. They are error-prone when displaced, resulting in significant deviations from their ideal sensor output. In this work, we propose a novel prototype that integrates an elbow pad with a sparse network of soft sensors. Our prototype is fully bio-compatible, stretchable, and wearable. We develop a learning-based method to predict the elbow orientation angle and achieve an average tracking error of 9.82 degrees for single-user multi-motion experiments. With transfer learning, our method achieves the average tracking errors of 10.98 degrees and 11.81 degrees across different motion types and users, respectively. Our core contributions lie in a solution that realizes robust and stable human joint motion tracking across different device displacements.