Researchers at the Massachusetts Institute of Technology have outlined their project for the three-dimensional digital knitting of intelligent textile sensors for applications such as activity recognition and biomechanical monitoring.
The research teams have presented an approach to develop seamless and scalable piezo-resistive matrix-based intelligent textiles using digital flat-bed and circular knitting machines. By combining and customizing functional and common yarns, the team can design the aesthetics and architect and engineer both the electrical and mechanical properties of a sensing textile.
Further, by incorporating a melting fibre, the researchers propose a method to shape and personalize a three-dimensional piezo-resistive fabric structure that can conform to the human body through thermoforming principles. It results in an intimate and robust textile structure, eliminating sensor drifts and maximizing accuracy while ensuring comfortability.
“In this work, we cover 3DKnITS textile design, fabrication approach, wireless hardware system, deep-learning enabled recognition methods, experimental results, and application scenarios,” the research team said. “Our digital knitting approach enables the fabrication of 2 to 3D pressure-sensitive textile interiors and wearables, including an intelligent mat, sock, and shoe that can be used for a variety of applications ranging from rehabilitation and sport science to gaming interfaces.”
