Fur-inspired triboelectric tactile sensing array for intelligent human-machine interaction

Abstract

Tactile sensing plays a crucial role as an approach of human-machine interaction in the digital era. In this work, inspired by animal fur, we propose a triboelectric tactile sensing array in order to achieve sensitive awareness of gentle palm interactions. Which is of great significance for enhancing the functionality of companion and pet robots. The tactile sensor consists of a cluster of single-electrode structured triboelectric sensing units based on PTFE film coated conductive yarns. The dynamic signals of the tactile sensing array can accurately perceive 3D-depth interaction information of touch such as direction, speed and gesture. It allows for more comprehensive and accurate pattern recognition in human-machine interaction scenarios. Furthermore, a deep learning model is used to assist the recognition of complex signals from the tactile sensing array under various interactions. Among a dataset of 17 palmar interactions, a recognition accuracy up to 96.8% was achieved. As a demonstration, we finally construct an intelligent human-machine interface based on this tactile sensing array. It is integrated onto a shape-shifting robot working as a piece of fur of an intelligent pet robot. With the help of this fur, the robot can accurately recognize the interaction from the tester and act accordingly.