Ultra-Robust and Sensitive Flexible Strain Sensor for Real-Time and Wearable Sign Language Translation

摘要

Flexible strain sensors with high sensitivity and high mechanical robustnessare highly desirable for their accurate and long-term reliable service inwearable human-machine interfaces. However, the current application offlexible strain sensors has to face a trade-off between high sensitivity and highmechanical robustness. The most representative examples are micro/nanocrack-based sensors and serpentine meander-based sensors. The former onetypically shows high sensitivity but limited robustness, while the latter is onthe contrary. Herein, ultra-robust and sensitive flexible strain sensors aredeveloped by crack-like pathway customization and ingenious modulation oflow/high-resistance regions on a serpentine meander structure. The sensorsshow high cyclic stability (10 000 cycles), strong tolerance to harshenvironments, high gauge factor (>1000) comparable with that of thecrack-based sensor, and fast response time (<58 ms). Finally, the sensors areintegrated into a wearable sign language translation system, which is wireless,low-cost, and lightweight. Recognition rates of over 98 are demonstrated forthe translation of 21 sign languages with the assistance of machine learning.This system facilitates achieving barrier-free communication between signersand nonsigners and offers broad application prospects in gesture interaction.