Robust hydrogel sensors for unsupervised learning enabled sign‐to‐verbal translation

Abstract Highly stretchable and robust strain sensors are rapidly emerging as promising candidates for a diverse array of wearable electronics and sensing devices. Conductive hydrogels represent a unique class of materials for bioelectronic applications due to their electrical and mechanical adaptability to human body. A common material engineering strategy is thus combining rigid electronic and/or ionic conductors with hydrogels to form conductive and stretchable composites. However, there exist trade-offs between high conductivity and excellent mechanical properties. To address this limitation, we designed a highly conductive yet highly stretchable hybrid hydrogel by simply encapsulating the liquid metal into polyacrylamide-alginate double networks. The resultant hydrogel simultaneously exhibits high conductivity (up to 22 S m-1), low elastic modulus (23 kPa), and ultrahigh stretchability (1500%) with excellent robustness (consistent performance against 12, 000 mechanical cycling), overcoming the traditional trade-off between electrical and mechanical properties. To demonstrate the potential impact of our technology on wearable electronics, a motion monitoring system with Self-Organizing Map was developed to achieve hand gesture monitoring and sign-to-speech translation. The use of our liquid metal-embedded hydrogels could be integral to the development of wearable electronics and human-machine interfaces.