As technology advances, human-machine interaction (HMI) demands more intuitive and natural methods. To meet this demand, smart gloves, capable of capturing intricate hand movements, are emerging as vital HMI tools. Moreover, triboelectric-based sensors, with their self-powered, cost-effective, and material various characteristics, can offer promising solutions for enhancing existing glove systems. However, a key limitation of these sensors is that charge leakage in the measurement circuit results in capturing only transient signals, rather than continuous changes. To address this issue, a charge-retained circuit that effectively prevents triboelectric signal attenuation is developed, enabling accurate measurement of continuous finger movements. This innovation forms the foundation of a highly integrated smart glove system, enhancing HMI functionality by combining continuous triboelectric signals with inertial sensor data. The system showcases a diverse range of applications, including complex robotic control, virtual reality interaction, smart home lighting adjustments, and intuitive interface operations. Furthermore, by leveraging artificial intelligence (AI) techniques, the system achieves accurate recognition of complex sign language with an impressive 99.38% accuracy. This work presents a charge-retained approach for continuous sensing with triboelectric-based sensors, offering valuable insights for developing future multifunctional HMI and sign language recognition systems. The proposed smart glove system, with its dual-mode sensing and AI integration, holds great potential for revolutionizing various domains and enhancing user experiences.
Keywords: artificial intelligence; gesture recognition; human‐machine interaction (HMI); signal processing; smart glove; triboelectric sensor.
© 2024 The Author(s). Advanced Science published by Wiley‐VCH GmbH.