Robust triboelectric information-mat enhanced by multi-modality deep learning for smart home

In metaverse, a digital-twin smart home is a vital platform for immersive communication between the physical and virtual world. Triboelectric nanogenerators (TENGs) sensors contribute substantially to providing smart-home monitoring. However, TENG deployment is hindered by its unstable output under environment changes. Herein, we develop a digital-twin smart home using a robust all-TENG based information mat (InfoMat), which consists of an in-home mat array and an entry mat. The interdigital electrodes design allows environment-insensitive ratiometric readout from the mat array to cancel the commonly experienced environmental variations. Arbitrary position sensing is also achieved because of the interval arrangement of the mat pixels. Concurrently, the two-channel entry mat generates multi-modality information to aid the 10-user identification accuracy to increase from 93% to 99% compared to the one-channel case. Furthermore, a digital-twin smart home is visualized by real-time projecting the information in smart home to virtual reality, including access authorization, position, walking trajectory, dynamic activities/sports, and so on.

Automated summary

This research develops a digital-twin smart home system that utilizes robust TENG technology for smart home monitoring and multi-modality information generation. By eliminating the influence of environmental changes and achieving arbitrary position sensing, the accuracy of user identification is improved. Additionally, by projecting the information into virtual reality, the visualization of the smart home is achieved.