Inverse‐Design of a Tactile Sensor With Self‐Information Storage by Fractal Encoding of the Hilbert Curve

Abstract Tactile perception is about capturing, processing, and interpreting tactile signals using tactile sensors to accurately understand the user's intentions, enabling more natural and efficient interaction. However, to achieve high resolution and high precision perception, current tactile sensors still pose challenges including complex signal decoupling and data redundancy. In this study, an adaptable paradigm based on Hilbert curves is used for an inverse‐design tactile (AHIT) sensor, which achieves tactile perception by hash mapping and contributes the function of self‐information storage. By using the fractal properties of Hilbert curves, the perceptive area and precision of AHIT sensors can traverse from low to high, accompanied by 1D signals and high resolution. AHIT sensors are therefore tailored to meet the requirements of versatile application scenarios such as multifunctional human‐machine interfaces, multi‐dimensional encryption and intention transmission. It is hoped that AHIT sensors demonstrate potential to minimize the interface between sensors and communication devices, improve data compression and reduce computational complexity, which is expected to drive rapid development in the field of intelligent tactile perception.