The fingertip is the most sensitive and richly endowed component of tactile perception, typically making direct contact with interacting objects. Its small-scale and refined perception characteristics render its ability to sense and process subtle tactile information critically important. However, traditional tactile perception systems encounter challenges such as high complexity in multi-point data processing and ineffective dynamic feature extraction.

Prof. Pengwen Xiong from Nanchang University proposed a biomimetic fingertip perception system for robotic applications, inspired by human tactile perception mechanisms. It has successfully achieved efficient integration and accurate extraction of detailed features in complex tactile data, and has been successfully applied to typical robotic tactile perception scenarios. This work is published in Science China: Technological Sciences with the title "A Biomimetic Perception System for Robotic Finger Tips Inspired by Human Tactile Perception".

A mountable biomimetic robotic fingertip is designed to simulate the functions of fingertip skin tactile receptors. A tactile signal coupling method based on time-frequency localization is proposed. Array-based multi-touchpoint response signals convert into composite time-domain signals using spatiotemporal frequency encoding. These signals combine with the short-time Fourier transform to generate tactile feature spectrograms that retain temporal characteristics. This process simulates the integration, decoupling, and processing of tactile information in the human nervous system. a tactile signal coupling method based on time-frequency localization.