Qi Xiangyu, Wang Linglu, Li Chuanbo, Wang Yang
School of Science, Minzu University of China, Beijing 100081, China.
Optoelectronics Research Centre, Minzu University of China, Beijing 100081, China.
ACS Appl Mater Interfaces. 2024 Oct 9;16(40):54475-54484. doi: 10.1021/acsami.4c12062. Epub 2024 Sep 30.
Tactile sensing, especially pressure and temperature recognition, is crucial for both humans and robots in identifying objects. The general solutions, which use piezoresistive, capacitive, and thermal resistance effects, are usually subject to single-mode sensing and an energy supply. Here, we propose a multimode self-powered sensor. The sensor can respond to pressure and temperature stimuli using triboelectric and thermoelectric effects. Furthermore, we developed a sensing system comprising sensors, a deep learning block, and a smart board. The deep learning model can fuse features of triboelectric and thermoelectric signals, enabling a high accuracy of 99.8% in recognizing ten objects. This method may provide the future design of self-powered sensors for object recognition in robotics.
触觉传感，尤其是压力和温度识别，对于人类和机器人识别物体都至关重要。使用压阻、电容和热阻效应的一般解决方案通常受限于单模传感和能量供应。在此，我们提出一种多模自供电传感器。该传感器可利用摩擦电和热电效应响应压力和温度刺激。此外，我们开发了一个由传感器、深度学习模块和智能板组成的传感系统。深度学习模型可以融合摩擦电和热电信号的特征，在识别十个物体时实现99.8%的高精度。这种方法可能为机器人技术中用于物体识别的自供电传感器的未来设计提供思路。
