仿生学
材料科学
感知
人工神经网络
人工智能
手势
计算机科学
计算机视觉
神经科学
心理学
作者
Hongsen Niu,Hao Li,Yang Li,Wenjing Yue,Song Gao,Wei Xiao,Guozhen Shen
出处
期刊:Nano Energy
[Elsevier]
日期:2022-12-23
卷期号:107: 108144-108144
被引量:24
标识
DOI:10.1016/j.nanoen.2022.108144
摘要
Traditional electronic skin (e-skin) with single micro-nano structures has a limited capacity to optimize the comprehensive sensing properties, which greatly hinders the intellectualization process. Herein, cocklebur-inspired bionic e-skin consisting of the “branch-seed-spininess” three-dimensional hierarchical structure, namely the P(VDF-TrFE) fiber-TiO2 pillar-TiO2 thorn structure (FPTS), is proposed. Benefiting from the hierarchical characteristics of the FPTS, the e-skin exhibits a high sensitivity of 0.163 kPa−1 (<20 kPa), wide pressure sensing range of 0–200 kPa, and ultrafast response/relaxation time of < 5.6 ms. In light of these salient features, versatile intelligent perception applications are explored. First, robot fingers are equipped with the FPTS e-skins and realize the traditional Chinese medicine pulse diagnosis of the radial artery in different positions and pressing degrees. Second, a flexible perception array with 100 FPTS e-skin units enables the spatial pressure mapping of flat/curved surfaces and the perception of different Braille characters. Most importantly, by making full use of the FPTS e-skin with a five-layer deep neural network, an intelligent gesture perception system is developed for accurate recognition (average accuracy: 98.33%) of sign language and precise control of the robot hand, which is of great significance for the development of intelligent sign language translation in artificial intelligence.
科研通智能强力驱动
Strongly Powered by AbleSci AI