神经形态工程学
计算机科学
人机交互
信息处理
机器人
仿生学
感知
人工智能
人工神经网络
神经科学
生物
作者
Xiangxiang Zhang,Chang-Guang Wang,Xin Pi,Bo Li,Yingxue Ding,Hexuan Yu,Jialue Sun,Pei Wang,You Chen,Qun Wang,Changchao Zhang,Xiancun Meng,Guangjun Chen,Dakai Wang,Ze Wang,Zhengzhi Mu,Honglie Song,Junqiu Zhang,Shichao Niu,Zhiwu Han
标识
DOI:10.1002/adma.202418108
摘要
Abstract Mechanical information is a medium for perceptual interaction and health monitoring of organisms or intelligent mechanical equipment, including force, vibration, sound, and flow. Researchers are increasingly deploying mechanical information recognition technologies (MIRT) that integrate information acquisition, pre‐processing, and processing functions and are expected to enable advanced applications. However, this also poses significant challenges to information acquisition performance and information processing efficiency. The novel and exciting mechanosensory systems of organisms in nature have inspired us to develop superior mechanical information bionic recognition technologies (MIBRT) based on novel bionic materials, structures, and devices to address these challenges. Herein, first bionic strategies for information pre‐processing are presented and their importance for high‐performance information acquisition is highlighted. Subsequently, design strategies and considerations for high‐performance sensors inspired by mechanoreceptors of organisms are described. Then, the design concepts of the neuromorphic devices are summarized in order to replicate the information processing functions of a biological nervous system. Additionally, the ability of MIBRT is investigated to recognize basic mechanical information. Furthermore, further potential applications of MIBRT in intelligent robots, healthcare, and virtual reality are explored with a view to solve a range of complex tasks. Finally, potential future challenges and opportunities for MIBRT are identified from multiple perspectives.
科研通智能强力驱动
Strongly Powered by AbleSci AI