首页|Research Conducted at Huazhong University of Science and Technology Has Provided New Information about Androids (Enhancing the Online Estimation of Finger Kinem atics From Semg Using Lstm With Attention Mechanisms)
Research Conducted at Huazhong University of Science and Technology Has Provided New Information about Androids (Enhancing the Online Estimation of Finger Kinem atics From Semg Using Lstm With Attention Mechanisms)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Robotics - Androids is the subject of a report. According to news originating from Wuhan, People's Rep ublic of China, by NewsRx correspondents, research stated, "Simultaneous and pro portional estimation of human finger kinematics using muscle interface has gaine d significant attention for human-robot interaction. Most existing researches fo cused on proposing novel estimation methods to achieve high estimation accuracy and validated them offline." Financial support for this research came from National Natural Science Foundatio n of China (NSFC). Our news journalists obtained a quote from the research from the Huazhong Univer sity of Science and Technology, "However, the gap between the online and offline estimation has not been fully considered which may lead to unpredictable deteri oration or failure in practical application. This paper quantifies the gap betwe en online and offline estimation performance and the underlying factors for such gap. The temporal variability of muscle activities represented by surface elect romyography (sEMG) is found to be more significant in online estimation which ch allenges the estimation model in computation complexity and temporal feature ext raction. To improve the online estimation accuracy, this paper proposes to combi ne an attention module with the long short-term memory (LSTM) network which enab les not only the global but also the local key information of sEMG signals being focused. The finger kinematics of five primary degrees of freedom (DoFs) is est imated from the sEMG recordings during some grasping tasks."
WuhanPeople's Republic of ChinaAsiaAndroidsEmerging TechnologiesHuman-Robot InteractionMachine LearningRob otRoboticsHuazhong University of Science and Technology
NETL
NSTL
