摘要
Various living creatures exhibit embodiment intelligence,which is reflected by a collaborative interaction of the brain,body,and environment.The actual behavior of embodiment intelligence is generated by a continuous and dynamic interaction between a subject and the environment through information perception and physical manipulation.The physical interaction between a robot and the environment is the basis for realizing embodied perception and learning.Tactile information plays a critical role in this physical interaction process.It can be used to ensure safety,stability,and compliance,and can provide unique information that is difficult to capture using other perception modalities.However,due to the limitations of existing sensors and perception and learning methods,the development of robotic tactile research lags significantly behind other sensing modalities,such as vision and hearing,thereby seriously restricting the development of robotic embodiment intelligence.This paper presents the current challenges related to robotic tactile embodiment intelligence and reviews the theory and methods of robotic embodied tactile intelligence.Tactile perception and learning methods for embodiment intelligence can be designed based on the development of new large-scale tactile array sensing devices,with the aim to make breakthroughs in the neuromorphic computing technology of tactile intelligence.
基金
supported by the National Natural Science Foundation of China under Grant No.61703284 and Grant No.61673238
作者简介
Corresponding author:Huaping Liu is an associate professor in the Department of Computer Science and Technology,Tsinghua University,Beijing,China.His main research interest is robot perception and learning.He served as a senior program committee member for the 2018 International Joint Conference on Artificial Intelligence.He was awarded the Andy Chi Best Paper Award in 2017.He served as the area chair for 2018 Robotics Science and Systems.He serves as an associate editor for several journals,including IEEE Transactions on Automation Science and Engineering,IEEE Transactions on Industrial Informatics,IEEE Robotics and Automation Letters,Neurocomputing,and Cognitive Computation,and some international conferences,including International Conference on Robotics and Automation and IEEE/RSJ International Conference on Intelligent Robots and Systems;Di Guo received her Bachelor’s degree from Beihang University,Beijing,China,in 2011.She received her Ph.D.degree in the Department of Computer Science and Technology,Tsinghua University,Beijing,China.Her main research interest is robotic manipulation and sensor fusion;Fuchun Sun is a professor in the Department of Computer Science and Technology,Tsinghua University,Beijing,China.His main research interest is intelligent control and robotics.He was a recipient of the distinguished Young Scholar from the National Science Fundation of China.He serves as the editor‐in‐chief for Cognitive Computation and Systems and an associate editor for a several international journals,including IEEE Transactions on Systems,Man and Cybernetics:Systems,IEEE Transactions on Fuzzy Systems,Mechatronics,and Robotics and Autonomous Systems;Wuqiang Yang received his B.Eng.(1982),M.Sc.(1985),and Ph.D.(1988)from Tsinghua University in Beijing,China.He joined University of Manchester Institute of Science and Technology(UMIST)in 1991 and became a professor in 2005.Currently,he is the director of Business Engagement and Innovation in the Department of Electrical and Electronics Engineering and the director of Joint Research Lab for Touch Sensors for Domestic Robots.His research focuses on emission computed tomography(ECT)and its industrial applications.He is an associate editor of IEEE Transactions on Instrumentation and Measurement and IET Science Measurement&Technology,and an editorial board member of seven other journals,including Measurement Science and Technology and Sensor Review.From 2010 to 2016,he was an IEEE Distinguished Lecturer.He is a visiting professor at several universities,including Tsinghua University.He is recognized by the International Center for Scientific Research(France)as one of the top 30 technology researchers in the world.He is a fellow of the IEEE,IET,and Institute of Measurement and Control;Steve Furber received his B.A.degree in mathematics and Ph.D.degree in aerodynamics from the University of Cambridge,UK.In 1980,he joined Acorn Computers in Cambridge,where he was a principal designer of the BBC microcomputer and the ARM 32‐bit RISC microprocessor.In 1990,he moved to the University of Manchester and became the ICL Professor of Computer Engineering in the School of Computer Science,where he leads research into asynchronous and low‐power systems and neural systems engineering,notably the SpiNNaker project.He is a fellow of the Royal Society,the Royal Academy of Engineering,the British Computer Society,the IEEE,and the IET,and a member of Academia European;Tengchen Sun graduated from the Department of Automation,and received his EMBA degree from Tsinghua University in Beijing,China.Since 1982,he has been working on embedded software development technology.He has more than 30 invention patents including material identification,tactile sensing architecture and related applications.He established Autoeasy Co.,Ltd.in 2005 and Tashan Technology Co.,Ltd.in 2017,focusing on AI multivariable touch technology based on capacitance.In 2019,Tashan Technology and the University of Manchester jointly established a Joint Research Lab for Touch Sensors for Domestic Robots.HMI solutions based on relevant patent technologies have been applied to clients such as Daimler,BMW and etc
