Title:基于物理信息系统观点的机械臂神经网络实时控制(Neural Network Based Control of Robotic Arms in Real Time: A CPS Perspective)
Abstract: With the advances of mechanics, electronics, computer engineering, using autonomous robots, or a collection of them, to perform various tasks is becoming increasingly popular in both industry and our daily lives. Control plays an important role for stable and accurate task execution while learning is outstanding in dealing with unknowns or uncertainties. Recent advances in machine learning provide us with an opportunity to employ innovative learning structures for efficient adaptation. However, it remains challenging on how to efficiently integrate learning with control efficiently to reach provable and guaranteed stability even in the worst case. In addition, as a typical cyber physical system(CPS), physical constraints and timing constraints, which used to be ignored to a large extent in conventional control design, have to be seriously addressed in practical applications. We have conducted a series of research in the past five years with the cross-layer design of the cyber part and the physical part by investigating the problem from a CPS perspective. This talk will present our recent results and insightson the establishment of a generic framework integrating control and learning, with compliance to inherent constraints of the controlled robots.
Bio: Shuai Li received the B.E. degree in electrical engineering from the Hefei University of Technology, Hefei, China, in 2005, the M.E. degree in control engineering from the University of Science and Technology of China, Hefei, in 2008, and the Ph.D. degree in electrical and computer engineering from the Stevens Institute of Technology, Hoboken, NJ, USA, in 2014. He joined Hong Kong Polytechnic University after graduation as a phd supervisor and led his group involving several PhD students and postdoctoral researchers to do research in robotics, cyber physical systems, intelligent control, etc. Dr. Li is an associate editor of the International Journal of Advanced Robotic Systems, Frontiers in Neurorobotics, and Neural Processing Letters.