Title: Learning-based Control with Application to Autonomous Systems

Abstract:

The traditional control theory relies on mathematical models of physical systems for estimation and control. In many applications such as power systems and robotics, it is difficult to obtain accurate system models due to the complexity of the system under study and the environment it interacts with. In recent years, learning-based control has attracted a lot of interest in various fields of engineering including manufacturing, robotics, and transportation systems. In this talk, we shall introduce some recent development in data-driven control, reinforcement learning, and Gaussian Process based learning, and demonstrate their application in autonomous systems such as sensor fusion for perception and trajectory planning.

Biography: Lihua Xie is Professor and President’s Chair in Control Engineering and Director, Center for Advanced Robotics Technology Innovation, Nanyang Technological University. He has served as the Head of Division of Control and Instrumentation and Co-Director, Delta-NTU Corporate Lab for Cyber-Physical Systems. His research interests include system theory and control, networked systems, multi-agent networks, learning-based control, and unmanned systems. He is an Editor-in-Chief for Unmanned Systems and Associate Editor for IEEE Control System Magazine. He has served as Editor for IET Book Series in Control and Associate Editor for a number of journals including IEEE Transactions on Automatic Control, Automatica, IEEE Transactions on Control Systems Technology, etc. He was an IEEE Distinguished Lecturer and the General Chair of the 62^nd IEEE Conference on Decision and Control (CDC 2023). He is currently Vice-President of IEEE Control System Society. Dr Xie is Fellow of Academy of Engineering Singapore, IEEE, IFAC, and CAA.