腾讯会议：428 375 066
The self-tuning regulators (STR) are a basic class of adaptive controllers designed by combing the celebrated least-squares estimate with the minimum (tracking) variance control, which had played a historical role in the development of adaptive control in both theory and applications. To justify the feasibility and efficiency of STR rigorously, it is necessary to establish a rigorous theory on the global stability and asymptotic optimality of the closed-loop stochastic systems under the STR. Surprisingly, this seemingly simple problem had actually been a longstanding open problem in control theory. This talk will give a retrospect of the research towards establishing a theory of STR, will present a detailed look at this theory for a basic class of linear stochastic systems, and will share some experiences and perspectives of the speaker himself. Revisiting STR may offer useful inspirations for investigating more complex adaptive (or intelligent) systems where machine learning is combined with feedback control, in the era of big data and AI.
Lei Guo received his B.S. degree in mathematics from Shandong University in 1982, and a Ph.D. degree in control theory from the Chinese Academy of Sciences (CAS) in 1987. He is currently a professor at the Academy of Mathematics and Systems Science, CAS. Dr. Guo is a Fellow of IEEE, a Member of CAS, a Fellow of the Academy of Sciences for the Developing World (TWAS), a Foreign Member of the Royal Swedish Academy of Engineering Sciences, and a Fellow of IFAC. He was awarded an honorary doctorate by the Royal Institute of Technology (KTH), Sweden. He was the recipient of the 1993 IFAC World Congress Young Author Prize for “solving a long-standing problem in control theory concerning convergence and convergence rate for the least-squares–based self-tuning regulators”. He was also the recipient of the 2019 Hendrik W. Bode Lecture Prize awarded by the IEEE Control Systems Society for “fundamental and practical contributions to the field of adaptive control, system identification, adaptive signal processing, stochastic systems, and applied mathematics”. His current research interests include adaptive systems theory, machine learning, control of nonlinear uncertain systems, PID control theory, distributed filtering and estimation, multi-agent systems, game-based control systems, and complex systems, among others.