10:00am – 11:00am
EIS-220
Speaker: Dr. Tielong Shen, Professor
Dept. of Applied Science and Engineering
Sofia University, Tokyo, Japan
Abstract: Recently, the mean-field approximation approach has attracted much attention from the research community of modeling and control of large-scale population of agents. In the practice of on-board energy efficiency optimization of vehicular powertrains, there has been considerable research literatures on using the mean-field approach to deal with the vehicle-to-vehicle coupling and decentralized control design by considering the collective behavior of vehicle crowd. This talk will begin with a short review of the mean-field approximation approach and its application in game and optimization problems. Then, learning-based approaches are introduced to modeling the mean-field behavior of vehicles. With this modeling method and reinforcement learning approaches, decentralized control design examples will be explained based on the speaker’s research experience.
Biography: Dr. Tielong Shen received his PhD degree in Mechanical Engineering from Sophia University 1992, and joined Sophia University as Assistant Professor with Tenure in April 1992, where he is serving as Professor. He is also serving Visiting Professor for Center for Power Source Research for Next-generation Mobility, Chiba University, Japan. His research interests include control theory and applications in automotive powertrain systems, power systems, and mechanical systems. Dr. Shen has author/co-authored eleven books and has published more than 300 research papers in peer-reviewed major journals. At the last year, he is awarded the 8th TCCT Outstanding Contribution Award. He is Fellow of SICE, and currently serving Director for The Society of Instrument and Control Engineers (SICE), Japan.