自动化学术论坛[2024第39期]：东京都立大学久保田直行教授学术报告会

报告时间：7月11日（周四）上午 8:30

报告地点：信息楼310学术报告厅

报 告 人：久保田直行（Naoyuki Kubota）教授，东京都立大学（Tokyo Metropolitan University）

报告题目：Multiscopic Topological Intelligence for Cognitive Robotics

主要内容：A study on cognitive robotics mainly deals with human-like intelligence on the whole cognitive mechanism such as cognitive development, behavior acquisition, and social communication based on constructivism. For example, to discuss behavior acquisition of mobile robots in dynamically changing environments, we should consider adaptation, learning, and evolution for mobility based on multiscale and multiphysics simulations using digital twin. In such a situation, the extraction of topological features and structures from online big data is useful. Therefore, we proposed the concept of topological twin. The purpose of topological twin is to (1) extract topological structures that are implicitly hidden in the real world, (2) explicitly reproduce them in the cyber world, and (3) simulate and analyze the real world in the cyber world. While we have to deal with the physical dynamics at the microscopic level, we have to deal with spatiotemporal qualitative knowledge at the macroscopic level. Furthermore, we need a mesoscopic integration method that connects microscopic and macroscopic topological features. In this way, the topological twin plays the important role in extracting and connecting structures hidden in real world from the multiscopic point of view. Furthermore, we need a multiscopic approach to deal with inference, learning, search, and prediction based on topological and graphical data as the methodology of topological intelligence. In this talk, we first introduce the concepts of cognitive robotics and multiscopic topological intelligence. Next, we explain different types of topological clustering methods and graph-based methods related to topological intelligence. Furthermore, we show several experimental results on topological intelligence for the mobility in robotics. Finally, we discuss the applicability and future direction of topological intelligence for cognitive robotics.

报告人简介： Naoyuki Kubota is currently a Professor in the Department of Mechanical Systems Engineering, the Graduate School of Systems Design, and Director of Community-centric Systems Research Center, Tokyo Metropolitan University, Japan. He received a doctoral degree from Nagoya University, Japan, in 1997. He joined Osaka Institute of Technology and Fukui University, Japan. He was an Associate Professor from 2005 to 2012, and a Professor from 2012 at the Graduate School of Systems Design, Tokyo Metropolitan University, Japan. He was a Visiting Professor at University of Portsmouth, UK and Seoul National University, and others. His current interests are in the fields of topological mapping, coevolutionary computation, spiking neural networks, robot partners, and informationally structured space. He has published more than 500 refereed journal and conference papers in the above research fields. He was an associate editor of the IEEE Transactions on Fuzzy Systems from 1999 to 2010, the IEEE CIS Intelligent Systems Applications Technical Committee, Robotics Task Force Chair from 2007 to 2014, IEEE Systems, Man, and Cybernetics Society, Japan Chapter Chair from 2018 to 2021, IEEE Transactions on Affective Computing Steering Committee Member since 2019, and others.