Keynote Speech Ⅰ
Prof. Tianyou Chai
Member of the Chinese Academy of Engineering
Fellow of IEEE and IFAC
Northeastern University, China
Brief Introduction: Tianyou Chai received the Ph.D. degree in control theory and engineering in 1985 from Northeastern University, Shenyang, China, where he became a Professor in 1988. He is the founder and Director of the Center of Automation, which became a National Engineering and Technology Research Center and a State Key Laboratory. He is a member of Chinese Academy of Engineering, IFAC Fellow and IEEE Fellow. He has served as director of Department of Information Science of National Natural Science Foundation of China from 2010 to 2018.
His current research interests include modeling, control, optimization and integrated automation and intelligence of complex industrial processes.
He has published 396 peer reviewed international journal papers. His paper titled Hybrid intelligent control for optimal operation of shaft furnace roasting process was selected as one of three best papers for the Control Engineering Practice Paper Prize for 2011-2013. He has developed control technologies with applications to various industrial processes. For his contributions, he has won 5 prestigious awards of National Natural Science, National Science and Technology Progress and National Technological Innovation, the 2007 Industry Award for Excellence in Transitional Control Research from IEEE Multiple-conference on Systems and Control, and the 2017 Wook Hyun Kwon Education Award from Asian Control Association.
Speech Title: Intelligent Integrated System for Optimal Decision-making and Control Based on End-edge-cloud Collaboration
Abstract: To address the challenges that online optimization of operational decision-making and control in complex industrial systems cannot be realized, this talk proposes a unified structure and algorithm for integrated operational optimal decision-making and control, by combining control, optimization, and prediction with AI technology. It also proposed a parameter self-learning and self-optimizing algorithm for operational optimal decision-making and control integrating systems, by combining mechanism analysis with deep learning, and digital twin with reinforcement learning. An intelligent integrated system for optimal decision-making and control based on end-edge-cloud collaboration is developed, by combining the proposed method and the end-edge-cloud collaboration technology of Industrial Internet. The system includes the end-optimal decision-making and control system under actual operation, as well as the cloud-edge collaborative parameter self-learning and self-optimizing system for decision-making and control system. The parameter self-learning and self-optimizing system in digital space collaborates with the optimal decision-making and control system under actual operation. Thus, the end-operational optimal decision-making and control system realizes self-learning and self-optimization. The system has been successfully applied in the energy intensive equipment—fused magnesium furnace and achieved remarkable results in the reduction of carbon emission.
Keynote Speech Ⅱ
Prof. Lihua Xie
Fellow of IEEE, SAEng, IFAC and CAA
Nanyang Technological University, Singapore
Brief Introduction: Lihua Xie received his PhD degree from the University of Newcastle, Australia. He is currently President’s Chair in Control Engineering with the School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore. He is the Director, National Research Foundation Centre for Advanced Robotics Technology Innovation (CARTIN) and Joint NTU-VinUni Centre for Robotics and Embodied Intelligence. He has served as Head of Control and Instrumentation Division and Director of Delta-NTU Corporate Laboratory for Cyber-Physical Systems. He has directed several major research programmes with a total funding of over S$100M. His research areas include robust control, multi-agent systems, learning-based control, and unmanned systems. He has authored and co-authored hundreds of research articles, 11 monographs and over 30 granted/filed patents. He has been listed as a highly cited researcher and has received numerous awards for his research including Best Paper Awards from IROS, ICRA, Asia Control Conference, and TCCT Outstanding Contribution Award. He has served as Editor-in-Chief of Unmanned Systems and Editor of IET Book Series on Control and Associate Editor of IEEE Transactions on Automatic Control, Automatica, IEEE Transactions on Control Systems Technology, IEEE Control System Magazine, etc. He was an IEEE Distinguished Lecturer, the General Chair of the 62nd IEEE Conference on Decision and Control, and a Vice-President of IEEE Control System Society. Professor Xie is Fellow of Academy of Engineering Singapore, Fellow of IEEE, Fellow of IFAC, and Fellow of CAA.
Speech Title: A Control-Theoretic Perspective on Inverse Reinforcement Learning
Abstract: Reinforcement learning (RL) has attracted significant attention in recent years due to its application in solving many complex problems such as embodied AI robot manipulation. However, its success depends on a proper reward design which, however, is challenging. Inverse reinforcement learning (IRL) aims to infer an underlying reward function from expert demonstrations, thereby eliminating the need for manually crafted rewards in RL. From a control-theoretic perspective, IRL can be viewed as a modern formulation of the inverse optimal control problem originally posed by Kalman. Despite substantial progress in recent years, several fundamental challenges must be addressed before IRL can be reliably deployed in real-world systems. These include robustness to noisy or suboptimal demonstrations, efficient learning from limited or low-quality data, and the incorporation of safety constraints in practical implementations. In this talk, we present a control- and optimization-based framework to address these challenges. First, we introduce a differential dynamic programming (DDP)-based IRL approach for reward learning from expert demonstrations and develop a closed-loop loss formulation to improve robustness against noise in the demonstrations. Second, to enhance data efficiency, we propose online and model-free IRL algorithms that adaptively refine the reward function using real-time data. We further discuss the interplay among safety, RL, and inverse optimality, and analyze the robustness properties of safe IRL-induced controllers. Finally, we demonstrate the application of IRL to robotics perception.
Keynote Speech Ⅲ
Prof. Long Wang
Winner of National Science Fund for Distinguished Young Scholars
Peking University, China
Brief Introduction: Long Wang was born in Xi'an, China. He received the bachelor's degree in automatic control from Tsinghua University in 1986, and Ph.D. degree in Dynamics and Control from Peking University in 1992. He has held research positions at the University of Toronto, Canada (1993, with Professor Bruce A. Francis), and the German Aerospace Center, Munich, Germany (1995-1997, with Professor Juergen E. Ackermann). He is currently the Cheung-Kong Chair Professor of Dynamics and Control, and the Director of Center for Systems and Control of Peking University. His research interests include complex networked systems, evolutionary game dynamics, artificial intelligence, and bio-mimetic robotics. Prof. Wang was the recipient of the National Science Prize (twice in 1999 and 2017), Guan Zhaozhi Control Theory Award, Zhang Siying Award in Decision and Control, and the Best Paper Awards for journal publications in Control Theory and Applications, Science China Information Sciences, etc. He has supervised more than 50 Ph.D. students. He has also given a number of plenary lectures at major conferences, including Chinese Control Conference, Chinese Conference on Systems Science, Chinese Conference on Intelligent Automation, etc. Email: longwang@pku.edu.cn
Speech Title: Evolutionary Game-theoretic Approach to Collective Intelligence
Abstract: Collective intelligence arises from local interactions and adaptive behavioral updates among individuals, manifesting as an emergent cognitive capability derived from distributed behaviors. Evolutionary game theory provides a unified analytical framework for characterizing the transition from microscopic decision-making to macroscopic order. This talk first introduces the fundamental concepts of game theory, highlighting the limitations of the full rationality assumption and presenting the evolutionary perspective under bounded rationality. We then discuss replicator equations and evolutionary dynamics in structured populations. Building on this foundation, this talk surveys two representative lines of research that employ evolutionary game theory to study collective intelligence. The first focuses on constructing models of collective estimation tasks to characterize how such intelligence emerges. The second emphasizes incentive design, exploring how adjustments to payoff structures can effectively enhance group performance in prediction tasks. Finally, the talk will summarize the advantages of evolutionary game theory in integrating microscopic behavior with macroscopic outcomes and outline directions for future research.
Keynote Speech Ⅳ
Prof. Xinping Guan
Winner of National Science Fund for Distinguished Young Scholars
Fellow of IEEE
Shanghai Jiao Tong University, China
Brief Introduction: Xinping Guan is a Chair Professor at the School of Automation and Sensing, Shanghai Jiao Tong University, and Deputy Director of the National Key Laboratory of Undersea Science and Engineering. He is an IEEE Fellow, a recipient of the Chang Jiang Scholars Program Distinguished Professorship awarded by the Ministry of Education of China, a National Science Fund for Distinguished Young Scholars awardee, and a member of the National “New Century Talents Project.” With nearly 30 years of research experience in network systems theory and applications, Prof. Guan has made pioneering and systematic contributions to the fundamental theories and methodologies of distributed sensing and cooperative control for networked systems. He proposed and established key theoretical frameworks for the integrated design of sensing, communication, and control systems, advancing the development of intelligent networked systems. His research achievements have received numerous prestigious awards, including two National Natural Science Awards of China (ranked first and second), the IEEE TCCPS Industrial Technical Excellence Award, two First Prizes of the Natural Science Awards from the Ministry of Education of China, and two First Prizes of the Shanghai Science and Technology Invention Awards. He has also received the IEEE Transactions on Fuzzy Systems Outstanding Paper Award and more than 10 Best Paper Awards at international conferences. Prof. Guan has published over 400 papers in leading journals and conferences, including 298 papers in IEEE Transactions journals and Automatica, as well as more than 50 papers in major Chinese academic journals. His publications have received over 31,000 citations on Google Scholar. He is the author of five academic monographs, holds more than 130 granted invention patents, and has led his team in developing six international standards. He has been recognized as an Elsevier Highly Cited Researcher for multiple consecutive years. Prof. Guan serves as an Executive Council Member of the Chinese Association of Automation, Deputy Chair of its Control Theory Technical Committee, President of the Shanghai Association of Automation, and has served as Deputy Secretary-General of the Ministry of Education’s Science and Technology Committee. He has also served on the editorial boards of eight international and Chinese journals, including IEEE Transactions on Systems, Man, and Cybernetics: Systems and IEEE/CAA Journal of Automatica Sinica.
Speech Title: A New Industrial Internet Architecture for Controllable End-to-End Performance in Multiple Scenarios
Abstract: As a landmark achievement in China's high-end manufacturing sector, domestic large passenger aircraft have in recent years steadily stepped onto the global competitive stage. Aircraft final assembly stands as the core link in the manufacturing workflow, involving the fitting of thousands of precision components, stringent process specifications, and ultra-high safety standards. It imposes exacting requirements on manufacturing accuracy as well as the real-time performance and reliability of information transmission. Against this backdrop, there is an urgent need to develop an efficient and stable shop-floor industrial Internet architecture. Such an architecture can strengthen the core supporting capacity of factory-wide networks and drive the innovation and upgrading of industrial Internet technologies. Nevertheless, aircraft final assembly currently faces three prominent bottlenecks that hinder intelligent manufacturing and collaborative optimization across production lines: difficulties in distributed full-factor perception, challenges in regulating end-to-end interactive performance, and barriers to coordinated control subject to multi-process constraints. This presentation first elaborates on the inherent complexity of aircraft final assembly scenarios and their critical demands for network support, highlighting the limitations of existing industrial network architectures. Second, focusing on a shop-floor industrial Internet architecture with controllable end-to-end performance, the speaker will illustrate an integrated design framework encompassing perception, transmission, computation and control, and review advances in its core enabling technologies. Special emphasis will be placed on the development of the world’s first capacity model for networked control systems, alongside a systematic comprehensive evaluation system built upon this model. Finally, the speaker will present practical deployment cases of the proposed architecture on the 5G-TSN industrial Internet platform at the Digital Zero Workshop of Shanghai Aircraft Manufacturing Co., Ltd., demonstrate results from multi-scenario performance simulation and verification, and discuss prospects for further applications in smart manufacturing and aeronautic assembly.