Keynote Speaker Ⅰ
Prof. Zhijun Zhang
South China University of Technology, China
Biography: Zhijun Zhang is a professor and doctoral supervisor of South China University of Technology. He is a high-level talent introduction scholar of South China University of Technology, an outstanding young person of Guangdong Province, and a young top talent of Guangdong Science and Technology Innovation. He has long been engaged in the research of neural network, control optimization and robotics. He is currently a member of the Committee on Hybrid Intelligence, Committee on Co-integrated Robotics, Committee on Adaptive Dynamic Planning and Reinforcement Learning, Committee on Visual Perception and Computation of the Chinese Society of Graphics and Imaging, Executive Editor-in-Chief of Global Journal of Neural Science, Associate Editor of International Journal of Robotics and Control. He is also the reviewer of more than 20 international SCI journals, reviewer of China National Foundation Committee, and reviewer of Guangdong High-tech Enterprises. His main original achievements include: (1) proposed a varying-parameter convergent-differential neural network model, which has super-exponential convergence and good robustness; (2) proposed a real-time natural human-robot interaction method based on neural dynamics to solve the robot real-time natural interaction problem; (3) proposed a robot hybrid multi-index intelligent optimization method to solve the multi-objective optimization problem of different layers; (4) independently developed prototypes of multi-modal polar extreme like human emotional interaction intelligent robots, intelligent flying robots, multimodal rehabilitation-assisted wheelchair robots, complex environment anti-epidemic mask detection intelligent robots, etc., and some of the results are on the way to industrialization.
Zhijun Zhang has published/accepted 100 papers in important international journals and conferences, 80 SCI journal papers, 42 SCI papers by first author/corresponding author, 27 IEEE Trans full papers by first author/corresponding author, 2 highly cited papers, and 2 books/chapters in English. The research has been positively cited and evaluated by high-level scholars including IEEE Fellow in the US. Received 95 invention patents and granted 11 invention patents. He presided over 1 National Natural Science Foundation of China (NSFC) project, 1 NSFC youth project, 1 Guangdong outstanding young person project, 1 Guangdong Young Top Talent project, 2 horizontal projects, and participated in 1 National Key R&D Program project. The total project funding is more than 4 million RMB. He received one best paper award from IEEE ICAL2011, one best paper award from ARM2020, one best paper award from ISAS2020, one nomination award from SCIS-CCC, and one workshop best poster award from IROS2019, the flagship conference of international robotics.
Title: Vary Parameter Recurrent Neural Network Applied to Intelligent Robots and Data Analysis
Abstract: Everything in nature changes with time is eternal and absolute, while stationary is only relative. Inspired by this fundamental law of nature and based on the neurodynamic approach, Dr. Zhijun Zhang designed and proposed a varying-parameter recurrent neural network. Various forms of varying- parameter recurrent neural networks are designed and derived, and it is theoretically demonstrated that the network has the property of super-exponential convergence in solving time-varying problems and robot motion planning problems. In solving noise-containing problems, this model can effectively suppress noise and has obvious advantages over similar methods. The network model can effectively overcome the limitations of the existing methods in terms of slow convergence and weak robustness in solving time-varying, nonlinear, underdetermined, and multi-solution problems of robot systems in complex environments, and has the advantages of high solution accuracy, fast error convergence, and robustness. In practical systems, this method can be applied to robot motion planning, natural human-robot interaction and flight controller design and many other aspects.
Keynote Speaker Ⅱ
Prof. Lu Liu
City University of Hong Kong, China
Biography: Dr. Lu Liu received her Ph.D. degree in 2008 in the Department of Mechanical and Automation Engineering, the Chinese University of Hong Kong. From 2009 to 2012, she was an Assistant Professor at The University of Tokyo, Japan, and then a Lecturer at The University of Nottingham, United Kingdom. Then she joined the City University of Hong Kong and is currently a Full Professor. Her research interests are primarily in networked dynamical systems, multi-robot systems, and nonlinear control systems. She received several best paper awards in flagship conferences, including the Guan Zhaozhi Award of the 27th Chinese Control Conference in 2008, and the Shimemura Young Author Award of the 11th Asian Control Conference in 2017. She received the Excellent Young Scientists Fund (Hong Kong and Macao) from the National Nature Science Foundation of China (NSFC) in 2022. Dr. Liu is an Associate Editor of IEEE Transactions on Cybernetics, IEEE Transactions on Fuzzy Systems, IEEE Robotics and Automation Letters, Control Theory and Technology, and Unmanned Systems. She served in the organizing committee of several international conferences including General Chair of the 2022 IEEE International Conference on Real-Time Computing and Robotics, General Chair of the 2022 IEEE International Conference on Control and Automation.
Title: Event-Triggered Cooperative Control of Multi-Agent Systems
Abstract: Cooperative control of multi-agent systems has received considerable attention in the systems and control community over the past two decades. This is mainly because of its great potential in real-world applications, such as search and rescue by a team of unmanned ground/aerial vehicles, and ocean sampling using a fleet of underwater gliders. In this talk, the cooperative output consensus problem for heterogeneous linear multi-agent systems by event-triggered control will be presented. First, the event-triggered control approach will be briefly reviewed. Then for the considered systems, a distributed event-triggered control strategy is proposed. With this control strategy, the output consensus of the system is achieved asymptotically with intermittent communication. Moreover, the continuous monitoring issue can be avoided.
More speakers are to be announced......