Prof. Jing Sun
(Keynote Speaker)

IEEE Fellow

University of Michigan, USA

Keynote Lecture: AUV Active Perception and Control: From an Energy Efficiency Perspective

Abstract: Autonomous Underwater Vehicles (AUVs), distinguished by their advanced autonomy, offer significant potential for expanding the horizons of underwater exploration and missions. However, using AUVs for extended range or deep-sea operations faces a substantial challenge due to limited vehicle endurance, thereby imposing constraints on their applications. This challenge can be effectively addressed by implementing sophisticated and robust energy management strategies, including energy-optimized planning and control methodologies. These approaches hold the potential to significantly augment AUV operational energy efficiency, thereby extending their endurance and broadening their operational scope.
      In this presentation, we will delve into the realm of AUV operations, specifically focusing on energy management strategies designed to enhance efficiency during sustained operations. We will introduce an active perception framework geared towards accurate flow predictions. Combining path planning with flow field identification, this approach enables AUV to adapt to the dynamic underwater environment for optimal energy efficiency. Additionally, for real-time control, an Economic Model Predictive Control (EMPC) has been developed. This EMPC leverages the inherent hydrodynamic characteristics of AUVs to strike a balance between optimality and computational efficiency. Through these discussions, we aim to shed light on innovative strategies that hold promises to enhance the overall energy efficiency of AUVs, thereby advancing their underwater exploration and mission capabilities in diverse operational scenarios.

Biography: Jing Sun received her Ph. D degree from the University of Southern California in 1989 and her master's and bachelor's degrees from the University of Science and Technology of China in 1984 and 1982, respectively. From 1989 to 1993, she was an assistant professor in the Electrical and Computer Engineering Department at Wayne State University. She joined Ford Research Laboratory in 1993, where she worked on advanced powertrain system controls. After spending almost ten years in the industry, she returned to academia in 2003. She joined the University of Michigan, where she is the Michael G. Parsons Collegiate Professor in the Naval Architecture and Marine Engineering Department, with joint appointments in the Electrical Engineering and Computer Science Department and Mechanical Engineering Department at the same university. She holds 44 U.S. patents and has published over 300 archived journal and conference papers. She is a Fellow of NAI (the National Academy of Inventors), IEEE (Institute of Electrical and Electronics Engineers), IFAC (International Federation of Automatic Control), and SNAME (the Society of Naval Architecture and Marine Engineering). She is a recipient of the 2003 IEEE Control System Technology Award.

Prof. Wei Ren
(Keynote Speaker)

University of California, USA

Keynote Lecture: Distributed Coordination in Multi-agent Systems: Algorithms and Applications

Abstract: While autonomous systems that perform solo missions can yield significant benefits, greater efficiency and operational capability will be realized from teams of autonomous systems operating in a coordinated fashion. Potential applications for networked multiple autonomous systems include environmental monitoring, search and rescue, space-based interferometers, hazardous material handling, and combat, surveillance, and reconnaissance systems. Networked multi-agent systems place high demands on features such as low cost, high adaptivity and scalability, increased flexibility, great robustness, and easy maintenance. To meet these demands, the current trend is to design distributed algorithms that rely on only local information and local interaction to achieve global group behavior.
      The purpose of this talk is to overview our recent research in distributed control, estimation and optimization in networked multi-agent systems. For distributed control, results on distributed synchronization for agents with various dynamics, distributed single-leader collective tracking with reduced interaction and partial measurements, and distributed multi-leader containment control with local interaction will be introduced. For distributed estimation, results on fully distributed information fusion with multiple networked sensors will be introduced, under very mild assumptions on local observability, communication graphs, and models. For distributed optimization, results on distributed convex optimization will be introduced, under realistic challenges such as non-identical constraints, fully distributed design, and time-varying cost functions. Application examples in multi-vehicle cooperative control will also be introduced.

Biography: Wei Ren is currently a Professor with the Department of Electrical and Computer Engineering, University of California, Riverside. He received the Ph.D. degree in Electrical Engineering from Brigham Young University, Provo, UT, in 2004. His research focuses on distributed control of multi-agent systems. Dr. Ren was a recipient of the IEEE Control Systems Society Antonio Ruberti Young Researcher Prize in 2017 and the National Science Foundation CAREER Award in 2008. He is an IEEE Fellow and IEEE Control Systems Society Distinguished Lecturer.

Prof. Xinjun Liu
(Keynote Speaker)

Tsinghua University, China

Keynote Lecture: Transformative robotic machining technology and equipment for large-scale structures

Abstract: In this talk, the connotation of scientific and technological innovation and its role in the history of human development will be reviewed firstly. Then, the importance of scientific and technological innovation research and equipment innovation and its application in engineering will be emphasized. The scientific and technological innovation research models will be discussed and some examples about processing of complex structures and large structural parts will be given. This talk will focus on the conception, technical verification and engineering application of innovative research and development of industrial robots. Some expectations on the innovative development of robotic equipment will be shared at end of the talk.

Biography: Xinjun Liu is a Full Professor with Tenure in Department of Mechanical Engineering at Tsinghua University, Beijing, China. He is the "Cheung Kong" Chair Professor, and the winner of National Outstanding Youth Fund of China. He is currently the MO Chair of International Federation for the Promotion of Mechanism and Machine Science (IFToMM) China-Beijing and the Director of the Beijing Key Laboratory of Precision and Ultra-precision Manufacturing Equipment and Control. From 2000 to 2001, he worked as a Postdoctoral Researcher at Tsinghua University. He was a Visiting Researcher at Seoul National University, Seoul, Korea in 2002-2003. He was the Alexander von Humboldt (AvH) Research Fellow at University of Stuttgart in Germany from 2004 to 2005. He was the Visiting Professor with Prof. Dr. Reimund Neugebauer at Fraunhofer Institute for Machine Tools and Forming Technology, Germany, in August of 2007. He has published over 190 papers in refereed journals and refereed conference proceedings and has been selected as Elsevier's Most Cited Chinese Researchers for seven consecutive years from 2014 to 2020, 90 authorized patents, and three books (including one book in English). His research interests include smart robotics, parallel mechanisms and robots, machining robots, and advanced and smart manufacturing equipment.

Dr. Hyun-Taek Choi
(Keynote Speaker)

Korea Research Institute of Ships and Ocean Engineering, South Korea

Keynote Lecture: Situational Awareness System for Autonomous Surface Vehicles: Safe Navigation and Surveillance

Abstract: This presentation introduces our ongoing research on the situational awareness system for autonomous surface vehicles, including unmanned surface vehicles (USVs) and autonomous ships (ASs). Our work primarily centers on developing deep-learning-based object detection and tracking algorithms for cameras, LiDAR, and radar sensors, alongside data fusion and multi-object tracking algorithms. Our objectives are twofold: ensuring safe navigation and enhancing surveillance capabilities. For this, we explain the distinctions between these two objectives and present experimental results demonstrating object detection at sea for each goal.

Biography: Hyun Choi received his BS, MS, and PhD degrees in Electrical Engineering from the Hanyang University, Korea in 1991, 1993, 2000 respectively. After working for Korea Telecom, Korea and ASL, University of Hawaii, USA as a post-doc, he joined Korea Research Institute of Ships and Ocean Engineering (KRISO), Korea in 2003. He has been leading many projects related to intelligent marine robotic applications including remotely-operated vehicles, autonomous underwater vehicles, unmanned surface vehicles, and autonomous ship. He served a director of ocean system engineering division from 2015 to 2017. His research interests are the design of marine robots, perception, advanced control & navigation using robotic intelligence. Now he is the president of Korea Robotics Society for 2024 and co-chair of IEEE RAS TC on Marine Robotics.

Prof. Dong Eui Chang
(Keynote Speaker)

Korea Advanced Institute of Science & Technology, South Korea

Keynote Lecture:Feedback integrators: A new method for structure-preserving numerical integration of dynamical systems

Abstract: Structure-preserving numerical integration for ordinary differential equations is very crucial in numerical simulation of dynamical systems. In general, numerical integration of ordinary differential equations is expected to preserve first integrals and state-space manifolds such as energy, angular momentum and SO(3) for the free rigid body dynamics. As such, structure-preserving integration has been a vast research area for which various algorithms have been developed such as symplectic integrators, variational integrators and so on. Most of the algorithms, however, require special tricks, case-by-case, such as solving implicitly defined algebraic equations at each integration step or using a particular parameterization of a given manifold.
     In this talk, I will present a new method of structure-preserving integration, called feedback integrators, which does not require any of these special tricks but rather allows one to generally use any off-the-shelf numerical integrators such as the Euler method and the Runge-Kutta method, in order to numerically integrate a given dynamical system while preserving its conserved quantities. Feedback integrators apply to holonomic mechanical systems and non-holonomic mechanical systems as well as regular mechanical systems. They also extend to controller design for systems defined on manifolds. The theory of feedback integrators is still in the making to which everyone is welcome.

Biography: Dong Eui Chang is a professor in the School of Electrical Engineering at KAIST, Head of the SeongNam-KAIST Next-Generation ICT Research Center, and Head of the KAIST-HwaSeong Science Hub. He served in 2021-2022 on the advisory board for Presidential Security Service for President of South Korea. He received his B.S. degree in Control & Instrumentation Engineering in 1994, his M.S. degree in Electrical Engineering in 1997, both from Seoul National University, and his Ph.D. degree in Control & Dynamical Systems from Caltech in 2002 under the supervision of Professor Jerrold E. Marsden. He was an associate professor in the Department of Applied Mathematics at the University of Waterloo before he joined KAIST in 2017. He is a co-author of the book “Deep Neural Networks in a Mathematical Framework” published by Springer in 2018. His research interests include control, robotics, mechanics, and AI.

Prof. Chunhui Zhao
(Invited Speaker)

Zhejiang University, China

Invited Lecture: Theoretical exploration and practice of industrial process fault diagnosis based on zero sample learning

Abstract: Fault diagnosis system is an important guarantee for the safe and reliable operation of industrial processes. Data-driven fault diagnosis modeling often depends on the collected sufficient historical fault data. However, in actual industrial processes, it is common that process failures have no historical samples and no labels. In this regard, we need to deal with a very challenging fault diagnosis task, that is, to consider diagnosing when there are no historical fault samples available for model training. We introduced the concept of zero-shot learning into the industrial field for the first time, and innovatively established a zero-shot-learning fault diagnosis method. By skillfully introducing a priori modeling knowledge with fault description as the carrier and adopting the attribute migration method, we overcame the concerned bottleneck problem that traditional fault diagnosis research cannot meet the sample size constraint. We theoretically analyzed and explained the effectiveness and feasibility of the zero-shot-learning diagnosis method based on fault description. In addition, the fault diagnosis performance in the case of zero samples is verified in the real megawatt thermal power process, and the results show that it is feasible to diagnose unseen target fault without samples. On this basis, the existing challenges, difficulties and future research directions are revealed.

Biography: Chunhui Zhao, Qiushi Distinguished Professor,and academic vice president of East China Jiaotong University. She is the recipient of the National Outstanding Youth Fund, and recipient of the Chinese Young Female Scientist Award, Fellow of Chinese Association of Automation.
     Her research interests include statistical machine learning and data mining for industrial application. She has authored or coauthored more than 220 papers in peer-reviewed international journals. She has published 3 monographs and one national textbook. She authorized more than 60 invention patents. She has hosted more than 20 scientific research projects, including National Natural Science Foundation of China project, National key R&D project, provincial projects and corporate cooperation projects. She has received the Ministry of Education Natural Science Award and other provincial and ministerial awards. She also received more than ten academic awards, including the First Prize of Natural Science of Chinese Association of Automation, the First Young Women Scientists Award of Chinese Association of Automation, etc. She has served AE of three International Journals, including Journal of Process Control, Control Engineering Practice and Neurocomputing, and three domestic journals, including Control and Decision, etc.

Assoc. Prof. Yue Gao
(Invited Speaker)

Shanghai Jiaotong University, China

Invited Lecture: Advancements in Learning-Based Control: Transforming the Mobility of Legged Robots and Their Real-World Applications

Abstract: Legged robots have a broad spectrum of applications, primarily due to their adaptation when traversing unstructured environments. Their complexity arises from diverse configurations such as bipedal, quadrupedal and hexapedal, extending to control models as multi-input, multi-output, multi-end-effector systems. This complexity introduces significant challenges in locomotion control and planning, including model identification, real-time computational demands, and adaptation to unseen tasks. The purpose of this talk is to provide an overview of our new research in learning-based control for legged robots. Leveraging advancements in reinforcement learning and deep learning, we have significantly enhanced legged robots' mobility, safety, and the ability of self-learning. Furthermore, this talk will highlight an interesting application of our research through the curling and skiing six-legged robots designed for Beijing Winter Olympics, demonstrating the real-world application potentials for learning-based control for legged robots.

Biography: Yue Gao, an associate professor and doctoral advisor at the School of Electronic Information and Electrical Engineering, AI Institute, Shanghai Jiao Tong University. She obtained her Bachelor of Science in Computer Science from the University of Wisconsin-Madison in 2008, she received Master of Science in Computer Science from Cornell University in 2012 and Ph.D.in Computer Science from Cornell University in 2016. Her research focuses on the control and planning for legged robots. Over the past five years, she has published more than 40 papers in SCI/EI journals, served as Principal Investigator for projects from National Natural Science Foundation and National Key Research and Development Program in China. Currently, she serves as an Associate Editor for Robotica journal. She has received awards as the Outstanding AI Leader at the World Artificial Intelligence Conference and the first prize in the National University Teaching Innovation Competition.

Dr. Yuyang Zhou
(Invited Speaker)

Edinburgh Napier University, UK

Invited Lecture: Fully Probabilistic Control Algorithm Design for a class of Complex Stochastic Systems

Abstract: Complex dynamical systems have garnered significant interest in the realms of control and engineering, as they offer a cohesive and natural framework for the mathematical modeling of diverse real-world systems, such as communication networks, power grids, and chemical processes. The inherent characteristics of these systems, such as high dimensionality, intricate structures, complex models with multiple modes of switching, and substantial uncertainties, pose notable challenges for system analysis, estimation, and particularly for control.
     This talk will introduce a novel decentralised probabilistic control framework designed for complex stochastic systems. It will offer a fresh research outlook dedicated to refining the control of such systems. In this talk, we will delineate the core principles and applications of the framework, showcasing its contribution to the development of innovative control strategies for complex stochastic systems.

Biography: Yuyang Zhou received her B.Sc. in Electrical & Electricity Engineering School in The University of Manchester, United Kingdom, 2014 and Electrical & Engineering School in Beijing JiaoTong University, China, 2014, and later her Ph.D. in control theory from Electrical & Electricity Engineering School in The University of Manchester, United Kingdom, 2018. After that, she became a Research Associate for three years in the Faculty of Engineering and Applied Science at Aston University, Birmingham, United Kingdom. She currently is a lecturer in group of Engineering and Mathematics, School of Computing, Engineering and Built Environment, Edinburgh Napier University, United Kingdom. She is also a guest editor for MDPI mathematics. Her current research focuses on probabilistic and stochastic control, minimum entropy control, pdf control and decentralized control, time-delay systems, networked and complex systems control with applications to power grids and Kalman filtering.