Plenary-Keynote Talks

Gary G. Yen, Professor, Oklahoma State University

Generative Model-based Large-scale Dynamic Multiobjective Optimization

Abstract: Dynamic multi-objective optimization problems (DMOPs) are often scaled to large-scale scenarios in real-world applications, which inevitably must face the triple challenges of massive search space, dynamic environmental changes and multi-objective conflicts simultaneously. This talk will survey generative modeled-based approaches, specifically an adversarial autoencoder-based large-scale dynamic multi-objective evolutionary framework. It integrates deep generative modeling techniques and large-scale multi-objective evolutionary algorithms to solve large-scale DMOPs effectively and efficiently. Specifically, a deep generative network training architecture is proposed for high-dimensional decision variables in large-scale DMOPs. It can transfer a generative model trained on Pareto-optimal solutions in the current environment to a new environment using only the auxiliary information exhibited through the movement trajectories of historical Pareto-optimal solutions, resulting in the generation of quality initial populations for the new environment. Meanwhile, any large-scale multi-objective evolutionary algorithm can be integrated into the proposed framework without extensive modifications. Experimental results on a typical dynamic multi-objective test suite with problem settings from 30 to 1,000 dimensions demonstrate that the optimization performance of the proposed framework outperforms existing state-of-the-art designs. Especially in large-scale scenarios, the proposed framework is considered superior in terms of solution quality and computational efficiency.

Biography: Gary G. Yen received the Ph.D. degree in electrical and computer engineering from the University of Notre Dame in 1992. He is currently a Regents Professor in the School of Electrical and Computer Engineering, Oklahoma State University. His research interest includes intelligent control, computational intelligence, evolutionary multiobjective optimization, conditional health monitoring, signal processing and their industrial/defense applications. Gary was an associate editor of the IEEE Transactions on Neural Networks and IEEE Control Systems Magazine during 1994-1999, and of the IEEE Transactions on Control Systems Technology, IEEE Transactions on Systems, Man and Cybernetics (Parts A and B) and IFAC Journal on Automatica and Mechatronics during 2000-2010. He is currently serving as an associate editor for the IEEE Transactions on Evolutionary Computation, IEEE Transactions on Cybernetics, IEEE Transactions on Emerging Topics on Computational Intelligence, and most recently IEEE Transactions on Artificial Intelligence. Gary served as Vice President for the Technical Activities, IEEE Computational Intelligence Society in 2004-2005 and was the founding editor-in-chief of the IEEE Computational Intelligence Magazine, 2006-2009. He was elected to serve as the President of the IEEE Computational Intelligence Society in 2010-2011 and is elected as a Distinguished Lecturer for the term 2012-2014, 2016-2018, and 2021-2023. He received Regents Distinguished Research Award from OSU in 2009, 2011 Andrew P Sage Best Transactions Paper award from IEEE Systems, Man and Cybernetics Society, 2013 Meritorious Service award from IEEE Computational Intelligence Society and 2014 Lockheed Martin Aeronautics Excellence Teaching award. He is a Fellow of IEEE, IET and IAPR.

Dario Floreano, Professor, Laboratory of Intelligent Systems, EPFL

Design and control of biologically informed drones

Abstract: Drones have taken the world by storm. In the past 15 years, they have become one of the fastest-growing robotics sectors and in some countries are even available on the shelves of a neighborhood supermarket. And yet, today’s commercial drones cannot yet compete with flying animals in terms of mechanical resilience, adaptability, and cooperation. In this talk I will describe research addressing these challenges that take inspiration from insects and birds for perception, body design, multi-modal locomotion, cooperative behavior, and also show translation of research results into commercial products.

Biography: Prof. Dario Floreano is director of the Laboratory of Intelligent Systems at Ecole Polytechnique Fédérale de Lausanne (EPFL). He has been the founding director of the Swiss National Center of Competence in Robotics from 2010 to 2022. Prof. Floreano holds an M.A. in Visual Perception, an M.S. in Neural Computation, and a PhD in Robotics. He held visiting research positions at Sony Computer Science Laboratory, at Caltech/JPL, and at Harvard University. His research interests are biologically inspired robotics and artificial intelligence. Prof. Floreano has made pioneering contributions to the fields of evolutionary robotics, aerial robotics, and soft robotics that have been published in more than 400 peer-reviewed articles, and five books (Artificial Neural Networks, Evolutionary Robotics, Bio-inspired Artificial Intelligence, Bio-inspired Flying Robots, Tales from a Robotic World) with MIT Press and Springer Verlag. He served in several advisory boards and committees, including the Future and Emerging Technologies division of the European Commission, the World Economic Forum Agenda Council, the International Society of Artificial Life, the International Neural Network Society, the Max-Planck Institute for Intelligent Systems, and in the editorial committee of ten scientific journals, including Science Robotics. In addition, he helped spinning off two drone companies (senseFly.com and Flyability.com) and the world-largest non-for-profit portal on robotics and A.I. (RoboHub.org). He is fellow of the IEEE, ELLIS, and ECLT societies.

Guimin Chen, Professor, Xi’an Jiaotong University

Compliant Multistable Mechanisms and Multistable Robots

Abstract: Multistable mechanisms are special class of compliant mechanisms that can hold several distinct positions without external power input at which the total strain energy stored in the flexible members falls in its minima. They have attracted a lot of attention in the field of metamaterials, mechanical computation, and shape morphing. This talk will discuss several unique multistable designs and their applications in robots to increase instantaneous power density of small actuators, achieving torso reconfiguration, and produce abrupt stiffness change.

Biography: Guimin Chen is a full professor of Institute of Robotics and Intelligent Systems at Xi’an Jiaotong University. He earned his BS, MS and Ph.D from Xidian University, and had been a visiting professor twice at Compliant Mechanism Research Lab of Brigham Young University. His major research interests include compliant mechanisms and their applications in robotics. He was the recipient of 2018 ASME Compliant Mechanisms Award. He served as an Associate Editor of ASME Journal of Mechanisms and Robotics and serves as an Associate Editor of IEEE Transactions on Automation Science and Engineering. He is also an editorial board member of Chinese Journal of Mechanical Engineering. He was elected as an ASME Fellow in 2023.

Xiang Li, Professor, Tsinghua University, China

Optimized and Personalized Human-In-the-Loop Adaptation Framework for Exoskeleton Systems

Abstract: One of the typical purposes of using lower-limb exoskeleton robots is to provide assistance to the wearer by supporting their weight and augmenting their physical capabilities according to a given task and human motion intentions. The generalizability of robots across different wearers in multiple tasks is important to ensure that the robot can provide correct and effective assistance in actual implementation. However, most lower-limb exoskeleton robots exhibit only limited generalizability. Therefore, this talk proposes a human-in-the-loop learning and adaptation framework for exoskeleton robots to improve their performance in various tasks and for different wearers. To suit different wearers, an individualized walking trajectory is generated online using dynamic movement primitives and Bayes optimization. To accommodate various tasks, a task translator is constructed using a neural network to generalize a trajectory to more complex scenarios. These generalization techniques are integrated into a unified variable impedance model, which regulates the exoskeleton to provide assistance while ensuring safety. The proposed framework is easy to implement, because it requires proprioceptive sensors only to perform and deploy data-efficient learning schemes. This makes the exoskeleton practical for deployment in complex scenarios, accommodating different walking patterns, habits, tasks, and conflicts.

Biography: Xiang Li is an Associate Professor with the Department of Automation, Tsinghua University. His research interests include robotic dexterous manipulation, human-robot collaboration, and multi-agent systems. He has published a monograph distributed by Springer and authored over 100 high-level journal and conference papers in the field of robotics, including publications in IJRR, TRO, Automatica, TAC, ICRA, and IROS. He has been the Associate Editor of IEEE Robotics and Automation Letters since 2022 and the Associate Editor of IEEE Transactions on Automation Science and Engineering since 2023. He was the Associate Editor of IEEE Robotics & Automation Magazine from 2019 to 2021 and the Associate Editor of ICRA in 2019, 2020, 2021, and 2023. He received the Highly Commended Paper Award in 2013 IFToMM, the Best Paper in Robotic Control in 2017 ICAR, the Best Application Paper Finalists in 2017 IROS, the T. J. Tarn Best Paper in Robotics in 2018 IEEE ROBIO, the T. J. Tarn Best Paper Finalists in 2023 IEEE ROBIO, and the Best Paper Award in 2023 ICRA DOM Workshop. He led the team and won the prizes in 2022 ICRA Sim2Real Challenge and 2023 ICRA Virtual Manipulation Challenge. He is the Program Chair of the 2023 IEEE International Conference on Real-time Computing and Robotics.

Samer MOHAMMED, Professor, University Paris-Est Créteil – UPEC

Physical Assistive Devices in Rehabilitation Robotics: from Laboratory Prototypes to Clinical Integration

Abstract: This talk will explore some advanced control strategies in wearable robotics, aiming to address diverse mobility challenges encountered by population suffering from neurological disorders affecting their movements. From both assistive and rehabilitative perspectives, the primary goal is to improve the physical daily living activities through customized solutions. The emphasis lies in developing systems that not only provide physical assistance but also respond to the wearer’s intention in real-time, adapting to their diverse needs. Several case studies will be discussed, which involve new control paradigms for an actuated ankle orthosis, impedance modulation strategies for lower limb exoskeletons used in sit-to-stand movement, real-time gait mode detection using Long Short-Term Memory algorithms and the application of Adaptive Functional Electrical Stimulation for individuals suffering from foot drop. These advancements demonstrate significant potential to enhance the mobility, independence, and overall quality of life for dependent individuals using these assistive devices. The effectiveness of the proposed methodologies is demonstrated through theoretical analyses, simulations, and experimental validations.

Biography: Samer Mohammed (Senior Member, IEEE) is Full Professor with the Laboratory of Images, Signals and Intelligent Systems, University of Paris-Est Créteil, France. He received the Ph.D. degree in robotics from the University of Montpellier, France, in 2006, and the Habilitation degree in robotics from the University of Paris-Est Créteil, Créteil, France, in 2016. He has authored or coauthored more than 100 high-level papers in scientific journals, books, and conference proceedings. His current research interests include modeling, identification, and control of robotic systems (wearable robots), artificial intelligence, and decision-support theory with target applications on assistive robotics. He is an Associate Editor of IEEE Transactions on Robotics since 2021 and Associate Editor of Frontiers in Control Engineering and Actuators-MDPI since 2022. He was Associate Editor of ICRA for the last five years. From 2006 to 2007, he was a JSPS Posdoctoral Fellow with AIST, Tsukuba, Japan. Dr. Mohammed is a Founding Co-Chair of the IEEE Robotics and Automation Society Technical Committee on Wearable Robotics. He is actively involved in different editorial committees of IEEE journal and conferences, and he co-organized several national and international workshops in the field of wearable robotics.

Shijie GUO, Professor, Hebei University of Technology

The Technical Challenges of Humanoid Multifunctional Nursing-care Robots

Abstract: With the acceleration of population aging, the expectations for practical applications of robots in nursing site are rapidly increasing. The development of nursing-care robots has become a hot topic in the field of robotics. At present, most nursing-care robots are single-functional products which are designed only to accomplish a specific task, such as transfer, mobility assistance, meal assistance, bathing, diapering and so on. However, aging leads to multiple declines in physical and cognitive functions. Single-functional robots are difficult to provide comprehensive care to the elderly for “less illness”, “slower decline”, “high quality of life”, and “dignified death”. Consequently, there is an urgent need to develop multifunctional nursing-care robots that serve as both “home helpers” and “health doctors”. Recently, autonomous humanoid multifunctional nursing-care robots have garnered significant attention. This lecture will first review the history of single-functional nursing-care robots, and then discuss the core technologies involved in humanoid nursing-care robots and present the recent progresses of our team toward creating multifunctions.

Biography: Prof. Shijie Guo received his doctor degree in mechanical engineering from Tokyo Institute of Technology, Japan, in 1992. He is currently a professor at Hebei University of Technology and a part-time professor at Fudan University, China. He is also the director of the Hebei Key Laboratory of Robot Perception and Human-Robot Interaction as well as the Engineering Research Center of the Ministry of Education of China for Intelligent Rehabilitation Equipment and Physiological Information Detection. Additionally, he also serves as the deputy director of the Academic Committee of Hebei University of Technology and editor-in-chief of Journal of Hebei University of Technology. He has long been engaged in the research of key technologies and applications of human-interaction robots, including robotic e-skin, electroactive polymer artificial muscles, nursing-care robots, rehabilitation robots, exoskeleton robots, etc. The intelligent robot skin tactile sensing system developed by his team was selected as the “Innovation China” pioneer technology by China Association for Science and Technology in 2020. The piggyback transfer robot he developed won the Gold Medal at the 8th China Entrepreneurial Design & Innovation Competition of Elderly Welfare Equipment in 2021. In 2022, as the principal investigator, he was awarded the First Prize for Science and Technology Progress in Hebei Province, China.