Modeling, Learning and Control of Complex Dynamical Systems
Description
This book offers readers a systematic exposition of the theoretical knowledge and application technology of Human-Robot Collaboration, Human-Robot Intelligence, and Human-Robot Dynamical Systems, filling an important gap in the current artificial intelligence research community. The highlights of this book include the critical concept of the Human-Robot Dynamical System and the pioneering technology of Human-Robot Dynamics Learning. Specifically, the Human-Robot Dynamical System represents a significant new research direction in the field of Human-Robot Intelligence. It encompasses the complex dynamical systems involved in human-robot collaboration and interaction applications, such as robot dynamics control, human behavior understanding, and human-robot motion-cognition-coupled interaction.
Human-Robot Dynamics Learning technology is designed specifically for Human-Robot Dynamical Systems. It is an innovative machine learning approach that combines techniques from artificial neural networks, control system theory, and classical mechanics. This technology excels in achieving precise mathematical expression and accurate modeling of the dynamic behavior of human-robot systems.
It provides an advanced framework for studying the theoretical and technological challenges in Human-Robot Collaboration and interaction applications, and it could offer a new research direction for developing the next generation of artificial intelligence.
More details
Persons
Jingting Zhang received the Ph.D. degree in mechanical engineering from at The University of Rhode Island, Kingston, RI, USA, in 2023. She has been a research assistant at the Intelligent Control & Robotics (IcRobots) Laboratory of The University of Rhode Island from 2018 to 2023, is currently an associate professor with the Automation Engineering Department, and the Center for Robotics at University of Electronic Science and Technology of China, Chengdu, P.R. China. Her research interests span over general areas of dynamics learning and control, human-robot interaction, intelligent rehabilitation robotics, and deterministic learning. She has authored and co-authored over 40 journal articles and conference papers in the field of robotics and control systems.
Chengzhi Yuan received the Ph.D. degree in mechanical engineering from North Carolina State University, Raleigh, NC, USA, in 2016. He is currently an associate professor with the Mechanical, Industrial and Systems Engineering Department, and the Director of the Intelligent Control & Robotics (IcRobots) Laboratory at The University of Rhode Island, Kingston, RI, USA. His research interests span over general areas of dynamic systems and control theory, with particular focuses on provable adaptive learning and control, hybrid systems, and multi-robot distributed control. He has authored and co-authored over 140 journal articles and conference papers.
Hong Cheng received the Ph.D. degree in Engineering from Xi'an Jiaotong University, Xi'an, P.R. China, in 2009, and studied for postdoctoral research at Carnegie Mellon University, Pittsburgh, PA, USA, from 2006 to 2011. He is the director of the Ethics Committee and Dean of the School of Mechanical and Electrical Engineering, University of Electronic Science and Technology of China. He is dedicated to the research of theory, technology, applications and industrialization of Human-Robot Intelligence and Rehabilitation robots. He has co-authored 3 textbooks and academic monographs, and has authored and co-authored over 150 journal articles and conference papers in the fields of intelligent autonomous, pattern recognition, and robotics. His research works have been cited over 2000 times on Google Scholar, with an H-index of 20; has applied for more than 150 national invention patents, with over 80 patents granted. He has been listed on Elsevier's "High Download List" of Chinese authors' papers from 2005-2015.
Cong Wang received the Ph.D. degree from the Department of Electrical and Computer Engineering, the National University of Singapore, Singapore, in 2002. He is the director of the Shandong University Center for Intelligent Medical Engineering, Recipient of the National Science Fund for Distinguished Young Scholars, National "Thousand Talents Program" leading talents in scientific and technological innovation. He has been at the forefront of research machine learning and artificial intelligence for dynamical systems. He and his collaborators have introduced a novel machine learning algorithm for dynamical systems, known as Deterministic Learning (or called Dynamic Learning). This work has led to advancements in dynamical pattern recognition, small oscillation fault diagnosis, and pattern-based intelligent control. Their research has addressed critical core technologies such as the early detection of aerodynamic instability in high-performance aero engines and the early detection of myocardial ischemia/myocardial infarction.
Content
Introduction.- Deterministic Learning for Nonlinear Uncertain Dynamical Systems.- Small Fault Detection for Nonlinear Uncertain Dynamical Systems.- Similar Fault Recognition for Nonlinear Uncertain Dynamical Systems.- Dynamics Learning Control of Nonlinear Uncertain Dynamical Systems.- Applications to Learning, Diagnosis and Control of Soft Robots.- Discussion and Outlook of Dynamics Learning and Control in HRC.