Dynamic Neural Networks for Motion Control of Redundant Manipulators

This book discusses the development and application of dynamic neural networks (DNNs) for solving complex motion control problems in redundant manipulators. Specifically, it presents a series of advanced DNNs, including noise-rejection DNNs, fuzzy-parameter DNNs, and so on, which are designed to optimize performance while ensuring robustness and computational efficiency. Based on the presented DNNs, this book further constructs a series of motion control schemes for redundant manipulators to address some key challenges such as cyclic motion, position and orientation tracking, and model-unknown scenarios. Each method is rigorously demonstrated for the convergence, and its effectiveness is validated through simulations and physical experiments. By integrating computational intelligence with control theory, this book provides a comprehensive framework for solving time-varying and noise-perturbed problems in robotics, making it a valuable resource for researchers and practitioners in the field.

Addresses motion control of redundant manipulators using dynamic neural networks Includes theoretical analyses on the models and physical experiments toward industrial manipulators Is convenient and suitable for undergraduate or postgraduate students as well as academic and industrial researchers

Autorentext

Mei Liu received the B.E. degree in communication engineering from Yantai University, Yantai, China, in 2011, the M.E. degree in pattern recognition and intelligent system from Sun Yat-sen University, Guangzhou, China, in 2014, and the Ph.D. degree in computer software and theory from University of Chinese Academy of Sciences, Beijing, China, in 2023. From 2016 to 2017, she had been with the Department of Computing, The Hong Kong Polytechnic University as a Research Assistant. Currently, she is a research assistant with Lanzhou University, Lanzhou, China. From 2023 to 2025, she had been a postdoctoral fellow with Multiscale Medical Robotics Center, The Chinese University of Hong Kong. Her. She serves as a guest editor for several journals such as Tsinghua Science and Technology and IET Electronics Letters. She has published more than 30 papers in IEEE TRANSACTIONS journals. Since 2020, Dr. Liu has received prestigious awards including the Second Prize in Natural Science of Gansu Province. Her main research interests include neural networks, robotics, and optimization. Jingkun Yan received the B.E. degree in automation from the Beijing Institute of Technology, Beijing, China, in 2018, and the Ph.D. degree in computer applications technology from Lanzhou University, Lanzhou, China, in 2024. Currently, she is a Lecturer with the School of Information Science and Engineering, Yunnan University, Kunming, China. Her research interests include neural networks, robotics, and model predictive control. Renpeng Huang received the B.E. degree in the School of Electrical Engineering and Automation from Wuhan University, Wuhan, China, in 2021. He is currently pursuing the M.E. degree in computer technology with the School of Information Science and Engineering, Lanzhou University, Lanzhou, China. His research interests include neural networks and robotics.

Inhalt

.- 1. Double-Index Control With DNN

.- 2. Cyclic Motion Control With Noise-Rejection DNN

.- 3. Trajectory-Tracking MPC With Z-type DNN

.- 4. Motion/Force Control With Fuzzy DNN

.- 5. Orientation Tracking Incorporated Multi-Criteria Control With DNN

.- 6. Position and Orientation-Tracking MPC With Finite-Time DNN

.- 7. Data-Driven RC2M Control With DNN

.- 8. Cerebellum-Inspired MPC With Discrete DNN.