ABSTRACT
Conventional Neural Network (NN) control for robots uses radial basis function (RBF) and for n-link robot with online control, the number of nodes and weighting matrix increases exponentially, which requires a number of calculations to be performed within a very short duration of time. This consumes a large amount of computational memory and may subsequently result in system failure. To avoid this problem, this paper proposes an innovative NN robot control using a dimension compressed RBF (DCRBF) for a class of n-degree of freedom (DOF) robot with full-state constraints. The proposed DCRBF NN control scheme can compress the nodes and weighting matrix greatly and provide an output that meets the prescribed tracking performance. Additionally, adaption laws are designed to compensate for the internal and external uncertainties. Finally, the effectiveness of the proposed method has been verified by simulations. The results indicate that the proposed method, integral Barrier Lyapunov Functions (iBLF), avoids the existing defects of Barrier Lyapunov Functions (BLF) and prevents the constraint violations.
Acknowledgments
The authors would like to thank Dr. Yiming Jiang of Key Lab of Autonomous Systems and Networked Control, South China University of Technology for the technical support provided.
Disclosure statement
No potential conflict of interest was reported by the authors.
ORCID
Jun Xia http://orcid.org/0000-0002-1224-6142
Yujia Zhang http://orcid.org/0000-0003-3991-7388
Chenguang Yang http://orcid.org/0000-0001-5255-5559
Min Wang http://orcid.org/0000-0001-7025-7651
Additional information
Notes on contributors
Jun Xia
Jun Xia received the B.Sc. and M.Sc. degrees from South China university of Technology. He is currently pursuing the Ph.D. degree with the Sun Yat-Sen University, Guangzhou, China. His research interests include surgical robot, computer version, SLAM, and machine learning.
Yujia Zhang
Yujia Zhang received the B.E. degree in electrical engineering and automation in Huazhong University of Science and Technology in 2015, and the M.S. degree in electrical engineering in South China University of Technology, China, in 2018. He is currently pursuing the Ph. D. degree in City University of Hong Kong. His current research interests include machine learning and computer vision.
Chenguang Yang
Chenguang Yang is a Professor of Robotics. He received the Ph.D. degree in control engineering from the National University of Singapore, Singapore, in 2010 and performed postdoctoral research in human robotics at Imperial College London, London, UK from 2009 to 2010. He has been awarded EU Marie Curie International Incoming Fellowship, UK EPSRC UKRI Innovation Fellowship, and the Best Paper Award of the IEEE Transactions on Robotics as well as over ten conference Best Paper Awards. His research interest lies in human robot interaction and intelligent system design.
Min Wang
Min Wang received the Ph.D. degree from the Institute of Complexity Science, Qingdao University, Qingdao, China, in 2009. From November 2017 to 2018, she is an academic visitor with Brunel University London, Uxbridge, United Kingdom. She is currently an Associate Professor with the School of Automation Science and Engineering, South China University of Technology, Guangzhou, China. She has authored or co-authored nearly 30 papers in top international journals. Dr. Wang was a recipient of the Excellent Doctoral Dissertations Award of Shandong Province in 2010, the Science and Technology New Star of Zhujiang, Guangzhou, in 2014, and the youth talent of Guangdong Tezhi Plan in 2016. Her current research interests include nonlinear systems, intelligent control, robot control, and dynamic learning.
Andy Annamalai
Andy Annamalai is currently a Senior Lecturer with Winchester University. Previously, he was a Lecturer with University of Highlands and Islands (UHI), Scotland, UK, prior to which he was a Researcher at the Marine and Industrial Dynamic Analysis Research Group, Plymouth University, UK.