Details

<p>Chapter 1. Introduction.- Chapter 2. A Novel Model Predictive Control Scheme Based on an Improved Newton Algorithm.- Chapter 3. A Novel Recurrent Neural Network for Robot Control.- Chapter 4. A Projected Zeroing Neural Network Model for the Motion Generation and Control.- Chapter 5. A Regularization Ensemble Based on Levenberg–Marquardt Algorithm for Robot Calibration.- Chapter 6. Novel Evolutionary Computing Algorithms for Robot Calibration.- Chapter 7. A Highly Accurate Calibrator Based on a Novel Variable Step-Size Levenberg-Marquardt Algorithm.- Chapter 8. Conclusion and Future Work.</p><br><p></p>

<p><b>Dr. Xin Luo</b> is a professor with the College of Computer and Information Science, Southwest University. His current research interests include Machine Intelligence, Big Data, and Cloud Computing. He has published over 200 papers (including over 87 IEEE TRANSACTIONS papers, 17 highly cited papers of ESI) in the above areas. His Google Scholar cited is more than 6300, and H-Index is 48. He has 35 authorized national invention patents. He was the Pioneer Hundred Talents Program of Chinese Academy of Sciences in 2016, the Advanced Support of the Pioneer Hundred Talents Program of Chinese Academy of Sciences in 2018, and the National High-Level Talents Special Support Program in 2020. He won the First Prize of Chongqing Natural Science Award (2019, No. 1), the First Prize of Wu Wenjun AI Science and Technology Progress Award (2018, No. 3), and the First Prize of Chongqing Science and Technology Progress Award (2018, No. 2). He serves as an associate editor for the <i>IEEE/CAA Journal of Automatica Sinica</i> and <i>IEEE Transactions on Neural Networks and Learning Systems</i>. He has received the Outstanding Associate Editor Award from <i>IEEE/CAA Journal of Automatica Sinica</i> in 2020.</p>

<p><b>Dr. Zhibin Li</b> is currently studying for the PhD degree in computer science from Chongqing University of Posts and Telecommunications united training by the Chongqing institute of green and intelligent technology, Chinese academy of sciences, Chongqing, China. His research interests include robot calibration, big data analysis and algorithm design for large-scale data applications. He has published over six SCI/EI papers, including top journals and conferences like IEEE TNNLS, JAS, RAL, and TCASII in the computer field.</p>

<p><b>Dr. Long Jin</b> joined the School of Information Science and Engineering, Lanzhou University, as a professor of computer science and engineering. He is currently serving as an editor for the Chinese Association for Artificial Intelligence (CAAI) Transactions on Intelligence Technology. His current research interests include neural networks, robotics, optimization, and intelligent computing.</p>

<p><b>Dr. Shuai Li </b>is an associate professor (Reader) at University of Oulu, Oulu, Finland. His research interests include robot manipulation and impedance control, multi-robot coordination, and articulated robot calibration.</p><br><p></p>

<p>This book mainly shows readers how to calibrate and control robots. In this regard, it proposes three control schemes: an error-summation enhanced Newton algorithm for model predictive control; RNN for solving perturbed time-varying underdetermined linear systems; and a new joint-drift-free scheme aided with projected ZNN, which can effectively improve robot control accuracy. Moreover, the book develops four advanced algorithms for robot calibration – Levenberg-Marquarelt with diversified regularizations; improved covariance matrix adaptive evolution strategy; quadratic interpolated beetle antennae search algorithm; and a novel variable step-size Levenberg-Marquardt algorithm – which can effectively enhance robot positioning accuracy.</p>

<p>In addition, it is exceedingly difficult for experts in other fields to conduct robot arm calibration studies without calibration data. Thus, this book provides a publicly available dataset to assist researchers from other fields in conductingcalibration experiments and validating their ideas. The book also discusses six regularization schemes based on its robot error models, i.e., L1, L2, dropout, elastic, log, and swish. Robots’ positioning accuracy is significantly improved after calibration. Using the control and calibration methods developed here, readers will be ready to conduct their own research and experiments.</p><br><p></p>

Shows how robot calibration and control technology can achieve high scalability in real industrial applications Proposes control schemes and calibration algorithms that can effectively improve robot positioning accuracy Offers a publicly available dataset to help researchers from other fields conduct calibration experiments