The material presented in this book addresses the analysis and design of learning control systems. It begins with an introduction to the concept of learning control, including a comprehensive literature review. The text follows with a complete and unifying analysis of the learning control problem for linear LTI systems using a system-theoretic approach which offers insight into the nature of the solution of the learning control problem. Additionally, several design methods are given for LTI learning control, incorporating a technique based on parameter estimation and a one-step learning control algorithm for finite-horizon problems. Further chapters focus upon learning control for deterministic nonlinear systems, and a time-varying learning controller is presented which can be applied to a class of nonlinear systems, including the models of typical robotic manipulators. The book concludes with the application of artificial neural networks to the learning control problem. Three specificways to neural nets for this purpose are discussed, including two methods which use backpropagation training and reinforcement learning. The appendices in the book are particularly useful because they serve as a tutorial on artificial neural networks.

Autorentext

Hyo-Sung Ahn has research interests in the areas of robust iterative learning control, periodic adaptive learning control, networked control systems, neural networks, mobile robotics, navigation, biomechatronics, and aerospace engineering. He was research engineer in Space Development and Research Center, Korea Aerospace Indusstries LTD, Korea, and Upper Midwest Aerospace Consortium, USA. He received the M.S. degree from the University of North Dakota in Aerospace Engineering and the Ph.D. in Electrical Engineering from Utah State University. Dr. Ahn, with his co-authors, has been the primary developer of the ideas in the monograph and has a deep understanding of the design of iterative learning control systems, especially as regards robustness. Professor Moore is the G.A. Dobelman Distinguished Chair and Professor of Engineering in the Division of Engineering at the Colorado School of Mines. He received the B.S. and M.S. degrees in electrical engineering from Louisiana State University and the University of Southern California, respectively. He received the Ph.D. in electrical engineering, with an emphasis in control theory, from Texas A&M University. Most recently he was a senior scientist at Johns Hopkins University's Applied Physics Laboratory, where he worked in the area of unattended air vehicles, cooperative control, and autonomous systems (2004-2005). He was previously an Associate Professor at Idaho State University (1989-1998) and a Professor of Electrical and Computer Engineering at Utah State University, where he was the Director of the Center for Self-Organizing and Intelligent Systems, directing multi-disciplinary research teams of students and professionals developing a variety of autonomous robots for government and commercial applications (1998 -2004). He also worked in industry for three years pre-Ph.D as a member of the technical staff at Hughes Aircraft Company. His general research interests include iterative learning control theory, autonomous systems and robotics, and applications of control to industrial and mechatronic systems. He is the author of the research monograph Iterative Learning Control for Deterministic Systems, published by Springer-Verlag in 1993, and co-author of the book Sensing, Modeling, and Control of Gas Metal Arc Welding, published by Elsevier in 2003. He is a professional engineer, involved in several professional societies and editorial activities, and is interested in engineering education pedagogy. Of particular relevance for the proposed monograph, Dr. Moore has been a seminal contributor and leader in the field of ILC. His early work in the field developed the idea of the supervector approach, and he has studied the problem of monotonic convergence, and he initiated the idea of studying robustness in the iteration domain. He has also been active in organizing ILC workshops, invited sessions on ILC at conferences, and editing special issues of journals. His insights on the ILC problem will directly influence the contents of the proposed monograph. Dr YangQuan Chen is presently an assistant professor of Electrical and Computer Engineering Department and the Acting Director for CSOIS (Center for Self-Organizing and Intelligent Systems, www.csois.usu.edu) at Utah State University. He obtained his Ph.D. from Nanyang Technological University, Singapore in 1998, an MS from Beijing Institute of Technology (BIT) in 1989, and a BS from University of Science and Technology of Beijing (USTB) in 1985. Dr Chen has 12 US patents granted and 2 US patent applications published, most related to the implementation of ILC algorithms, which lends special insight into the ILC application examples found in the mongraph. He has published more than 200 academic papers and (co)authored more than 50 industrial reports. His recent books include Solving Advanced Applied Mathematical Problems Using Matlab (with Dingyu Xue, Tsinghua University Press. August 2004. 419 pages

Inhalt
1 Introduction to the Monograph.- 1.1 Background and Motivation: Transient Response Control.- 1.2 Organization of the Monograph.- 2 Iterative Learning Control: An Overview.- 2.1 Introduction.- 2.2 Literature Review.- 2.3 Problem Formulation.- 3 Linear Time-Invariant Learning Control.- 3.1 Convergence with Zero Error.- 3.2 Convergence with Non-Zero Error.- 3.3 The Nature of the Solution.- 4 LTI Learning Control via Parameter Estimation.- 4.1 System Description.- 4.2 Main Result.- 4.3 Comments.- 5 Finite-Horizon Learning Control.- 5.1 l?-Optimal Learning Control with Memory.- 5.2 Learning Convergence in One Step.- 5.3 Learning Control with Multirate Sampling.- 5.4 Examples.- 5.5 Comments and Extensions.- 6 Nonlinear Learning Control.- 6.1 Learning Control for Nonlinear Systems.- 6.2 Learning Controller for a Class of Nonlinear Systems.- 7 Artificial Neural Networks for Iterative Learning Control.- 7.1 Neural Network Controllers.- 7.2 Static Learning Controller Using an ANN.- 7.3 Dynamical Learning Controller Using an ANN.- 7.4 Reinforcement Learning Controller Using an ANN.- 8 Conclusion.- 8.1 Summary.- 8.2 Directions for Future Research.- Appendix A: Some Basic Results on Multirate Sampling.- A.1 Introduction.- A.3 Basic Result.- Appendix B: Tutorial on Artificial Neural Networks.- B.1 An Introduction to Neural Networks.- B.1.1 Neurons.- B.1.2 Interconnection Topology.- B.1.3 Learning Laws.- B.2 Historical Background.- B.3 Properties of Neural Networks.- B.3.1 Pattern Classification and Associative Memory.- B.3.2 Self-Organization and Feature Extraction.- B.3.3 Optimization.- B.3.4 Nonlinear Mappings.- B.4 Neural Nets and Computers.- B.5 Derivation of Backpropagation.- B.6 Neural Network References.- References.