Learning Control

This is the first textbook on a generally applicable control strategy for turbulence and other complex nonlinear systems. The approach of the book employs powerful methods of machine learning for optimal nonlinear control laws. This machine learning control (MLC) is motivated and detailed in Chapters 1 and 2. In Chapter 3, methods of linear control theory are reviewed. In Chapter 4, MLC is shown to reproduce known optimal control laws for linear dynamics (LQR, LQG). In Chapter 5, MLC detects and exploits a strongly nonlinear actuation mechanism of a low-dimensional dynamical system when linear control methods are shown to fail. Experimental control demonstrations from a laminar shear-layer to turbulent boundary-layers are reviewed in Chapter 6, followed by general good practices for experiments in Chapter 7. The book concludes with an outlook on the vast future applications of MLC in Chapter 8. Matlab codes are provided for easy reproducibility of the presented results. The book includes interviews with leading researchers in turbulence control (S. Bagheri, B. Batten, M. Glauser, D. Williams) and machine learning (M. Schoenauer) for a broader perspective. All chapters have exercises and supplemental videos will be available through YouTube.

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 specific ways 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.

This book develops a coherent and quite general theoretical approach to algorithm design for iterative learning control based on the use of operator representations and quadratic optimization concepts including the related ideas of inverse model control and gradient-based design. Using detailed examples taken from linear, discrete and continuous-time systems, the author gives the reader access to theories based on either signal or parameter optimization. Although the two approaches are shown to be related in a formal mathematical sense, the text presents them separately as their relevant algorithm design issues are distinct and give rise to different performance capabilities. Together with algorithm design, the text demonstrates the underlying robustness of the paradigm and also includes new control laws that are capable of incorporating input and output constraints, enable the algorithm to reconfigure systematically in order to meet the requirements of different reference and auxiliary signals and also to support new properties such as spectral annihilation. Iterative Learning Control will interest academics and graduate students working in control who will find it a useful reference to the current status of a powerful and increasingly popular method of control. The depth of background theory and links to practical systems will be of use to engineers responsible for precision repetitive processes.

Methods by which robots can learn control laws that enable real-time reactivity using dynamical systems; with applications and exercises. This book presents a wealth of machine learning techniques to make the control of robots more flexible and safe when interacting with humans. It introduces a set of control laws that enable reactivity using dynamical systems, a widely used method for solving motion-planning problems in robotics. These control approaches can replan in milliseconds to adapt to new environmental constraints and offer safe and compliant control of forces in contact. The techniques offer theoretical advantages, including convergence to a goal, non-penetration of obstacles, and passivity. The coverage of learning begins with low-level control parameters and progresses to higher-level competencies composed of combinations of skills. Learning for Adaptive and Reactive Robot Control is designed for graduate-level courses in robotics, with chapters that proceed from fundamentals to more advanced content. Techniques covered include learning from demonstration, optimization, and reinforcement learning, and using dynamical systems in learning control laws, trajectory planning, and methods for compliant and force control . Features for teaching in each chapter: applications, which range from arm manipulators to whole-body control of humanoid robots; pencil-and-paper and programming exercises; lecture videos, slides, and MATLAB code examples available on the author’s website . an eTextbook platform website offering protected material[EPS2] for instructors including solutions.

This book belongs to the subject of control and systems theory. It studies a novel data-driven framework for the design and analysis of iterative learning control (ILC) for nonlinear discrete-time systems. A series of iterative dynamic linearization methods is discussed firstly to build a linear data mapping with respect of the system’s output and input between two consecutive iterations. On this basis, this work presents a series of data-driven ILC (DDILC) approaches with rigorous analysis. After that, this work also conducts significant extensions to the cases with incomplete data information, specified point tracking, higher order law, system constraint, nonrepetitive uncertainty, and event-triggered strategy to facilitate the real applications. The readers can learn the recent progress on DDILC for complex systems in practical applications. This book is intended for academic scholars, engineers, and graduate students who are interested in learning control, adaptive control, nonlinear systems, and related fields.

A timely guide using iterative learning control (ILC) as a solution for multi-agent systems (MAS) challenges, showcasing recent advances and industrially relevant applications Explores the synergy between the important topics of iterative learning control (ILC) and multi-agent systems (MAS) Concisely summarizes recent advances and significant applications in ILC methods for power grids, sensor networks and control processes Covers basic theory, rigorous mathematics as well as engineering practice

Random fading communication is a type of attenuation damage of data over certain propagation media. Establishing a systematic framework for the design and analysis of learning control schemes, the book studies in depth the iterative learning control for stochastic systems with random fading communication. The authors introduce both cases where the statistics of the random fading channels are known in advance and unknown. They then extend the framework to other systems, including multi-agent systems, point-to-point tracking systems, and multi-sensor systems. More importantly, a learning control scheme is established to solve the multi-objective tracking problem with faded measurements, which can help practical applications of learning control for high-precision tracking of networked systems. The book will be of interest to researchers and engineers interested in learning control, data-driven control, and networked control systems.