Learning-Enabled Autonomous Systems

Control, Verification, and Monitoring
1. Auflage 2026
ISBN: 978-1-041-30277-3
Verlag: Taylor & Francis

Buch, Englisch, 208 Seiten, Format (B × H): 156 mm x 234 mm

This book examines how to design intelligent systems that are not only adaptive but also safe and reliable. This book bridges the gap between traditional control theory and modern data-driven learning, presenting a unified framework for creating autonomous systems capable of robust decision-making in uncertain and dynamic environments.

Learning-Enabled Autonomous Systems: Control, Verification, and Monitoring stands out as a unique resource for designing trustworthy autonomous systems. It introduces data-driven control methods that allow systems to learn from real-world data, enabling adaptability and intelligence without sacrificing mathematical rigor. The book explores advanced control strategies for nonlinear systems, ensuring computational practicality for real-world applications. It also provides innovative techniques for verifying neural network controllers and safeguarding system performance through runtime monitoring frameworks. By uniting control theory, machine learning, and systems verification, this book offers a holistic approach to creating systems that are not only intelligent but also resilient, transparent, and dependable. It includes case studies, algorithmic insights, and design guidelines that connect theoretical principles to hands-on engineering practice.

This book is tailored for graduate students, researchers, and practitioners in control systems, robotics, artificial intelligence, and systems engineering. It is ideal for those seeking to deepen their understanding of learning-enabled control systems, whether for academic study or real-world application.

Zielgruppe

Postgraduate and Professional Reference

Autoren/Hrsg.

Lan, Jianglin

Fachgebiete

• Technische Wissenschaften Technik Allgemein Systems Engineering
• Technische Wissenschaften Technik Allgemein Mess- und Automatisierungstechnik
• Technische Wissenschaften Elektronik | Nachrichtentechnik Elektronik Robotik

Inhaltsverzeichnis

1 Introduction 2 Data-Driven Reachability-Based Model Predictive Control 3 Data-Driven Dual-Loop Model Predictive Control 4 Data-Driven Constrained Control Policy Learning 5 Data-Driven Nonlinear Control Using Nonlinearity Cancellation 6 Data-Driven Sliding Mode Control 7 Learning Observer-Based Control 8 Verification of NN-Controlled Linear Systems 9 Learning Lyapunov Barrier Certificate for Nonlinear Systems 10 Runtime Monitoring for NN-Controlled Linear Systems 11 Runtime Monitoring for NN-Controlled Nonlinear Systems References

Über Autor(innen)

Dr. Jianglin Lan is a Lecturer in Autonomous Systems and Leverhulme Early Career Fellow at the James Watt School of Engineering, University of Glasgow, and an Honorary Research Fellow at Imperial College London. He received his PhD in Control and Intelligent Systems Engineering from the University of Hull, following master’s and bachelor’s degrees in control and automation from leading Chinese universities. His research focuses on safe and robust autonomous systems, data-driven control, and neural network verification. Dr. Lan has held visiting positions at Carnegie Mellon University, Wageningen University, and LAMIH CNRS, France,. He also serves as an Editor for the International Journal of Adaptive Control and Signal Processing.