دانلود کتاب کنترل، یادگیری و بهینه‌سازی با کاربردها در وسایل نقلیه متصل و خودران

The field of transportation is undergoing a profound transformation driven by the convergence of control systems, machine learning, and system optimization. This synergy is accelerating the evolution of connected and autonomous vehicles (CAVs), which are moving beyond heavy reliance on human drivers. Autonomous vehicles (AVs) execute driving tasks with minimal human intervention, while connected vehicles (CVs) are equipped with communication modules to enable information exchange. The integration of these two technologies—CAVs—makes vehicles as decision making agents in safety-critical networked systems, paving the way for building a transportation system that is safer, more efficient, and sustainable. This book explores how control, learning, and optimization tackle the core challenges of scalability, coordination, and uncertainty under constraints in CAVs. Control theory provides the formal safety guarantees and constraint satisfaction. At the vehicle level, model-based and adaptive control algorithms are developed to realize trajectory tracking, compensate for unknown disturbances, and ensure robustness. At the system level, this philosophy extends to the stability and reliability of traffic flows. Machine learning, particularly reinforcement learning (RL), offers a paradigm for handling uncertainty. Through high-fidelity simulations and experiments, CAVs learn to make safe, efficient, and human-like decisions in complex, mixed traffic environments. By employing predictive modeling, machine learning, and advanced sensor fusion, CAVs can anticipate and respond to hazardous situations with greater precision and speed than traditions. However, there exists a tension between adaptability and guarantees, which motivates several integrated approaches in the book. Optimization ameliorates traffic efficiency from an individual vehicle’s perspective to a system-level objective. Leveraging real-time data and advanced algorithms, CAVs significantly reduce energy consumption without compromising performance. Vehicle-to-everything (V2X) communication allows conflict-free collaboration at intersections and merging zones, while transportation agencies can optimize infrastructure utilization and allocation. However, the translation from theoretical design to widespread, real world deployment of CAVs encounters significant obstacles, such as ensuring the safe coexistence of autonomous and human-driven vehicles, achieving real-time coordination across large-scale CAV platoons, fortifying systems against cyber threats, and enabling robust decision making under uncertainty. These open issues drive the extensive research presented in this edited book.