This chapter delves into the use of artificial intelligence (AI) methods for efficient scheduling of automatic guided vehicles (AGVs) in today’s manufacturing systems. AGVs are key material handling units for operations in flexible manufacturing systems (FMS), where dynamic production needs and real-time limits call for smart decision-making. The chapter presents a thorough description of AGV systems, including their architecture, components, and importance in intralogistics automation. The scheduling concept is then presented in the FMS context with the emphasis on optimized vehicle allocation, routing, and task priority to reduce idle time, minimize material transfer delays, and increase overall productivity. A central part of the chapter explores AI-based scheduling methodologies such as rule-based systems, heuristic algorithms, genetic algorithms, neural networks, and reinforcement learning methodologies. These techniques are assessed in terms of their capability to handle issues like deadlock avoidance, traffic jams, and efficient utilization of the available resources. The chapter also presents a detailed study of AGV dispatching systems and compares centralized, decentralized, and hybrid dispatching structures. It focuses on hybrid dispatching rules, which make use of real-time heuristic decision-making complemented with long-term optimization goals, and offers a stable and flexible framework for AGV control. Case studies and simulation findings are provided to illustrate the performance of AI-based scheduling approaches in enhancing system throughput and flexibility. Industry 4.0 technologies like IoT and digital twins are integrated to emphasize future trends and increase the responsiveness of AGV systems. A comprehensive view is presented showing that AI can transform AGV scheduling and dispatching to make it a main facilitator for flexible, agile, smart, and efficient manufacturing systems.