A Review of Advances in AI-AMR Integration for Real-Time Material Flow Optimization in EV Manufacturing
The rapid evolution of electric vehicle (EV) manufacturing has intensified the need for highly adaptive, efficient, and intelligent material handling systems capable of operating in dynamic production environments. This review examines recent advances in the integration of Artificial Intelligence (AI) with Autonomous Mobile Robots (AMRs) for real-time material flow optimization in EV manufacturing ecosystems. It explores how AI-driven perception, decision-making, and predictive analytics enhance the operational capabilities of AMRs, enabling them to respond autonomously to fluctuating production demands, layout constraints, and supply chain uncertainties. The study synthesizes developments in machine learning algorithms, reinforcement learning, computer vision, and digital twin technologies that collectively enable real-time route optimization, task allocation, congestion avoidance, and energy-efficient navigation within smart factories. Particular attention is given to the role of edge computing and Industrial Internet of Things (IIoT) architectures in facilitating low-latency communication and decentralized intelligence, which are critical for real-time responsiveness. The review also evaluates system level integration challenges, including interoperability with Manufacturing Execution Systems (MES), scalability, cybersecurity risks, and safety compliance in human-robot collaborative environments. Furthermore, it highlights emerging trends such as swarm intelligence, multi-agent coordination, and adaptive scheduling frameworks that are redefining material flow strategies in EV production lines. By consolidating current research and industrial practices, this paper identifies key performance improvements in throughput, operational efficiency, and cost reduction attributed to AI-AMR integration. It also outlines future research directions, including the development of explainable AI models, resilient control architectures, and sustainable energy aware robotic systems. Overall, this review provides a comprehensive foundation for understanding how AI-enabled AMRs are transforming material flow optimization and shaping the next generation of intelligent EV manufacturing systems.