Artificial Intelligence in Smart Logistics and Supply Chain Collaborative Scheduling: An Applied Investigation

Abstract

The integration of artificial intelligence (AI) into smart logistics and supply chain collaborative scheduling has emerged as a critical area of research, yet the capacity of AI systems to engage with complex scheduling optimization tasks remains underexplored. This study aims to investigate the extent to which AI technologies, particularly large language models and deep reinforcement learning approaches, can reproduce, challenge, and enhance collaborative scheduling mechanisms within logistics ecosystems. Through three case studies: intelligent vehicle routing optimization, warehouse order picking coordination, and cross border supply chain delay prediction, a mixed methods approach combining qualitative analysis of AI generated strategies with quantitative benchmarking using publicly available logistics datasets was employed. The results reveal that AI driven approaches demonstrate strong capabilities in generating feasible scheduling solutions aligned with optimization objectives but exhibit limitations in handling dynamic disruptions and multi agent coordination under uncertainty. Specifically, performance varied across scenarios, with deep reinforcement learning achieving superior results in vehicle scheduling tasks while struggling with inventory coupling complexities. This study contributes to the understanding of AI's potential and limitations in logistics scheduling applications, offering insights for future development of autonomous supply chain coordination systems.