Pretrained LLMs as Real-Time Controllers for Robot Operated Serial Production Line

The manufacturing industry is undergoing a transformative shift, driven by cutting-edge technologies like 5G, AI, and cloud computing. Despite these advancements, effective system control, which is crucial for optimizing production efficiency, remains a complex challenge due to the intricate, knowledge-dependent nature of manufacturing processes and the reliance on domain-specific expertise. Conventional control methods often demand heavy customization, considerable computational resources, and lack transparency in decision-making. In this work, we investigate the feasibility of using large language models (LLMs), particularly GPT-4, as a straightforward, adaptable solution for controlling manufacturing systems, specifically, mobile robot scheduling. We introduce an LLM-based control framework to assign mobile robots to different machines in robot assisted serial production lines, evaluating its performance in terms of system throughput. Numerical results show that the proposed framework improves average throughput by approximately 70%–80% compared to traditional scheduling heuristics such as first-come-first-served, shortest processing time, and longest processing time. Furthermore, the LLM-based controller achieves throughput within 5%–10% of a trained multi-agent reinforcement learning approach, while eliminating the need for environment-specific training or retraining. These results indicate that the proposed LLM-based solution is particularly well-suited for manufacturing environments where technical expertise, computational resources, and financial investment are limited, and where decision transparency and scalability are critical requirements.