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

TL;DR

This work tackles real-time control of robot-operated serial production lines by evaluating a pretrained LLM-based controller, specifically GPT-4, for mobile robot scheduling. It proposes a three-layer prompt-driven framework (input, processing, output) that enables action decisions without environment-specific retraining, emphasizing transparency and scalability. Across two configurations, the LLM-based approach achieves throughput comparable to MARL and superior to FCFS, SPT, and LPT, while offering explainability and reduced computational overhead. The study demonstrates the practical viability of LLMs as accessible, scalable controllers in dynamic manufacturing environments, with clear pathways for integration and future improvements in robustness and external knowledge incorporation.

Abstract

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. Our proposed framework outperforms traditional scheduling approaches such as First-Come-First-Served (FCFS), Shortest Processing Time (SPT), and Longest Processing Time (LPT). While it achieves performance that is on par with state-of-the-art methods like Multi-Agent Reinforcement Learning (MARL), it offers a distinct advantage by delivering comparable throughput without the need for extensive retraining. These results suggest that the proposed LLM-based solution is well-suited for scenarios where technical expertise, computational resources, and financial investment are limited, while decision transparency and system scalability are critical concerns.

Figures (6)

• Figure 1: A general robot assisted serial production line
• Figure 2: Proposed LLM-based control framework
• Figure 3: Performance comparison based on configuration 1
• Figure 4: Performance comparison based on configuration 2
• Figure 5: Actions comparison from LLM and MARL