Dynamic Task Adaptation for Multi-Robot Manufacturing Systems with Large Language Models

2025-05-28

AI Summary

In multi-robot manufacturing systems, unexpected failures disrupt ongoing tasks, and conventional predefined rule-based approaches lack the adaptability required for real-time dynamic response. Method: This paper proposes the first large language model (LLM)-based online dynamic task reassignment framework. It integrates structured robot state modeling, real-time fault detection, and multi-agent coordinated control, leveraging the LLM’s semantic understanding and reasoning capabilities over production constraints and anomalous scenarios to autonomously generate context-aware rescheduling policies—without manual rule engineering. Contribution/Results: Evaluated on a real production line, the framework significantly improves task recovery success rate and substantially enhances system robustness and operational continuity. This work pioneers the integration of LLMs into online task rescheduling for manufacturing systems, establishing a novel, interpretable, and adaptive paradigm for intelligent, flexible manufacturing.

Technology Category

• Intelligent Robots: Multi-Robot Systems
• Planning, Routing, and Scheduling: Planning with Language Models
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Recent manufacturing systems are increasingly adopting multi-robot collaboration to handle complex and dynamic environments. While multi-agent architectures support decentralized coordination among robot agents, they often face challenges in enabling real-time adaptability for unexpected disruptions without predefined rules. Recent advances in large language models offer new opportunities for context-aware decision-making to enable adaptive responses to unexpected changes. This paper presents an initial exploratory implementation of a large language model-enabled control framework for dynamic task reassignment in multi-robot manufacturing systems. A central controller agent leverages the large language model's ability to interpret structured robot configuration data and generate valid reassignments in response to robot failures. Experiments in a real-world setup demonstrate high task success rates in recovering from failures, highlighting the potential of this approach to improve adaptability in multi-robot manufacturing systems.

Problem

• Enabling real-time adaptability in multi-robot systems without predefined rules
• Using large language models for dynamic task reassignment during robot failures
• Improving task success rates in multi-robot manufacturing through adaptive responses

Innovation

• LLM-enabled control framework for task reassignment
• Interprets structured robot data dynamically
• Achieves high task success post-failure