Dynamic Task Adaptation for Multi-Robot Manufacturing Systems with Large Language Models
Jonghan Lim, Ilya Kovalenko
TL;DR
The paper addresses dynamic task adaptation in multi-robot manufacturing under disruptions to planned assignments. It proposes an LLM-enabled central controller that reasons over structured representations of robot capabilities, tasks, and constraints to reassign tasks when disruptions occur, selecting an exploration robot and proposing a new configuration $\mathcal{K}'_{r_e}$ such that $\forall \varphi_l \in \mathcal{C}_{\tau_d}, \varphi_l(\mathcal{K}'_{r_e})=\text{valid}$. Key contributions include a preliminary LLM-based decision framework, a structured prompting and feedback mechanism, and a proof-of-concept demonstration on a two-robot physical setup showing successful recovery from disruptions. The findings indicate promising adaptability for real-world manufacturing with acknowledged limitations in spatial reasoning and potential hallucinations, motivating future integration of runtime knowledge bases to enhance robustness and safety.
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.