Integrating LLMs and Digital Twins for Adaptive Multi-Robot Task Allocation in Construction

2025-06-22

AI Summary

Coordinating multiple robots in dynamic, uncertain environments—such as construction sites—poses significant challenges for real-time, adaptive scheduling. Method: This paper proposes a closed-loop adaptive scheduling framework integrating digital twin technology, integer programming (IP), and large language models (LLMs). A digital twin enables real-time bidirectional mapping between physical robots and their virtual counterparts; an IP model captures task dependencies and robot heterogeneity; and an LLM-driven natural-language interface parses unstructured human instructions to autonomously update optimization constraints—enabling zero-code, human-in-the-loop adaptation. Contribution/Results: The framework achieves high computational efficiency, with LLM-based constraint extraction attaining 97.3% accuracy. It demonstrates robust dynamic responsiveness, cross-scenario generalizability, and strong potential for industrial deployment in complex, safety-critical environments.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Intelligent Robots: Learning & Optimization for ROB
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

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

Abstract

Multi-robot systems are emerging as a promising solution to the growing demand for productivity, safety, and adaptability across industrial sectors. However, effectively coordinating multiple robots in dynamic and uncertain environments, such as construction sites, remains a challenge, particularly due to unpredictable factors like material delays, unexpected site conditions, and weather-induced disruptions. To address these challenges, this study proposes an adaptive task allocation framework that strategically leverages the synergistic potential of Digital Twins, Integer Programming (IP), and Large Language Models (LLMs). The multi-robot task allocation problem is formally defined and solved using an IP model that accounts for task dependencies, robot heterogeneity, scheduling constraints, and re-planning requirements. A mechanism for narrative-driven schedule adaptation is introduced, in which unstructured natural language inputs are interpreted by an LLM, and optimization constraints are autonomously updated, enabling human-in-the-loop flexibility without manual coding. A digital twin-based system has been developed to enable real-time synchronization between physical operations and their digital representations. This closed-loop feedback framework ensures that the system remains dynamic and responsive to ongoing changes on site. A case study demonstrates both the computational efficiency of the optimization algorithm and the reasoning performance of several LLMs, with top-performing models achieving over 97% accuracy in constraint and parameter extraction. The results confirm the practicality, adaptability, and cross-domain applicability of the proposed methods.

Problem

• Coordinating multi-robot systems in dynamic construction environments
• Adapting task allocation for unpredictable disruptions and delays
• Integrating LLMs and Digital Twins for real-time schedule updates

Innovation

• Integrates Digital Twins for real-time synchronization
• Uses Integer Programming for task allocation
• Employs LLMs for natural language adaptation