A LLM-informed multi-agent AI system for drone-based visual inspection for infrastructure

Liu, Jiucai, Li, Haijiang ORCID: https://orcid.org/0000-0001-6326-8133, Chai, Chengzhang ORCID: https://orcid.org/0000-0001-6911-8048, Chen, Kehong and Wang, Dalei 2025. A LLM-informed multi-agent AI system for drone-based visual inspection for infrastructure. Advanced Engineering Informatics 68 (A) , 103643. 10.1016/j.aei.2025.103643 Item availability restricted.

PDF - Accepted Post-Print Version Restricted to Repository staff only until 12 July 2026 due to copyright restrictions. Available under License Creative Commons Attribution Non-commercial No Derivatives. Download (5MB)

Abstract

The development of large language models (LLMs) holds the potential to significantly advance automation in the Architecture, Engineering, and Construction (AEC) industry. This paper explores the application of LLM-powered agent systems in drone-based visual inspection, focusing on three core aspects. First, a multi-agent framework is proposed, composed of five specialized sub-agents—Router, PathPlanner, Controller, Perceptioner, and Retriever—that collaboratively handle inspection subtasks such as 3D spatial reasoning, path planning, and UAV control. Second, a novel image-based pipeline is introduced to generate multi-criteria semantic point clouds and abstract them into 3D Scene Graphs (3DSGs), enabling spatial-semantic reasoning aligned with human intent. These 3DSGs act as both knowledge storage and reasoning engines. Third, the system is evaluated through simulations and laboratory experiments, demonstrating its ability to automate inspection workflows and provide a foundation for extensible AI-agent systems. The results highlight the advantages of LLM-based agents in flexible task delegation and high-level decision-making. While current implementations rely on general-purpose LLMs accessed via commercial APIs—introducing some latency and adaptation gaps—these aspects also point to promising directions for future optimization and domain-specific enhancement. Overall, the study presents an early yet promising step toward collaborative human–machine intelligence in infrastructure inspection, where autonomous agents augment human decision-making through interactive, context-aware support.

Item Type:	Article
Date Type:	Publication
Status:	In Press
Schools:	Schools > Engineering
Publisher:	Elsevier
ISSN:	1474-0346
Date of First Compliant Deposit:	15 July 2025
Date of Acceptance:	7 July 2025
Last Modified:	16 Jul 2025 16:00
URI:	https://orca.cardiff.ac.uk/id/eprint/179829

Actions (repository staff only)

Edit Item