IGLC.net
EXPORT DATE: 19 June 2026

@CONFERENCE{Zeng2026,
author={Zeng, Xianghui and Jiang, Liu and Cheng, Zhiyuan and Chen, Yu },
editor={Hamzeh, Farook and Poshdar, Mani and Garcia-Lopez,, Nelly P. },
title={Lean post-typhoon recovery: multi-agent look-ahead and constraints for the Last Planner System}, 
journal={Proceedings of the 34th Annual Conference of the International Group for Lean Construction (IGLC 34)}, 
booktitle={Proceedings of the 34th Annual Conference of the International Group for Lean Construction (IGLC 34)}, 
year={2026},
pages={250-259},
url={http://www.iglc.net/papers/details/2561},
doi={10.24928/2026/0273},
affiliation={PhD Student, School of Civil Engineering and Architecture, Hainan University, Haikou, China,  25110814000020@hainanu.edu.cn, orcid.org/0009-0008-5084-8575  ; Associate Professor, School of Civil Engineering and Architecture, Hainan University, Haikou, China,  oxazajl@hainanu.edu.cn, orcid.org/0000-0002-3355-2157   ; Undergraduate student, School of Civil Engineering and Architecture, Hainan University, Haikou, China,  20223005212@hainanu.edu.cn ; Master Student, School of Civil Engineering and Architecture, Hainan University, Haikou, China,  19989716938@163.com, orcid.org/0009-0008-1120-6393 },
abstract={Post-typhoon recovery involves high-variability work in which plan reliability is frequently undermined by late discovery of constraints, fragmented information, and rework. Rapid post-typhoon building recovery requires integrating heterogeneous evidence and converting it into actionable and auditable plans. This paper proposes a Lean Construction informed, knowledge-driven framework that combines a multi-modal knowledge graph (MMKG) with multi-agent orchestration for end-to-end building damage assessment and recovery planning, aligned with the Last Planner System (LPS) through look-ahead planning, make-ready checks, and explicit constraint management. The MMKG captures emergency management criteria, typhoon evolution and exposure status, building-level damage evidence, and reusable post-disaster recovery templates. The approach uses the MMKG as a shared and traceable evidence base, enabling multi-agent orchestration to generate a constraint log, assign make-ready status, and support weekly work plan release under explicit rule-based conditions. Typhoon Yagi is used as an illustrative proof-of-concept case to demonstrate how heterogeneous post-typhoon evidence can be translated into LPS-oriented planning artifacts. The results indicate that the framework is feasible for generating traceable planning outputs under multi-source uncertainty; however, quantitative field-scale validation and execution stage performance assessment remain future work. },
author_keywords={Last Planner System, multi-agent, knowledge-driven, multi-modal knowledge graph, Typhoon disaster. },
address={Singapore, Singapore },
issn={2789-0015 },
publisher={ },
language={English},
document_type={Conference Paper},
source={IGLC},
}