34th Annual Conference of the International Group for Lean Construction (IGLC 34) - Singapore, Singapore - 2026

https://doi.org/10.24928/2026/0273

Lean post-typhoon recovery: multi-agent look-ahead and constraints for the Last Planner System

Xianghui Zeng1, Liu Jiang2, Zhiyuan Cheng3 & Yu Chen4

1PhD Student, School of Civil Engineering and Architecture, Hainan University, Haikou, China, [email protected], orcid.org/0009-0008-5084-8575
2Associate Professor, School of Civil Engineering and Architecture, Hainan University, Haikou, China, [email protected], orcid.org/0000-0002-3355-2157
3Undergraduate student, School of Civil Engineering and Architecture, Hainan University, Haikou, China, [email protected]
4Master Student, School of Civil Engineering and Architecture, Hainan University, Haikou, China, [email protected], 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.

Keywords

Last Planner System, multi-agent, knowledge-driven, multi-modal knowledge graph, Typhoon disaster.

Files


Full Text
 

Reference

Download: BibTeX | RIS Format

Reference in APA 7th edition format:

Zeng, X., Jiang, L., Cheng, Z. & Chen, Y.. (2026). Lean post-typhoon recovery: multi-agent look-ahead and constraints for the Last Planner System. In Hamzeh, F., Poshdar, M., & Garcia-Lopez,, N. P. (Eds.), Proceedings of the 34th Annual Conference of the International Group for Lean Construction (IGLC 34) (pp. 250–259). https://doi.org/10.24928/2026/0273

Shortened reference for use in IGLC papers:

Zeng, X., Jiang, L., Cheng, Z. & Chen, Y.. (2026). Lean post-typhoon recovery: multi-agent look-ahead and constraints for the Last Planner System. IGLC34. https://doi.org/10.24928/2026/0273

 

Founded in 1993, the IGLC is an international network of researchers from practice and academia in architecture, engineering, and construction (AEC) who feel that the practice, education, and research of the AEC industry have to be radically renewed in order to respond to the global challenges ahead.

2015 © All Rights Reserved.