LOAA : towards a common understanding of the levels of AI automation in BIM authoring

Tools

Du, Changyu and Noichl, Florian and Nousias, Stavros and Borrmann, André; Moreno-Rangel, Alejandro and Kumar, Bimal, eds. (2025) LOAA : towards a common understanding of the levels of AI automation in BIM authoring. In: EG-ICE 2025. University of Strathclyde Publishing, GBR, pp. 434-442. ISBN 9781914241826 (https://doi.org/10.17868/strath.00093260)

[thumbnail of Du-etal-EG-ICE-2025-LOAA-towards-a-common-understanding-of-the-levels-of-AI-automation]
Preview
 Text. Filename: Du-etal-EG-ICE-2025-LOAA-towards-a-common-understanding-of-the-levels-of-AI-automation.pdf
Final Published Version
License: Creative Commons Attribution 4.0 logo
Download (1MB)| Preview

Abstract

This paper introduces a taxonomy for Levels of AI Automation (LOAA) that sys-tematically classifies the involvement and autonomy of AI in BIM authoring. The taxonomy distinguishes two key phases within BIM authoring and proposes five levels of automation ranging from human-driven processes to complete AI auton-omy. The taxonomy is grounded in established automation frameworks and CAD design evolution, and its applicability is demonstrated through case studies in BIM generative design and Scan-to-BIM scenarios. By categorizing recent publi-cations into distinct LOAA levels, the proposed framework aims to guide re-searchers and practitioners in advancing AI integration in BIM authoring.

  • Item type:Book Section
    ID code:93260
    Dates:
    Date
    Event
    1 July 2025
    Published
    9 June 2025
    Accepted
    Subjects:Fine Arts > Architecture
    Department:Faculty of Engineering > Architecture
    Depositing user: Pure Administrator
    Date deposited:27 Jun 2025 10:47
    Last modified:21 Sep 2026 00:04
    URI:https://strathprints.strath.ac.uk/id/eprint/93260
CORE (COnnecting REpositories)