Artificial intelligence for designing, building and operating the built world.
André Borrmann develops artificial intelligence methods for the built environment: multi-agent frameworks built on large language models for generative design, deep learning for point cloud and image interpretation, machine learning for construction process analysis and, most recently, learned world models and agentic AI for robotized construction. He holds the Chair of Computing in Civil and Building Engineering at the Technical University of Munich and directs the TUM Georg Nemetschek Institute - AI for the Built World, TUM's central institute for artificial intelligence in the built environment. He is spokesperson of the DFG Research Unit 5672 on the information backbone of robotized construction and originator of the Fabrication Information Modeling (FIM) concept. He coauthored the 2015 BIM roadmap of the German Federal Ministry of Transport and is technical lead of ISO 7517 Level of Information Need.
Multi-agent frameworks built on large language models generate building models from natural-language instructions; models trained on large-scale BIM usage logs recommend the next modeling command.
Key paper: Text2BIM: Generating Building Models Using a Large Language Model-Based Multiagent Framework (Journal of Computing in Civil Engineering, 2026)
Deep learning turns dense point clouds and site imagery into semantic building models that serve as digital twins of existing structures.
Key paper: From dense point clouds to semantic digital models: End-to-end AI-based automation procedure for Manhattan-world structures (Automation in Construction, 2024)
Continuous image capture, object detection and knowledge graphs make construction progress measurable and open to analysis.
Key paper: From data to knowledge: Construction process analysis through continuous image capturing, object detection, and knowledge graph creation (Automation in Construction, 2024)
Fabrication Information Modeling links digital design with robotic fabrication; learned world models and agentic AI prepare robots for the construction site.
Design Healing goes beyond checking a building model against regulations: it proposes model changes that resolve the violations it finds.
Key paper: Design Healing framework for automated code compliance (Automation in Construction, 2025)
The information backbone of robotized construction
Additive to Predictive Manufacturing for Multistorey Construction Using Learning by Printing and Networked Robotics
Additive Manufacturing in Construction
AI-based automation of repetitive design steps in BIM modeling
AI-based processing of CAD models for automated planning of computer-aided manufacturing
More than 15 million euros raised in more than 30 competitively awarded projects since 2011, funded by the German Research Foundation (DFG), the European Union, German federal ministries, the Bavarian Research Foundation and industry.
117 peer-reviewed journal papers, 332 peer-reviewed conference papers, 41 book chapters and 4 books (2006 - 2026).
15 best-paper awards at international conferences and journals (2008 - 2026), among them ICCCBE, ECPPM, EG-ICE, CIB-W78, the European Conference on Computing in Construction, eSIM, the ISPRS TC I Mid-term Symposium and the ASCE Journal of Computing in Civil Engineering, mostly as coauthor.
Doctoral supervision: 28 doctorates completed (2013 - 2025), 15 doctoral researchers currently supervised.
+49 89 289 23047 (CCBE secretariat)
Technical University of Munich
Arcisstraße 21
80333 Munich, Germany
Professor of Computing in Civil and Building EngineeringDirector, TUM Georg Nemetschek Institute - AI for the Built World