Autocompletion Of Floor Plans For The Early Design Phase In Architecture: Foundations, Existing Methods, And Research Outlook

Viktor Eisenstadt DFKI / University of Hildesheim
Jessica Bielski Technical University of Munich
Burak Mete Technical University of Munich
Christoph Langenhan Technical University of Munich
Klaus-Dieter Althoff DFKI / University of Hildesheim
Andreas Dengel DFKI

This paper contributes the current research state and possible future developments of AI-based autocompletion of architectural floor plans and shows demand for its establishment in computer-aided architectural design to facilitate decent work, economic growth through accelerating the design process to meet the future workload. Foundations of data representations together with the autocompletion contexts are defined, existing methods described and evaluated in the integrated literature review, and criteria for qualitative and sustainable autocompletion are proposed. Subsequently, we contribute three unique deep learning-based autocompletion methods currently in development for the research project metis-II. They are described in detail from a technical point of view on the backdrop of how they adhere to the proposed criteria for creating our novel AI.

Keywords: Artificial Intelligence, Architectural Design, Floor Plan, Autocompletion, Sdg 8, Sdg 9

View Full Paper