‘What Is the Next Step?’ Supporting Architectural Room Configuration Process with Case-Based Reasoning and Recurrent Neural Networks

Viktor Eisenstadt, Klaus-Dieter Althoff

In: Keith Brawner, Roman Barták (Hrsg.). 32nd International FLAIRS Conference. International FLAIRS Conference (FLAIRS-2019) May 19-22 Sarasota Florida United States AAAI Press 5/2019.


This paper presents the first results of the research into AI based support of the room configuration process during the early design phases in architecture. Room configuration (also: room layout or space layout) is an essential stage of the initial design phase: its results are crucial for user-friendliness and success of the planned utilization of the architectural object. Our approach takes into account different possible actions of the configuration process, such as adding, removing, or (re)assigning of the room type. Its mode of operation is based on specific process chain clusters, where each cluster represents a contextual subset of previous configuration steps and provides a recurrent neural network trained on this cluster data only to suggest the next step, and a case base that is used to determine if the current process chain belongs to this cluster. The most similar cluster then tries to suggest the next step of the process. The approach is implemented in a distributed CBR framework for support of early conceptual design in architecture and was evaluated with a high number of process chain queries to prove its general suitability.

Weitere Links

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence