Generation of Floor Plan Variations with Convolutional Neural Networks and Case-based Reasoning An approach for transformative adaptation of room configurations within a framework for support of early conceptual design phases

Generation of Floor Plan Variations with Convolutional Neural Networks and Case-based Reasoning An approach for transformative adaptation of room configurations within a framework for support of early conceptual design phases

Eisenstadt, Viktor; Langenhan, Christoph; Althof, Klaus-Dieter

Article:

We present an approach for computer-aided generation of different variations offloor plans during the early phases of conceptual design in architecture. Theearly design phases are mostly characterized by the processes of inspirationgaining and search for contextual help in order to improve the building design athand. The generation method described in this work uses the novel as well asestablished artificial intelligence methods, namely, generative adversarial netsand case-based reasoning, for creation of possible evolutions of the currentdesign based on the most similar previous designs. The main goal of thisapproach is to provide the designer with information on how the current floorplan can evolve over time in order to influence the direction of the design process.The work described in this paper is part of the methodology FLEA (Find, Learn,Explain, Adapt) whose task is to provide a holistic structure for support of theearly conceptual phases in architecture. The approach is implemented as theadaptation component of the framework MetisCBR that is based on FLEA.

We present an approach for computer-aided generation of different variations offloor plans during the early phases of conceptual design in architecture. Theearly design phases are mostly characterized by the processes of inspirationgaining and search for contextual help in order to improve the building design athand. The generation method described in this work uses the novel as well asestablished artificial intelligence methods, namely, generative adversarial netsand case-based reasoning, for creation of possible evolutions of the currentdesign based on the most similar previous designs. The main goal of thisapproach is to provide the designer with information on how the current floorplan can evolve over time in order to influence the direction of the design process.The work described in this paper is part of the methodology FLEA (Find, Learn,Explain, Adapt) whose task is to provide a holistic structure for support of theearly conceptual phases in architecture. The approach is implemented as theadaptation component of the framework MetisCBR that is based on FLEA.

Palavras-chave:

DOI: 10.5151/proceedings-ecaadesigradi2019_648

Referências bibliográficas

• [1]

Como citar:

Eisenstadt, Viktor; Langenhan, Christoph; Althof, Klaus-Dieter; "Generation of Floor Plan Variations with Convolutional Neural Networks and Case-based Reasoning An approach for transformative adaptation of room configurations within a framework for support of early conceptual design phases", p-79-84. In: Proceedings of 37 eCAADe and XXIII SIGraDi Joint Conference, “Architecture in the Age of the 4Th Industrial Revolution”, Porto 2019, Sousa, José Pedro; Henriques, Gonçalo Castro; Xavier, João Pedro (eds.). São Paulo: Blucher, 2019.
ISSN 23186968, DOI 10.5151/proceedings-ecaadesigradi2019_648