Architectural layout design through deep learning and agent-based modeling: A hybrid approach

This paper presents a novel hybrid approach for generating automated 2D architectural layouts by combining agent-based modeling with deep learning algorithms. The primary goal of this research is to maintain the designers' high-level, supervisory control over the generated results and process, allowing them to manage the whole process so that the created results satisfy the desired topological and geometrical constraints. The proposed hybrid approach consists of two different methods. First, hierarchical phases of agent-based modeling are simulated to generate a bubble diagram that satisfies the topological conditions. A rule-based algorithm converts bubble diagrams into heat maps. Second, the pix2pix algorithm translates the heat maps into an architectural spatial layout as a conditional GAN and deep learning approach. In doing so, a unique dataset was manually generated, and the cGAN algorithm was trained based on this dataset. The hybrid method of these processes makes it possible to generate an architectural layout based on a particular footprint and desired high-level constraints. The findings of agent-based modeling showed complete consistency with the required topological requirements, whereas deep learning results demonstrated the ability of cGAN to satisfy geometrical constraints learned throughout the training phase. The hybrid method's results showed enhanced computational accuracy in generating synthetic architectural layouts compared to previous studies.