Abstract

The advent of artificial intelligence (AI) in architecture is still in its early days but offers promising results. More than a mere opportunity, such potential represents a major step ahead, about to reshape the architectural discipline. This chapter proposes to evidence this promise when applied to the built environment. Specifically, we apply AI to floor plan generation and analysis. Our approach is threefold: (I) to generate floor plans using generative adversarial network models, i.e., optimize the generation of a large and highly diverse quantity of floor plan designs, (II) to qualify floor plans, i.e., offer a proper classification methodology built on reliable metrics (footprint, orientation, thickness and texture, program, connectivity, and circulation), and (III) to allow users to “browse” through generated design options. In a nutshell, the machine, once the extension of our pencil, can today be leveraged to map architectural knowledge and trained to assist us in creating viable design options. This chapter offers an initial roadmap and an early evidence of this promise.