GenFloor: Interactive generative space layout system via encoded tree graphs

Automated floorplanning or space layout planning has been a long-standing NP-hard problem in the field of computer-aided design, with applications integrated circuits, architecture, urbanism, and operational research. In this paper, we introduce GenFloor, an interactive design system that takes geometrical, topological, performance goals constraints as input provides optimized spatial solutions output. As part our work, propose three novel permutation methods for existing graph representations, namely O-Tree B∗-Tree representations. We implement proposed package Dynamo, visual programming tool, custom GUI additional evaluation functionalities to facilitate designers their generative workflow. Furthermore, illustrate GenFloor two sets case-study experiments residential tasks by (a) measuring ability find known optimal solution, (b) observing how can generate diverse floorplans while addressing given constant problem. Our results indicate convergence global optimum is achieved offering set floorplan corresponding local optimums solution landscape.