Early-Stage Floor Plan Generation as a Multi-Objective Optimization Problem

Abstract

Architectural design of floor plans is a time consuming and labor-intensive task. Computer-aided architectural design can ease this work and an automatic floor plan generation tool in the early stages of floor plan design is beneficial. In this thesis a model is proposed that attempts to automatically generate floor plans for office buildings and further push the research field of computer-aided architectural design. The model is an implementation of NSGA-II with newly presented mutations, objective functions and representation of floor plans. The thesis provides experiments and results for generating floor plans for existing building structures. The proposed model is able to generate feasible solutions for small building structures with respect to the objective functions and architectural constraints.