Residential complex design as a Constraint Satisfaction Problem

Abstract

The design of mass housing projects, with their complex array of apartment types and constraints, can be challenging for architects. Automated-organizing programs can assist in exploring various design alternatives, but the computational cost of checking all possible building organizations grows exponentially. This paper describes a method that utilizes a variant of the Constraint Satisfaction Problem (CSP) to bound and direct the growth of search trees. The method allows designers to explore design alternatives using geometrical objects and incorporates constraints related to daylight and privacy evaluation. Two search tree strategies, breadth-first search (BFS) and depth-first search (DFS), are implemented using a custom solver, with DFS proving suitable for larger search trees and BFS being appropriate for searching through the entire tree. By clearly defining the problem and adjusting the constraints, designers can efficiently explore the design space and obtain valid building alternatives in a reasonable time.