Patterns, heuristics for architectural design support: Making use of evolutionary modelling in design

Abstract

Software used by architectural and industrial designers has shifted from becoming a tool for drafting, towards use in verification, simulation, project management and remote project sharing. In more advanced models, design parameters for the designed object can be adjusted so that a family of variations can be produced rapidly. With the advances in computer aided design (CAD) technology, design options can now be generated and analyzed in real time. However the use of digital tools to support design as an activity is still at an early stage and has largely been limited in functionality with regard to the design process. To date, major CAD vendors have not developed an integrated tool that is able to leverage specialised design knowledge from various discipline domains (known as expert knowledge systems) as well as to support the creation of design alternatives that satisfy different forms of constraints. We propose that evolutionary computing and machine learning be linked with parametric design techniques in order to monitor a designer's cognition and intent based on their design history. This will lead to results that impact future work on design support systems which are capable of supporting implicit constraint and problem definition for wicked problems that are difficult to quantify. ©2010, Association for Research in Computer-Aided Architectural Research in Asia (CAADRIA).