A Ga-enabled VR framework for generating alternative 3D interior space configurations
This dissertation is a prototype development project to design and implement a Desktop VR (Virtual Reality) framework for generating and evaluating Pareto-optimal alternate 3D spatial configurations using GA (genetic algorithms). The lack of standard procedures to facilitate the coherent and comprehensive planning of spatial configurations hinders the optimal exploitation of valuable interior spaces. This research puts forth a multi-objective optimization methodology for creating alternative interior space configuration scenarios and provides a visual means for assessing the desktop VR-based Pareto-optimal solutions. The search spaces (function domains) are extremely large in these design problems, and the optimization procedure involves conflicting objective functions, and limitations in the form of constraint functions. This research proposes a Desktop VR (Virtual Reality) framework for generating and evaluating optimal alternate 3D spatial configurations using GA (genetic algorithms). Based on the extensive literature review conducted for this study, no such earlier research integrating MOGA (Multiobjective Genetic Algorithm) with Desktop VR for solving interior spatial configuration problems could be found. Normally, when employing genetic algorithms (GA) for multiobjective optimization, a group of Pareto-optimal solutions (Pareto set) are available for the planners and decision-makers, wherefrom one solution ought to be picked. Therefore, this study applies a tool to not only visually evaluate the plans, but also to interact with those plans to develop them further if needed. GA formulation involves defining the objective functions/constraints, and also includes defining the GA coding (integer), fitness function, and setting the parameters including mutation rate, crossover type and rate, number of generations etc. Subsequently, the virtual world scenarios corresponding to the Pareto-optimal plans are generated. The subsequent step involves the computer graphics (CG) component wherein genotype-compatible 3D software objects are rendered. Besides enabling the optimal spatial configuration of the scene elements, this framework also facilitates evaluation and interaction via the 3D VR worlds. Also, where appropriate, the framework aids the proactive exploration, analysis, and finalization of design aspects such as color, size, lighting, etc. of the various elements prior to the actual construction. This serves as a generic framework that can be extended to other CG domains as well.^
Gary R. Bertoline, Purdue University.
Information Technology|Education, Technology of|Computer Science