Designer-driven 3D buildings generated using Variable Neighborhood Search

Abstract

Abstract-This paper presents a mechanism to generate virtual buildings considering designer constraints and guidelines. This mechanism is implemented as a pipeline of different Variable Neighborhood Search (VNS) optimization processes in which several subproblems are tackled (1) rooms locations, (2) connectivity graph, and (3) element placement. The core VNS algorithm includes some variants to improve its performance, such as, for example constraint handling and biased operator selection. The optimization process uses a toolkit of construction primitives implemented as "smart objects" providing basic elements such as rooms, doors, staircases and other connectors. The paper also shows experimental results of the application of different designer constraints to a wide range of buildings from small houses to a large castle with several underground levels.

BIMBOT-(Artificial intelligence applied to BIM design)

“…-Partitioning of spaces (Peña, Viedma, Muelas, LaTorre and Peña, 2014): Division of interior spaces according to considerations of design, use and connectivity between rooms.…”

“…BIMBOT is based on previous works that have been adapted to the construction sector. The AIbased constraint optimization engine, LurtisEngine, was originally designed to create 3D scenarios for the creative industries and is the core of HouseBuilder (a tool for creating building structures) and InteriorDecorator (which designs interior spaces) (Peña, Viedma, Muelas, LaTorre and Peña, 2014).…”

“…• Particionamiento de espacios (Peña, Viedma, Muelas, LaTorre and Peña, 2014): División de espacios interiores atendiendo a consideraciones de diseño, uso y conectividad entre estancias.…”

“…BIMBOT se basa en trabajos previos que se han adaptado al sector de la construcción. El motor de optimización de restricciones basado en IA, LurtisEngine, fue diseñado originalmente para crear escenarios en 3D para las industrias creativas y es el núcleo de HouseBuilder (una herramienta para crear estructuras de edificios) e InteriorDecorator (que diseña espacios interiores) (Peña, Viedma, Muelas, LaTorre and Peña, 2014). Asimismo, la tecnología de este motor de optimización se ha aplicado con éxito en otros enfoques de diseño basado en IA, como el diseño de fuselaje de aviones (Muelas,Peña,Muzhetskaya,LaTorre and Miguel,208).…”

An Integrated Framework for AI Assisted Level Design in 2D Platformers

“…Computer-aided design tools have become widely used in many production pipeline to reduce development time and costs. These tools often involve the procedural generation of one or more types of artifact; notable examples include SpeedTree 3 , which allows the automatic generation of vegetation in 3D environments, Volcano [7], that creates 3D models of swords by exploiting interactive evolution, and the Procedural Building Generator [8], that generates 3D buildings based on designer constraints and guidelines. In this section, we overview the most relevant work on difficulty metrics in video games and on computer-aided design tools for content generation in 2D platformers; we refer the reader to [9] for a more general and exhaustive discussion of procedural content generation (PCG) in games.…”