magistrsko delo
Abstract
Samodejno generiranje arhitekturnih tlorisov zahteva upoštevanje mnogih omejitev in pravil, postavljenih glede na preference uporabnika, ki se nanašajo na strukturo, funkcionalnost, geometrijo in povezljivost prostorov. V magistrskemu delu predstavimo implementacijo sistema, ki je navdahnjen s pravili oblikovne slovnice in oborožen z evolucijskimi algoritmi omogoča samodejno generiranje tlorisov. Glede na uporabnikove omejitve definiramo več kriterijev, katerih ocene sestavljajo vrednost primernosti. V delu primerjamo različne načine izračuna ocen in preverimo učinek specifičnih mutacij, definiranih za ta problem, ter variabilne stopnje križanja in mutacije.
V proces generiranja vključimo tudi uporabnika, ki lahko med evolucijo na interaktiven način vpliva na razporeditev prostorov v tlorisu. Z implementiranim sistemom lahko dosežemo optimizacijo vseh kriterijev za podan scenarij na interaktiven ali neinteraktiven način, vendar ni zagotovljeno, da bo vsak tloris sprejemljiv.
Keywords
generiranje arhitekturnih tlorisov;genetsko programiranje;interaktivnost;oblikovna slovnica;magisteriji;
Data
Language: |
Slovenian |
Year of publishing: |
2022 |
Typology: |
2.09 - Master's Thesis |
Organization: |
UL FRI - Faculty of Computer and Information Science |
Publisher: |
[E. Čebokli] |
UDC: |
004.89:728(043.2) |
COBISS: |
136534531
|
Views: |
34 |
Downloads: |
7 |
Average score: |
0 (0 votes) |
Metadata: |
|
Other data
Secondary language: |
English |
Secondary title: |
Architectural floor plan generation using genetic algorithms |
Secondary abstract: |
Automatic generation of architectural floor plans requires many constraints and rules to be considered, based on the user's preferences regarding the structure, functionality, geometry and connectivity of the rooms. In this work, we present the implementation of a system that allows automatic generation of floor plans using evolutionary algorithms and techniques inspired by shape grammars. Depending on the user's constraints, we define several criteria whose scores represent the fitness score. We compare different ways of calculating fitness scores; furthermore, we explore the effect of specific mutations defined for this problem, and variable crossover and mutation rates.
We also involve the user in the generation process, where they can change the layout of the floor plan during the evolution in an interactive way. The implemented system can achieve the optimization of all objectives for a given scenario in an interactive or non-interactive way, however, it is not guaranteed that every floor plan will be acceptable. |
Secondary keywords: |
architectural floor plan generation;genetic programming;interactivity;computer science;computer and information science;master's degree;Gradnja;Arhitekturni načrti;Genetski algoritmi;Računalništvo;Univerzitetna in visokošolska dela; |
Type (COBISS): |
Master's thesis/paper |
Study programme: |
1000471 |
Embargo end date (OpenAIRE): |
1970-01-01 |
Thesis comment: |
Univ. v Ljubljani, Fak. za računalništvo in informatiko |
Pages: |
43-48 str. |
ID: |
17421079 |