Design with shape grammars and reinforcement learning

Authors: Manuela Ruiz-Montiel, Javier Boned, Juan Gavilanes, Eduardo Jiménez, Lawrence Mandow, José-Luis Pérez-de-la-Cruz

Abstract: 
Shape grammars are a powerful and app ealing formalism for automatic shape generation in computerbased design systems. This pap er presents a proposal complementing the generative power of shape grammars with reinforcem ent learning techniques. We use simple (naive) shape grammars capable of generating a large variety of different designs. In order to generate those designs that comply with given design requirements, the grammar is subject to a process of machine learning using reinforcement learning techniques. Based on this method, we have developed a system for architectural design, aimed at generating two-dimensional layout schemes of single-family housing units. Using relatively simple grammar rules, we learn to generate schemes that satisfy a set of requirements stated in a design guideline. Obtained results are presented and discussed.

Keywords:
Computational design
Shape grammars
Reinforcement learning
Architecture

Published in: Advanced Engineering Informatics (Volume 27, Issue 2, January 2013)

Publisher: Elsevier

ISSN Information: 1474-0346

Design with shape grammars and reinforcement learning

Bình luận của bạn

*

*

*

*

 Captcha

Gửi bình luận nhập lại