Application of Algorithmic Generation to Kindergarten Design
- 356 Downloads
Previous automated building layout studies focus more on optimization than design diversity. However, designers constantly generate new goals in a design task owing to the complex constraints and ill-defined evaluation criteria, and then they have to repeat the optimization consequently. We consider that a more interactive human-machine cooperative design should rapidly create considerable design alternatives with performance analysis in preliminary design period for architects to select. Inspired by Monte Carlo Tree Search (MCTS), we propose an algorithm which can generate various acceptable solutions rapidly for building layout problem. In this article, this algorithm is applied to a kindergarten design project to investigate its efficacy, and to discuss its potential for universal building layout problems and machine learning.
KeywordsAlgorithmic generation Automated building layout Monte Carlo Tree Search Human-machine cooperative design
This research was supported by National Natural Science Foundation of China (51578277) and Major Program of National Natural Science Foundation of China (51538005).
- 1.Eastman, C.N.: Spatial synthesis in computer-aided building design (1975)Google Scholar
- 3.Myszkowski, P., Nisztuk, M.: Usability of contemporary tools for the computational design of architectural objects: review, features evaluation and reflection (2017)Google Scholar
- 5.neo SUNGOD CITY / MOON GODDESS CITY. https://makoto-architect.com/ALGODEX_e_neoSUNGOD_CITY.html
- 6.Del Río-Cidoncha, G., Martínez-Palacios, J., Eugenio Iglesias, J.: A multidisciplinary model for floorplan design, 3457–3476 (2007)Google Scholar
- 7.Lomker, T., Frazer, J., Tang, M.: Designing with Machines: Solving Architectural Layout Planning Problems by the Use of a Constraint Programming Language and Scheduling Algorithms. ASCAAD, Sharjah, United Arab Emirates (2006)Google Scholar
- 9.Wortmann, T., Waibel, C., Nannicini, G., Evins, R., Schroepfer, T., Carmeliet, J.: Are Genetic Algorithms Really the Best Choice in Building Energy Optimization? (2017)Google Scholar
- 10.Nourian, P.: Configraphics: graph theoretical methods for design and analysis of spatial configurations. A + BE: Archit. Built Environ. 6, 1–348 (2016)Google Scholar
- 11.Ball, L.J., Lambell, N.J., Reed, S.E., Reid, F.J.M.: The Exploration of Solution Options in Design: A ‘Naturalistic Decision Making’ Perspective, Context: Fifth Design Thinking Research Symposium—dtrs (2001)Google Scholar
- 13.Akin, Ö.: Variants in Design Cognition. Design Knowing & Learning Cognition in Design Education, pp. 105–124 (2001)Google Scholar
- 14.Th, C., Leiserson, C., Rivest, Z.: Introduction to Algorithms (1990)Google Scholar
- 16.Van Eyck, J., Ramon, J., Guiza, F., Meyfroidt, G., Bruynooghe, M., van den Berghe, G.: Guided Monte Carlo Tree Search for planning in learned environments, pp. 33–47 (2013)Google Scholar