Exploring Co-design with an AI Partner: The GAI-A Interface in Architectural Education

被引:0
作者
Gul, Leman Figen [1 ]
Delikanli, Burak [1 ,2 ]
Unesi, Ogulcan [2 ]
Gul, Ertugrul Omer [3 ]
机构
[1] Istanbul Tech Univ, Dept Architecture, Sariyer, Turkiye
[2] Istanbul Tech Univ, Grad Sch, Sariyer, Turkiye
[3] Univ New South Wales, Sch Comp Sci & Engn, Sydney, NSW, Australia
来源
COOPERATIVE DESIGN, VISUALIZATION, AND ENGINEERING, CDVE 2024 | 2024年 / 15158卷
关键词
Co-design; AI Partner; Generative AI; Design Creativity; CREATIVITY; TOOLS;
D O I
10.1007/978-3-031-71315-6_1
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The integration of advanced information and communication technologies has revolutionized collaborative working processes, especially in creative design, allowing stakeholders to interact across locations and time zones. Originally designed to facilitate human collaboration, these systems have evolved to include collaborative interactions between humans and Artificial Intelligence (AI) models, reaching new heights with the integration of Generative Artificial Intelligence (GenAI) models. In this study, we introduce a co-design interface, Generative Artificial Intelligence for Architecture (referred to as GAI-A), for the initial design phase to stimulate creative design. GAI-A provides a collaborative space for designers to work with an AI partner that suggests visuals based on the images provided. Over the span of four consecutive academic semesters, we have rigorously implemented and evaluated this innovative environment in the architectural design studio at Istanbul Technical University, aiming to elucidate its multifaceted applications and implications within the academic discourse of architecture. The interface of GAI-A is evaluated through Creativity Support Index and surveys and semi-structured interviews. The research explores critical aspects, including co-design possibilities with GenAI models, and optimal utilization techniques, providing valuable insights into design pedagogy.
引用
收藏
页码:1 / 12
页数:12
相关论文
共 28 条
[1]   OpenCrowd: A Human-Al Collaborative Approach for Finding Social Influencers via Open-Ended Answers Aggregation [J].
Arous, Ines ;
Yang, Jie ;
Khayati, Mourad ;
Cudre-Mauroux, Philippe .
WEB CONFERENCE 2020: PROCEEDINGS OF THE WORLD WIDE WEB CONFERENCE (WWW 2020), 2020, :1851-1862
[2]  
Bown Oliver., 2015, ICCC, P126
[3]   Quantifying the Creativity Support of Digital Tools through the Creativity Support Index [J].
Cherry, Erin ;
Latulipe, Celine .
ACM TRANSACTIONS ON COMPUTER-HUMAN INTERACTION, 2014, 21 (04)
[4]   Cooperative AI: machines must learn to find common ground [J].
Dafoe, Allan ;
Bachrach, Yoram ;
Hadfield, Gillian ;
Horvitz, Eric ;
Larson, Kate ;
Graepel, Thore .
NATURE, 2021, 593 (7857) :33-36
[5]  
Davis N., 2021, P AAAI C ARTIFICIAL, V9, P9, DOI 10.1609/aiide.v9i6.12603
[6]  
Davis N, 2015, SPR SER CULT COMPUT, P109, DOI 10.1007/978-1-4471-6681-8_7
[7]  
De Bono E., 2015, The Mechanism of Mind: Understand How Your Mind Works to Maximise Memory and Creative Potential
[8]  
Del Campo M., 2024, Diffusions in Architecture: Artificial Intelligence and Image Generators
[9]  
Elgammal A, 2017, Arxiv, DOI arXiv:1706.07068
[10]  
Goodfellow IJ., 2014, arXiv, DOI [10.48550/ARXIV.1406.2661, DOI 10.48550/ARXIV.1406.2661]