Scribd
Upload
39 views6 pages

Ai in Architecture

about how AI is used in architecture

Uploaded by

kesanashashipriya
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
39 views6 pages

Ai in Architecture

about how AI is used in architecture

Uploaded by

kesanashashipriya
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 6

ABSTRACT

AI IN ARCHITECTURE

Artificial intelligence is a phenomenon that currently influences every aspect of


life. AI applications already started to change the business methods in different
disciplines. Architecture is one of the disciplines that is highly affected by the
developments in AI technologies. The complex nature of the practice makes
architecture a significant area of experiment for artificial intelligence
applications. From building information modelling to advanced visualization
techniques, artificial intelligence and architecture’s collaboration has important
outcomes that affect the practice’s present and future. However, the permanent
and more fundamental effects of AI on architecture must be followed in the
architectural education curricula which provides the basics for the future of the
profession. This paper presents a study that reviews the methods of artificial
intelligence in architecture from an educational perspective.

K. Shashi Priya

22311A1934

ECM-A

V
CHAPTER 5
IMPLEMENTATION

Architectural education has a complex structure with various modules. Every


module has a different purpose and characteristics. In the core of the education
there is the design studio. All other courses’ knowledge is conveyed on the
design studio where the students can reflect their educational gains and improve
their design skills. In this paper, this four-fold definition of architectural
education is used as the basis of the proposed strategies. The next subchapters
present the strategies and methods for the implementation of AI into each
module of architectural education.

Implementation of AI models to support creativity in conceptual design and


investigates two issues: (1) how AI can be integrated within existing CAD
software and which models are suitable for AI-CAD integration, and (2) to what
extent AI models can learn about design and interface with the designer to
suggest new design possibilities. The presentation describes three different
strategies for training AI to be a design partner: (1) learning from design
expertise, (2) learning from playfulness, and (3) learning from analogies. Each
strategy is applied to train different typologies of models – from Generative
Models to Reinforcement Learning Agents – and demonstrated through
applications and benchmarks in the fields of architectural and structural design.

7
With the support of AI, courses for representation methods in architecture may
become something more than only teaching how to use digital technologies and
computers as drafting tools, they may become real design instruments.
According to Chaillou (2019), the machine, once the extension of our pencil,
can today be leveraged to map architectural knowledge, and trained to assist us
in creating viable design options. Courses in the representation module of
architectural education are the most suitable place for this paradigm shift to
happen. Parametric and algorithmic design is already on the agenda of
architecture and it has somewhat a place in the architectural education
curriculum. However, the attempts to put these emerging design tools are based
on the personal efforts and dedication of educators and students. An institutional
approach is needed for these methods to be effective parts of the curriculum.
Parametric and algorithmic design methods that are influenced by AI need to be
compulsory rather than elective courses for every student to be aware of the
importance of these design methods. Being proficient to use these tools,
students may direct their energy and interest to more effective aspects of design.

Additionally, AI also affects representation through novel methods like VR,


AR, and 3d printing. Students need to be aware of these methods for digital
communication to create more impressive presentations. Alternative realities
also help students to experience their designs in 1 to 1 scale and more
intimately, so that they can initialize their design approach better. 3d printing
tools help students with their physical models by enabling them to bravely try
complex forms without the suspicion to materialize the physical model. In brief,
AI may have revolutionary effects on the representation module of architectural
education if implemented properly. A holistic model needs to be applied for all
the tools to function in harmony and be beneficial for the students.

13
CHAPTER 8
CONCLUSION

The connection between AI and architecture is undeniable. Many different


fields of work prove that AI has a lot to offer for architecture. If architects can

use the opportunity to utilize AI in various phases of design and construction,


the nature of the profession will change irreversibly. The advent of AI in
Architecture is still in its early days but offers promising results (Chaillou,
2019). However, nowadays it is too early to speak about a fundamental change
because the relationship between AI and architecture is superficial; it does not
come from the ground. For a stronger relationship and change in the basic
understanding of the profession, the form of architectural education needs to be
calibrated towards the utilization of AI. However, the road is long, and
educators must progress carefully so that the process of the implementation
works properly. Rather than personal and discontinued efforts, a holistic and
systematic approach is needed. Architects and architecture students need to
remember that except its advanced levels of complexity and numerous
alternatives it offers, AI is still a tool for design and the architect is the designer.
It only processes the data according to defined algorithms. AI does not
understand context, or design in historical context is an overcomplicated issue
for AI.
16

CHAPTER 9
REFERENCES

Ahmed, S., Liwicki, M., Weber, M., Dengel, A., 2012.

“Automatic Room Detection and Room Labeling from Architectural Floor Plans”,
IAPR International Workshop on Document Analysis Systems, 339-343.
https://doi.org/10.1109/DAS.2012.22.

Aliaga, D.G., Rosen, P.A., Bekins, D.R., 2007. ”Style Grammars for Intearctive
Visualization of Architecture”, Ieee Transactions on Visualization and Computer
Graphics, 13(4):786-797.

As, I., Pal, S., Basu, P., 2018. “Artificial intelligence in architecture: Generating
conceptual design via deep learning”, International Journal of Architectural
Computing, Vol. 16(4) 306–327. https://doi.org/10.1177/1478077118800982.

Attia, S., Beltran, L., De Herde, A., Hensen, J., 2009. “Architect Friendly: A
Comparison of Ten Different Building Performance Simulation Tools”, Eleventh
International IBPSA Conference, Glasgow, Scotland, 204-211.

Azhar, S., Hein, M., and Sketo, B. 2008. “Building information modeling: Benefits,
risks and challenges.” Proc., 44th Associated Schools of Construction National
Conference, Auburn, AL.
17

You might also like