Artificial Intelligence in Architecture: Investigating the Ability of Accessible AI Tools to Produce an Architecture Project.

AbstractThis paper investigates the capabilities of multiple free and accessible AI tools to design and implement a theoretical architectural project and assesses their effectiveness and potential impact as well as connectivity to given contexts. The main aspects of this investigation include the design and creativity, planning, basic construction and renders. The work was conducted through presenting the selected project to ChatGPT and prompting it to create a design and to generate prompts that were input into the image-generating AI tools MaketAI and BlueWillow to produce the final presentation. ChatGPT was able to understand the objectives of the given task and to create a functional design with meaningful ideas for materials and elements that establish a relationship to the environment and design settings. But it was also observed that the AI-generated design was “on the safer side” being box-shaped and having typical interior arrangement, indicating that AI may be lacking in establishing original innovative ideas that are not recycles of training data. Moreover, it was found that the structural aspect is in crucial need for human input, as AI has followed generic construction standards that may not apply to specific contexts. The results are also found to be highly dependable on the original prompt written by human as well as the following prompts generated by AI, which further demonstrates that human input is momentous.These findings imply that despite the ability of AI to generate useful designs, human input remains crucial for infusing expression and ensuring certainty in primitive-aspects of architectural designs and conclude a promising future with the prospect of human-robot collaboration.

Institutions

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2024-09-14
DOI
https://doi.org/10.5281/zenodo.17117486
Primary Topic
Geochemistry and Geologic Mapping
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Artificial Intelligence in Architecture: Investigating the Ability of Accessible AI Tools to Produce an Architecture Project.

Zenodo (CERN European Organization for Nuclear Research)
Geochemistry and Geologic Mapping
article

Artificial Intelligence in Architecture: Investigating the Ability of Accessible AI Tools to Produce an Architecture Project.

article en

Abstract

AbstractThis paper investigates the capabilities of multiple free and accessible AI tools to design and implement a theoretical architectural project and assesses their effectiveness and potential impact as well as connectivity to given contexts. The main aspects of this investigation include the design and creativity, planning, basic construction and renders. The work was conducted through presenting the selected project to ChatGPT and prompting it to create a design and to generate prompts that were input into the image-generating AI tools MaketAI and BlueWillow to produce the final presentation. ChatGPT was able to understand the objectives of the given task and to create a functional design with meaningful ideas for materials and elements that establish a relationship to the environment and design settings. But it was also observed that the AI-generated design was “on the safer side” being box-shaped and having typical interior arrangement, indicating that AI may be lacking in establishing original innovative ideas that are not recycles of training data. Moreover, it was found that the structural aspect is in crucial need for human input, as AI has followed generic construction standards that may not apply to specific contexts. The results are also found to be highly dependable on the original prompt written by human as well as the following prompts generated by AI, which further demonstrates that human input is momentous.These findings imply that despite the ability of AI to generate useful designs, human input remains crucial for infusing expression and ensuring certainty in primitive-aspects of architectural designs and conclude a promising future with the prospect of human-robot collaboration.

Zenodo (CERN European Organization for Nuclear Research)
TU Wien (AT)
Openalex Percentile: Top 45%
Geochemistry and Geologic Mapping
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.