How Generative AI supports human in conceptual design
Liuging Chen, Yaxuan Song, Jia Guo, Lingyun Sun, Peter Childs, Yuan Yin
TL;DR
This study addresses the lack of empirical evidence on how Generative AI supports human designers in conceptual design. It employs an experimental design with novice designers assigned to four groups (ChatGPT, Midjourney, Combined, and Human) across two design tasks, evaluating performance via participant ratings and expert assessments, and analyzing design prompts. The findings show Generative AI mainly aids early stages such as problem definition, idea generation, and idea evolution, while idea selection and evaluation remain predominantly human-led; AI assistance also improves overall evaluation scores, though combining text-to-text and text-to-image models did not yield a synergistic effect. The results highlight stage-aware roles for different AI modalities and point to the need for workflow-integrated, user-centered design of AI-assisted conceptual design tools. These insights offer practical guidance for developing AI-powered design support that enhances creativity while preserving human judgment.
Abstract
Generative Artificial Intelligence (Generative AI) is a collection of AI technologies that can generate new information such as texts and images. With its strong capabilities, Generative AI has been actively studied in creative design processes. However, limited studies have explored the roles of humans and Generative AI in conceptual design processes, leaving a gap for human-AI collaboration investigation. To address this gap, this study uncovers the contributions of different Generative AI technologies in assisting humans in the conceptual design process. Novice designers completed two design tasks with or without the assistance of Generative AI. Results revealed that Generative AI primarily assists humans in problem definition and idea generation stages, while idea selection and evaluation remain predominantly human-led. Additionally, with Generative AI assistance, the idea selection and evaluation stages were further enhanced. Based on the findings, we discuss the role of Generative AI in human-AI collaboration and implications for enhancing future conceptual design support with Generative AI assistance.