Show simple item record

contributor authorYao, Jiayi
contributor authorChen, Pei
contributor authorLi, Zhuoshu
contributor authorCai, Yichen
contributor authorWu, Yexinrui
contributor authorYou, Weitao
contributor authorSun, Lingyun
date accessioned2025-04-21T10:10:52Z
date available2025-04-21T10:10:52Z
date copyright1/30/2025 12:00:00 AM
date issued2025
identifier issn1050-0472
identifier othermd_147_7_071703.pdf
identifier urihttp://yetl.yabesh.ir/yetl1/handle/yetl/4305655
description abstractIn the product conceptual design, designers utilize multiple design representations to ideate, externalize, and refine concepts iteratively. Mixed representations, defined as the simultaneous presentation of multiple representations, foster deeper insights and facilitate broader exploration compared to focusing on a single representation. However, designers often struggle with the cumbersome process of creating, transforming, and refining these representations. Advanced artificial intelligence (AI) capabilities now significantly lower the barriers to creating text, images, and 3D models, presenting substantial potential for application in design practice. However, the current design tools based on generative AI tend to produce polished product images directly, hindering designers from continuously deliberating on mixed representations and thus limiting their creative potential. Therefore, on the basis of a formative study, we propose StepIdeator, a step-by-step design tool driven by generative AI. This tool facilitates seamless transition and refinement of mixed-design representations. Through a comparative study (N = 16), we validated StepIdeator's effectiveness in improving idea externalization and enhancing creativity. Furthermore, the results revealed that designers perceived greater confidence, ownership, and sense of contribution when collaborating with StepIdeator.
publisherThe American Society of Mechanical Engineers (ASME)
titleStepIdeator: Utilizing Mixed Representations to Support Step-By-Step Design With Generative Artificial Intelligence
typeJournal Paper
journal volume147
journal issue7
journal titleJournal of Mechanical Design
identifier doi10.1115/1.4067426
journal fristpage71703-1
journal lastpage71703-19
page19
treeJournal of Mechanical Design:;2025:;volume( 147 ):;issue: 007
contenttypeFulltext


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record