arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2503.04417cs.AIcs.MA
收藏

从创意到CAD:一个语言模型驱动的多智能体协同设计系统

From Idea to CAD: A Language Model-Driven Multi-Agent System for Collaborative Design

Honda Research Institute Europe(本田欧洲研究所)

Felix Ocker, Stefan Menzel, Ahmed Sadik, Thiago Rios

AI总结:

本文提出一种基于VLM的多智能体系统,通过结合需求工程、CAD工程和视觉质量保证智能体,从草图或文本自动生成并迭代细化CAD模型,提升了工业与业余设计过程的效率。

摘要:

使用计算机辅助设计(CAD)创建数字模型是一个需要深入专业知识的过程。在工业产品开发中,该过程通常涉及由需求工程、CAD本身以及质量保证组成的整个工程师团队。我们提出了一种方法,利用基于视觉语言模型(VLM)的多智能体系统来映射这种团队结构,该系统可访问参数化CAD工具及工具文档。通过结合用于需求工程、CAD工程和基于视觉的质量保证的智能体,可以从草图和/或文本描述中自动生成模型。生成的模型可以在与用户的迭代验证循环中进行协同细化。我们的方法有潜力提高设计过程的有效性,无论对于工业专家还是为3D打印创建模型的爱好者均如此。我们以各种设计任务为例展示了该架构的潜力,并提供了若干消融实验,证明了该架构各个组件的益处。

英文摘要:

Creating digital models using Computer Aided Design (CAD) is a process that requires in-depth expertise. In industrial product development, this process typically involves entire teams of engineers, spanning requirements engineering, CAD itself, and quality assurance. We present an approach that mirrors this team structure with a Vision Language Model (VLM)-based Multi Agent System, with access to parametric CAD tooling and tool documentation. Combining agents for requirements engineering, CAD engineering, and vision-based quality assurance, a model is generated automatically from sketches and/ or textual descriptions. The resulting model can be refined collaboratively in an iterative validation loop with the user. Our approach has the potential to increase the effectiveness of design processes, both for industry experts and for hobbyists who create models for 3D printing. We demonstrate the potential of the architecture at the example of various design tasks and provide several ablations that show the benefits of the architecture's individual components.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑