arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~

基于接地大语言模型的CAD模型自动装配指令生成:一种人在回路框架

Automated Assembly Instruction Generation from CAD Models Using Grounded Large Language Models: A Human-in-the-Loop Framework

Aaron Dsouza, Mohammed Azeez Khan, Ashutosh Mishra, Arshaan Khan, Neha K. Nair, Amar Kumar Behera

arXiv 2610.11896首次发表:更新:

发表机构

National Institute of Technology Warangal; Nawab Shah Alam Khan College of Engineering and Technology; Indian Institute of Technology Kanpur(瓦朗加尔国家理工学院; 纳瓦布·沙阿·阿拉姆·汗工程技术学院; 坎普尔印度理工学院)

机构由 AI 辅助整理,请以论文原文为准。

AI 中文总结

本文提出一种人在回路框架,将CAD模型映射为ProductGraph,经拓扑排序生成装配流程,结合规则与模型检查,在人工审核后导出装配指令,验证了六部件装配的可行性。

AI 中文摘要

装配文档是一种下游制造产物,通常仍需人工解读CAD模型来编写。结构化产品数据和大语言模型均已可用,但CAD解读、装配序列规划、指令编写及人工监督的研究大多各自独立开展。本文提出CAD接地的装配指令生成:即利用从CAD模型提取的结构化工程信息,生成受约束的自然语言装配流程。所提框架将STEP装配映射为类型化ProductGraph中间表示,通过确定性拓扑排序推导优先级顺序,仅基于所选图上下文将每一步转化为语言描述,附加每步的视觉文档,并应用基于规则和模型辅助的检查。在人工审核员解决所有质量标记前,PDF导出保持禁用。案例研究在一个内置的六部件参考装配上验证了端到端可行性:该流程保留了报告的装配顺序,并将数量、材料和扭矩信息纳入导出的手册页面。泛化性和几何验证仍是未解决的经验问题。本文的贡献是一种架构,将工程状态、确定性推理、接地语言生成、验证及人工发布环节分离开来。

英文摘要

Assembly documentation is a downstream manufacturing artifact that is still usually authored by interpreting CAD models by hand. Structured product data and large language models are both available, yet studies of CAD interpretation, assembly sequence planning, instruction writing, and human oversight have largely proceeded separately. This paper formulates CAD-grounded assembly instruction generation: the production of natural-language assembly procedures constrained by structured engineering information extracted from CAD models. The proposed framework maps a STEP assembly to a typed ProductGraph intermediate representation, derives a precedence order by deterministic topological sorting, realizes each step as language conditioned only on selected graph context, attaches per-step visual documentation, and applies rule-based and model-assisted checks. PDF export remains disabled until a human reviewer resolves every quality flag. The case study establishes endto-end feasibility on a built-in six-part reference assembly: the pipeline preserves a reported assembly order and carries quantity, material, and torque into an exported manual page. Generalization and geometric validation remain open empirical questions. The contribution is an architecture that separates engineering state, deterministic reasoning, grounded language realization, verification, and human release.

Comments16 pages, 6 figures, 4 tables

论文原文

arXiv 摘要页 · PDF 原文 · HTML 原文

↑