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

Key points

• Assembly documentation is a downstream manufacturing artifact that is still usually authored by interpreting CAD models by hand.1
• 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.1
• 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.1
• The contribution is an architecture that separates engineering state, deterministic reasoning, grounded language realization, verification, and human release.1

Sources (1)

• [1]Automated Assembly Instruction Generation from CAD Models Using Grounded Large Language Models: A Human-in-the-Loop Framework
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 01:04 PM

  This paper formulates CAD-grounded assembly instruction generation: the production of natural-language assembly procedures constrained by structured engineering information extracted from CAD models.

  Assembly documentation is a downstream manufacturing artifact that is still usually authored by interpreting CAD models by hand.

Extractive summary: sentences quoted from the sources.