arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2605.10568cs.LOcs.SE
收藏

通过分离逻辑的正确性构建G代码生成:一种神经符号方法

Correct-by-Construction G-Code Generation: A Neuro-Symbolic Approach via Separation Logic

SLING AI Inc.(SLING AI 公司)

Yeonseok Lee

AI总结:

本文提出了一种神经符号框架,通过分离逻辑证明器将GLLM方法的神经生成能力与形式验证相结合,利用几何数据构建两组件架构,将物理碰撞转化为逻辑空间数据 race,从而生成自我校正的G代码生成系统,减少人工监督,提高自主制造的安全性和验证性。

摘要:

本文提出了一种神经符号框架,用于G代码生成,旨在将GLLM方法的神经生成能力与形式验证相结合,通过分离逻辑(SL)证明器进行形式验证。为了建立可靠的物理基准,该框架利用OpenCASCADE框架从3D CAD模型(STEP文件)中提取确定性的边界表示。所提取的几何数据支持双组件架构:LLM作为初始代码生成器,而SL证明器利用空间堆模型进行评估。通过将物理碰撞概念化为逻辑空间数据 race(分离联结的违反),我们的框架将证明失败转化为结构化的数学反馈。这些失败被压缩成边界框,作为LLM迭代自我校正的指令。最终,本文旨在开发一个自我校正的系统,减少对人工监督的需求,从而实现更安全和验证的自主制造。

英文摘要:

This paper proposes a neuro-symbolic framework for G-code generation that seeks to integrate the neural generative capabilities of the GLLM method (Abdelaal et al., 2025) with formal verification via a Separation Logic (SL) prover. To establish a reliable physical baseline, the framework extracts deterministic boundary representations from 3D CAD models (STEP files) using the OpenCASCADE framework. This extracted geometric data supports a two-component architecture: the LLM serves as an initial code generator, while the SL Prover, utilizing a Spatial Heap model, evaluates the output. By conceptualizing physical collisions as logical Spatial Data Races -- violations of the separating conjunction in SL -- our framework translates proof failures into structured mathematical feedback. These failures are condensed into bounding boxes that serve as directives for the LLM's iterative self-correction. Ultimately, this work aims to develop a self-correcting system that reduces the need for human supervision, leading to safer and verified autonomous manufacturing.

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。

↑