arXiv cs.AI· Joschka Kersting, Gesa Benndorf·· 12 小时前AI 评分31
从代码生成器到工程伙伴：面向 PLC 编程的工厂感知智能体
From Code Generator to Engineering Companion: A Plant-aware Agent for PLC Programming
AI 导读
研究者提出一种工厂感知的对话式 PLC 编程 copilot，在检索增强 LLM 生成合规 Structured Text 的基础上，加入工厂特定上下文摄取、以对话为先的交互模式，以及从聊天到部署的分级工具访问阶梯。系统面向真实工厂基础设施设计，并让工程师掌控每个产生实际影响的步骤。该工作发表于 2026 IEEE ETFA。
正文 · 原文
Abstract:Programmable Logic Controller (PLC) coding remains a manual, IDE-centric task that demands constant context switching between documentation, project files, and code editors. Recent work has demonstrated that retrieval-augmented large language models can generate vendor-compliant Structured Text at high compilation rates \cite{pred}, yet these systems treat code generation as a one-shot pipeline: the engineer submits a query and receives code, with no persistent knowledge of the specific plant. We present a plant-aware conversational copilot that extends this paradigm in three directions: plant-specific context ingestion, a chat-first interaction model for explanation and debugging, and a graduated tool-access ladder from chat to deployment. The system is designed for real plant infrastructure and keeps the engineer in control of each step that produces real-world effects.
| Subjects: | Software Engineering (cs.SE); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.28160 [cs.SE] |
| (or arXiv:2610.28160v1 [cs.SE] for this version) | |
| https://doi.org/10.48550/arXiv.2610.28160 arXiv-issued DOI via DataCite (pending registration) |
|
| Journal reference: | 2026 IEEE 31st International Conference on Emerging Technologies and Factory Automation (ETFA), Västerås, Sweden, 2026 |
| Related DOI: | https://doi.org/10.1109/ETFA68377.2026.11725227
DOI(s) linking to related resources |
Submission history
From: Joschka Kersting [view email]
[v1]
Tue, 20 Oct 2026 13:02:14 UTC (3,343 KB)
来源：arXiv cs.AI · arxiv.org