基于 ISO 11783 网络的机器可读操作手册研究：面向离线多语言 LLM 辅助
Machine-Readable Operator Manuals over the ISO 11783 Network for Offline, Multilingual LLM Assistance
AI 导读
一项 arXiv 论文提出在 ISO 11783 CAN 总线上对农机操作手册进行语义同步，为拖拉机侧 LLM 助手建立本地知识库。实验中完整手册通过物理 ISO 11783 网络传输耗时 31 到 89 秒；Markdown 格式文件最小，三种格式的问答性能大体相当。
正文 · 原文
Abstract:If agricultural machinery is to support intelligent, offline assistance, then the system must access technical documentation dynamically. In this paper, the Semantic Synchronization of operator manuals over ISO 11783-based CAN buses is analyzed, defined as the process that brings the local knowledge base of a tractor-side assistant into agreement with the operator manual of the connected implement. Data transfer performance was benchmarked using Markdown, JSON, and XML; various open-weight Large Language Models (LLMs) were also evaluated in cross-lingual query tasks. The automatic evaluation of the answers was validated against four human raters. A complete manual was transferred over a physical ISO 11783 network in 31 to 89 s, depending on format and transport settings, which is comparable to the object pool upload that operators already wait for at the first coupling of an implement. Markdown produced the smallest files, while the question-answering performance was comparable across the three formats for most models. With retrieval-augmented generation, locally run models answered most questions on the English manual correctly, with no advantage of the largest model over 7B and 8B models, but performed worse on the five other language editions. Keyword retrieval failed across languages, whereas semantic retrieval provided the cross-lingual capability. The exchange requires only a new parameter group that uses the existing request and transport mechanisms of ISO 11783, which makes it a candidate for standardization. The study is a proof of concept with inference on PC-grade hardware; deployment on embedded agricultural hardware remains future work.
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Information Retrieval (cs.IR) |
| Cite as: | arXiv:2610.31863 [cs.CL] |
| (or arXiv:2610.31863v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.31863 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Timo Oksanen [view email]
[v1]
Thu, 22 Oct 2026 19:52:26 UTC (1,730 KB)
来源：arXiv cs.AI · arxiv.org