arXiv cs.AI· Nenad Petrovic, Alois Knoll·· 13 小时前AI 评分34
基于 AI 的 SDV 端到端汽车设计与软件开发工具链
AI-Based End-to-End Automotive Design and Software Development for SDVs
AI 导读
一项研究提出将 LLM 与模型驱动工程（MDE）结合的 AI 工具链，可把自然语言需求自动转换为系统架构、可执行软件和验证产物，面向软件定义汽车（SDV）的端到端开发。该方法强调可追溯性、一致性与安全关键汽车开发合规性，并在支持自适应巡航和紧急制动的集中式车载计算平台上通过 HiL 与 SiL 环境完成验证。研究同时讨论了当前能力、实际限制及未来方向。
正文 · 原文
Abstract:This paper explores the potential of Artificial Intelligence (AI) to enable end-to-end automotive design and software development for Software-Defined Vehicles (SDVs). Based on our contributions within the Central Car Server (CeCaS) and follow-up EU-funded projects, we present an AI-driven toolchain integrating Large Language Models (LLMs) with Model-Driven Engineering (MDE) to automate the transformation of natural-language requirements into system architectures, executable software, and validation artifacts. The approach emphasizes traceability, consistency, and compliance with safety-critical automotive development requirements. Validation is performed on a centralized vehicle computing platform supporting adaptive cruise control and emergency braking, tested in Hardware-in-the-Loop (HiL) and Software-in-the-Loop (SiL) environments. We discuss current capabilities, practical limitations, and future directions toward increasingly automated, reliable, and quality-assured automotive software development with minimal human intervention.
| Subjects: | Software Engineering (cs.SE); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.29160 [cs.SE] |
| (or arXiv:2610.29160v1 [cs.SE] for this version) | |
| https://doi.org/10.48550/arXiv.2610.29160 arXiv-issued DOI via DataCite (pending registration) |
|
| Journal reference: | ELIV Conference 2026, Baden-Baden, Germany |
Submission history
From: Nenad Petrovic [view email]
[v1]
Wed, 21 Oct 2026 03:51:37 UTC (828 KB)
来源：arXiv cs.AI · arxiv.org