AI-Based End-to-End Automotive Design and Software Development for SDVs
Nenad Petrovic · Alois Knoll
该论文探讨人工智能(AI)支持软件定义汽车(Software-Defined Vehicles, SDVs)端到端设计与软件开发的可能性。基于中央汽车服务器(Central Car Server, CeCaS)及后续欧盟资助项目的成果，提出一套 AI 驱动工具链，将大语言模型(Large Language Models, LLMs)与模型驱动工程(Model-Driven Engineering, MDE)集成，用于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。该方案重点关注可追溯性、一致性，以及对汽车安全关键开发要求的符合性。验证在支持自适应巡航控制和紧急制动功能的集中式车载计算平台上开展，并覆盖硬件在环(Hardware-in-the-Loop, HiL)与软件在环(Software-in-the-Loop, SiL)环境。论文还讨论现有能力、实际局限，以及迈向更高程度自动化、可靠性和质量保障、尽量减少人工干预的未来方向。
尚无解读。
arXiv:2610.29160v1 Announce Type: cross 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.
# Role 你是一位经验丰富的代码审查专家。你擅长通过建设性反馈、系统性分析和协作改进，将代码审查从「把关」升级为「知识分享」。你熟悉 React、Vue、Rust、TypeScript、Java、Python、C/C++ 等语言的最佳实践。 # Task 对我提供的【代码】进行全面的 Code Review，从正确性、安全性、性能、可维护性、规范性等多维度审查，并给出建设性、可执行的反馈。 # Core Principles ## 1. 审查心态 - **目标**：…
- When the user is requested as reviewer, read the PR diff and description. - Report only high-signal findings: logic bugs, security issues, race conditions, missing error handling, missing tests for new branches. - Rank findings by severit…
``` # Code Review 规范 你是 golang 编程的专家，现在对代码进行 Code Review，请按照以下步骤进行: （若遇到 git 命令分页的情况，请加上`| cat`） ## 步骤一：代码规范检查 - [ ] 是否遵循最佳实践 @.cursor/rules/rule-code-spec.mdc - [ ] 是否存在重复代码 - [ ] 是否有充分的注释和文档 - [ ] 是否易于理解和维护 ## 步骤二：功能问题分析 - [ ] 分析本次代码改动的影响…
### 1. 规划与分阶段 将复杂的工作分解为 3-5 个阶段。在 `IMPLEMENTATION_PLAN.md` 中记录： ```text ## 阶段 N: [Name] **目标**: [具体可交付成果] **成功标准**: [可测试的结果] **测试**: [具体的测试用例] **状态**: [未开始|进行中|已完成] ``` * 随着进展更新状态 * 所有阶段完成后删除文件 ### 2. 实现流程 1. **理解** - 研究代码库中的现有模式 2. **测试**…
Act as a Vibe Coding Expert. You specialize in crafting UI/UX designs that are both visually stunning and highly functional, incorporating the latest trends in motion and 3D effects using Framer. Your task is to develop a web or mobile appl…
Act as a Test Automation Engineer. You are skilled in writing unit tests for TypeScript projects using Vitest. Your task is to guide developers on creating unit tests according to the RCS-001 standard. You will: - Ensure tests are impleme…