arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.15591cs.SE
收藏

Req2Road: 一个用于SDV测试资产生成和车载执行的生成式AI管道

Req2Road: A GenAI Pipeline for SDV Test Artifact Generation and On-Vehicle Execution

Mercedes-Benz AG(梅赛德斯-奔驰集团);Institute for Architecture of Application Systems, University of Stuttgart(斯图加特大学应用系统架构研究所);Institute for Robotics, Artificial Intelligence and Embedded Systems, Technical University of Munich(慕尼黑工业大学机器人、人工智能与嵌入式系统研究所)

Denesa Zyberaj, Lukasz Mazur, Pascal Hirmer, Nenad Petrovic, Marco Aiello, Alois Knoll

AI总结:

本文提出了一种生成式AI管道,用于SDV子系统的测试资产生成和车载执行,通过自动化生成Gherkin场景并验证其可执行性。

摘要:

在软件定义车辆中测试功能具有挑战性,因为需求是以自然语言书写的,规范结合了文本、表格和图表,而测试资产分散在异构工具链中。大型语言模型和视觉-语言模型用于提取信号和行为逻辑,以自动生成Gherkin场景,然后转换为可运行的测试脚本。车辆信号规范(VSS)整合标准规范信号引用,支持在子系统和测试台架之间移植。该管道使用检索增强生成,在映射前预选候选VSS信号。我们评估了该方法在安全相关的儿童存在检测系统上的效果,在虚拟环境和实际车辆上执行生成的测试。我们的评估涵盖了Gherkin的有效性、VSS映射质量以及端到端可执行性。结果表明,在我们的设置中,36个需求中有32个(89%)可以转换为可执行的场景,而人工审查和有针对性的替换仍然是必要的。本文是对SDV子系统端到端需求到测试管道的可行性及架构演示,已在模拟和车辆在环设置中评估了一个CPDS案例。

英文摘要:

Testing functionality in Software-Defined Vehicles is challenging because requirements are written in natural language, specifications combine text, tables, and diagrams, while test assets are scattered across heterogeneous toolchains. Large Language Models and Vision-Language Models are used to extract signals and behavioral logic to automatically generate Gherkin scenarios, which are then converted into runnable test scripts. The Vehicle Signal Specification (VSS) integration standardizes signal references, supporting portability across subsystems and test benches. The pipeline uses retrieval-augmented generation to preselect candidate VSS signals before mapping. We evaluate the approach on the safety-relevant Child Presence Detection System, executing the generated tests in a virtual environment and on an actual vehicle. Our evaluation covers Gherkin validity, VSS mapping quality, and end-to-end executability. Results show that 32 of 36 requirements (89\%) can be transformed into executable scenarios in our setting, while human review and targeted substitutions remain necessary. This paper is a feasibility and architectural demonstration of an end-to-end requirements-to-test pipeline for SDV subsystems, evaluated on a CPDS case in simulation and Vehicle-in-the-Loop settings.

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。

↑