arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2403.16289cs.AI
收藏

使用大型语言模型工程化自动驾驶的安全需求

Engineering Safety Requirements for Autonomous Driving with Large Language Models

Volvo Cars(沃尔沃汽车);Chalmers University of Technology(查尔姆斯理工大学);University of Gothenburg(哥德堡大学);Zenseact

Ali Nouri, Beatriz Cabrero-Daniel, Fredrik Törner, Hȧkan Sivencrona, Christian Berger

AI总结:

本研究提出一个基于LLMs和提示的流水线原型,用于自动细化分解安全需求、审查冗余矛盾需求,并通过设计科学多轮迭代和专家评估验证其在汽车领域SafetyOps中的有效性。

摘要:

需求工件中的变更和更新在汽车领域可能很频繁,这对SafetyOps构成了挑战。大型语言模型(LLMs)凭借其出色的自然语言理解和生成能力,可以在每次更新后自动细化和分解需求方面发挥关键作用。在本研究中,我们提出了一个由提示和LLMs组成的流水线原型,该原型接收一个项目定义并以安全需求的形式输出解决方案。该流水线还执行需求数据集的审查,并识别冗余或矛盾的需求。我们首先确定了执行HARA所需的特征,然后定义了测试以评估LLM在满足这些标准方面的能力。我们采用设计科学方法进行多次迭代,并让来自不同公司的专家对每个周期进行定量和定性评估。最后,该原型在一家案例公司中实施,由负责团队评估其效率。

英文摘要:

Changes and updates in the requirement artifacts, which can be frequent in the automotive domain, are a challenge for SafetyOps. Large Language Models (LLMs), with their impressive natural language understanding and generating capabilities, can play a key role in automatically refining and decomposing requirements after each update. In this study, we propose a prototype of a pipeline of prompts and LLMs that receives an item definition and outputs solutions in the form of safety requirements. This pipeline also performs a review of the requirement dataset and identifies redundant or contradictory requirements. We first identified the necessary characteristics for performing HARA and then defined tests to assess an LLM's capability in meeting these criteria. We used design science with multiple iterations and let experts from different companies evaluate each cycle quantitatively and qualitatively. Finally, the prototype was implemented at a case company and the responsible team evaluated its efficiency.

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。

↑