Engineering Safety Requirements for Autonomous Driving with Large Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914727562575872 |
|---|---|
| author | Nouri, Ali Cabrero-Daniel, Beatriz Törner, Fredrik Sivencrona, Hȧkan Berger, Christian |
| author_facet | Nouri, Ali Cabrero-Daniel, Beatriz Törner, Fredrik Sivencrona, Hȧkan Berger, Christian |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_16289 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Engineering Safety Requirements for Autonomous Driving with Large Language Models Nouri, Ali Cabrero-Daniel, Beatriz Törner, Fredrik Sivencrona, Hȧkan Berger, Christian Artificial Intelligence 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. |
| title | Engineering Safety Requirements for Autonomous Driving with Large Language Models |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2403.16289 |