Welcome Your New AI Teammate: On Safety Analysis by Leashing Large Language Models (2403.09565v1)
Abstract: DevOps is a necessity in many industries, including the development of Autonomous Vehicles. In those settings, there are iterative activities that reduce the speed of SafetyOps cycles. One of these activities is "Hazard Analysis & Risk Assessment" (HARA), which is an essential step to start the safety requirements specification. As a potential approach to increase the speed of this step in SafetyOps, we have delved into the capabilities of LLMs. Our objective is to systematically assess their potential for application in the field of safety engineering. To that end, we propose a framework to support a higher degree of automation of HARA with LLMs. Despite our endeavors to automate as much of the process as possible, expert review remains crucial to ensure the validity and correctness of the analysis results, with necessary modifications made accordingly.
- “ISO 26262:2018 (all parts), Road Vehicles — Functional Safety,” standard, International Organization for Standardization, 2018.
- “ISO 21448:2022, Road Vehicles — Safety of the Intended Functionality,” standard, International Organization for Standardization, 2022.
- UNECE, “UN Regulation No. 157 - Automated Lane Keeping Systems (ALKS),” 2021.
- A. Nouri, C. Berger, and F. Törner, “On STPA for Distributed Development of Safe Autonomous Driving: An Interview Study,” in Proceedings of the 49th EUROMICRO Conference on Software Engineering and Advanced Applications (SEAA), (DURRES, ALBANIA), Sep. 2023.
- Google, “What is DevOps?,” 2022.
- U. Siddique, “SafetyOps,” arXiv preprint arXiv:2008.04461, 2020.
- A. Nouri, C. Berger, and F. Törner, “An Industrial Experience Report about Challenges from Continuous Monitoring, Improvement, and Deployment for Autonomous Driving Features,” in Euromicro Conference on Software Engineering and Advanced Applications, pp. 358–365, 2022.
- L. Giray, “Prompt engineering with chatgpt: A guide for academic writers,” Annals of Biomedical Engineering (2023).
- A. Gilson, C. Safranek, T. Huang, V. Socrates, L. Chi, R. Taylor, and D. Chartash, “How well does chatgpt do when taking the medical licensing exams? the implications of large language models for medical education and knowledge assessment,” 12 2022.
- CNECT, 2021.
- R. Bommasani et al., “On the opportunities and risks of foundation models,” 2022.
- J. White, Q. Fu, S. Hays, M. Sandborn, C. Olea, H. Gilbert, A. Elnashar, J. Spencer-Smith, and D. C. Schmidt, “A prompt pattern catalog to enhance prompt engineering with chatgpt,” 2023.
- O. Zheng, M. Abdel-Aty, D. Wang, Z. Wang, and S. Ding, “Chatgpt is on the horizon: Could a large language model be suitable for intelligent traffic safety research and applications?,” 2023.
- Y. Qi, X. Zhao, S. Khastgir, and X. Huang, “Safety analysis in the era of large language models: A case study of stpa using chatgpt,” 2023.
- S. Diemert and J. H. Weber, “Can large language models assist in hazard analysis?,” 2023.
- A. R. Hevner, S. T. March, J. Park, and S. Ram, “Design science in information systems research,” MIS Quarterly, vol. 28, no. 1, pp. 75–105, 2004.
- R. Wieringa, Design Science Methodology for Information Systems and Software Engineering. 01 2014.