Welcome Your New AI Teammate: On Safety Analysis by Leashing Large Language Models
This addresses the need to speed up safety engineering processes in DevOps for industries like Autonomous Vehicles, but it is incremental as it relies on existing LLMs with human oversight.
The paper tackles the slow Hazard Analysis & Risk Assessment (HARA) step in SafetyOps for Autonomous Vehicles by proposing a framework using Large Language Models (LLMs) to increase automation, though expert review remains essential for validity.
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 Large Language Models (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.