FTA generation using GenAI with an Autonomy sensor Usecase

TL;DR

This paper investigates the use of Generative AI, specifically Large Language Models, to automate Fault Tree Analysis for autonomous vehicle sensors, demonstrating the potential for prompt engineering and visualization tools.

Contribution

It introduces a novel approach to generate Fault Tree Analysis using GenAI and prompt engineering for autonomous driving sensor failure scenarios.

Findings

Feasibility of training LLMs for FTA tasks

Use of PlantUML for visualizing fault trees

Potential to automate FTA in autonomous systems

Abstract

Functional safety forms an important aspect in the design of systems. Its emphasis on the automotive industry has evolved significantly over the years. Till date many methods have been developed to get appropriate FTA(Fault Tree analysis) for various scenarios and features pertaining to Autonomous Driving. This paper is an attempt to explore the scope of using Generative Artificial Intelligence(GenAI) in order to develop Fault Tree Analysis(FTA) with the use case of malfunction for the Lidar sensor in mind. We explore various available open source Large Language Models(LLM) models and then dive deep into one of them to study its responses and provide our analysis. This paper successfully shows the possibility to train existing Large Language models through Prompt Engineering for fault tree analysis for any Autonomy usecase aided with PlantUML tool.