A Survey on the Application of Large Language Models in Scenario-Based Testing of Automated Driving Systems

TL;DR

This survey reviews how Large Language Models are applied in scenario-based testing of Automated Driving Systems, highlighting their roles, strategies, challenges, and future research directions.

Contribution

It systematically categorizes LLM applications in ADS testing, summarizes key characteristics and strategies, and identifies open challenges and research opportunities.

Findings

LLMs are used in scenario generation and validation.

Key characteristics of LLMs influence testing strategies.

Five open challenges guide future research.

Abstract

The safety and reliability of Automated Driving Systems (ADSs) must be validated prior to large-scale deployment. Among existing validation approaches, scenario-based testing has been regarded as a promising method to improve testing efficiency and reduce associated costs. Recently, the emergence of Large Language Models (LLMs) has introduced new opportunities to reinforce this approach. While an increasing number of studies have explored the use of LLMs in the field of automated driving, a dedicated review focusing on their application within scenario-based testing remains absent. This survey addresses this gap by systematically categorizing the roles played by LLMs across various phased of scenario-based testing, drawing from both academic research and industrial practice. In addition, key characteristics of LLMs and corresponding usage strategies are comprehensively summarized. The paper concludes by outlining five open challenges and potential research directions. To support ongoing research efforts, a continuously updated repository of recent advancements and relevant open-source tools is made available at: https://github.com/ftgTUGraz/LLM4ADSTest.