Generative AI for Testing of Autonomous Driving Systems: A Survey

2025-08-27

AI Summary

Autonomous driving systems (ADS) lack efficient, scalable testing methodologies for functional and safety validation across diverse operational scenarios. Method: We conduct a systematic literature review of 91 studies to categorize generative AI applications in ADS testing into six scenario-based paradigms; integrate and empirically evaluate mainstream datasets, simulation platforms, evaluation metrics, and benchmarks; and identify critical technical challenges. Contribution/Results: We establish the first structured knowledge framework for generative AI–enabled ADS testing, identifying 27 key challenges. Our analysis reveals both empirical effectiveness and inherent limitations of current approaches. The work delivers a reusable practical guideline, a curated list of open research questions, and a forward-looking research roadmap—collectively enhancing test coverage, efficiency, and methodological rigor in ADS validation.

Technology Category

• Multiagent Systems: Adversarial Agents
• Application Domains: Mobility, Driving & Flight
• Computer Vision: Generative Adversarial Networks (GANs) for Vision

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Autonomous driving systems (ADS) have been an active area of research, with the potential to deliver significant benefits to society. However, before large-scale deployment on public roads, extensive testing is necessary to validate their functionality and safety under diverse driving conditions. Therefore, different testing approaches are required, and achieving effective and efficient testing of ADS remains an open challenge. Recently, generative AI has emerged as a powerful tool across many domains, and it is increasingly being applied to ADS testing due to its ability to interpret context, reason about complex tasks, and generate diverse outputs. To gain a deeper understanding of its role in ADS testing, we systematically analyzed 91 relevant studies and synthesized their findings into six major application categories, primarily centered on scenario-based testing of ADS. We also reviewed their effectiveness and compiled a wide range of datasets, simulators, ADS, metrics, and benchmarks used for evaluation, while identifying 27 limitations. This survey provides an overview and practical insights into the use of generative AI for testing ADS, highlights existing challenges, and outlines directions for future research in this rapidly evolving field.

Problem

• Testing autonomous driving systems for safety and functionality
• Applying generative AI to improve ADS testing efficiency
• Addressing challenges in diverse scenario-based ADS validation

Innovation

• Generative AI creates diverse test scenarios
• Systematic analysis of 91 studies conducted
• Focuses on scenario-based ADS testing methods