Coverage-Guided Road Selection and Prioritization for Efficient Testing in Autonomous Driving Systems

2026-01-13

AI Summary

This work addresses the inefficiency in autonomous driving testing caused by excessive redundant scenarios, which significantly hampers fault detection. To tackle this issue, the authors propose a test case selection method that balances diversity and coverage. The approach first clusters driving scenarios based on road geometry and dynamic behavioral features, then selects representative test cases through coverage-guaranteed sampling. A multi-dimensional prioritization strategy is further introduced, integrating geometric complexity, driving difficulty, and historical failure data. Experimental evaluation on the OPENCAT dataset and the Udacity simulator demonstrates that the method reduces the number of test cases by 89% on average while retaining 79% of failure-inducing scenarios, achieving up to a 95-fold acceleration in early fault detection.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Security and Privacy: Large-scale security measurements
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Autonomous Driving Assistance Systems (ADAS) rely on extensive testing to ensure safety and reliability, yet road scenario datasets often contain redundant cases that slow down the testing process without improving fault detection. To address this issue, we present a novel test prioritization framework that reduces redundancy while preserving geometric and behavioral diversity. Road scenarios are clustered based on geometric and dynamic features of the ADAS driving behavior, from which representative cases are selected to guarantee coverage. Roads are finally prioritized based on geometric complexity, driving difficulty, and historical failures, ensuring that the most critical and challenging tests are executed first. We evaluate our framework on the OPENCAT dataset and the Udacity self-driving car simulator using two ADAS models. On average, our approach achieves an 89% reduction in test suite size while retaining an average of 79% of failed road scenarios. The prioritization strategy improves early failure detection by up to 95x compared to random baselines.

Problem

• test redundancy
• autonomous driving
• road scenario
• test prioritization
• coverage

Innovation

• test prioritization
• coverage-guided selection
• scenario clustering
• autonomous driving testing
• redundancy reduction