Scenario-Based Test Reduction and Prioritization for Multi-Module Autonomous Driving Systems

TL;DR

This paper introduces a novel approach for reducing and prioritizing test scenarios in autonomous driving systems by encoding driving scenes, segmenting recordings, and prioritizing based on scene coverage and rarity, significantly reducing testing time while maintaining fault detection.

Contribution

The paper presents an industry-level method for test reduction and prioritization in multi-module autonomous driving systems, improving efficiency without sacrificing fault detection capability.

Findings

Reduced test recordings by over 34% while maintaining fault detection.

Achieved 22% to 39% and 41% to 53% improvements in fault detection metrics.

Validated on industry-level Apollo system across multiple road maps.

Abstract

When developing autonomous driving systems (ADS), developers often need to replay previously collected driving recordings to check the correctness of newly introduced changes to the system. However, simply replaying the entire recording is not necessary given the high redundancy of driving scenes in a recording (e.g., keeping the same lane for 10 minutes on a highway). In this paper, we propose a novel test reduction and prioritization approach for multi-module ADS. First, our approach automatically encodes frames in a driving recording to feature vectors based on a driving scene schema. Then, the given recording is sliced into segments based on the similarity of consecutive vectors. Lengthy segments are truncated to reduce the length of a recording and redundant segments with the same vector are removed. The remaining segments are prioritized based on both the coverage and the rarity of driving scenes. We implemented this approach on an industry level, multi-module ADS called Apollo and evaluated it on three road maps in various regression settings. The results show that our approach significantly reduced the original recordings by over 34% while keeping comparable test effectiveness, identifying almost all injected faults. Furthermore, our test prioritization method achieves about 22% to 39% and 41% to 53% improvements over three baselines in terms of both the average percentage of faults detected (APFD) and TOP-K.