arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2412.13802cs.SEcs.RO
收藏

SimADFuzz:面向自动驾驶系统的仿真反馈模糊测试

SimADFuzz: Simulation-Feedback Fuzz Testing for Autonomous Driving Systems

Nanjing University of Aeronautics and Astronautics(南京航空航天大学);Birkbeck, University of London(伦敦大学伯克贝克学院)

Huiwen Yang, Yu Zhou, Taolue Chen

AI总结:

针对自动驾驶系统仿真测试中现有模糊测试忽略时空动态及仿真反馈的问题,提出SimADFuzz框架,利用违规预测模型优化场景选择并采用距离引导变异策略,有效生成揭示系统违规的高质量场景,比现有方法多发现32个违规。

摘要:

自动驾驶系统(ADS)近年来取得了显著进展。然而,由于驾驶场景的复杂性与不确定性,确保其安全性和可靠性仍是一项关键挑战。本文聚焦于ADS的仿真测试,其中生成多样且有效的测试场景是一项核心任务。现有的模糊测试方法存在局限性,例如忽略了场景的时空动态性,且未能利用仿真反馈(如速度、加速度和航向)来指导场景选择与变异。为解决这些问题,我们提出了SimADFuzz,一个旨在生成高质量场景以揭示ADS行为违规的新型框架。具体而言,SimADFuzz采用违规预测模型来评估ADS发生违规的可能性,从而优化场景选择。此外,SimADFuzz提出了距离引导的变异策略,以增强子代场景中车辆间的交互,从而触发更多车辆的边缘行为。综合实验表明,SimADFuzz优于最先进的模糊测试器,多识别出32个独特的违规,其中包括4个可复现的车辆-车辆和车辆-行人碰撞案例。这些结果证明了SimADFuzz在增强自动驾驶系统鲁棒性和安全性方面的有效性。

英文摘要:

Autonomous driving systems (ADS) have achieved remarkable progress in recent years. However, ensuring their safety and reliability remains a critical challenge due to the complexity and uncertainty of driving scenarios. In this paper, we focus on simulation testing for ADS, where generating diverse and effective testing scenarios is a central task. Existing fuzz testing methods face limitations, such as overlooking the temporal and spatial dynamics of scenarios and failing to leverage simulation feedback (e.g., speed, acceleration and heading) to guide scenario selection and mutation. To address these issues, we propose SimADFuzz, a novel framework designed to generate high-quality scenarios that reveal violations in ADS behavior. Specifically, SimADFuzz employs violation prediction models, which evaluate the likelihood of ADS violations, to optimize scenario selection. Moreover, SimADFuzz proposes distance-guided mutation strategies to enhance interactions among vehicles in offspring scenarios, thereby triggering more edge-case behaviors of vehicles. Comprehensive experiments demonstrate that SimADFuzz outperforms state-of-the-art fuzzers by identifying 32 more unique violations, including 4 reproducible cases of vehicle-vehicle and vehicle-pedestrian collisions. These results demonstrate SimADFuzz's effectiveness in enhancing the robustness and safety of autonomous driving systems.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑