一句话：提出 Foresee，通过预测近失事件并局部模糊测试，更高效发现自动驾驶系统隐藏故障。
基于仿真的测试是自动驾驶系统部署前可靠性评估的标准手段，但现有缺陷发现技术要么不可靠要么昂贵。论文基于仿真中近失事件可能预示潜在失败的洞见，提出 Foresee：用不当行为预测器计算自车未来状态，识别近失候选，并在其邻域执行局部模糊测试以暴露未知失败。作者在 CARLA 模拟器多场景中，对端到端和模块化自动驾驶系统评估不同配置，并与 DriveFuzz 比较互补性。结果表明，Foresee 比随机方法多发现 128.70% 失败，比最佳失败预测器多 38.09%，速度分别快 2.49 倍和 1.42 倍；与 DriveFuzz 结合可将失败检测提升至多 93.94%。
Simulation-based testing is the standard practice for assessing the reliability of self-driving cars’ software before deployment. Existing bug-finding techniques are either unreliable or expensive. We build on the insight that near misses observed during simulations may point to potential failures. We propose Foresee, a technique that identifies near misses using a misbehavior forecaster that computes possible future states of the ego-vehicle under test. Foresee performs local fuzzing in the neighborhood of each candidate near miss to surface previously unknown failures. In our empirical study, we evaluate the effectiveness of different configurations of Foresee using several scenarios provided in the CARLA simulator on both end-to-end and modular self-driving systems and examine its complementarity with the state-of-the-art fuzzer DriveFuzz. Our results show that Foresee is both more effective and more efficient than the baselines. Foresee exposes 128.70% and 38.09% more failures than a random approach and a state-of-the-art failure predictor while being 2.49 × and 1.42 × faster, respectively. Moreover, when used in combination with DriveFuzz, Foresee enhances failure detection by up to 93.94%.
@inproceedings{abs-2512-18823,
title = {Misbehavior Forecasting for Focused Autonomous Driving Systems Testing},
author = {M M Abid Naziri and Stefano Carlo Lambertenghi and Andrea Stocco and Marcelo d'Amorim},
booktitle = {ICSE},
year = {2026},
doi = {10.1145/3744916.3787829}
}