Neural Network Guided Evolutionary Fuzzing for Finding Traffic Violations of Autonomous Vehicles
Neural Network Guided Evolutionary Fuzzing for Finding Traffic Violations of Autonomous Vehicles
复制标题
神经网络引导的自动驾驶车辆交通违法行为进化模糊识别
DOI：
10.1109/tse.2022.3195640
复制
发表时间：
2021-09
影响因子：
7.4
通讯作者：
Ziyuan Zhong;G. Kaiser;Baishakhi Ray
中科院分区：
文献类型：
--
作者：
Ziyuan Zhong;G. Kaiser;Baishakhi Ray
自动驾驶汽车和卡车，自动驾驶汽车（avs），不应该被监管机构和公众接受，直到他们对它们的安全性和可靠性有更高的信心--这可以通过测试最实际、最有说服力地实现。但现有的测试方法不足以检查av控制器的端到端行为，而这些行为又涉及到与多个独立代理（如行人和人类驾驶的车辆）的交互。虽然在街道和高速公路上试驾自动驾驶汽车无法捕捉到许多罕见的事件，但现有的基于模拟的测试方法主要集中在简单的场景上，并且不能很好地扩展到需要对周围环境进行复杂感知的复杂驾驶情况。为了解决这些限制，我们提出了一种新的模糊测试技术，称为AutoFuzz，它可以利用广泛使用的AV模拟器的API语法来生成语义和时间有效的复杂驾驶场景（场景序列）。为了在大搜索空间中有效地搜索交通违规诱导场景，我们提出了一种约束神经网络（NN）进化搜索方法来优化AutoFuzz。我们的原型在一个最先进的基于学习的控制器，两个基于规则的控制器和一个工业级控制器上的五个场景的评估表明，AutoFuzz在高保真仿真环境中有效地发现了数百个交通违规。对于每个场景，AutoFuzz可以找到比最佳基线方法平均多10-39%的独特流量违规。此外，通过AutoFuzz发现的交通违规对基于学习的控制器进行微调，成功地减少了新版本av控制器软件中发现的交通违规。
Self-driving cars and trucks, autonomous vehicles (avs), should not be accepted by regulatory bodies and the public until they have much higher confidence in their safety and reliability — which can most practically and convincingly be achieved by testing. But existing testing methods are inadequate for checking the end-to-end behaviors of av controllers against complex, real-world corner cases involving interactions with multiple independent agents such as pedestrians and human-driven vehicles. While test-driving avs on streets and highways fails to capture many rare events, existing simulation-based testing methods mainly focus on simple scenarios and do not scale well for complex driving situations that require sophisticated awareness of the surroundings. To address these limitations, we propose a new fuzz testing technique, called AutoFuzz, which can leverage widely-used av simulators’ API grammars to generate semantically and temporally valid complex driving scenarios (sequences of scenes). To efficiently search for traffic violations-inducing scenarios in a large search space, we propose a constrained neural network (NN) evolutionary search method to optimize AutoFuzz. Evaluation of our prototype on one state-of-the-art learning-based controller, two rule-based controllers, and one industrial-grade controller in five scenarios shows that AutoFuzz efficiently finds hundreds of traffic violationsin high-fidelity simulation environments. For each scenario, AutoFuzz can find on average 10-39% more unique traffic violationsthan the best-performing baseline method. Further, fine-tuning the learning-based controller with the traffic violationsfound by AutoFuzz successfully reduced the traffic violationsfound in the new version of the av controller software.