Neural Network Guided Evolutionary Fuzzing for Finding Traffic Violations of Autonomous Vehicles

Abstract

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 violations in high-fidelity simulation environments. For each scenario, AutoFuzz can find on average 10-39% more unique traffic violations than the best-performing baseline method. Further, fine-tuning the learning-based controller with the traffic violations found by AutoFuzz successfully reduced the traffic violations found in the new version of the AV controller software.

References in corpus (9)

• pymoo: Multi-objective Optimization in Python
• Efficient Black-box Assessment of Autonomous Vehicle Safety
• DeepBillboard: Systematic Physical-World Testing of Autonomous Driving Systems
• The Relevance of Classic Fuzz Testing: Have We Solved This One?
• ConAML: Constrained Adversarial Machine Learning for Cyber-Physical Systems
• Exploring Adversarial Robustness of Multi-Sensor Perception Systems in Self Driving
• Adversarial Evaluation of Autonomous Vehicles in Lane-Change Scenarios
• AdvSim: Generating Safety-Critical Scenarios for Self-Driving Vehicles
• Multimodal Safety-Critical Scenarios Generation for Decision-Making Algorithms Evaluation

Cited by in corpus (3)

• A Survey on Scenario-Based Testing for Automated Driving Systems in High-Fidelity Simulation
• MarMot: Metamorphic Runtime Monitoring of Autonomous Driving Systems
• Dance of the ADS: Orchestrating Failures through Historically-Informed Scenario Fuzzing