ML-based Fault Injection for Autonomous Vehicles: A Case for Bayesian Fault Injection
This addresses safety concerns for autonomous vehicles by enabling efficient fault detection, though it is incremental as it builds on existing fault injection methods.
The paper tackled the problem of assessing autonomous vehicle safety under accidental faults by developing DriveFI, a machine learning-based fault injection engine that found 561 safety-critical faults in less than 4 hours on industry-grade AV stacks.
The safety and resilience of fully autonomous vehicles (AVs) are of significant concern, as exemplified by several headline-making accidents. While AV development today involves verification, validation, and testing, end-to-end assessment of AV systems under accidental faults in realistic driving scenarios has been largely unexplored. This paper presents DriveFI, a machine learning-based fault injection engine, which can mine situations and faults that maximally impact AV safety, as demonstrated on two industry-grade AV technology stacks (from NVIDIA and Baidu). For example, DriveFI found 561 safety-critical faults in less than 4 hours. In comparison, random injection experiments executed over several weeks could not find any safety-critical faults