PerturbationDrive: A Framework for Perturbation-Based Testing of ADAS
This provides a tool for improving safety in autonomous driving by addressing vulnerabilities in ADAS to input variations, though it is incremental as it builds on existing perturbation methods.
The paper tackles the problem of testing the robustness and generalization of Advanced Driver Assistance Systems (ADAS) by presenting PerturbationDrive, a framework that uses over 30 image perturbations and integrates with simulators and procedural generation to enable systematic evaluation across diverse scenarios.
Advanced driver assistance systems (ADAS) often rely on deep neural networks to interpret driving images and support vehicle control. Although reliable under nominal conditions, these systems remain vulnerable to input variations and out-of-distribution data, which can lead to unsafe behavior. To this aim, this tool paper presents the architecture and functioning of PerturbationDrive, a testing framework to perform robustness and generalization testing of ADAS. The framework features more than 30 image perturbations from the literature that mimic changes in weather, lighting, or sensor quality and extends them with dynamic and attention-based variants. PerturbationDrive supports both offline evaluation on static datasets and online closed-loop testing in different simulators. Additionally, the framework integrates with procedural road generation and search-based testing, enabling systematic exploration of diverse road topologies combined with image perturbations. Together, these features allow PerturbationDrive to evaluate robustness and generalization capabilities of ADAS across varying scenarios, making it a reproducible and extensible framework for systematic system-level testing.