Simulation-based Adversarial Test Generation for Autonomous Vehicles with Machine Learning Components
This addresses the problem of certifying safety for autonomous vehicles, but it is incremental as it adapts existing test generation methods to this domain.
The paper tackles the challenge of testing autonomous driving systems with machine learning components by presenting a simulation-based adversarial test generation framework, demonstrating its use to automatically identify problematic scenarios and increase system reliability.
Many organizations are developing autonomous driving systems, which are expected to be deployed at a large scale in the near future. Despite this, there is a lack of agreement on appropriate methods to test, debug, and certify the performance of these systems. One of the main challenges is that many autonomous driving systems have machine learning components, such as deep neural networks, for which formal properties are difficult to characterize. We present a testing framework that is compatible with test case generation and automatic falsification methods, which are used to evaluate cyber-physical systems. We demonstrate how the framework can be used to evaluate closed-loop properties of an autonomous driving system model that includes the ML components, all within a virtual environment. We demonstrate how to use test case generation methods, such as covering arrays, as well as requirement falsification methods to automatically identify problematic test scenarios. The resulting framework can be used to increase the reliability of autonomous driving systems.