Towards Benchmarking and Assessing the Safety and Robustness of Autonomous Driving on Safety-critical Scenarios
This work addresses safety gaps in autonomous driving deployment, focusing on edge cases that are critical for real-world accidents, though it is incremental in building upon existing evaluation methods.
The paper tackles the lack of safety and robustness assessment for autonomous driving in safety-critical scenarios by defining these scenarios and developing a testing platform for comprehensive evaluation, aiming to support industry standardization and reduce real-world risks.
Autonomous driving has made significant progress in both academia and industry, including performance improvements in perception task and the development of end-to-end autonomous driving systems. However, the safety and robustness assessment of autonomous driving has not received sufficient attention. Current evaluations of autonomous driving are typically conducted in natural driving scenarios. However, many accidents often occur in edge cases, also known as safety-critical scenarios. These safety-critical scenarios are difficult to collect, and there is currently no clear definition of what constitutes a safety-critical scenario. In this work, we explore the safety and robustness of autonomous driving in safety-critical scenarios. First, we provide a definition of safety-critical scenarios, including static traffic scenarios such as adversarial attack scenarios and natural distribution shifts, as well as dynamic traffic scenarios such as accident scenarios. Then, we develop an autonomous driving safety testing platform to comprehensively evaluate autonomous driving systems, encompassing not only the assessment of perception modules but also system-level evaluations. Our work systematically constructs a safety verification process for autonomous driving, providing technical support for the industry to establish standardized test framework and reduce risks in real-world road deployment.