Saved in:
Bibliographic Details
Main Authors: Li, Jingzheng, Liu, Xianglong, Wei, Shikui, Chen, Zhijun, Li, Bing, Guo, Qing, Yang, Xianqi, Pu, Yanjun, Wang, Jiakai
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.23708
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917978638909440
author Li, Jingzheng
Liu, Xianglong
Wei, Shikui
Chen, Zhijun
Li, Bing
Guo, Qing
Yang, Xianqi
Pu, Yanjun
Wang, Jiakai
author_facet Li, Jingzheng
Liu, Xianglong
Wei, Shikui
Chen, Zhijun
Li, Bing
Guo, Qing
Yang, Xianqi
Pu, Yanjun
Wang, Jiakai
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2503_23708
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards Benchmarking and Assessing the Safety and Robustness of Autonomous Driving on Safety-critical Scenarios
Li, Jingzheng
Liu, Xianglong
Wei, Shikui
Chen, Zhijun
Li, Bing
Guo, Qing
Yang, Xianqi
Pu, Yanjun
Wang, Jiakai
Robotics
Artificial Intelligence
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.
title Towards Benchmarking and Assessing the Safety and Robustness of Autonomous Driving on Safety-critical Scenarios
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2503.23708