Long-tail and rare event problems become crucial when autonomous driving algorithms are applied in the real world. For the purpose of evaluating systems in challenging settings, we propose a generative framework to create safety-critical scenarios for evaluating specific task algorithms. We first represent the traffic scenarios with a series of autoregressive building blocks and generate diverse scenarios by sampling from the joint distribution of these blocks. We then train the generative model as an agent (or a generator) to investigate the risky distribution parameters for a given driving algorithm being evaluated. We regard the task algorithm as an environment (or a discriminator) that returns a reward to the agent when a risky scenario is generated. Through the experiments conducted on several scenarios in the simulation, we demonstrate that the proposed framework generates safety-critical scenarios more efficiently than grid search or human design methods. Another advantage of this method is its adaptiveness to the routes and parameters.
AdvDiffuser: Generating Adversarial Safety-Critical Driving Scenarios via Guided Diffusion
School of Computer Science and Engineering, Sun Yat-Sen University（中山大学计算机科学与工程学院）；School of Computer Science, Wuhan University（武汉大学计算机学院）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Mechanical and Automotive Engineering, Qingdao University of Technology（青岛理工大学机械与汽车工程学院）
AuthSim: Towards Authentic and Effective Safety-critical Scenario Generation for Autonomous Driving Tests
Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所）；School of Science, Beijing University of Posts and Telecommunications（北京邮电大学理学院）；University of Chinese Academy of Sciences（中国科学院大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
Generating Realistic Safety-Critical Scenarios for Vehicle-Pedestrian Interactions
Transportation Informatics Lab, Department of Civil and Environmental Engineering, Old Dominion University（交通信息实验室，土木与环境工程系，旧 Dominion 大学）；Inner Mongolia Center for Transportation Research, Inner Mongolia University（内蒙古交通研究所，内蒙古大学）；School of Transportation and Logistics, National Engineering Laboratory of Integrated Transportation Big Data Application Technology, National and Local Joint Engineering Research Center of Integrated Transportation Intelligence, Southwest Jiaotong University（交通运输学院，国家集成交通大数据应用技术工程实验室，国家与地方联合集成交通智能工程研究中心，西南交通大学）
LD-Scene: LLM-Guided Diffusion for Controllable Generation of Adversarial Safety-Critical Driving Scenarios
The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；School of Computer Science and Engineering, Sun Yat-sen University（中山大学计算机科学与工程学院）
KG-ASG: Collision-Knowledge-Guided Closed-Loop Adversarial Scenario Generation With Primary-Support Attribution
Guangdong Provincial Key Laboratory of Intelligent Transportation System, School of Intelligent Systems Engineering, Shenzhen Campus of Sun Yat-sen University（广东省智能交通系统重点实验室，智能系统工程学院，中山大学深圳校区）
Generating Critical Scenarios for Testing Automated Driving Systems
Faculty of Information Technology, University of Engineering and Technology, Vietnam National University（越南国家大学工程技术学院信息技术学院）；School of Information Science, Japan Advanced Institute of Science and Technology（日本先进科学技术学院信息科学学院）
