发表机构
Yonsei University（延世大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出COSTER框架，利用交通先验确定碰撞时间与位置，通过碰撞快照和时间反演生成安全关键场景，提升合理性、多样性和数据效率，并将碰撞率降低31%。
AI 中文摘要
安全关键交通场景的生成对于自动驾驶车辆的训练和评估至关重要。现有方法通常利用简化的对抗目标来扰动交通场景中已有智能体的轨迹，以诱发安全关键的交互，但这可能限制生成场景的合理性和多样性。尽管插入新的对抗性车辆可以缓解这一限制，但如何以场景特定的方式确定插入的时间和位置仍然具有挑战性。在本工作中，我们提出了碰撞快照引导的时间反演安全关键场景生成框架（COSTER），该框架利用学习到的交通先验来确定合理的碰撞时间和位置。COSTER首先通过将一辆新车辆在识别出的碰撞状态下与目标车辆接触插入到交通场景中，构建一个碰撞快照。从该碰撞快照出发，使用条件变分自编码器执行时间反演展开，将插入车辆的运动轨迹向后重建至更早的时间步。实验表明，COSTER在合理性、多样性和数据效率方面优于现有方法。此外，在Waymo开放运动数据集的安全关键场景中，使用COSTER生成场景训练的智能体将碰撞率降低了31%，同时提高了自车任务完成率。项目网站可通过此https URL访问。
英文摘要
The generation of safety-critical traffic scenarios is essential for training and evaluating autonomous vehicles. Prior approaches typically perturb the trajectories of existing agents in a traffic scenario using simplified adversarial objectives to induce safety-critical interactions, which can limit the plausibility and diversity of the generated scenarios. Although inserting new adversarial vehicles can alleviate this limitation, determining when and where to introduce them in a scenario-specific manner remains challenging. In this work, we introduce \underline{CO}llision \underline{S}napshot guided \underline{T}im\underline{E}-\underline{R}eversed safety-critical scenario generation (COSTER), a framework that leverages learned traffic priors to determine plausible collision times and locations. COSTER first constructs a collision snapshot by inserting a new vehicle in contact with the target vehicle at the identified collision state within a traffic scenario. Starting from this collision snapshot, a conditional variational autoencoder is used to perform a time-reversed rollout, reconstructing the trajectory of the inserted vehicle backward toward earlier timesteps. Experiments show that COSTER outperforms existing methods in plausibility, diversity, and data efficiency. Moreover, agents trained on COSTER-generated scenarios reduce collision rates by 31\% on safety-critical scenarios from the Waymo Open Motion Dataset while also improving ego task completion. The project website is available at https://anonym-121.github.io/COSTER/.
Comments8 pages, 3 figures
