外观
论文arXiv 2610.0617123 天前
用于端到端驾驶安全评估的可控且照片级真实的行人风险运动生成
原文链接：Controllable and Photorealistic Pedestrian Risky Motion Generation for End-to-End Driving Safety Evaluation（arXiv 2610.06171 · 发布日期：2026-10-05）
Controllable and Photorealistic Pedestrian Risky Motion Generation for End-to-End Driving Safety Evaluation
ControlPed结合冲突轨迹合成与3DGS生成可控照片级安全关键场景，并在88个渲染场景中评估端到端驾驶模型。
核心要点
- 稀有安全关键车-人交互需要传感器级真实场景，轨迹生成缺少视觉，视频方法缺少可控性。
- ControlPed基于HazardPed生成冲突轨迹，经文本条件运动扩散提升为3D人体运动，并用可动画3DGS渲染多视角观测。
- 在88个照片级渲染场景中，七个领先端到端驾驶模型平均HDScore从88.8降至47.4。
- 作者表示将发布数据集和测试基准，以促进车-人交互安全评估。
验证范围与局限：验证范围为88个渲染照片级场景和七个端到端驾驶模型。
英文摘要 (Abstract)
Evaluating end-to-end autonomous driving under rare, safety-critical vehicle-pedestrian interactions requires photorealistic, sensor-level scenarios. However, trajectory-based scenario generators cannot synthesize raw visual observations, whereas video-based approaches lack controllability. To bridge this gap, we present ControlPed, a novel framework that combines trajectory-level conflict synthesis with 3D Gaussian Splatting (3DGS) to generate photorealistic, motion-controllable safety-critical scenarios. Built upon HazardPed, a dataset derived from 10,352 traffic videos comprising 422 conflict trajectories, HD maps, and 857 annotated 3D human motions, ControlPed first generates conflict trajectories, lifts them into 3D human motion sequences via text-conditioned motion diffusion, and finally renders multi-view sensor observations using animatable 3DGS avatars. Safety evaluation in 88 rendered photorealistic scenarios reveals that seven leading end-to-end driving models suffer a severe performance drop, with their mean HDScore plunging from 88.8 to 47.4, exposing major failure modes under dangerous pedestrian behaviors. The dataset and testing benchmarks will be released to facilitate safety assessment of vehicle-pedestrian interactions.
作者：Siyuan Liu, Miao Li, Haibao Yu, Haohong Lin, Qing Zhou, Bingbing Nie, Ding Zhao
来源
本页事实对应的公开页面，以原文为准。