自动驾驶

SUV: Future Scene Understanding as Video Generation for End-to-End Driving

SUV：将未来场景理解建模为视频生成的端到端驾驶

Yibo Yuan, Jiacheng Fu, Jiangtong Zhu, Yi Li, Jianhua Han, Meng Tian, Zhuohan Liu, Zhiwei Xiong, Hang Xu, Jianwu Fang, Jianru Xue

专题命中 端到端驾驶 ：end-to-end driving(title,abstract)；trajectory planning(abstract)；分类 cs.CV

AI总结 SUV是将未来场景理解建模为视频生成的端到端驾驶框架，其在NAVSIM-v2和WOD-E2E基准上优于近期SOTA方法，实现了更优的轨迹规划性能。

Comments 16 pages, 5 figures. Code: https://github.com/ASH-2046/SUV

CADET: Physics-Grounded Causal Auditing and Training-Free Deconfounding of End-to-End Driving Planners

CADET: 基于物理的因果审计与无训练去混杂的端到端驾驶规划器

Zikun Guo, Yuanyuan Li, Rongjin Zou

机构 * School of Electronics Engineering, Kyungpook National University（庆北国立大学电子工程学院） 纠错

专题命中 端到端驾驶 ：end-to-end driving(title)；分类 cs.RO、cs.AI

AI总结 提出CADET框架，无需重新训练即可审计和修复预训练端到端驾驶规划器中的虚假关联，通过物理因果图识别混杂因素并干预测试时输入。

Comments 8pages 4figures