arXivDaily arXiv每日学术速递 周一至周五更新

视觉与机器人

自动驾驶

自动驾驶感知、规划、BEV、占用预测、激光雷达和仿真评测。

2025-12-23 至 2025-12-23 共收录 5 信号源:cs.RO, cs.CV, eess.IV, cs.AI

1. 端到端驾驶 5 篇

2512.19133 2025-12-23 cs.RO cs.CV 84%

WorldRFT: Latent World Model Planning with Reinforcement Fine-Tuning for Autonomous Driving

WorldRFT: 通过强化微调的潜在世界模型进行自动驾驶的规划

Pengxuan Yang, Ben Lu, Zhongpu Xia, Chao Han, Yinfeng Gao, Teng Zhang, Kun Zhan, XianPeng Lang, Yupeng Zheng, Qichao Zhang

专题命中 端到端驾驶 :autonomous driving(title,abstract);LiDAR(abstract);分类 cs.RO、cs.CV

AI总结 WorldRFT通过强化学习微调提升自动驾驶规划性能,实现安全性和效率的双重优化。

Comments AAAI 2026, first version

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.17370 2025-12-23 cs.RO cs.AI 81%

TakeAD: Preference-based Post-optimization for End-to-end Autonomous Driving with Expert Takeover Data

TakeAD: 基于偏好的端到端自动驾驶后优化方法与专家接管数据

Deqing Liu, Yinfeng Gao, Deheng Qian, Qichao Zhang, Xiaoqing Ye, Junyu Han, Yupeng Zheng, Xueyi Liu, Zhongpu Xia, Dawei Ding, Yifeng Pan, Dongbin Zhao

机构 * The State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences(多模态人工智能系统国家重点实验室,中国科学院自动化研究所) School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院) School of Automation and Electrical Engineering, University of Science and Technology Beijing(北京科技大学自动化与电气工程学院) Chongqing Chang’an Technology Co., Ltd.(重庆长安科技有限公司)

专题命中 端到端驾驶 :autonomous driving(title,abstract);分类 cs.RO、cs.AI

AI总结 TakeAD通过基于偏好的后优化框架利用专家接管数据,提升端到端自动驾驶闭环性能。

Comments This work has been accepted by IEEE RA-L. Manuscript submitted: July, 8, 2025; Accepted: November, 24, 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.12826 2025-12-23 cs.RO cs.CV 81%

UncAD: Towards Safe End-to-end Autonomous Driving via Online Map Uncertainty

UncAD: 向通过在线地图不确定性实现安全端到端自动驾驶迈进

Pengxuan Yang, Yupeng Zheng, Qichao Zhang, Kefei Zhu, Zebin Xing, Qiao Lin, Yun-Fu Liu, Zhiguo Su, Dongbin Zhao

机构 * Key Laboratory of Safety Intelligent Mining in Non-coal Open-pit Mines, National Mine safety Administration, Guangdong Guangzhou, 510000, China(安全智能采矿非煤矿山重点实验室,国家矿山安全监察局,广东广州,510000,中国) The State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences(多模态人工智能系统国家重点实验室,自动化研究所,中国科学院) School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China(人工智能学院,中国科学院大学,北京,中国) EACON, Fujian, China(福建中国EACON)

专题命中 端到端驾驶 :autonomous driving(title,abstract);分类 cs.RO、cs.CV

AI总结 UncAD通过引入在线地图不确定性,提升自动驾驶安全性,减少碰撞和冲突率。

Journal ref 2025 IEEE International Conference on Robotics and Automation (ICRA)

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.18878 2025-12-23 cs.CV cs.AI 62%

CrashChat: A Multimodal Large Language Model for Multitask Traffic Crash Video Analysis

CrashChat: 一种多模态大语言模型用于多任务交通事故视频分析

Kaidi Liang, Ke Li, Xianbiao Hu, Ruwen Qin

机构 * Stony Brook University(石溪大学) The Pennsylvania State University(宾夕法尼亚州立大学)

专题命中 端到端驾驶 :autonomous driving(abstract);分类 cs.CV、cs.AI

AI总结 CrashChat是一种多模态大语言模型,用于多任务交通事故视频分析,通过任务解耦和分组策略提升事故识别、定位等任务的性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.22714 2025-12-23 cs.DC cs.LG cs.PF 50%

Libra: Unleashing GPU Heterogeneity for High-Performance Sparse Matrix Multiplication

Libra:释放GPU异构性以实现高性能稀疏矩阵乘法

Jinliang Shi, Shigang Li, Youxuan Xu, Xueying Wang, Rongtian Fu, Zhi Ma, Tong Wu

机构 * Beijing University of Posts and Telecommunications(北京邮电大学)

专题命中 端到端驾驶 :occupancy(abstract)

AI总结 Libra通过高效利用异构GPU资源,显著提升了稀疏矩阵乘法运算的性能,平均比现有基线方法快1.77至2.9倍。

详情

展开后加载摘要…

URL PDF HTML 收藏