arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~

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。

2026-03-23 至 2026-03-23 共收录 5 信号源:cs.RO, cs.CV, eess.IV, cs.AI

1. 感知 5 篇

2511.08015 2026-03-23 cs.CV cs.AI 84%

Invisible Triggers, Visible Threats! Road-Style Adversarial Creation Attack for Visual 3D Detection in Autonomous Driving

不可见的触发器,可见的威胁!面向自动驾驶视觉3D检测的路式对抗生成攻击

Jian Wang, Lijun He, Yixing Yong, Haixia Bi, Fan Li

专题命中 感知 :autonomous driving(title,abstract);LiDAR(abstract);分类 cs.CV、cs.AI

AI总结 本文提出AdvRoad,通过生成自然道路风格的对抗性贴纸,提升自动驾驶系统在视觉3D检测中的鲁棒性,实验表明其在不同检测器和场景中均有效。

Comments Accepted by the AAAI 2026 (Main Track)

Journal ref AAAI Conference on Artificial Intelligence, 40(12), 9903-9911. (2026)

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.02245 2026-03-23 cs.RO 70%

CoInfra: A Large-Scale Cooperative Infrastructure Perception System and Dataset for Vehicle-Infrastructure Cooperation in Adverse Weather

CoInfra:一种大规模协作基础设施感知系统及数据集,用于恶劣天气下的车-基础设施协作

Minghao Ning, Yufeng Yang, Keqi Shu, Shucheng Huang, Jiaming Zhong, Maryam Salehi, Mahdi Rahmani, Jiaming Guo, Yukun Lu, Chen Sun, Aladdin Saleh, Ehsan Hashemi, Amir Khajepour

机构 * Department of Mechanical and Mechatronics Engineering, University of Waterloo(滑铁卢大学机械与机电工程系) Department of Mechanical Engineering, University of New Brunswick(新不伦瑞克大学机械工程系) Department of Data and Systems Engineering, University of Hong Kong(香港大学数据与系统工程系) Technology Partnerships and Innovations, Rogers Communications, Canada Inc.(罗杰斯通讯公司技术创新部) Department of Mechanical Engineering, University of Alberta(阿尔伯塔大学机械工程系)

专题命中 感知 :autonomous driving(abstract);LiDAR(abstract);分类 cs.RO

AI总结 本文提出CoInfra系统,通过14个路侧传感器节点和5G网络实现多节点协同感知,涵盖8个节点的环形城市交叉口在四种天气条件下的数据,验证基础设施感知在复杂交通场景中的安全提升作用。

Comments This paper has been submitted to the Transportation Research Part C: Emerging Technologies for review

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.20188 2026-03-23 cs.CV 57%

Wildfire Spread Scenarios: Increasing Sample Diversity of Segmentation Diffusion Models with Training-Free Methods

野火蔓延场景:通过无训练方法增加分割扩散模型的样本多样性

Sebastian Gerard, Josephine Sullivan

机构 * KTH Royal Institute of Technology(皇家理工学院)

专题命中 感知 :autonomous driving(abstract);分类 cs.CV

AI总结 本文提出通过无训练方法提升分割扩散模型样本多样性,验证了粒子引导和SPELL等技术在野火蔓延场景中的有效性,提升了HM IoU指标。

Comments Accepted at NLDL 2026. This version contains small corrections compared to the initial publication, see appendix for details

Journal ref Proceedings of the 7th Northern Lights Deep Learning Conference (NLDL), PMLR, Jan. 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.19776 2026-03-23 cs.CV 57%

ReManNet: A Riemannian Manifold Network for Monocular 3D Lane Detection

ReManNet:一种用于单目3D车道检测的黎曼流形网络

Chengzhi Hong, Bijun Li

机构 * State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing(信息工程测绘遥感国家重点实验室)

专题命中 感知 :BEV(abstract);分类 cs.CV

AI总结 本文提出ReManNet,通过将道路视为三维空间中的光滑2D流形,利用黎曼流形上的高斯描述符和轻量级门机制,提升单目3D车道检测的几何一致性与形状对齐性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.19308 2026-03-23 cs.LG cs.AI cs.MA 57%

GT-Space: Enhancing Heterogeneous Collaborative Perception with Ground Truth Feature Space

GT-Space:通过地面真实特征空间增强异构协作感知

Wentao Wang, Haoran Xu, Guang Tan

机构 * Sun Yat-sen University, Shenzhen Campus(中山大学深圳校区) Peng Cheng Laboratory (PCL)(鹏城实验室)

专题命中 感知 :autonomous driving(abstract);分类 cs.AI

AI总结 本文提出GT-Space框架,通过构建地面真实标签的共同特征空间,实现异构agent的统一特征对齐,避免了传统方法中需要重新训练编码器或设计解释器模块的局限,提升了多agent协作感知的准确性和鲁棒性。

详情

展开后加载摘要…

URL PDF HTML 收藏