自动驾驶

Co-Fusion4D: Spatio-temporal Collaborative Fusion for Robust 3D Object Detection

Co-Fusion4D：面向鲁棒3D目标检测的时空协同融合

Wenxuan Li, Qin Zou, Shoubing Chen, Chi Chen, Yingyi Yang, Qingxiang Meng

机构 * Tsinghua University（清华大学） 纠错

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

AI总结 提出Co-Fusion4D框架，通过当前帧主导-历史帧互补机制和双注意力融合模块，解决BEV检测器中跨帧时空不一致问题，在nuScenes上达到74.9% mAP和75.6% NDS。

Are We Ready for Real-Time LiDAR Semantic Segmentation in Autonomous Driving?

Samir Abou Haidar, Alexandre Chariot, Mehdi Darouich, Cyril Joly, Jean-Emmanuel Deschaud

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

Comments Accepted to IROS 2024 PPNIV Workshop

Exploring Camera Encoder Designs for Autonomous Driving Perception

Barath Lakshmanan, Joshua Chen, Shiyi Lan, Maying Shen, Zhiding Yu, Jose M. Alvarez

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

OccTrack360: 4D Panoptic Occupancy Tracking from Surround-View Fisheye Cameras

OccTrack360: 从环视鱼眼相机实现4D全景占用跟踪

Yongzhi Lin, Kai Luo, Yuanfan Zheng, Hao Shi, Mengfei Duan, Yang Liu, Kailun Yang

机构 * School of Artificial Intelligence and Robotics, Hunan University（人工智能与机器人学院，湖南大学） ； State Key Laboratory of Extreme Photonics and Instrumentation, Zhejiang University（极端光子学与仪器国家重点实验室，浙江大学） ； National Engineering Research Center of Robot Visual Perception and Control Technology, Hunan University（机器人视觉感知与控制技术国家工程研究中心，湖南大学） 纠错

专题命中 感知 ：occupancy(title,abstract)；autonomous driving(abstract)；分类 cs.RO、cs.CV、eess.IV

AI总结 OccTrack360提出新的4D全景占用跟踪基准及FoSOcc框架，解决鱼眼成像中的球面投影和体素定位问题，提升占用跟踪性能。

Comments Accepted to IEEE/RSJ IROS 2026. The benchmark and source code will be made publicly available at https://github.com/YouthZest-Lin/OccTrack360

NRSeg: Noise-Resilient Learning for BEV Semantic Segmentation via Driving World Models

NRSeg: 通过驾驶世界模型实现噪声鲁棒的BEV语义分割学习

Siyu Li, Fei Teng, Yihong Cao, Kailun Yang, Zhiyong Li, Yaonan Wang

机构 * School of Artificial Intelligence and Robotics and the National Engineering Research Center of Robot Visual Perception and Control Technology, Hunan University（人工智能与机器人学院和机器人视觉感知与控制技术国家工程研究中心，湖南大学） 纠错

专题命中 感知 ：BEV(title,abstract)；autonomous driving(abstract)；分类 cs.RO、cs.CV、eess.IV

AI总结 NRSeg通过驾驶世界模型生成的合成数据增强BEV语义分割学习，提出PGCM、BiDPP和HLSE模块以提升模型鲁棒性和分割性能。

Comments Accepted to IEEE Transactions on Image Processing (TIP). The source code will be made publicly available at https://github.com/lynn-yu/NRSeg

A Unified Perception-Language-Action Framework for Adaptive Autonomous Driving

Yi Zhang, Erik Leo Haß, Kuo-Yi Chao, Nenad Petrovic, Yinglei Song, Chengdong Wu, Alois Knoll

机构 * Chair of Robotics, Artificial Intelligence and Embedded Systems Technical University of Munich (TUM)（机器人、人工智能与嵌入系统教授席 Technical University of Munich） 纠错

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

LiDAR-based End-to-end Temporal Perception for Vehicle-Infrastructure Cooperation

Zhenwei Yang, Jilei Mao, Wenxian Yang, Yibo Ai, Yu Kong, Haibao Yu, Weidong Zhang

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

Comments 13 pages, 7 figures

NextStop: An Improved Tracker For Panoptic LIDAR Segmentation Data

Nirit Alkalay, Roy Orfaig, Ben-Zion Bobrovsky

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

Robusto-1 Dataset: Comparing Humans and VLMs on real out-of-distribution Autonomous Driving VQA from Peru

Dunant Cusipuma, David Ortega, Victor Flores-Benites, Arturo Deza

专题命中 感知 ：autonomous driving(title)；self-driving(abstract)；occupancy(abstract)；分类 cs.RO、cs.CV、cs.AI

Comments A pre-print. 26 pages. Link to Code + Data: https://huggingface.co/datasets/Artificio/robusto-1

CarFormer: Self-Driving with Learned Object-Centric Representations

Shadi Hamdan, Fatma Güney

专题命中 感知 ：self-driving(title,abstract)；BEV(abstract)；分类 cs.RO、cs.CV、cs.AI

Comments Accepted to ECCV 2024, code and the pre-trained models can be found at https://kuis-ai.github.io/CarFormer/

Improved LiDAR Odometry and Mapping using Deep Semantic Segmentation and Novel Outliers Detection

Mohamed Afifi, Mohamed ElHelw

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

BM2CP: Efficient Collaborative Perception with LiDAR-Camera Modalities

Binyu Zhao, Wei Zhang, Zhaonian Zou

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

Comments 14 pages, 8 figures. Accepted by CoRL 2023

AdvSim: Generating Safety-Critical Scenarios for Self-Driving Vehicles

Jingkang Wang, Ava Pun, James Tu, Sivabalan Manivasagam, Abbas Sadat, Sergio Casas, Mengye Ren, Raquel Urtasun

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

Comments CVPR 2021. Corrected typos in the adversarial objective

3D Object Detection for Autonomous Driving: A Comprehensive Survey

Jiageng Mao, Shaoshuai Shi, Xiaogang Wang, Hongsheng Li

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

Comments Accepted to International Journal of Computer Vision (IJCV). Project page is at https://github.com/PointsCoder/Awesome-3D-Object-Detection-for-Autonomous-Driving

Sparse Cross-scale Attention Network for Efficient LiDAR Panoptic Segmentation

Shuangjie Xu, Rui Wan, Maosheng Ye, Xiaoyi Zou, Tongyi Cao

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

Comments Accepted by the Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI-22)

A Pedestrian Detection and Tracking Framework for Autonomous Cars: Efficient Fusion of Camera and LiDAR Data

Muhammad Mobaidul Islam, Abdullah Al Redwan Newaz, Ali Karimoddini

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

Lidar based Detection and Classification of Pedestrians and Vehicles Using Machine Learning Methods

Farzad Shafiei Dizaji

专题命中 感知 ：LiDAR(title,abstract)；self-driving(abstract)；分类 cs.RO、cs.CV、eess.IV

TiG-BEV: Multi-view BEV 3D Object Detection via Target Inner-Geometry Learning

Peixiang Huang, Li Liu, Renrui Zhang, Song Zhang, Xinli Xu, Baichao Wang, Guoyi Liu

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

Comments Code link: https://github.com/ADLab3Ds/TiG-BEV

WILD SAM: A Simulated-and-Real Data Augmentation for Autonomous Driving Perception under Challenging Weather

WILD SAM：面向自动驾驶感知的模拟与现实数据增强方法

Hamed Khatounabadi, Xiaohu Lu, Hayder Radha

机构 * Electrical and Computer Engineering（电气与计算机工程） ； Michigan State University（密歇根州立大学） 纠错

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

AI总结 本文提出WILD SAM方法，通过伪标签去噪和模拟训练缓解恶劣天气导致的领域偏移问题，实验表明其在Four Seasons数据集上提升了AP至13%。

JarvisIR: Elevating Autonomous Driving Perception with Intelligent Image Restoration

Yunlong Lin, Zixu Lin, Haoyu Chen, Panwang Pan, Chenxin Li, Sixiang Chen, Yeying Jin, Wenbo Li, Xinghao Ding

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

Comments 25 pages, 15 figures

AdvSwap: Covert Adversarial Perturbation with High Frequency Info-swapping for Autonomous Driving Perception

Yuanhao Huang, Qinfan Zhang, Jiandong Xing, Mengyue Cheng, Haiyang Yu, Yilong Ren, Xiao Xiong

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

Comments 27th IEEE International Conference on Intelligent Transportation Systems (ITSC)

Dynamic Object Detection and Tracking in Construction: A Fisheye Camera and LiDAR Sensor Fusion Model

建筑中的动态目标检测与跟踪：一种鱼眼相机与激光雷达传感器融合模型

Yilong Chen, Huili Huang, Yong K. Cho

机构 * Georgia Institute of Technology（佐治亚理工学院） 纠错

专题命中 感知 ：LiDAR(title,abstract)；occupancy(abstract)；分类 cs.RO、cs.CV

AI总结 针对建筑等复杂环境中机器人动态目标检测与跟踪问题，提出融合鱼眼相机与激光雷达传感器的框架，通过在配准点云里识别移动物体、投影坐标分配语义标签并结合图像检测更新卡尔曼滤波器观测，具有高精度、简单且鲁棒的特点。

Comments 4 pages, 8 figures, submitted to IEEE International Conference on Robotics and Automation (ICRA) 2025 Future of Construction Workshop

ATN3D: Density-Aware LiDAR-Radar Early 3D Object Detection Under Extreme Sparsity

ATN3D：面向极端稀疏性的密度感知激光雷达-雷达早期3D目标检测

Debojyoti Biswas, Xianbiao Hu

机构 * University of California, Berkeley（加州大学伯克利分校） ； Tsinghua University（清华大学） 纠错

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

AI总结 针对远距离稀疏感知下早期融合丢失信息、通道监督不均衡的问题，提出ATN3D框架，通过密度感知融合、占用门控邻域聚合、证据条件通道自注意力和距离感知损失，在VoD数据集上显著提升远距离检测性能。

UnsOcc: 3D Semantic Occupancy Prediction in Unstructured Scene via Rendering Fusion

UnsOcc：非结构化场景下基于渲染融合的3D语义占用预测

Ye Wu, Ruiqi Song, Baiyong Ding, Nanxin Zeng, Junjie Cheng, Yunfeng Ai

机构 * School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院） ； Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所） ； Waytous Inc.（Waytous公司） 纠错

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

AI总结 提出UnsOcc多模态框架，通过渲染融合模块和基于高斯溅射的细节感知辅助监督，解决非结构化场景中跨模态融合困难与长尾分布问题，在露天矿和nuScenes数据集上超越现有方法。

Comments 8 pages

123D: Unifying Multi-Modal Autonomous Driving Data at Scale

123D：规模化统一多模态自动驾驶数据

Daniel Dauner, Valentin Charraut, Bastian Berle, Tianyu Li, Long Nguyen, Jiabao Wang, Changhui Jing, Maximilian Igl, Holger Caesar, Boris Ivanovic, Yiyi Liao, Andreas Geiger, Kashyap Chitta

机构 * KE:SAI ； University of Tübingen（图宾根大学） ； Tübingen AI Center（图宾根人工智能中心） ； NVIDIA Research（NVIDIA研究） ； Valeo Brain（法雷奥大脑） ； OpenDriveLab at Shanghai Innovation Institute（上海创新研究院自动驾驶实验室） ； Zhejiang University（浙江大学） ； Delft University of Technology（代尔夫特理工大学） 纠错

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

AI总结 123D通过单一API统一多模态自动驾驶数据，解决数据碎片化、同步难题，并提供分析工具，支持跨数据集3D目标检测和强化学习规划应用。

Feasibility of Indoor Frame-Wise Lidar Semantic Segmentation via Distillation from Visual Foundation Model

基于视觉基础模型的知识蒸馏的室内点云语义分割可行性

Haiyang Wu, Juan J. Gonzales Torres, George Vosselman, Ville Lehtola

机构 * 1 Department of Earth Observation Science, Faculty of Geo-Information Science ； Earth Observation (ITC), University of Twente, 7522 NB Enschede, The Netherlands 纠错

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

AI总结 本文探讨了通过知识蒸馏从视觉基础模型中学习的方法，用于室内点云语义分割，展示了在无人工标注的情况下，该方法在室内场景中的有效性。

Geometry-Aware Cross Modal Alignment for Light Field-LiDAR Semantic Segmentation

面向几何的多模态对齐用于光场-激光雷达语义分割

Jie Luo, Yuxuan Jiang, Xin Jin, Mingyu Liu, Yihui Fan

机构 * Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院） 纠错

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

AI总结 本文提出融合光场数据和点云数据的多模态语义分割网络，通过特征补全和深度感知模块提升复杂场景下的分割性能，优于单模态方法。

RQR3D: Reparametrizing the regression targets for BEV-based 3D object detection

RQR3D：基于鸟瞰图的3D目标检测的回归目标重新参数化

Ozsel Kilinc, Cem Tarhan

机构 * Amazon Lab 126（亚马逊126实验室） ； Togg/Trutek AI Team（Togg/Trutek人工智能团队） 纠错

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

AI总结 本文提出RQR3D方法，通过重新参数化回归目标将旋转目标检测转化为关键点回归任务，实现高效且准确的3D目标检测，适用于自动驾驶场景。

Comments To appear in proceedings of CVPR Findings 2026

Benchmarking Multi-View BEV Object Detection with Mixed Pinhole and Fisheye Cameras

基于混合针孔和鱼眼相机的多视图鸟眼图物体检测基准测试

Xiangzhong Liu, Hao Shen

机构 * Machine Learning Group, fortiss GmbH（fortiss GmbH机器学习组） 纠错

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

AI总结 本文提出混合相机配置下的多视图鸟眼图检测基准，通过转换KITTI-360为nuScenes格式，评估了三种BEV架构在不同策略下的性能，证明投影自由架构更抗鱼眼畸变。

Comments 8 pages,5 figures, IEEE International Conference on Robotics and Automation (ICRA),Vienna, Austria, 1-5 June 2026

INSIGHT: Enhancing Autonomous Driving Safety through Vision-Language Models on Context-Aware Hazard Detection and Edge Case Evaluation

洞察：通过基于视觉-语言模型的上下文感知危险检测与边缘案例评估提升自动驾驶安全性

Dianwei Chen, Zifan Zhang, Lei Cheng, Yuchen Liu, Xianfeng Terry Yang

机构 * University of Maryland（马里兰大学） ； North Carolina State University（北卡罗来纳州立大学） 纠错

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

AI总结 本文提出INSIGHT框架，通过多模态数据融合提升自动驾驶中危险检测和边缘案例评估的准确性和泛化能力，实验表明在BDD100K数据集上显著提高了危险预测的准确性和鲁棒性。