自动驾驶 - arXivDaily 专题

2311.06796 2023-11-14 cs.CV 70%

Deep Perspective Transformation Based Vehicle Localization on Bird's Eye View

Abtin Mahyar, Hossein Motamednia, Dara Rahmati

专题命中 BEV与占用：self-driving(abstract)；BEV(abstract)；分类 cs.CV

Comments 7 pages, 2 figures

2311.02503 2023-11-07 cs.CV 70%

MapSeg: Segmentation guided structured model for online HD map construction

Mingchao Jiang, Yin Cheng, Linghai Liu

专题命中 BEV与占用：autonomous driving(abstract)；BEV(abstract)；分类 cs.CV

2212.07271 2023-08-30 cs.RO 70%

Gaussian Process Mapping of Uncertain Building Models with GMM as Prior

Qianqian Zou, Claus Brenner, Monika Sester

专题命中 BEV与占用：LiDAR(abstract)；occupancy(abstract)；分类 cs.RO

2304.03650 2023-08-21 cs.CV 70%

A Cross-Scale Hierarchical Transformer with Correspondence-Augmented Attention for inferring Bird's-Eye-View Semantic Segmentation

Naiyu Fang, Lemiao Qiu, Shuyou Zhang, Zili Wang, Kerui Hu, Kang Wang

专题命中 BEV与占用：autonomous driving(abstract)；BEV(abstract)；分类 cs.CV

2308.07732 2023-08-16 cs.CV 70%

UniTR: A Unified and Efficient Multi-Modal Transformer for Bird's-Eye-View Representation

Haiyang Wang, Hao Tang, Shaoshuai Shi, Aoxue Li, Zhenguo Li, Bernt Schiele, Liwei Wang

专题命中 BEV与占用：autonomous driving(abstract)；BEV(abstract)；分类 cs.CV

Comments Accepted by ICCV2023

2306.09700 2023-06-19 cs.CV 70%

End-to-End Vectorized HD-map Construction with Piecewise Bezier Curve

Limeng Qiao, Wenjie Ding, Xi Qiu, Chi Zhang

专题命中 BEV与占用：autonomous driving(abstract)；BEV(abstract)；分类 cs.CV

Comments Accepted by CVPR2023

2306.04540 2023-06-08 cs.CV 70%

NeMO: Neural Map Growing System for Spatiotemporal Fusion in Bird's-Eye-View and BDD-Map Benchmark

Xi Zhu, Xiya Cao, Zhiwei Dong, Caifa Zhou, Qiangbo Liu, Wei Li, Yongliang Wang

专题命中 BEV与占用：autonomous driving(abstract)；BEV(abstract)；分类 cs.CV

2305.13635 2023-05-24 cs.RO 70%

Exploiting Radio Fingerprints for Simultaneous Localization and Mapping

Ran Liu, Billy Pik Lik Lau, Khairuldanial Ismail, Achala Chathuranga, Chau Yuen, Simon X. Yang, Yong Liang Guan, Shiwen Mao, U-Xuan Tan

专题命中 BEV与占用：LiDAR(abstract)；occupancy(abstract)；分类 cs.RO

Comments This paper has been accepted by IEEE Pervasive Computing with DOI: 10.1109/MPRV.2023.3274770

2207.08536 2023-03-21 cs.CV 70%

UniFusion: Unified Multi-view Fusion Transformer for Spatial-Temporal Representation in Bird's-Eye-View

Zequn Qin, Jingyu Chen, Chao Chen, Xiaozhi Chen, Xi Li

专题命中 BEV与占用：autonomous driving(abstract)；BEV(abstract)；分类 cs.CV

2302.13540 2023-02-28 cs.CV 70%

OccDepth: A Depth-Aware Method for 3D Semantic Scene Completion

Ruihang Miao, Weizhou Liu, Mingrui Chen, Zheng Gong, Weixin Xu, Chen Hu, Shuchang Zhou

专题命中 BEV与占用：autonomous driving(abstract)；occupancy(abstract)；分类 cs.CV

2208.09394 2022-08-22 cs.CV 70%

PersDet: Monocular 3D Detection in Perspective Bird's-Eye-View

Hongyu Zhou, Zheng Ge, Weixin Mao, Zeming Li

专题命中 BEV与占用：autonomous driving(abstract)；BEV(abstract)；分类 cs.CV

2204.07623 2022-04-19 cs.RO 70%

Active Mapping via Gradient Ascent Optimization of Shannon Mutual Information over Continuous SE(3) Trajectories

Arash Asgharivaskasi, Shumon Koga, Nikolay Atanasov

专题命中 BEV与占用：LiDAR(abstract)；occupancy(abstract)；分类 cs.RO

2003.13883 2021-10-19 cs.RO 70%

Autonomous Cave Surveying with an Aerial Robot

Wennie Tabib, Kshitij Goel, John Yao, Curtis Boirum, Nathan Michael

专题命中 BEV与占用：LiDAR(abstract)；occupancy(abstract)；分类 cs.RO

Comments 17 pages, 14 figures; accepted for publication in IEEE Transactions on Robotics (TRO 2021) and adds additional experimental results

2109.14065 2021-09-30 cs.RO 70%

Localization of a Smart Infrastructure Fisheye Camera in a Prior Map for Autonomous Vehicles

Subodh Mishra, Armin Parchami, Enrique Corona, Punarjay Chakravarty, Ankit Vora, Devarth Parikh, Gaurav Pandey

专题命中 BEV与占用：BEV(abstract)；LiDAR(abstract)；分类 cs.RO

Comments Submitted to ICRA 2022

2107.06711 2021-07-15 cs.CV 70%

PDC: Piecewise Depth Completion utilizing Superpixels

Dennis Teutscher, Patrick Mangat, Oliver Wasenmüller

专题命中 BEV与占用：autonomous driving(abstract)；LiDAR(abstract)；分类 cs.CV

Comments This paper has been accepted at IEEE Intelligent Transportation Systems Conference (ITSC), 2021

2105.12182 2021-07-02 cs.RO 70%

Self-Calibration of the Offset Between GPS and Semantic Map Frames for Robust Localization

Wei-Kang Tseng, Angela P. Schoellig, Timothy D. Barfoot

专题命中 BEV与占用：self-driving(abstract)；LiDAR(abstract)；分类 cs.RO

Comments Accepted for publication in CRV 2021; corrected reference 4

2010.16322 2021-03-30 cs.RO cs.AI cs.CV cs.LG eess.IV 70%

DeepWay: a Deep Learning Waypoint Estimator for Global Path Generation

Vittorio Mazzia, Francesco Salvetti, Diego Aghi, Marcello Chiaberge

专题命中 BEV与占用：occupancy(abstract)；分类 cs.RO、cs.CV、eess.IV

Comments Submitted to Computers and Electronics in Agriculture

Journal ref Volume 184, May 2021, 106091

1808.08685 2020-02-21 cs.CV 70%

HMS-Net: Hierarchical Multi-scale Sparsity-invariant Network for Sparse Depth Completion

Zixuan Huang, Junming Fan, Shenggan Cheng, Shuai Yi, Xiaogang Wang, Hongsheng Li

专题命中 BEV与占用：autonomous driving(abstract)；LiDAR(abstract)；分类 cs.CV

Comments IEEE Trans. on Image Processing

1909.04631 2020-01-28 cs.RO 70%

Bayesian Spatial Kernel Smoothing for Scalable Dense Semantic Mapping

Lu Gan, Ray Zhang, Jessy W. Grizzle, Ryan M. Eustice, Maani Ghaffari

专题命中 BEV与占用：LiDAR(abstract)；occupancy(abstract)；分类 cs.RO

1908.07085 2019-08-21 cs.CV 70%

BoxNet: A Deep Learning Method for 2D Bounding Box Estimation from Bird's-Eye View Point Cloud

Ehsan Nezhadarya, Yang Liu, Bingbing Liu

专题命中 BEV与占用：BEV(abstract)；LiDAR(abstract)；分类 cs.CV

1807.01262 2019-05-07 cs.RO 70%

Tackling Occlusions & Limited Sensor Range with Set-based Safety Verification

Piotr Franciszek Orzechowski, Annika Meyer, Martin Lauer

专题命中 BEV与占用：occupancy(abstract)；trajectory planning(abstract)；分类 cs.RO

Journal ref 2018 21st International Conference on Intelligent Transportation Systems (ITSC)

2606.31919 2026-07-01 cs.RO cs.AI cs.CV 新提交 67%

MVP-Nav: Multi-layer Value Map Planner Navigator

MVP-Nav: 多层价值地图规划导航器

Wenyuan Xie, Shaokai Wu, Yijin Zhou, Yanbiao Ji, Guodong Zhang, Bayram Bayramli, Qiuchang Li, Xunchu Zhou, Yue Ding, Hongtao Lu

机构 * Shanghai Jiao Tong University（上海交通大学）

专题命中 BEV与占用：occupancy(abstract)；分类 cs.RO、cs.CV、cs.AI

AI总结针对零样本目标导航中缺乏深度信息导致的物理不确定性，提出MVP-Nav框架，通过3D基础模型重建物理占用并构建多层价值地图，实现语义与物理约束的统一规划，达到最先进性能。

2606.27250 2026-06-26 cs.CR cs.DC 新提交 67%

Tilikum: Transaction Fair Ordering on a DAG without Weak Edges

Tilikum: 无需弱边的DAG上交易公平排序

Giulio Segalini, Yigit Çolakoğlu, Marko Putnik, Jérémie Decouchant

专题命中 BEV与占用：BEV(abstract,abstract_cn)

AI总结提出Tilikum，一种基于DAG的账本协议，通过中位数时间戳聚合实现交易公平排序，无需弱边，在抵抗重排序攻击的同时实现高达39倍吞吐量提升。

2606.26932 2026-06-26 eess.SY cs.SY 新提交 67%

Battery thermal-safety reserve erosion by mandatory cabin ventilation in shared-cooling electric vehicles

共享冷却电动汽车中强制座舱通风导致的电池热安全储备侵蚀

Yifan Wang

专题命中 BEV与占用：BEV(abstract,abstract_cn)

AI总结针对共享冷却系统中强制通风消耗电池热储备的问题，提出一种结合物理引导科学机器学习代理、电网连接出发热储备、空气质量定价通风分配和双控制屏障函数的预测控制器，在保持电池温度、CO₂浓度和舒适性的同时降低能耗20%。

Comments 19 pages, 5 figures

2606.01994 2026-06-04 cs.DB 67%

Real-world and simulated thermal data from 960 residential multi-zone buildings in Central Europe

来自中欧960个住宅多区域建筑的真实世界和模拟热数据

Fabian Raisch, Matthias Kersken, Markus Male, Benjamin Tischler

专题命中 BEV与占用：occupancy(abstract,abstract_cn)

AI总结本文介绍了ThermBuild数据集，包含两栋独户住宅的真实测量数据和958个TRNSYS建筑模型的模拟数据，用于数据驱动的热动力学建模，支持节能控制、故障检测与诊断。

2308.10313 2026-05-12 econ.GN q-fin.EC 67%

Exploring the Role of Perceived Range Anxiety in Adoption Behavior of Plug-in Electric Vehicles

探索感知行驶焦虑在插电式电动汽车采纳行为中的作用

Fatemeh Nazari, Abolfazl Mohammadian

专题命中 BEV与占用：BEV(abstract,abstract_cn)

AI总结本文通过嵌套logit模型探讨行驶焦虑对电动汽车采纳行为的影响，发现对纯电动车的偏好受行驶焦虑影响，但对插电式混合动力车无显著影响。

Comments 27 pages, 3 figures, 5 tables. Journal of Smart Cities and Society. 2026;0(0)

2604.20764 2026-04-23 eess.SY cs.LG cs.SY 67%

Personalized electric vehicle energy consumption estimation framework that integrates driver behavior with map data

个性化电动汽车能耗估计框架：整合驾驶员行为与地图数据

Sreechakra Vasudeva Raju Rachavelpula, Sangwhan Cha

机构 * Department of Computer and Information Sciences, Harrisburg University of Science and Technology（计算机与信息科学系，哈里斯堡大学科学与技术学院）

专题命中 BEV与占用：BEV(abstract,abstract_cn)

AI总结本文提出一种整合地图上下文特征与驾驶员特定速度预测及物理能耗模型的个性化电动车能耗估计框架，通过结合路线选择、道路特征处理、规则参考速度生成器、基于PID控制器的车辆动力学模拟器和双向LSTM模型，实现准确的能耗和SOC轨迹预测。

Comments 28 pages, 19 figures

2604.15495 2026-04-20 cs.AI cs.CV cs.HC cs.RO 67%

GIST: Multimodal Knowledge Extraction and Spatial Grounding via Intelligent Semantic Topology

GIST：通过智能语义拓扑进行多模态知识提取与空间定位

Shivendra Agrawal, Bradley Hayes

机构 * University of Colorado Boulder（科罗拉多大学博尔德分校）

专题命中 BEV与占用：occupancy(abstract)；分类 cs.RO、cs.CV、cs.AI

AI总结 GIST通过智能语义拓扑提取多模态知识，构建语义标注的导航拓扑，实现复杂环境中的空间定位与人类-AI交互任务。

2504.06355 2026-04-20 cs.LG 67%

An Information-Geometric Approach to Artificial Curiosity

基于信息几何的人工好奇心方法

Alexander Nedergaard, Pablo A. Morales

机构 * Institute of Neuroinformatics University of Zurich and ETH Zurich（神经信息学研究所苏黎世大学和苏黎世联邦理工学院）

专题命中 BEV与占用：occupancy(abstract,abstract_cn)

AI总结本文提出基于信息几何的框架，通过信息单调性和环境交互不变性约束内在奖励为严格凹函数，从而实现探索与利用的平衡，整合了基础探索方法。

Comments Comments: 24 pages, 2 figures; version accepted for publication at AISTATS 2026

2601.14477 2026-04-14 cs.CV cs.AI eess.IV 67%

XD-MAP: Cross-Modal Domain Adaptation via Semantic Parametric Maps for Scalable Training Data Generation

XD-MAP：通过语义参数地图实现跨模态领域适应以实现可扩展的训练数据生成

Frank Bieder, Hendrik Königshof, Haohao Hu, Fabian Immel, Yinzhe Shen, Jan-Hendrik Pauls, Christoph Stiller

机构 * KIT Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）； FZI Research Center for Information Technology（FZI信息技术研究中心）

专题命中 BEV与占用：LiDAR(abstract)；分类 cs.CV、eess.IV、cs.AI

AI总结本文提出XD-MAP，通过语义参数地图将图像数据集中的传感器特定知识转移到LiDAR领域，无需手动标注即可提升多模态领域适应性能。

Comments 10 pages, 7 figures, 3 tables, accepted at CVPRW

1. BEV与占用 3758 篇

Deep Perspective Transformation Based Vehicle Localization on Bird's Eye View

MapSeg: Segmentation guided structured model for online HD map construction

Gaussian Process Mapping of Uncertain Building Models with GMM as Prior

A Cross-Scale Hierarchical Transformer with Correspondence-Augmented Attention for inferring Bird's-Eye-View Semantic Segmentation

UniTR: A Unified and Efficient Multi-Modal Transformer for Bird's-Eye-View Representation

End-to-End Vectorized HD-map Construction with Piecewise Bezier Curve

NeMO: Neural Map Growing System for Spatiotemporal Fusion in Bird's-Eye-View and BDD-Map Benchmark

Exploiting Radio Fingerprints for Simultaneous Localization and Mapping

UniFusion: Unified Multi-view Fusion Transformer for Spatial-Temporal Representation in Bird's-Eye-View

OccDepth: A Depth-Aware Method for 3D Semantic Scene Completion

PersDet: Monocular 3D Detection in Perspective Bird's-Eye-View

Active Mapping via Gradient Ascent Optimization of Shannon Mutual Information over Continuous SE(3) Trajectories

Autonomous Cave Surveying with an Aerial Robot

Localization of a Smart Infrastructure Fisheye Camera in a Prior Map for Autonomous Vehicles

PDC: Piecewise Depth Completion utilizing Superpixels

Self-Calibration of the Offset Between GPS and Semantic Map Frames for Robust Localization

DeepWay: a Deep Learning Waypoint Estimator for Global Path Generation

HMS-Net: Hierarchical Multi-scale Sparsity-invariant Network for Sparse Depth Completion

Bayesian Spatial Kernel Smoothing for Scalable Dense Semantic Mapping

BoxNet: A Deep Learning Method for 2D Bounding Box Estimation from Bird's-Eye View Point Cloud

Tackling Occlusions & Limited Sensor Range with Set-based Safety Verification

MVP-Nav: Multi-layer Value Map Planner Navigator

Tilikum: Transaction Fair Ordering on a DAG without Weak Edges

Battery thermal-safety reserve erosion by mandatory cabin ventilation in shared-cooling electric vehicles

Real-world and simulated thermal data from 960 residential multi-zone buildings in Central Europe

Exploring the Role of Perceived Range Anxiety in Adoption Behavior of Plug-in Electric Vehicles

Personalized electric vehicle energy consumption estimation framework that integrates driver behavior with map data

GIST: Multimodal Knowledge Extraction and Spatial Grounding via Intelligent Semantic Topology

An Information-Geometric Approach to Artificial Curiosity

XD-MAP: Cross-Modal Domain Adaptation via Semantic Parametric Maps for Scalable Training Data Generation