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。

共收录 1476 信号源:cs.RO, cs.CV, eess.IV, cs.AI

1. 仿真评测 1476 篇

2607.23537 2026-07-28 cs.AI 新提交 70%

ObsDriveBench: Benchmarking Multimodal Understanding under Adverse Weather with Observability Awareness

ObsDriveBench:具有可观测性意识的恶劣天气下多模态理解基准测试

Qiao Yan, Yihan Wang, Zhenghao Xing, Jiaqi Xu, Pheng-Ann Heng

机构 * Department of Computer Science and Engineering, The Chinese University of Hong Kong(香港中文大学计算机科学与工程系) Institute of Medical Intelligence and XR, The Chinese University of Hong Kong(香港中文大学医学智能与扩展现实研究所)

专题命中 仿真评测 :autonomous driving(abstract);LiDAR(abstract);分类 cs.AI

AI总结 研究恶劣天气下视觉语言模型在多模态输入时的表现,引入ObsDriveBench基准测试,通过可观测性元标注等构建含多类问题的测试集,实验发现现有模型性能降,还引入ObsDrive模型提升其在多方面的鲁棒性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.22078 2026-07-27 cs.CV 新提交 70%

CommandLM: Data driven behavior level descriptor for ego vehicles

CommandLM:用于自动驾驶车辆的数据驱动行为级描述符

Boris Tokic, Constantin Selzer, Fabian B. Flohr

机构 * Munich University of Applied Sciences(慕尼黑应用技术大学)

专题命中 仿真评测 :autonomous driving(abstract);LiDAR(abstract);分类 cs.CV

AI总结 研究针对自动驾驶系统中可解释行为级决策需求,提出多模态大语言模型CommandLM,通过融合多传感器数据生成行为描述,经特定训练和适配器处理,实验表现优于基线,人工评估显示其输出可助力行为审计,实现高效透明的行为级理解。

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.08716 2026-07-22 cs.CV 版本更新 70%

Great X: A Unified Multi-Modal Simulator Bridging the Sim2Real Gap for 6G

Great X:一种统一的多模态模拟器,弥合6G的模拟与现实差距

Yuan Gao, Kongwu Huang, Jun Jiang, Shiyi Mu, Shugong Xu

机构 * Shanghai University(上海大学) Xi’an Jiaotong-Liverpool University(西安交通大学利物浦大学)

专题命中 仿真评测 :LiDAR(abstract,abstract_cn);分类 cs.CV

AI总结 针对6G无线研究中多模态数据集收集难题及现有模拟器不足,提出在虚幻引擎实现统一单引擎模拟器Great-X,集成光线追踪等技术,构建含大量同步样本的Great-MCD,实验显示其性能优于现有模拟器及测量数据基线。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.15431 2026-06-16 cs.RO 新提交 70%

A Corridor-Scale CARLA-VISSIM Co-Simulation Framework for Multi-Intersection Urban Traffic

面向多交叉口城市走廊的CARLA-VISSIM联合仿真框架

Sima Ashayer, Austin Haris, Mina Sartipi

机构 * University of Tennessee at Chattanooga(田纳西大学查塔努加分校)

专题命中 仿真评测 :LiDAR(abstract,abstract_cn);分类 cs.RO

AI总结 提出CARLA-VISSIM双向步进同步联合仿真框架,集成微观交通逻辑与高保真3D渲染,在田纳西州查塔努加市MLK大道约15个交叉口走廊上验证,支持混合控制与感知就绪的走廊级交通研究。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.06130 2026-06-05 cs.RO 70%

Towards Realistic 3D Sonar Simulation

面向真实3D声纳仿真

Youssef Attia, Davide Costa, Francesco Wanderlingh, Filippo Campagnaro, Enrico Simetti

机构 * IEEE

专题命中 仿真评测 :LiDAR(abstract,abstract_cn);分类 cs.RO

AI总结 本文提出一种模块化架构,结合GPU加速图形引擎与物理声学传播原理,在NVIDIA Isaac Sim中实现基于Water Linked 3D-15传感器的体积3D声纳模型,并通过硬件在环配置验证其有效性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.04569 2026-06-04 cs.RO 70%

MineXplore: An Open-Source Reinforcement Learning Exploration Benchmark for GNSS-Denied Underground Environment

MineXplore: 面向GNSS拒止地下环境的开源强化学习探索基准

Abhishek S, Badrikanath Praharaj, Sreeram MV

机构 * University of California, Berkeley(加州大学伯克利分校) Stanford University(斯坦福大学)

专题命中 仿真评测 :LiDAR(abstract,abstract_cn);分类 cs.RO

AI总结 提出基于真实矿井数据的开源MuJoCo导航基准MineXplore,通过六阶段管道重建隧道网络,验证了在GNSS拒止、光照退化等极端条件下策略学习的稳定性与可复现性。

Comments 7 pages,11 figures, Submitted to the workshop Xplore:Cross-Disciplinary aspects of Exploration in Robotics, Reinforcement Learning and Search Held at International Conference on Robotics and Automation (ICRA)

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.02370 2026-06-02 cs.RO 70%

A Simulation Platform for Flapping-Wing Vehicles

扑翼飞行器仿真平台

Haichuan Li, Tomi Westerlund

专题命中 仿真评测 :LiDAR(abstract,abstract_cn);分类 cs.RO

AI总结 针对扑翼飞行器仿真与现实差距大的问题,提出FWAV-Sim高保真仿真平台,集成复合气动模型、湍流生成和真实传感器模拟,提升自主系统开发效果。

详情

展开后加载摘要…

URL PDF HTML 收藏
2406.07125 2026-05-21 cs.CR cs.AI cs.LG 70%

CARACAS: vehiCular ArchitectuRe for detAiled Can Attacks Simulation

CARACAS:用于详细CAN攻击模拟的车辆架构

Sadek Misto Kirdi, Nicola Scarano, Franco Oberti, Luca Mannella, Stefano Di Carlo, Alessandro Savino

机构 * Politecnico di Torino, Department of Control(都灵理工大学控制与计算机工程系)

专题命中 仿真评测 :BEV(abstract,abstract_cn);分类 cs.AI

AI总结 本文提出CARACAS,一种用于模拟详细CAN攻击的车辆模型,通过结合Simulink等仿真框架和攻击模型的稳健表示,生成合成数据集以提高IDS的检测能力,重点展示电池电动车的扭矩控制攻击模拟。

Comments 6 pages, 8 figures, TrustAICyberSec workshop - IEEE ISCC 2024

Journal ref Proceeding of the 29th IEEE Symposium on Computers and Communications, ISCC 2024

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.23180 2026-05-19 cs.CV 70%

GaussianDWM: 3D Gaussian Driving World Model for Unified Scene Understanding and Multi-Modal Generation

GaussianDWM: 基于3D高斯场景表示的统一场景理解和多模态生成驱动世界模型

Tianchen Deng, Xuefeng Chen, Yi Chen, Qu Chen, Yuyao Xu, Lijin Yang, Le Xu, Yu Zhang, Bo Zhang, Wuxiong Huang, Hesheng Wang

机构 * Shanghai Jiao Tong University(上海交通大学) Tsinghua University(清华大学) MEGVII Technology(商汤科技) Mach Drive

专题命中 仿真评测 :BEV(abstract,abstract_cn);分类 cs.CV

AI总结 本文提出基于3D高斯表示的统一驱动世界模型框架,实现3D场景理解和多模态生成,并通过语言引导采样策略和双条件生成模型提升生成效果,实验验证其在nuScenes和NuInteract数据集上的优越性能。

Comments Accepted by CVPR 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.24295 2026-04-28 cs.RO 70%

Projected Attainable Speed Space: A Driving Efficiency Metric Connecting Instantaneous Evaluation to Travel Time

投影可达到速度空间:连接即时评估与旅行时间的驾驶效率度量

Xiaohua Zhao, Zhaowei Huang, Chen Chen, Haiyi Yang

机构 * Beijing Key Laboratory of Traffic Engineering, Beijing University of Technology(北京交通工程重点实验室,北京工业大学)

专题命中 仿真评测 :autonomous driving(abstract);self-driving(abstract);分类 cs.RO

AI总结 本文提出投影可达到速度空间(PASS)模型,通过整合运动学和空间交通信息,提供一种统一的驾驶效率评估框架,用于连接即时和旅行层面的分析,验证其在不同时间尺度上的一致性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.17915 2026-04-21 cs.CV 70%

OneDrive: Unified Multi-Paradigm Driving with Vision-Language-Action Models

OneDrive: 统一的多范式驾驶与视觉-语言-动作模型

Yiwei Zhang, Xuesong Chen, Jin Gao, Hanshi Wang, Fudong Ge, Weiming Hu, Shaoshuai Shi, Zhipeng Zhang

机构 * State Key Laboratory of Multimodal Artificial Intelligence Systems, CASIA School of Artificial Intelligence, University of Chinese Academy of Sciences AutoLab, School of Artificial Intelligence, Shanghai Jiao Tong University Voyager Research, Didi Chuxing School of Information Science(多模态人工智能系统国家重点实验室,中国科学院自动化所人工智能学院,中国科学院大学,AutoLab,上海交通大学人工智能学院,Voyager Research,滴滴出行,信息科学与技术学院)

专题命中 仿真评测 :autonomous driving(abstract);trajectory planning(abstract);分类 cs.CV

AI总结 本文提出基于预训练视觉语言模型的统一自动驾驶框架,通过单一Transformer解码器整合异构解码行为,实现多任务联合优化,实验表明在nuScenes和NAVSIM上取得最优性能,且推理效率高。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.16984 2026-04-21 cs.CV 70%

Adverse-to-the-eXtreme Panoptic Segmentation: URVIS 2026 Study and Benchmark

极端恶劣环境全景分割挑战:URVIS 2026研究与基准

Yiting Wang, Nolwenn Peyratout, Tim Brodermann, Jiahui Wang, Yusi Cao, Michele Cazzola, Elie Tarassov, Takuya Kobayashi, Abderrahim Kasmi, Guillaume Allibert, Cédric Demonceaux, Valentina Donzella, Kurt Debattista, Radu Timofte, Zongwei Wu, Christos Sakaridis

机构 * MUSES-AXPS

专题命中 仿真评测 :LiDAR(abstract,abstract_cn);分类 cs.CV

AI总结 本文报告了URVIS 2026挑战赛,首次针对极端恶劣环境下的全景分割,基于MUSES数据集,采用加权全景质量指标评估,总结了挑战设定、基准结果及当前进展与挑战。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.18079 2026-02-23 cs.CR cs.RO 70%

Dynamic Deception: When Pedestrians Team Up to Fool Autonomous Cars

动态欺骗:当行人联手欺骗自动驾驶汽车

Masoud Jamshidiyan Tehrani, Marco Gabriel, Jinhan Kim, Paolo Tonella

机构 * Università della Svizzera italiana(瑞士意大利大学)

专题命中 仿真评测 :autonomous driving(abstract);driving perception(abstract);分类 cs.RO

AI总结 本文提出通过多个动态元素协作放大对抗信号,以引发自动驾驶车辆的系统级故障,展示动态协作在对抗攻击中的有效性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.18238 2026-02-10 cs.CV 70%

CARLA2Real: a tool for reducing the sim2real appearance gap in CARLA simulator

CARLA2Real: 一种用于减少CARLA模拟器中仿真到现实外观差距的工具

Stefanos Pasios, Nikos Nikolaidis

机构 * School of Informatics, Aristotle University of Thessaloniki(信息学院,亚里士多德大学)

专题命中 仿真评测 :autonomous driving(abstract);self-driving(abstract);分类 cs.CV

AI总结 CARLA2Real通过提升仿真数据的真实感,减少仿真到现实的外观差距,生成高质量合成数据用于自动驾驶研究。

Comments 22 pages

Journal ref IEEE Transactions on Intelligent Transportation Systems (2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.15260 2026-01-30 cs.CV 70%

DrivIng: A Large-Scale Multimodal Driving Dataset with Full Digital Twin Integration

DrivIng: 一个具有完整数字孪生集成的大规模多模态驾驶数据集

Dominik Rößle, Xujun Xie, Adithya Mohan, Venkatesh Thirugnana Sambandham, Daniel Cremers, Torsten Schön

机构 * Department of Computer Science and AImotion Bavaria, Technische Hochschule Ingolstadt(计算机科学系和AImotion巴伐利亚,因斯布鲁克大学) School of Computation, Information and Technology, Technical University of Munich(计算、信息与技术学院,慕尼黑技术大学)

专题命中 仿真评测 :autonomous driving(abstract);LiDAR(abstract);分类 cs.CV

AI总结 DrivIng是一个具有完整数字孪生集成的大规模多模态驾驶数据集,提供高精度定位和多传感器数据,用于自动驾驶感知算法的评估和仿真到现实测试。

Comments Copyright 2026 IEEE. This is the accepted manuscript (postprint), not the final published version. For code and dataset, see https://github.com/cvims/DrivIng

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.13245 2026-01-21 cs.CV 70%

CymbaDiff: Structured Spatial Diffusion for Sketch-based 3D Semantic Urban Scene Generation

CymbaDiff:基于结构化的空间扩散用于基于草图的3D语义城市场景生成

Li Liang, Bo Miao, Xinyu Wang, Naveed Akhtar, Jordan Vice, Ajmal Mian

机构 * The University of Western Australia(西澳大学) AIML, The University of Adelaide(阿德莱德大学) The University of Melbourne(墨尔本大学)

专题命中 仿真评测 :autonomous driving(abstract);LiDAR(abstract);分类 cs.CV

AI总结 CymbaDiff通过结构化空间扩散提升基于草图的3D语义城市场景生成的语义一致性与空间真实性。

Comments Accepted by NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.01194 2025-12-19 cs.RO 70%

RoboLoc: A Benchmark Dataset for Point Place Recognition and Localization in Indoor-Outdoor Integrated Environments

RoboLoc:用于室内-室外集成环境中的点位识别和定位的基准数据集

Jaejin Jeon, Seonghoon Ryoo, Sang-Duck Lee, Soomok Lee, Seungwoo Jeong

机构 * Department of Data, Network and AI, Ajou University(数据、网络与人工智能系,亚运会大学) Korea Railroad Research Institute(韩国铁路研究院) Department of Mobility Engineering, Ajou University(移动工程系,亚运会大学)

专题命中 仿真评测 :BEV(abstract);LiDAR(abstract);分类 cs.RO

AI总结 RoboLoc是一个用于室内外集成环境的点位识别和定位基准数据集,通过真实机器人轨迹和多领域转换,评估多种先进模型的泛化能力。

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.05187 2025-12-02 cs.NI cs.AI cs.LG 70%

Resource-Efficient Beam Prediction in mmWave Communications with Multimodal Realistic Simulation Framework

毫米波通信中基于多模态真实模拟框架的高效波束预测

Yu Min Park, Yan Kyaw Tun, Eui-Nam Huh, Walid Saad, Choong Seon Hong

机构 * Department of Computer Science and Engineering, Kyung Hee University(计算机科学与工程系,庆尚大学) Bradley Department of Electrical and Computer Engineering, Virginia Tech(电气与计算机工程系,弗吉尼亚理工大学) Department of Electronic Systems, Aalborg University(电子系统系,奥尔堡大学)

专题命中 仿真评测 :autonomous driving(abstract);LiDAR(abstract);分类 cs.AI

AI总结 本文提出了一种基于多模态真实模拟框架的资源高效学习框架,通过跨模态关系知识蒸馏算法,利用雷达数据实现高精度波束预测,同时降低计算复杂性和对多模态传感器数据的依赖。

Comments 13 pages, 9 figures, Submitted to IEEE Transactions on Mobile Computing on Dec. 01, 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.18341 2025-10-22 cs.CV 70%

ViSE: A Systematic Approach to Vision-Only Street-View Extrapolation

Kaiyuan Tan, Yingying Shen, Haiyang Sun, Bing Wang, Guang Chen, Hangjun Ye

机构 * Xiaomi EV(小米电动车)

专题命中 仿真评测 :autonomous driving(abstract);LiDAR(abstract);分类 cs.CV

详情

展开后加载摘要…

URL PDF HTML 收藏
2405.14584 2025-10-10 cs.CV 70%

SE3D: A Framework For Saliency Method Evaluation In 3D Imaging

Mariusz Wiśniewski, Loris Giulivi, Giacomo Boracchi

专题命中 仿真评测 :autonomous driving(abstract);LiDAR(abstract);分类 cs.CV

Journal ref 2024 IEEE International Conference on Image Processing (ICIP), pp. 89-95

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.00730 2025-09-04 cs.CV 70%

SEED4D: A Synthetic Ego--Exo Dynamic 4D Data Generator, Driving Dataset and Benchmark

Marius Kästingschäfer, Théo Gieruc, Sebastian Bernhard, Dylan Campbell, Eldar Insafutdinov, Eyvaz Najafli, Thomas Brox

机构 * Continental University of Freiburg(弗赖堡大学) Australian National University(澳大利亚国立大学) University of Oxford(牛津大学) University of Tübingen(图宾根大学)

专题命中 仿真评测 :autonomous driving(abstract);LiDAR(abstract);分类 cs.CV

Comments WACV 2025. Project page: https://seed4d.github.io/. Code: https://github.com/continental/seed4d

Journal ref Proceedings of the Winter Conference on Applications of Computer Vision (WACV), 7741-7753, 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.20965 2025-08-29 cs.CV 70%

DrivingGaussian++: Towards Realistic Reconstruction and Editable Simulation for Surrounding Dynamic Driving Scenes

Yajiao Xiong, Xiaoyu Zhou, Yongtao Wan, Deqing Sun, Ming-Hsuan Yang

机构 * Wangxuan Institute of Computer Technology, Peking University(北京大学王炫计算机技术研究所) Google DeepMind(谷歌DeepMind) University of California, Merced(加州大学默塞德分校)

专题命中 仿真评测 :autonomous driving(abstract);LiDAR(abstract);分类 cs.CV

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.12729 2025-08-19 cs.RO cs.SY eess.SY 70%

MCTR: Midpoint Corrected Triangulation for Autonomous Racing via Digital Twin Simulation in CARLA

Junhao Ye, Cheng Hu, Yiqin Wang, Weizhan Huang, Nicolas Baumann, Jie He, Meixun Qu, Lei Xie, Hongye Su

机构 * Department of Control Science and Engineering, Zhejiang University, Hangzhou, China(浙江大学控制科学与工程学院) Ningbo Innovation Center, Zhejiang University, Ningbo, China(浙江大学宁波创新中心) Center for Project-Based Learning, D-ITET, ETH Zurich(苏黎世联邦理工学院项目导向学习中心) Technische Universität Wien, Vienna, Austria(维也纳技术大学)

专题命中 仿真评测 :LiDAR(abstract);trajectory planning(abstract);分类 cs.RO

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.16912 2025-07-31 cs.RO 70%

UAV See, UGV Do: Aerial Imagery and Virtual Teach Enabling Zero-Shot Ground Vehicle Repeat

Desiree Fisker, Alexander Krawciw, Sven Lilge, Melissa Greeff, Timothy D. Barfoot

机构 * University of Toronto Robotics Institute(多伦多大学机器人研究所) University of Toronto Institute of Aerospace Studies(多伦多大学航空航天研究学院) Ingenuity Labs(Ingenuity实验室) Department of Electrical and Computer Engineering(电气与计算机工程系)

专题命中 仿真评测 :autonomous driving(abstract);LiDAR(abstract);分类 cs.RO

Comments 8 pages, 8 figures, accepted to IROS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.23129 2025-05-30 cs.CV 70%

HMAD: Advancing E2E Driving with Anchored Offset Proposals and Simulation-Supervised Multi-target Scoring

Bin Wang, Pingjun Li, Jinkun Liu, Jun Cheng, Hailong Lei, Yinze Rong, Huan-ang Gao, Kangliang Chen, Xing Pan, Weihao Gu

机构 * HAOMO.AI Technology Co., Ltd(HAOMO.AI技术有限公司) Tsinghua University(清华大学)

专题命中 仿真评测 :autonomous driving(abstract);BEV(abstract);分类 cs.CV

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.15412 2025-05-22 cs.RO cs.IT cs.NI math.IT 70%

Evaluation of Mobile Environment for Vehicular Visible Light Communication Using Multiple LEDs and Event Cameras

Ryota Soga, Shintaro Shiba, Quan Kong, Norimasa Kobori, Tsukasa Shimizu, Shan Lu, Takaya Yamazato

机构 * School of Engineering, Nagoya University, Nagoya, Japan(名古屋大学工学系) Woven by Toyota, Inc.(丰田公司) TOYOTA MOTOR CORPORATION(丰田汽车公司)

专题命中 仿真评测 :autonomous driving(abstract);LiDAR(abstract);分类 cs.RO

Comments 6 pages, IEEE IV 2025 conference paper

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.03100 2025-03-06 cs.RO 70%

Car-STAGE: Automated framework for large-scale high-dimensional simulated time-series data generation based on user-defined criteria

Asma A. Almutairi, David J. LeBlanc, Arpan Kusari

专题命中 仿真评测 :autonomous driving(abstract);LiDAR(abstract);分类 cs.RO

详情

展开后加载摘要…

URL PDF HTML 收藏
2310.03505 2025-01-22 cs.RO 70%

RadaRays: Real-time Simulation of Rotating FMCW Radar for Mobile Robotics via Hardware-accelerated Ray Tracing

Alexander Mock, Martin Magnusson, Joachim Hertzberg

专题命中 仿真评测 :autonomous driving(abstract);LiDAR(abstract);分类 cs.RO

详情

展开后加载摘要…

URL PDF HTML 收藏
2312.14150 2025-01-17 cs.CV 70%

DriveLM: Driving with Graph Visual Question Answering

Chonghao Sima, Katrin Renz, Kashyap Chitta, Li Chen, Hanxue Zhang, Chengen Xie, Jens Beißwenger, Ping Luo, Andreas Geiger, Hongyang Li

专题命中 仿真评测 :autonomous driving(abstract);end-to-end driving(abstract);分类 cs.CV

Comments Accepted to ECCV 2024 as Oral paper

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.21739 2024-11-08 cs.CV 70%

SS3DM: Benchmarking Street-View Surface Reconstruction with a Synthetic 3D Mesh Dataset

Yubin Hu, Kairui Wen, Heng Zhou, Xiaoyang Guo, Yong-Jin Liu

专题命中 仿真评测 :autonomous driving(abstract);LiDAR(abstract);分类 cs.CV

Comments NeurIPS 2024, Track on Datasets and Benchmarks

详情

展开后加载摘要…

URL PDF HTML 收藏