自动驾驶 - arXivDaily 专题

2603.23607 2026-04-07 cs.CV cs.RO 73%

LongTail Driving Scenarios with Reasoning Traces: The KITScenes LongTail Dataset

长尾驾驶场景与推理轨迹：KITScenes长尾数据集

Royden Wagner, Omer Sahin Tas, Jaime Villa, Felix Hauser, Yinzhe Shen, Marlon Steiner, Dominik Strutz, Carlos Fernandez, Christian Kinzig, Guillermo S. Guitierrez-Cabello, Hendrik Königshof, Fabian Immel, Richard Schwarzkopf, Nils Alexander Rack, Kevin Rösch, Kaiwen Wang, Jan-Hendrik Pauls, Martin Lauer, Igor Gilitschenski, Holger Caesar, Christoph Stiller

机构 * Karlsruhe Institute of Technology (KIT)（卡尔斯鲁厄理工学院）； FZI Research Center for Information Technology（FZI信息技术研究中心）； University Charles III of Madrid（马德里卡洛斯三世大学）； Technical University of Madrid（马德里理工大学）； University of Toronto（多伦多大学）； Delft University of Technology（代尔夫特理工大学）

专题命中端到端驾驶：self-driving(abstract)；end-to-end driving(abstract)；分类 cs.RO、cs.CV

AI总结本文提出KITScenes长尾数据集，通过多视角视频、轨迹、指令和推理轨迹提升模型在长尾驾驶场景下的泛化能力，评估指令遵循与语义连贯性。

Comments 21 pages; v2: update MMS values (bugfix)

2603.14497 2026-03-18 cs.CV cs.RO 73%

WorldVLM: Combining World Model Forecasting and Vision-Language Reasoning

WorldVLM：结合世界模型预测与视觉语言推理

Stefan Englmeier, Katharina Winter, Fabian B. Flohr

机构 * Munich University of Applied Sciences（慕尼黑应用科学大学）

专题命中端到端驾驶：autonomous driving(abstract)；end-to-end driving(abstract)；分类 cs.RO、cs.CV

AI总结 WorldVLM结合视觉语言模型与世界模型，通过统一架构提升自动驾驶中的环境预测与决策能力，解决空间理解受限问题。

Comments 8 pages, 6 figures, 5 tables; submitted to IEEE

2602.01536 2026-02-03 cs.RO cs.CV 73%

UniDWM: Towards a Unified Driving World Model via Multifaceted Representation Learning

UniDWM: 通过多维表征学习实现统一的驾驶世界模型

Shuai Liu, Siheng Ren, Xiaoyao Zhu, Quanmin Liang, Zefeng Li, Qiang Li, Xin Hu, Kai Huang

机构 * Department of XXX, University of YYY, Location, Country（XXX系，YYY大学，地点，国家）； School of ZZZ, Institute of WWW, Location, Country（ZZZ学院，WWW研究所，地点，国家）； Xpeng Motors Technology Co Ltd（小鹏汽车科技有限公司）

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

AI总结 UniDWM通过多维表征学习实现统一驾驶世界模型，提升自动驾驶中的轨迹规划和4D重建能力。

2503.09215 2025-11-20 cs.CV cs.AI 73%

Other Vehicle Trajectories Are Also Needed: A Driving World Model Unifies Ego-Other Vehicle Trajectories in Video Latent Space

Jian Zhu, Zhengyu Jia, Tian Gao, Jiaxin Deng, Shidi Li, Lang Zhang, Fu Liu, Peng Jia, Xianpeng Lang

机构 * Project Leader（项目负责人）

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

Comments 8 pages, 7 figures

2405.05956 2024-10-29 cs.RO cs.CV 73%

Probing Multimodal LLMs as World Models for Driving

Shiva Sreeram, Tsun-Hsuan Wang, Alaa Maalouf, Guy Rosman, Sertac Karaman, Daniela Rus

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

Comments https://github.com/sreeramsa/DriveSim https://www.youtube.com/watch?v=Fs8jgngOJzU

2301.12264 2023-06-27 cs.RO cs.AI cs.LG 73%

Controlling Steering with Energy-Based Models

Mikita Balesni, Ardi Tampuu, Tambet Matiisen

专题命中端到端驾驶：self-driving(abstract)；end-to-end driving(abstract)；分类 cs.RO、cs.AI

2205.13817 2022-12-20 cs.LG cs.AI cs.RO 73%

Iso-Dream: Isolating and Leveraging Noncontrollable Visual Dynamics in World Models

Minting Pan, Xiangming Zhu, Yunbo Wang, Xiaokang Yang

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

2101.06679 2021-01-19 cs.CV cs.RO 73%

End-to-end Interpretable Neural Motion Planner

Wenyuan Zeng, Wenjie Luo, Simon Suo, Abbas Sadat, Bin Yang, Sergio Casas, Raquel Urtasun

专题命中端到端驾驶：self-driving(abstract)；LiDAR(abstract)；分类 cs.RO、cs.CV

Comments CVPR 2019 (Oral)

1804.09364 2018-12-14 cs.RO cs.CV cs.LG 73%

Driving Policy Transfer via Modularity and Abstraction

Matthias Müller, Alexey Dosovitskiy, Bernard Ghanem, Vladlen Koltun

专题命中端到端驾驶：autonomous driving(abstract)；end-to-end driving(abstract)；分类 cs.RO、cs.CV

Comments Accepted at Conference on Robotic Learning (CoRL'18) http://proceedings.mlr.press/v87/mueller18a.html

1803.09386 2018-10-16 cs.LG cs.CV cs.RO stat.ML 73%

A Systematic Comparison of Deep Learning Architectures in an Autonomous Vehicle

Michael Teti, William Edward Hahn, Shawn Martin, Christopher Teti, Elan Barenholtz

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

Comments 16 pages, 14 figures, 2 tables

2607.09045 2026-07-13 eess.SY cs.SY 新提交 71%

Can the Cloud Drive? Infrastructure Feasibility of Offloading Autonomous Driving Across 5G and 6G

云能驱动自动驾驶吗？跨5G和6G卸载自动驾驶的基础设施可行性

Pouya Parsa, Kawon Han, Seongjin Choi

专题命中端到端驾驶：autonomous driving(title)

AI总结探讨云能否驱动自动驾驶，通过耦合通信限制、GPU服务模型等构建分析框架，应用于纽约市，研究发现通信、计算、成本依次起约束作用，延迟决定模型可行性，成本决定是否经济。

Comments 25 pages, 10 figures

2603.28889 2026-04-01 cs.DB 71%

DeepEye: A Steerable Self-driving Data Agent System

DeepEye：一种可调节的自动驾驶数据代理系统

Boyan Li, Yiran Peng, Yupeng Xie, Sirong Lu, Yizhang Zhu, Xing Mu, Xinyu Liu, Yuyu Luo

专题命中端到端驾驶：self-driving(title)

AI总结本文提出DeepEye，一种基于工作流的生产级数据代理系统，通过统一多模态协调协议和分层推理机制，解决异构数据源联合分析和上下文爆炸问题，实现透明执行和自动化优化。

Comments SIGMOD Demo (2026)

2509.05351 2025-09-09 cond-mat.soft cs.LG 71%

Self-Driving Laboratory Optimizes the Lower Critical Solution Temperature of Thermoresponsive Polymers

Guoyue Xu, Renzheng Zhang, Tengfei Luo

机构 * Self-Driving Laboratory（自主实验室）

专题命中端到端驾驶：self-driving(title)

2205.12203 2022-05-25 cs.NI 71%

Autonomous Driving From the Sky: Design and End-to-End Performance Evaluation

Matteo Bordin, Marco Giordani, Michele Polese, Tommaso Melodia, Michele Zorzi

专题命中端到端驾驶：autonomous driving(title)

2510.18313 2026-06-23 cs.CV 版本更新 70%

OmniNWM: Omniscient Driving Navigation World Models

OmniNWM：全知驾驶导航世界模型

Bohan Li, Zhuang Ma, Dalong Du, Baorui Peng, Zhujin Liang, Zhenqiang Liu, Xianda Guo, Zheng Zhu, Chao Ma, Yueming Jin, Xin Jin, Hao Zhao, Wenjun Zeng

机构 * Shanghai Jiao Tong University（上海交通大学）； Eastern Institute of Technology（东部技术研究所）； PhiGent ； National University of Singapore（新加坡国立大学）； Tsinghua University（清华大学）； Wuhan University（武汉大学）

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

AI总结提出OmniNWM全知全景导航世界模型，在统一概率框架下处理状态、动作和奖励三个维度，实现多模态全景视频生成、零样本轨迹控制及内在奖励机制，在生成保真度和控制精度上达到SOTA。

Comments ECCV 2026

2606.14763 2026-06-16 cs.RO cs.LG math.OC 新提交 70%

Bayesian Optimization for Learning Nonlinear MPC in Autonomous Agent Navigation

自主智能体导航中学习非线性模型预测控制的贝叶斯优化

Lorenzo Ortolani, Gabriel Voss, Gabriele Beltrami, Francesco Dorati, Tommaso Felice Banfi

机构 * Talos Robotics AI

专题命中端到端驾驶：LiDAR(abstract)；occupancy(abstract)；分类 cs.RO

AI总结提出一种无地图框架，结合滚动时域规划与非线性MPC，利用贝叶斯优化自动调参，在仿真和实物四足机器人上实现高效导航。

Comments Published at the IEEE ICRA 2026 Xplore Workshop (Oral), Cross-Disciplinary aspects of Exploration in Robotics, Reinforcement Learning, and Search

2605.14696 2026-05-15 cs.CV 70%

EponaV2: Driving World Model with Comprehensive Future Reasoning

EponaV2：通过全面的未来推理驱动世界模型

Jiawei Xu, Zhizhou Zhong, Zhijian Shu, Mingkai Jia, Mingxiao Li, Jia-Wang Bian, Qian Zhang, Kaicheng Zhang, Jin Xie, Jian Yang, Wei Yin

机构 * PCA Lab, VCIP, College of Computer Science, Nankai University（PCA实验室、VCIP、计算机科学学院、南开大学）； Horizon Robotics ； HKUST（香港科技大学）； NJUPT（南京工程大学）； NTU（国立台湾大学）； Anyverse ； School of Intelligence Science and Technology, Nanjing University（智能科学与技术学院、南京大学）

专题命中端到端驾驶：autonomous driving(abstract)；trajectory planning(abstract)；分类 cs.CV

AI总结本文提出EponaV2，一种新的驾驶世界模型范式，通过全面的未来推理实现高质量规划。模型通过预测更全面的未来表示，结合3D和语义模态，提升环境理解与现实推理能力，从而改进轨迹规划。

2509.16894 2025-09-23 cs.RO 70%

End2Race: Efficient End-to-End Imitation Learning for Real-Time F1Tenth Racing

Zhijie Qiao, Haowei Li, Zhong Cao, Henry X. Liu

机构 * Department of Civil and Environmental Engineering, University of Michigan（土木与环境工程系，密歇根大学）； University of Michigan Transportation Research Institute（密歇根大学交通研究所）

专题命中端到端驾驶：autonomous driving(abstract)；LiDAR(abstract)；分类 cs.RO

2507.08901 2025-07-15 cs.RO 70%

End-to-End Generation of City-Scale Vectorized Maps by Crowdsourced Vehicles

Zebang Feng, Miao Fan, Bao Liu, Shengtong Xu, Haoyi Xiong

机构 * NavInfo Co., Ltd.（NavInfo公司）； Beijing Institute of Graphic Communication（北京图形通信学院）； Autohome Inc.（Autohome公司）

专题命中端到端驾驶：autonomous driving(abstract)；LiDAR(abstract)；分类 cs.RO

Comments Accepted by ITSC'25

2505.18650 2025-05-27 cs.CV 70%

ProphetDWM: A Driving World Model for Rolling Out Future Actions and Videos

Xiaodong Wang, Peixi Peng

机构 * Peking University（北京大学）； Peng Cheng Laboratory（鹏城实验室）

专题命中端到端驾驶：autonomous driving(abstract)；end-to-end driving(abstract)；分类 cs.CV

Comments 9 pages, 7 figures

2503.21232 2025-03-28 cs.AI 70%

Knowledge Graphs as World Models for Semantic Material-Aware Obstacle Handling in Autonomous Vehicles

Ayush Bheemaiah, Seungyong Yang

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

2311.02817 2024-12-30 cs.RO 70%

Safe-VLN: Collision Avoidance for Vision-and-Language Navigation of Autonomous Robots Operating in Continuous Environments

Lu Yue, Dongliang Zhou, Liang Xie, Feitian Zhang, Ye Yan, Erwei Yin

专题命中端到端驾驶：LiDAR(abstract)；occupancy(abstract)；分类 cs.RO

Journal ref IEEE Robotics and Automation Letters, 2024

2412.08562 2024-12-12 cs.RO cs.MA 70%

An End-to-End Collaborative Learning Approach for Connected Autonomous Vehicles in Occluded Scenarios

Leandro Parada, Hanlin Tian, Jose Escribano, Panagiotis Angeloudis

专题命中端到端驾驶：autonomous driving(abstract)；LiDAR(abstract)；分类 cs.RO

Journal ref Journal reference: 2023 IEEE 26th International Conference on Intelligent Transportation Systems, pp. 5548-5554, 2023

2403.06845 2024-04-12 cs.CV 70%

DriveDreamer-2: LLM-Enhanced World Models for Diverse Driving Video Generation

Guosheng Zhao, Xiaofeng Wang, Zheng Zhu, Xinze Chen, Guan Huang, Xiaoyi Bao, Xingang Wang

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

Comments Project Page: https://drivedreamer2.github.io

2204.02675 2022-04-07 cs.CV cs.CR 70%

Rolling Colors: Adversarial Laser Exploits against Traffic Light Recognition

Chen Yan, Zhijian Xu, Zhanyuan Yin, Xiaoyu Ji, Wenyuan Xu

专题命中端到端驾驶：autonomous driving(abstract)；self-driving(abstract)；分类 cs.CV

Comments To be published in USENIX Security 2022

2105.11705 2021-10-19 cs.CV 70%

SBEVNet: End-to-End Deep Stereo Layout Estimation

Divam Gupta, Wei Pu, Trenton Tabor, Jeff Schneider

专题命中端到端驾驶：self-driving(abstract)；BEV(abstract)；分类 cs.CV

Comments WACV 2022

2010.14924 2021-06-30 cs.CV 70%

Multimodal End-to-End Learning for Autonomous Steering in Adverse Road and Weather Conditions

Jyri Maanpää, Josef Taher, Petri Manninen, Leo Pakola, Iaroslav Melekhov, Juha Hyyppä

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

Comments 8 pages, 8 figures, included in the conference proceedings of the 2020 25th International Conference on Pattern Recognition (ICPR), 2021

Journal ref 2020 25th International Conference on Pattern Recognition (ICPR), 2021, pp. 699-706

1711.01458 2017-11-07 cs.CV 70%

DDD17: End-To-End DAVIS Driving Dataset

Jonathan Binas, Daniel Neil, Shih-Chii Liu, Tobi Delbruck

专题命中端到端驾驶：autonomous driving(abstract)；end-to-end driving(abstract)；分类 cs.CV

Comments Presented at the ICML 2017 Workshop on Machine Learning for Autonomous Vehicles

2606.00267 2026-06-02 cs.CV cs.AI cs.LG cs.RO 67%

StressDream: Steering Video World Models for Robust Policy Evaluation and Improvement

StressDream: 引导视频世界模型实现鲁棒的策略评估与改进

Junwon Seo, Sushant Veer, Ran Tian, Wenhao Ding, Apoorva Sharma, Karen Leung, Edward Schmerling, Marco Pavone, Andrea Bajcsy

机构 * Carnegie Mellon University（卡内基梅隆大学）； NVIDIA Research（NVIDIA研究）； University of Washington（华盛顿大学）； Stanford University（斯坦福大学）

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

AI总结提出StressDream方法，通过优化扩散视频世界模型的初始噪声，在推理时引导生成高影响且合理的未来场景，以支持鲁棒的策略评估与改进。

Comments Project page: https://junwon.me/StressDream/

2605.21372 2026-05-21 cs.CV cs.AI cs.LG cs.RO 67%

Closed Loop Dynamic Driving Data Mixture for Real-Synthetic Co-Training

闭环动态驾驶数据混合用于真实-合成协同训练

Hongzhi Ruan, Pei Liu, Weiliang Ma, Zhengning Li, Xueyang Zhang, Jun Ma, Dan Xu, Kun Zhan

机构 * Li Auto（力汽车）； HKUST（香港科技大学）； HKUST (GZ)（香港科技大学（广州））

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

AI总结本文提出了一种闭环动态数据混合方法，通过动态优化过程调整训练数据混合比例，以提升模型性能，解决了在有限预算下优化数据混合的关键问题。

1. 端到端驾驶 725 篇

LongTail Driving Scenarios with Reasoning Traces: The KITScenes LongTail Dataset

WorldVLM: Combining World Model Forecasting and Vision-Language Reasoning

UniDWM: Towards a Unified Driving World Model via Multifaceted Representation Learning

Other Vehicle Trajectories Are Also Needed: A Driving World Model Unifies Ego-Other Vehicle Trajectories in Video Latent Space

Probing Multimodal LLMs as World Models for Driving

Controlling Steering with Energy-Based Models

Iso-Dream: Isolating and Leveraging Noncontrollable Visual Dynamics in World Models

End-to-end Interpretable Neural Motion Planner

Driving Policy Transfer via Modularity and Abstraction

A Systematic Comparison of Deep Learning Architectures in an Autonomous Vehicle

Can the Cloud Drive? Infrastructure Feasibility of Offloading Autonomous Driving Across 5G and 6G

DeepEye: A Steerable Self-driving Data Agent System

Self-Driving Laboratory Optimizes the Lower Critical Solution Temperature of Thermoresponsive Polymers

Autonomous Driving From the Sky: Design and End-to-End Performance Evaluation

OmniNWM: Omniscient Driving Navigation World Models

Bayesian Optimization for Learning Nonlinear MPC in Autonomous Agent Navigation

EponaV2: Driving World Model with Comprehensive Future Reasoning

End2Race: Efficient End-to-End Imitation Learning for Real-Time F1Tenth Racing

End-to-End Generation of City-Scale Vectorized Maps by Crowdsourced Vehicles

ProphetDWM: A Driving World Model for Rolling Out Future Actions and Videos

Knowledge Graphs as World Models for Semantic Material-Aware Obstacle Handling in Autonomous Vehicles

Safe-VLN: Collision Avoidance for Vision-and-Language Navigation of Autonomous Robots Operating in Continuous Environments

An End-to-End Collaborative Learning Approach for Connected Autonomous Vehicles in Occluded Scenarios

DriveDreamer-2: LLM-Enhanced World Models for Diverse Driving Video Generation

Rolling Colors: Adversarial Laser Exploits against Traffic Light Recognition

SBEVNet: End-to-End Deep Stereo Layout Estimation

Multimodal End-to-End Learning for Autonomous Steering in Adverse Road and Weather Conditions

DDD17: End-To-End DAVIS Driving Dataset

StressDream: Steering Video World Models for Robust Policy Evaluation and Improvement

Closed Loop Dynamic Driving Data Mixture for Real-Synthetic Co-Training