自动驾驶 - arXivDaily 专题

2307.03988 2023-07-11 cs.AI cs.RO 62%

PCG-based Static Underground Garage Scenario Generation

Wenjin Li, Kai Li

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

2004.09705 2022-09-26 cs.RO cs.AI 62%

Explainable Goal-Driven Agents and Robots -- A Comprehensive Review

Fatai Sado, Chu Kiong Loo, Wei Shiung Liew, Matthias Kerzel, Stefan Wermter

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

2207.10295 2022-07-22 cs.LG cs.AI cs.RO 62%

Addressing Optimism Bias in Sequence Modeling for Reinforcement Learning

Adam Villaflor, Zhe Huang, Swapnil Pande, John Dolan, Jeff Schneider

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

2203.15041 2022-06-10 cs.RO cs.CV cs.LG cs.SY eess.SY 62%

Socially Compliant Navigation Dataset (SCAND): A Large-Scale Dataset of Demonstrations for Social Navigation

Haresh Karnan, Anirudh Nair, Xuesu Xiao, Garrett Warnell, Soeren Pirk, Alexander Toshev, Justin Hart, Joydeep Biswas, Peter Stone

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

Journal ref Robotics and Automation Letters (RA-L) 2022

2201.04279 2022-01-13 cs.CV cs.LG cs.RO cs.SD eess.AS 62%

Dynamical Audio-Visual Navigation: Catching Unheard Moving Sound Sources in Unmapped 3D Environments

Abdelrahman Younes

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

2201.03195 2022-01-11 eess.IV cs.CV 62%

End-to-end lossless compression of high precision depth maps guided by pseudo-residual

Yuyang Wu, Wei Gao

专题命中端到端驾驶：LiDAR(abstract)；分类 cs.CV、eess.IV

Comments Data Compression Conference 2022

2108.08265 2021-10-06 cs.CV cs.RO 62%

End-to-End Urban Driving by Imitating a Reinforcement Learning Coach

Zhejun Zhang, Alexander Liniger, Dengxin Dai, Fisher Yu, Luc Van Gool

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

Comments Published at ICCV 2021

2107.00222 2021-07-02 cs.CV cs.RO 62%

Deep auxiliary learning for visual localization using colorization task

Mi Tian, Qiong Nie, Hao Shen, Xiahua Xia

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

2105.01799 2021-05-06 cs.RO cs.AI 62%

Towards End-to-End Deep Learning for Autonomous Racing: On Data Collection and a Unified Architecture for Steering and Throttle Prediction

Shakti N. Wadekar, Benjamin J. Schwartz, Shyam S. Kannan, Manuel Mar, Rohan Kumar Manna, Vishnu Chellapandi, Daniel J. Gonzalez, Aly El Gamal

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

Comments 6 pages, 10 figures, 3 tables

2011.07948 2021-04-30 cs.CV cs.LG cs.RO 62%

A Follow-the-Leader Strategy using Hierarchical Deep Neural Networks with Grouped Convolutions

Jose Solomon, Francois Charette

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

Comments 11 pages, 7 figures, 3 tables

2006.12136 2021-01-22 cs.LG cs.AI cs.RO 62%

Safe Reinforcement Learning via Curriculum Induction

Matteo Turchetta, Andrey Kolobov, Shital Shah, Andreas Krause, Alekh Agarwal

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

2010.10949 2021-01-14 cs.RO cs.CV 62%

DiSCO: Differentiable Scan Context with Orientation

Xuecheng Xu, Huan Yin, Zexi Chen, Yue Wang, Rong Xiong

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

2008.05927 2020-08-14 cs.CV cs.RO 62%

End-to-end Contextual Perception and Prediction with Interaction Transformer

Lingyun Luke Li, Bin Yang, Ming Liang, Wenyuan Zeng, Mengye Ren, Sean Segal, Raquel Urtasun

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

Comments IROS 2020

1910.09998 2020-06-04 cs.RO cs.AI cs.LG 62%

Learning Resilient Behaviors for Navigation Under Uncertainty

Tingxiang Fan, Pinxin Long, Wenxi Liu, Jia Pan, Ruigang Yang, Dinesh Manocha

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

Comments accepted to ICRA 2020

2003.07745 2020-03-18 cs.AI cs.RO 62%

Learning to Optimize Autonomy in Competence-Aware Systems

Connor Basich, Justin Svegliato, Kyle Hollins Wray, Stefan Witwicki, Joydeep Biswas, Shlomo Zilberstein

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

Comments To be published in Proceedings of the 19th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2020). 9 pages

1912.06704 2019-12-17 cs.CV cs.RO 62%

Hierarchical Deep Stereo Matching on High-resolution Images

Gengshan Yang, Joshua Manela, Michael Happold, Deva Ramanan

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

Comments CVPR 2019

1905.06712 2019-05-17 cs.RO cs.AI 62%

Autonomous Vehicle Control: End-to-end Learning in Simulated Urban Environments

Hege Haavaldsen, Max Aasboe, Frank Lindseth

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

Comments 12 pages, 3 figures

1809.10124 2019-02-05 cs.RO cs.AI cs.LG 62%

Learning Navigation Behaviors End-to-End with AutoRL

Hao-Tien Lewis Chiang, Aleksandra Faust, Marek Fiser, Anthony Francis

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

Comments Accepted to RA-L/ICRA 2019. Chiang and Faust contributed equally

1807.02371 2018-09-03 cs.CV cs.RO 62%

End-to-End Race Driving with Deep Reinforcement Learning

Maximilian Jaritz, Raoul de Charette, Marin Toromanoff, Etienne Perot, Fawzi Nashashibi

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

Comments ICRA 2018

1802.06869 2018-02-21 eess.IV cs.CV 62%

Invertible Autoencoder for domain adaptation

Yunfei Teng, Anna Choromanska, Mariusz Bojarski

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

1704.07911 2017-04-27 cs.CV cs.LG cs.NE cs.RO 62%

Explaining How a Deep Neural Network Trained with End-to-End Learning Steers a Car

Mariusz Bojarski, Philip Yeres, Anna Choromanska, Krzysztof Choromanski, Bernhard Firner, Lawrence Jackel, Urs Muller

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

2306.08865 2023-06-16 cs.CV cs.LG 61%

One-Shot Learning of Visual Path Navigation for Autonomous Vehicles

Zhongying CuiZhu, Francois Charette, Amin Ghafourian, Debo Shi, Matthew Cui, Anjali Krishnamachar, Iman Soltani

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

Comments Machine Learning for Autonomous Driving Workshop at the 35th Conference on Neural Information Processing Systems (NeurIPS 20222), New Orleans, USA

2608.14407 2026-08-17 cs.AI 新提交 57%

The Past and Future of AI Scientists

AI科学家的过去与未来

Ross D. King

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

AI总结本文综述AI科学家的过去与未来，指出其核心挑战是多技术集成，现有技术已支持构建更通用系统，其有望变革科学，诺贝尔图灵挑战目标进展超前。

2608.02953 2026-08-11 cs.CV 版本更新 57%

RealWeather: Realistic and Scene-Faithful Weather Translation with Driving World Models

RealWeather：基于驾驶世界模型的逼真且场景忠实的天气转换

Yuwei Ning, Liangzhi Wang, Yi Xiao, Zhenhua Wu, Yun Pang, Mingkun Chang, Jichang Li, Guanbin Li

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

AI总结 RealWeather是一种驾驶世界模型，通过渐进式逼真度引导和场景忠实度强化学习优化实现逼真且场景忠实的天气转换，在视觉逼真度、结构保留等方面优于现有方法，支持长尾天气场景生成与零样本泛化。

Comments Under submission

2606.10804 2026-08-06 cs.CV 版本更新 57%

SCAIL-2: Unifying Controlled Character Animation with End-to-End In-Context Conditioning

SCAIL-2：通过端到端上下文条件统一受控角色动画

Wenhao Yan, Fengjia Guo, Zhuoyi Yang, Jie Tang

机构 * Z.ai ； Tsinghua University（清华大学）

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

AI总结提出SCAIL-2框架，通过端到端上下文条件统一受控角色动画，绕过中间表示直接利用驱动视频，并合成MotionPair-60K数据集，采用上下文掩码和模式RoPE实现统一，结合Bias-Aware DPO减少误差，显著优于现有方法。

2607.27036 2026-07-30 cs.CV cs.LG 新提交 57%

Mitigating Compounding Error via Video Representation Regularization

通过视频表示正则化缓解复合误差

Taiye Chen, Qi Zhang, Yisen Wang

机构 * Peking University（北京大学）

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

AI总结针对视频扩散世界模型自回归生成的复合误差问题，研究发现其与表示维度崩溃相关，提出视频表示正则化方法，在VBench指标上显著优于Diffusion Forcing，提升了长视频生成的鲁棒性。

2607.22868 2026-07-28 cs.AI cs.CR cs.LG 新提交 57%

What Can Be Enforced? A Theory of Certified Runtime Safety for Tool-Using Agents

什么可以被强制执行？关于使用工具的智能体的认证运行时安全理论

Shawn Ray

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

AI总结研究使用工具的智能体认证运行时安全，区分三个问题：确定性门与安全策略、外部法则下的边界及证书、闭环边界识别；介绍了相关方法，通过多种实验针对差异进行研究。

Comments 26 pages, 8 figures. Extended version with complete proofs and additional experiments

2607.19774 2026-07-23 cs.RO 新提交 57%

Defer to Plan: Adaptive Multi-Agent Fusion for End-to-End V2X Driving

听从计划：用于端到端车路协同驾驶的自适应多智能体融合

Nuoran Li, Zhang Zhang, Yueran Zhao, Tianze Wang, Chao Sun

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

AI总结研究车路协同辅助自动驾驶中现有方法不足，提出端到端协同驾驶系统，用MotionNetwork融合信息、注意力机制压缩特征、自回归解码器融合多智能体特征及引入MoE架构，提升驾驶分数并保持通信效率。

Comments Accepted at IEEE ICME 2026

2607.18637 2026-07-22 cs.RO cs.LG 新提交 57%

End-to-end Conditional Diffusion for Realistic and Controllable Visual Traffic Scenario Generation

用于逼真且可控的视觉交通场景生成的端到端条件扩散

Jingzheng Li, Yufei Ge, Zhijun Chen, Qianren Mao, Zizhe Wang, Binhang Qi, Bing Li, Keyu Chen, Baochang Zhang, Xianglong Liu, Philip S Yu

机构 * Zhongguancun Laboratory（中关村实验室）； Tianjin University（天津大学）； Beihang University（北京航空航天大学）； Nanyang Technological University（南洋理工大学）； Tsinghua University（清华大学）； State Key Laboratory of Software Development Environment（软件开发环境国家重点实验室）； University of Illinois Chicago（伊利诺伊大学芝加哥分校）

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

AI总结研究如何生成逼真且可控的视觉交通场景，提出端到端条件扩散框架E2E-CDiff，基于前视图视觉观察联合去噪未来运动状态等，减轻规划控制不匹配，实验表明其在可控性与逼真性权衡上表现良好，还能引发挑战性交互，作为自我规划器有竞争力。

2512.02851 2026-07-20 cs.RO 版本更新 57%

EmbodiedDiffusion: End-to-End Traversability-Guided Visual Diffusion for Heterogeneous Robot Navigation

EmbodiedDiffusion：用于异构机器人导航的端到端可通行性引导视觉扩散

Iana Zhura, Sausar Karaf, Faryal Batool, Nipun Dhananjaya Weerakkodi Mudalige, Valerii Serpiva, Ali Alridha Abdulkarim, Aleksey Fedoseev, Didar Seyidov, Hajira Amjad, Dzmitry Tsetserukou

机构 * Intelligent Space Robotics Laboratory, Center for Digital Engineering, Skolkovo Institute of Science and Technology（智能空间机器人实验室，数字工程中心，斯克尔科沃科学与技术研究所）

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

AI总结针对自主导航中视觉可通行性估计问题，EmbodiedDiffusion框架利用无规划器合成监督等，同时预测可通行性地图与生成可行轨迹，经训练提炼语义到轻量级模型，能快速适应新平台，在多机器人室内环境中实现高效导航与轨迹生成。

Comments This work has been submitted for publication and is currently under review

1. 端到端驾驶 731 篇

PCG-based Static Underground Garage Scenario Generation

Explainable Goal-Driven Agents and Robots -- A Comprehensive Review

Addressing Optimism Bias in Sequence Modeling for Reinforcement Learning

Socially Compliant Navigation Dataset (SCAND): A Large-Scale Dataset of Demonstrations for Social Navigation

Dynamical Audio-Visual Navigation: Catching Unheard Moving Sound Sources in Unmapped 3D Environments

End-to-end lossless compression of high precision depth maps guided by pseudo-residual

End-to-End Urban Driving by Imitating a Reinforcement Learning Coach

Deep auxiliary learning for visual localization using colorization task

Towards End-to-End Deep Learning for Autonomous Racing: On Data Collection and a Unified Architecture for Steering and Throttle Prediction

A Follow-the-Leader Strategy using Hierarchical Deep Neural Networks with Grouped Convolutions

Safe Reinforcement Learning via Curriculum Induction

DiSCO: Differentiable Scan Context with Orientation

End-to-end Contextual Perception and Prediction with Interaction Transformer

Learning Resilient Behaviors for Navigation Under Uncertainty

Learning to Optimize Autonomy in Competence-Aware Systems

Hierarchical Deep Stereo Matching on High-resolution Images

Autonomous Vehicle Control: End-to-end Learning in Simulated Urban Environments

Learning Navigation Behaviors End-to-End with AutoRL

End-to-End Race Driving with Deep Reinforcement Learning

Invertible Autoencoder for domain adaptation

Explaining How a Deep Neural Network Trained with End-to-End Learning Steers a Car

One-Shot Learning of Visual Path Navigation for Autonomous Vehicles

The Past and Future of AI Scientists

RealWeather: Realistic and Scene-Faithful Weather Translation with Driving World Models

SCAIL-2: Unifying Controlled Character Animation with End-to-End In-Context Conditioning

Mitigating Compounding Error via Video Representation Regularization

What Can Be Enforced? A Theory of Certified Runtime Safety for Tool-Using Agents

Defer to Plan: Adaptive Multi-Agent Fusion for End-to-End V2X Driving

End-to-end Conditional Diffusion for Realistic and Controllable Visual Traffic Scenario Generation

EmbodiedDiffusion: End-to-End Traversability-Guided Visual Diffusion for Heterogeneous Robot Navigation