世界模型 - arXivDaily 专题

2311.18393 2023-12-01 cs.LG cs.RO 56%

Data-efficient Deep Reinforcement Learning for Vehicle Trajectory Control

Bernd Frauenknecht, Tobias Ehlgen, Sebastian Trimpe

专题命中自动驾驶：model-based RL(abstract)；分类 cs.LG、cs.RO

2102.04738 2021-12-10 cs.CV cs.AI cs.LG cs.RO 56%

End-to-End Deep Learning of Lane Detection and Path Prediction for Real-Time Autonomous Driving

Der-Hau Lee, Jinn-Liang Liu

专题命中自动驾驶：分类 cs.AI、cs.LG、cs.CV；simulation model(abstract)

Comments 6 pages, 4 figures

2103.10290 2021-05-12 cs.LG cs.RO 56%

Integrated Decision and Control: Towards Interpretable and Computationally Efficient Driving Intelligence

Yang Guan, Yangang Ren, Qi Sun, Shengbo Eben Li, Haitong Ma, Jingliang Duan, Yifan Dai, Bo Cheng

专题命中自动驾驶：model-based reinforcement learning(abstract)；分类 cs.LG、cs.RO

1711.10785 2018-08-03 cs.LG cs.RO 56%

Automating Vehicles by Deep Reinforcement Learning using Task Separation with Hill Climbing

Mogens Graf Plessen

专题命中自动驾驶：model-based reinforcement learning(abstract)；分类 cs.LG、cs.RO

Comments 10 pages, 6 figures, 1 table

2603.24989 2026-03-30 cs.RO cs.AI 53%

Learning Rollout from Sampling:An R1-Style Tokenized Traffic Simulation Model

从采样中学习：一种R1风格的分词交通仿真模型

Ziyan Wang, Peng Chen, Ding Li, Chiwei Li, Qichao Zhang, Zhongpu Xia, Guizhen Yu

机构 * State Key Laboratory of Intelligent Transportation System, Key Laboratory of Autonomous Transportation Technology for Special Vehicles, Ministry of Industry and Information Technology, School of Transportation Science and Engineering, Beihang University（北京航空航天大学交通科学与工程学院，智能交通系统国家重点实验室，特种车辆自主运输技术重点实验室（工业和信息化部））； State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所，多模态人工智能系统国家重点实验室）

专题命中自动驾驶：simulation model(title)；分类 cs.AI、cs.RO

AI总结本文提出R1Sim模型，通过分词交通仿真结合熵引导采样和GRPO优化，实现探索与利用的平衡，生成真实安全的多智能体行为。

2607.13028 2026-08-06 cs.LG cs.AI cs.RO 版本更新 50%

TerraZero: Procedural Driving Simulation for Zero-Demonstration Self-Play at Scale

TerraZero：用于大规模零演示自博弈的过程式驾驶模拟

Zhouchonghao Wu, Akshay Rangesh, Weixin Li, Wei-Jer Chang, Zachary Lee, Saeed Bonab, Tim Wang, Wei Zhan

机构 * Applied Intuition（应用直觉）

专题命中自动驾驶：分类 cs.AI、cs.LG、cs.RO；dynamics model(abstract)

AI总结研究旨在训练强大自动驾驶智能体，提出TerraZero过程式驾驶模拟器和自博弈训练堆栈，其速度快、逼真且多样。通过特定方式填充地图生成无限场景，智能体仅靠强化学习训练，能零样本泛化，在多个基准测试中表现出色。

Comments Technical Report from Applied Intuition Research

2603.05842 2026-08-04 cs.RO 版本更新 50%

Expert Knowledge-driven Reinforcement Learning for Autonomous Racing via Trajectory Guidance and Dynamics Constraints

专家知识驱动的强化学习用于自动驾驶赛车：通过轨迹引导和动力学约束

Bo Leng, Weiqi Zhang, Zhuoren Li, Lu Xiong, Guizhe Jin, Ran Yu, Chen Lv

机构 * College of Automotive and Energy Engineering, Tongji University（同济大学汽车与能源工程学院）； School of Mechanical and Aerospace Engineering, Nanyang Technological University（南洋理工大学机械与航空航天工程学院）

专题命中自动驾驶：environment model(abstract)；分类 cs.RO

AI总结本文提出TraD-RL方法，通过轨迹引导和动力学约束强化学习，提升自动驾驶赛车的性能与安全性。

2605.02405 2026-06-26 cs.LG 版本更新 50%

Closed-Loop CO2 Storage Control With History-Based Reinforcement Learning and Latent Model-Based Adaptation

基于历史强化学习和潜在模型自适应的闭环CO2封存控制

Sofianos Panagiotis Fotias, Vassilis Gaganis

专题命中自动驾驶：latent dynamics(abstract)；分类 cs.LG

AI总结提出一种闭环CO2封存控制框架，结合历史条件策略和潜在模型自适应，仅利用井口观测数据实现接近特权状态性能，并在异常工况下优于直接无模型重调。

2606.12990 2026-06-12 cs.LG 新提交 50%

Exposure Bias as Epistemic Underidentification in Recursive Forecasting

递归预测中的曝光偏差作为认知欠识别问题

Riku Green, Zahraa S. Abdallah, Telmo M Silva Filho

机构 * University of Bristol（布里斯托大学）

专题命中自动驾驶：latent dynamics(abstract)；分类 cs.LG

AI总结本文证明递归多步预测中的曝光偏差不仅是分布偏移，更是部分可观测性下的认知欠识别问题，并提出基于来源变量的误差分解与校正方法。

Comments Accepted for ICML 2026 EIML workshop

1804.08871 2026-06-04 eess.SY cs.RO cs.SY 50%

Representing the Unknown - Impact of Uncertainty on the Interaction between Decision Making and Trajectory Generation

表示未知 - 不确定性对决策制定与轨迹生成交互的影响

Marcus Nolte, Susanne Ernst, Jan Richelmann, Markus Maurer

机构 * Institute of Control Engineering（控制工程研究所）

专题命中自动驾驶：environment model(abstract)；分类 cs.RO

AI总结本文探讨了不确定性对自动驾驶车辆运动规划问题参数和环境模型要求的影响，强调了决策制定与轨迹生成之间明确接口的重要性。

2403.10559 2026-04-22 cs.LG cs.AI cs.RO 50%

Generative Models and Connected and Automated Vehicles: A Survey in Exploring the Intersection of Transportation and AI

生成模型与连接与自动化车辆：探索交通与人工智能交汇点的综述

Bo Shu, Yiting Zhang, Saisai Hu, Dong Shu

机构 * School of Engineering Science（工程科学学院）； Shandong Xiehe University（山东谢河大学）； Department of Electrical Engineering（电气工程系）； Northwestern University（西北大学）； Department of Computer Science（计算机科学系）； Pace University（帕克大学）

专题命中自动驾驶：分类 cs.AI、cs.LG、cs.RO；predictive model(abstract)

AI总结本文综述了生成模型与连接自动化车辆在交通与AI交汇领域的应用，探讨其在预测建模、模拟精度和自动驾驶决策中的提升作用及面临的挑战。

2603.13399 2026-03-17 cs.CV 50%

FlowAD: Ego-Scene Interactive Modeling for Autonomous Driving

FlowAD: 无人驾驶中的自体场景交互建模

Mingzhe Guo, Yixiang Yang, Chuanrong Han, Rufeng Zhang, Shirui Li, Ji Wan, Zhipeng Zhang

机构 * AutoLab, School of Artificial Intelligence, Shanghai Jiao Tong University（上海交通大学人工智能学院AutoLab）； Baidu Inc（百度公司）

专题命中自动驾驶：environment model(abstract)；分类 cs.CV

AI总结本文提出FlowAD框架，通过自体场景交互建模提升自动驾驶性能，利用场景流建模动态变化，结合新颖的FCP指标评估场景理解能力，实验表明其在碰撞率和驾驶评分上均优于现有方法。

2509.08221 2025-09-11 cs.RO 50%

A Comprehensive Review of Reinforcement Learning for Autonomous Driving in the CARLA Simulator

Elahe Delavari, Feeza Khan Khanzada, Jaerock Kwon

专题命中自动驾驶：model-based RL(abstract)；分类 cs.RO

2508.07453 2025-08-12 eess.SY cs.AI cs.MA cs.RO cs.SY 50%

Noise-Aware Generative Microscopic Traffic Simulation

Vindula Jayawardana, Catherine Tang, Junyi Ji, Jonah Philion, Xue Bin Peng, Cathy Wu

机构 * Massachusetts Institute of Technology（麻省理工学院）； Vanderbilt University（范德比大学）； NVIDIA Corporation（NVIDIA公司）

专题命中自动驾驶：分类 cs.AI、cs.RO、cs.MA；simulation model(abstract)

2406.13223 2024-12-16 cs.RO 50%

Act Better by Timing: A timing-Aware Reinforcement Learning for Autonomous Driving

Guanzhou Li, Jianping Wu, Yujing He

专题命中自动驾驶：environment model(abstract)；分类 cs.RO

2312.15817 2024-10-10 cs.CV cs.LG cs.RO eess.IV 50%

A Unified Generative Framework for Realistic Lidar Simulation in Autonomous Driving Systems

Hamed Haghighi, Mehrdad Dianati, Valentina Donzella, Kurt Debattista

专题命中自动驾驶：分类 cs.LG、cs.CV、cs.RO；simulation model(abstract)

2401.15803 2024-01-31 cs.RO cs.AI cs.CV cs.SY eess.SY 50%

GarchingSim: An Autonomous Driving Simulator with Photorealistic Scenes and Minimalist Workflow

Liguo Zhou, Yinglei Song, Yichao Gao, Zhou Yu, Michael Sodamin, Hongshen Liu, Liang Ma, Lian Liu, Hao Liu, Yang Liu, Haichuan Li, Guang Chen, Alois Knoll

专题命中自动驾驶：分类 cs.AI、cs.CV、cs.RO；dynamics model(abstract)

2309.00709 2023-09-06 cs.AI cs.LG cs.RO 50%

Reinforcement Learning with Human Feedback for Realistic Traffic Simulation

Yulong Cao, Boris Ivanovic, Chaowei Xiao, Marco Pavone

专题命中自动驾驶：分类 cs.AI、cs.LG、cs.RO；simulation model(abstract)

Comments 9 pages, 4 figures

2301.13313 2023-04-28 cs.LG cs.AI cs.RO 50%

Incorporating Recurrent Reinforcement Learning into Model Predictive Control for Adaptive Control in Autonomous Driving

Yuan Zhang, Joschka Boedecker, Chuxuan Li, Guyue Zhou

专题命中自动驾驶：分类 cs.AI、cs.LG、cs.RO；dynamics model(abstract)

2008.09417 2020-11-10 cs.CV cs.LG cs.RO 50%

Action-Based Representation Learning for Autonomous Driving

Yi Xiao, Felipe Codevilla, Christopher Pal, Antonio M. Lopez

专题命中自动驾驶：分类 cs.LG、cs.CV、cs.RO；dynamics model(abstract)

Comments This paper has been accepted to the Conference on Robot Learning (CoRL 2020)

1. 自动驾驶 140 篇

Data-efficient Deep Reinforcement Learning for Vehicle Trajectory Control

End-to-End Deep Learning of Lane Detection and Path Prediction for Real-Time Autonomous Driving

Integrated Decision and Control: Towards Interpretable and Computationally Efficient Driving Intelligence

Automating Vehicles by Deep Reinforcement Learning using Task Separation with Hill Climbing

Learning Rollout from Sampling:An R1-Style Tokenized Traffic Simulation Model

TerraZero: Procedural Driving Simulation for Zero-Demonstration Self-Play at Scale

Expert Knowledge-driven Reinforcement Learning for Autonomous Racing via Trajectory Guidance and Dynamics Constraints

Closed-Loop CO2 Storage Control With History-Based Reinforcement Learning and Latent Model-Based Adaptation

Exposure Bias as Epistemic Underidentification in Recursive Forecasting

Representing the Unknown - Impact of Uncertainty on the Interaction between Decision Making and Trajectory Generation

Generative Models and Connected and Automated Vehicles: A Survey in Exploring the Intersection of Transportation and AI

FlowAD: Ego-Scene Interactive Modeling for Autonomous Driving

A Comprehensive Review of Reinforcement Learning for Autonomous Driving in the CARLA Simulator

Noise-Aware Generative Microscopic Traffic Simulation

Act Better by Timing: A timing-Aware Reinforcement Learning for Autonomous Driving

A Unified Generative Framework for Realistic Lidar Simulation in Autonomous Driving Systems

GarchingSim: An Autonomous Driving Simulator with Photorealistic Scenes and Minimalist Workflow

Reinforcement Learning with Human Feedback for Realistic Traffic Simulation

Incorporating Recurrent Reinforcement Learning into Model Predictive Control for Adaptive Control in Autonomous Driving

Action-Based Representation Learning for Autonomous Driving