Autonomous Driving Simulation

Follow this topic Ask about this topic

Latest papers 217

25 papers in the last four weeks, up 79% on the four weeks before. 0.1% of all new papers.

All topics

Think at 5 Hz, Act at 20 Hz: Asynchronous Fast-Slow Vision-Language-Action Inference for Closed-Loop Driving
Jul 17, 2026Yun Li, Jiachen Gong, Simon Thompson +7Efficient VLA Model Inference Vision-Language-Action Models
The University of Tokyo, Tokyo, Japan · TIER IV, Inc., Tokyo, Japan · Huawei
Chat2Scenic: An Iterative RAG-Based Framework for Scenario Generation in Autonomous Driving
Jul 15, 2026Yuan Gao, Wenting Miao, Mattia Piccinini +3Autonomous Driving Benchmarks Retrieval-Augmented Generation
Professorship of Autonomous Vehicle Systems, TUM School of Engineering and Design, Technical University of Munich, 85748 Garching, Germany; Munich Institute of Robotics and Machine Intelligence (MIRMI) · University College London, London, United Kingdom
Instant NuRec: Feed-Forward 3D Gaussian Reconstruction for Driving Scene Simulation
Jul 15, 2026NVIDIA, :, Jiahui Huang +143D Gaussian Splatting Multi-View 3D Reconstruction
NVIDIA†
M $^\text{4}$ World: A Multi-view Multimodal Driving World Model for Interactive Object Manipulation and Minute-long Streaming
Jul 15, 2026Ke Cheng, Hanqiao Ye, Lei Shi +8Multi-View Video Generation Long-Horizon Video Generation
1Meituan · Institute of Automation, Chinese Academy of Sciences · 3Beijing Institute of Technology
nuTruck: Benchmarking Autonomous Driving Planning for Distributed Electric-drive Trucks
Jul 15, 2026Jinyu Miao, Pu Zhang, Yifei He +5Autonomous Driving Datasets Autonomous Driving Benchmarks
School of Vehicle and Mobility, Tsinghua University, Beijing, China · KargoBot.AI Inc., Beijing, China
TerraZero: Procedural Driving Simulation for Zero-Demonstration Self-Play at Scale
Jul 14, 2026Zhouchonghao Wu, Akshay Rangesh, Weixin Li +4Self-Play RL RL for Autonomous Driving
1Applied Intuition · University of California, Berkeley
Shift & Drift: A Zero-Shot Benchmark for Generalizable and Robust Autonomous Driving Motion Planning
Jul 8, 2026Alessandro Canevaro, Hang Yu, Julian Schmidt +5Autonomous Driving Benchmarks Distribution Shift
Mercedes-Benz AG, Research & Development, Sindelfingen, Germany · University of Tübingen, Tübingen, Germany · Karlsruhe Institute of Technology, ITIV, Karlsruhe, Germany
CARLA-GS: Decoupling Representation, Reasoning, and Physics Simulation for Autonomous Driving Corner-Case Synthesis
Jul 8, 2026Kaicong Huang, Meng Ma, Ruimin KeAutonomous Driving Safety Evaluation Autonomous Driving
Department of Civil and Environmental Engineering, Rensselaer Polytechnic Institute, 110 Eighth Street, Troy, NY USA 12180.
Flow-ERD: Agent-type Aware Flow Matching with Entropy-Regularized Distillation for Diverse Traffic Simulation
Jul 8, 2026Seulbin Hwang, Kiyoung Om, Daejung Kim +1Autonomous Driving Benchmarks Flow Matching
NAVER LABS Corp., Republic of Korea
WildCity: A Real-World City-Scale Testbed for Rendering, Simulation, and Spatial Intelligence
Jul 7, 2026Xiangyu Han, Mengyu Yang, Jiaqi Li +9Autonomous Driving Datasets 3D Reconstruction
May Mobility, Ann Arbor, MI, USA · New York University, New York, NY, USA · Stanford University, Stanford, CA, USA +1
Point as Skeleton: Accumulated Point Cloud Enhanced Autoregressive Generation for Closed-Loop Autonomous Driving Simulation
Jul 7, 2026Songbur Wong, Xiaosong Jia, Junqi You +12Autoregressive Video Generation Autonomous Driving Simulation
1Shanghai Jiao Tong University · 3Fudan University · 4Shanghai Artificial Intelligence Laboratory +3
A Risk-Field Enhanced Closed-Loop Digital Twin Framework for Autonomous Driving Safety Validation
Jul 7, 2026Yongzhi LiuAutonomous Driving Safety Evaluation Digital Twins
School of Mechanical Engineering Southeast University Nanjing, China
Beyond Perfect Priors: Adaptive Gaussian Graph for 4D Driving Reconstruction in the Wild
Jul 7, 2026Xiaoyun Dong, Qian Xu, Yun Wang +3Autonomous Driving Benchmarks Dynamic Scene Reconstruction
City University of Hong Kong · Hon Hai Research Institute
OmniSCS: Omni Safety-Critical Scenario Synthesis for Autonomous Driving via a Fully Editable Driving World
Jul 7, 2026Xiaoyun Dong, Qian Xu, Yang Lu +33D Scene Editing Autonomous Driving Safety Evaluation
City University of Hong Kong · Hon Hai Research Institute
CCFM: Collision-Constrained Flow Matching for Safety-Critical Scenario Generation
Jul 5, 2026Ke Li, Kaidi Liang, Yuxin Ding +3Flow Matching Autonomous Driving Safety Evaluation
Stony Brook University, Stony Brook, NY 11794, USA · Pennsylvania State University, University Park, PA 16802, USA
Agent-driven Long-tail Simulation for Autonomous Driving
Jul 5, 2026Junru Gu, Lijin Yang, Jianing Huang +3Autonomous Driving Benchmarks Language Model-Based Control
1IIIS, Tsinghua University · 2Bosch Research
Controllable Sim Agents with Behavior Latents
Jul 2, 2026Juanwu Lu, Junyu Zhu, Ziran WangHuman Behavior Simulation Imitation Learning
Purdue University · University of Tokyo
CommonRoad-Game: A Human-in-the-Loop Simulation Framework for Autonomous Driving
Jul 1, 2026Yunfei Bi, Youran WangHuman-in-the-Loop Evaluation Autonomous Driving Planning
Technical University of Munich Munich, Germany
ECoSim: Data Efficient Fine-Tuning for Controllable Traffic Simulation
Jul 1, 2026Yu-Hsiang Chen, Wei-Jer Chang, Yi-Ting Chen +1Synthetic Data Generation for Robotics Autonomous Driving Simulation
National Yang Ming Chiao Tung University, Taiwan · University of California, Berkeley, USA
DriveWeaver: Point-Conditioned Video Inpainting for Controllable Vehicle Insertion in Autonomous Driving Simulation
Jun 30, 2026Junzhe Jiang, Zipei Ma, Zijie Pan +1Synthetic Data Augmentation Autonomous Driving
School of Data Science, Fudan University · Shanghai Innovation Institute
Bridging Local Observation and Global Simulation in Closed-Loop Traffic Modeling
Jun 30, 2026Ziyan Wang, Tan Xiang, Peng Chen +1Test-Time Adaptation Autonomous Driving Simulation
The University of Hong Kong · Beihang University
ForgeDrive: Bidirectional Cross-Conditioning for Unified Visual-Action Generation in Autonomous Driving
Jun 30, 2026Xuchang Zhong, He Zheng, Chenxu Zhao +8Diffusion-Based Planning World Models
1Amap, Alibaba Group · 2Tsinghua University
Long-term Traffic Simulation via Structured Autoregressive Modeling
Jun 30, 2026Lingyu Xiao, Zexin Feng, Xintao YanIntelligent Transportation Systems Autonomous Driving Simulation
The University of Hong Kong, Pokfulam, Hong Kong
Scenario Generation for Testing of Autonomous Driving Systems Using Real-World Failure Records
Jun 30, 2026Anjali Parashar, Chuchu FanAutonomous Driving Safety Evaluation Synthetic Data Generation
Massachusetts Institute of Technology, Cambridge, MA
InfiniVerse: Occupancy Guided Unbounded Scene Generation for Autonomous Driving
Jun 30, 2026Xiaoyu Ye, Leheng Li, Xinyu Ji +8Long-Horizon Video Generation 3D Scene Generation
The Chinese University of Hong Kong, Shenzhen · The Hong Kong University of Science and Technolody(Guangzhou) · Nanyang Technological University +2
TrafficAlign: Aligning Large Language Models for Traffic Scenario Generation
Jun 27, 2026Zhi Tu, Liangkun Niu, Tianyi ZhangLLM Alignment Autonomous Driving Safety Evaluation
Purdue University
Proposal-Conditioned Latent Diffusion for Closed-Loop Traffic Scenario Generation
Jun 25, 2026Shubham Vaijanath Phoolari, Aleyna Kara, Christoph Lauer +1Diffusion Guidance Diffusion Model Acceleration
Authors are with CARIAD SE, Germany. · Author is with the Institute of Automotive Engineering (FZD), TU Darmstadt, Germany. · Author is with the Technical University of Munich, Germany.
OSC2Runner: OpenSCENARIO 2.x Compliant High-Fidelity AV Simulation in CARLA
Jun 25, 2026Thoshitha Gamage, Lasanthi GamageAutonomous Driving Simulation
Southern Illinois University Edwardsville, Edwardsville, IL, USA · Webster University, St. Louis, MO, USA
DriveStack-VLA: Render-Teacher Alignment for BEV-Based DeepStack Vision-Language-Action Model
Jun 23, 2026Jingke Wang, Zhenru Zhao, Shuangming Lei +8VLMs for Autonomous Driving End-to-End Autonomous Driving
Zhejiang University, Hangzhou, China. · The 2012 Labs, Huawei.
A Query-Driven Communication-Efficient Digital Twins Design for Autonomous Driving
Jun 22, 2026Nuocheng Yang, Longyu Zhou, Sihua Wang +2Autonomous Driving Digital Twins
Beijing Laboratory of Advanced Information Network, and the Beijing Key Laboratory of Network System Architecture and Convergence, Beijing University of Posts and Telecommunications, Beijing 100876, China · Information Systems Technology and Design Pillar, Singapore University of Technology and Design, 487372, Singapore

Jul 17, 2026J/K move · Enter open · S save

Think at 5 Hz, Act at 20 Hz: Asynchronous Fast-Slow Vision-Language-Action Inference for Closed-Loop Driving

Yun Li, Jiachen Gong, Simon Thompson, Ehsan Javanmardi+6

The University of Tokyo, Tokyo, Japan · TIER IV, Inc., Tokyo, Japan · Huawei

Efficient VLA Model Inference Vision-Language-Action Models Autonomous Driving Planning Autonomous Driving Simulation

Open paper AskPDF arXiv

Large language models bring instruction following and scene reasoning to end-to-end driving, but their inference latency collides with the control rate a vehicle requires. Existing closed-loop agents hide this gap by invoking the model on alternate simulation ticks and replaying the previous command in between, so half of all control outputs ignore the newest observations. We present a fast-slow architecture that removes this compromise. A frozen 7B vision-language backbone acts as the slow system, digesting navigation instructions and visual history at low frequency while exposing its per-layer key-value cache as a standing representation of the scene. A lightweight action expert acts as the fast system, attending to this cache and to the current camera frame at every simulation tick to regress waypoints in a single forward pass. Since the cache lags behind the world at deployment, we train the expert under randomized staleness, aligning training with asynchronous execution. On LangAuto-Short routes in CARLA, our system produces fresh control at every 50 ms simulation tick and lifts route completion from 37.0 to 94.0 over the frame-skipping baseline. A frame-skip ablation with the same expert separates the two factors at work: the expert raises the driving score on its own, while per-tick freshness raises completion from 82.1 to 94.0 and cuts red-light violations by a third. Trained on a single town, the expert transfers zero-shot to two unseen towns, holding 84-94% route completion where the baseline reaches 31-41%. It reduces open-loop waypoint error by nearly a factor of four compared to the backbone's own action head, at a per-tick model cost of 32 ms that is independent of history length on a single consumer GPU.