mlsanityData to 14 Oct 2026

Bench2Drive: Towards Multi-Ability Benchmarking of Closed-Loop End-To-End Autonomous Driving

arXiv 2406.03877 ↗First posted 6 Jun 2024cs.RO cs.CVcited by 252

On the map: End-to-end autonomous driving → End-to-end system architecture

Abstract (arXiv)

In an era marked by the rapid scaling of foundation models, autonomous driving technologies are approaching a transformative threshold where end-to-end autonomous driving (E2E-AD) emerges due to its potential of scaling up in the data-driven manner. However, existing E2E-AD methods are mostly evaluated under the open-loop log-replay manner with L2 errors and collision rate as metrics (e.g., in nuScenes), which could not fully reflect the driving performance of algorithms as recently acknowledged in the community. For those E2E-AD methods evaluated under the closed-loop protocol, they are tested in fixed routes (e.g., Town05Long and Longest6 in CARLA) with the driving score as metrics, which is known for high variance due to the unsmoothed metric function and large randomness in the long route. Besides, these methods usually collect their own data for training, which makes algorithm-level fair comparison infeasible. To fulfill the paramount need of comprehensive, realistic, and fair testing environments for Full Self-Driving (FSD), we present Bench2Drive, the first benchmark for evaluating E2E-AD systems' multiple abilities in a closed-loop manner. Bench2Drive's official training data consists of 2 million fully annotated frames, collected from 13638 short clips uniformly distributed under 44 interactive scenarios (cut-in, overtaking, detour, etc), 23 weathers (sunny, foggy, rainy, etc), and 12 towns (urban, village, university, etc) in CARLA v2. Its evaluation protocol requires E2E-AD models to pass 44 interactive scenarios under different locations and weathers which sums up to 220 routes and thus provides a comprehensive and disentangled assessment about their driving capability under different situations. We implement state-of-the-art E2E-AD models and evaluate them in Bench2Drive, providing insights regarding current status and future directions.

Key facts. Cited by 252 papers in the map (data through 14 Oct 2026). Placed in End-to-end system architecture, one of 9 directions in End-to-end autonomous driving. Builds on 52 of its 66 references that are in the map. First posted on arXiv 6 Jun 2024.

Builds on

52 of 66 references.

Closest ancestors · 12

Same direction, newest first

  1. 2024Towards learning-based planning:The nuPlan benchmark for real-world autonomous driving7 Mar
  2. 2023Is Ego Status All You Need for Open-Loop End-to-End Autonomous Driving?5 Dec
  3. 2023DriveAdapter: Breaking the Coupling Barrier of Perception and Planning in End-to-End Autonomous Driving1 Aug
  4. 2023Hidden Biases of End-to-End Driving Models13 Jun
  5. 2023Rethinking the Open-Loop Evaluation of End-to-End Autonomous Driving in nuScenes17 May
  6. 2023Think Twice before Driving: Towards Scalable Decoders for End-to-End Autonomous Driving10 May
  7. 2022ST-P3: End-to-end Vision-based Autonomous Driving via Spatial-Temporal Feature Learning15 Jul
  8. 2022MMFN: Multi-Modal-Fusion-Net for End-to-End Driving1 Jul
  9. 2022Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baseline16 Jun
  10. 2022TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving31 May
  11. 2021Autonomy 2.0: Why is self-driving always 5 years away?16 Jul
  12. 2021Multi-Modal Fusion Transformer for End-to-End Autonomous Driving19 Apr

Other references · 40

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  4. 2021On the Opportunities and Risks of Foundation Modelscited by 4,033
  5. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,451
  6. 2017CARLA: An Open Urban Driving Simulatorcited by 2,449
  7. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,218
  8. 2022Planning-oriented Autonomous Drivingcited by 1,087
  9. 2022BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representationcited by 850
  10. 2023Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecastingcited by 707
  11. 2023VAD: Vectorized Scene Representation for Efficient Autonomous Drivingcited by 622
  12. 2017End-to-end Driving via Conditional Imitation Learningcited by 485
28 more
  1. 2019Learning by Cheatingcited by 383
  2. 2024Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllabilitycited by 347
  3. 2019Exploring the Limitations of Behavior Cloning for Autonomous Drivingcited by 346
  4. 2019Causal Confusion in Imitation Learningcited by 288
  5. 2018The highD Dataset: A Drone Dataset of Naturalistic Vehicle Trajectories on German Highways for Validation of Highly Automated Driving Systemscited by 277
  6. 2023Parting with Misconceptions about Learning-based Vehicle Motion Planningcited by 242
  7. 2022Safety-Enhanced Autonomous Driving Using Interpretable Sensor Fusion Transformercited by 212
  8. 2021End-to-End Urban Driving by Imitating a Reinforcement Learning Coachcited by 194
  9. 2019SiamFC++: Towards Robust and Accurate Visual Tracking with Target Estimation Guidelinescited by 177
  10. 2021NEAT: Neural Attention Fields for End-to-End Autonomous Drivingcited by 174
  11. 2023Waymax: An Accelerated, Data-Driven Simulator for Large-Scale Autonomous Driving Researchcited by 160
  12. 2022Model-Based Imitation Learning for Urban Drivingcited by 150
  13. 2024GenAD: Generalized Predictive Model for Autonomous Drivingcited by 150
  14. 2019End-to-End Model-Free Reinforcement Learning for Urban Driving using Implicit Affordancescited by 149
  15. 2023LLM4Drive: A Survey of Large Language Models for Autonomous Drivingcited by 136
  16. 2022Learning from All Vehiclescited by 135
  17. 2022Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipecited by 122
  18. 2022HDGT: Heterogeneous Driving Graph Transformer for Multi-Agent Trajectory Prediction via Scene Encodingcited by 110
  19. 2022PlanT: Explainable Planning Transformers via Object-Level Representationscited by 105
  20. 2024Think2Drive: Efficient Reinforcement Learning by Thinking in Latent World Model for Quasi-Realistic Autonomous Driving (in CARLA-v2)cited by 52
  21. 2023Policy Pre-training for Autonomous Driving via Self-supervised Geometric Modelingcited by 26
  22. 2020BARK: Open Behavior Benchmarking in Multi-Agent Environmentscited by 21
  23. 2023LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarioscited by 20
  24. 2020IDE-Net: Interactive Driving Event and Pattern Extraction from Human Datacited by 19
  25. 2023Coaching a Teachable Studentcited by 19
  26. 2024AMP: Autoregressive Motion Prediction Revisited with Next Token Prediction for Autonomous Drivingcited by 13
  27. 2024Efficient Preference-based Reinforcement Learning via Aligned Experience Estimationcited by 9
  28. 2023DRL-Based Trajectory Tracking for Motion-Related Modules in Autonomous Drivingcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 16; 2025: 99; 2026: 137.

252 papers.

Sort:

By area:

  1. 2025AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuningcited by 260
  2. 2025ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Drivingcited by 198
  3. 2025ORION: A Holistic End-to-End Autonomous Driving Framework by Vision-Language Instructed Action Generationcited by 178
  4. 2025OpenDriveVLA: Towards End-to-end Autonomous Driving with Large Vision Language Action Modelcited by 176
  5. 2024Senna: Bridging Large Vision-Language Models and End-to-End Autonomous Drivingcited by 156
  6. 2025End-to-End Driving with Online Trajectory Evaluation via BEV World Modelcited by 151
  7. 2025SimLingo: Vision-Only Closed-Loop Autonomous Driving with Language-Action Alignmentcited by 150
  8. 2025Alpamayo-R1: Bridging Reasoning and Action Prediction for Generalizable Autonomous Driving in the Long Tailcited by 146
  9. 2025DriveTransformer: Unified Transformer for Scalable End-to-End Autonomous Drivingcited by 126
  10. 2024DriveArena: A Closed-loop Generative Simulation Platform for Autonomous Drivingcited by 98
  11. 2025DriveMoE: Mixture-of-Experts for Vision-Language-Action Model in End-to-End Autonomous Drivingcited by 86
  12. 2025Don't Shake the Wheel: Momentum-Aware Planning in End-to-End Autonomous Drivingcited by 84
38 more
  1. 2025A Survey on Vision-Language-Action Models for Autonomous Drivingcited by 72
  2. 2025Impromptu VLA: Open Weights and Open Data for Driving Vision-Language-Action Modelscited by 60
  3. 2025Pure Vision Language Action (VLA) Models: A Comprehensive Surveycited by 49
  4. 2024V2X-VLM: End-to-End V2X Cooperative Autonomous Driving Through Large Vision-Language Modelscited by 47
  5. 2025Raw2Drive: Reinforcement Learning with Aligned World Models for End-to-End Autonomous Driving (in CARLA v2)cited by 47
  6. 2026DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generationcited by 45
  7. 2025ReSim: Reliable World Simulation for Autonomous Drivingcited by 44
  8. 2025Centaur: Robust End-to-End Autonomous Driving with Test-Time Trainingcited by 42
  9. 2025iPad: Iterative Proposal-centric End-to-End Autonomous Drivingcited by 42
  10. 2025RAP: 3D Rasterization Augmented End-to-End Planningcited by 41
  11. 2025Hydra-NeXt: Robust Closed-Loop Driving with Open-Loop Trainingcited by 39
  12. 2025DriveDPO: Policy Learning via Safety DPO For End-to-End Autonomous Drivingcited by 39
  13. 2026SGDrive: Scene-to-Goal Hierarchical World Cognition for Autonomous Drivingcited by 38
  14. 2025HiP-AD: Hierarchical and Multi-Granularity Planning with Deformable Attention for Autonomous Driving in a Single Decodercited by 35
  15. 2025Vision-Language-Action Models for Autonomous Driving: Past, Present, and Futurecited by 33
  16. 2024Hidden Biases of End-to-End Driving Datasetscited by 30
  17. 2026Drive-JEPA: Video JEPA Meets Multimodal Trajectory Distillation for End-to-End Drivingcited by 30
  18. 2025The Role of World Models in Shaping Autonomous Driving: A Comprehensive Surveycited by 29
  19. 2024End-to-End Autonomous Driving without Costly Modularization and 3D Manual Annotationcited by 28
  20. 2025SpaceDrive: Infusing Spatial Awareness into VLM-based Autonomous Drivingcited by 28
  21. 2025DiffAD: A Unified Diffusion Modeling Approach for Autonomous Drivingcited by 26
  22. 2026SparseDriveV2: Scoring is All You Need for End-to-End Autonomous Drivingcited by 26
  23. 2024How to Synthesize Text Data without Model Collapse?cited by 25
  24. 2025Sce2DriveX: A Generalized MLLM Framework for Scene-to-Drive Learningcited by 25
  25. 2025ImagiDrive: A Unified Imagination-and-Planning Framework for Autonomous Drivingcited by 25
  26. 2025MindDrive: A Vision-Language-Action Model for Autonomous Driving via Online Reinforcement Learningcited by 25
  27. 2025AdaWM: Adaptive World Model based Planning for Autonomous Drivingcited by 24
  28. 2025LEAD: Minimizing Learner-Expert Asymmetry in End-to-End Drivingcited by 23
  29. 2026DriveVA: Video Action Models are Zero-Shot Driverscited by 23
  30. 2025ReasonPlan: Unified Scene Prediction and Decision Reasoning for Closed-loop Autonomous Drivingcited by 22
  31. 2025GuideFlow: Constraint-Guided Flow Matching for Planning in End-to-End Autonomous Drivingcited by 22
  32. 2026UniDrive-WM: Unified Understanding, Planning and Generation World Model for Autonomous Drivingcited by 20
  33. 2025Reinforced Refinement with Self-Aware Expansion for End-to-End Autonomous Drivingcited by 19
  34. 2026UniDriveVLA: Unifying Understanding, Perception, and Action Planning for Autonomous Drivingcited by 19
  35. 2025BridgeDrive: Diffusion Bridge Policy for Closed-Loop Trajectory Planning in Autonomous Drivingcited by 18
  36. 2025STSBench: A Spatio-temporal Scenario Benchmark for Multi-modal Large Language Models in Autonomous Drivingcited by 17
  37. 2025DIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous Drivingcited by 17
  38. 2026Fail2Drive: Benchmarking Closed-Loop Driving Generalizationcited by 17

50 most cited of 252 All 252 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Bench2Drive-R: Turning Real World Data into Reactive Closed-Loop Autonomous Driving Benchmark by Generative Model
  2. 2023End-to-end Autonomous Driving: Challenges and Frontiers
  3. 2024NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking
  4. 2024Data-Centric Evolution in Autonomous Driving: A Comprehensive Survey of Big Data System, Data Mining, and Closed-Loop Technologies
  5. 2025Unraveling the Effects of Synthetic Data on End-to-End Autonomous Driving
  6. 2025WOD-E2E: Waymo Open Dataset for End-to-End Driving in Challenging Long-tail Scenarios
  7. 2026MDrive: Benchmarking Closed-Loop Cooperative Driving for End-to-End Multi-agent Systems
  8. 2026OVPD: A Virtual-Physical Fusion Testing Dataset of OnSite Auton-omous Driving Challenge