mlsanityData to 7 Oct 2026

End-to-end system architecture

282 papers2 this weekLow confidence in this grouping: the papers may belong to more than one topic, or the group may changeLow confidence in this grouping: the papers may belong to more than one topic, or the group may change · About

Keywords: driving, autonomous, end-to-end, autonomous driving, planning

Key facts. End-to-end system architecture: 282 papers on arXiv since 2021 (data through 7 Oct 2026). 95 of its 282 mapped papers (34%) cite “TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving” (2022, arXiv 2205.15997). 68 of its 282 mapped papers (24%) cite “End-to-end Autonomous Driving: Challenges and Frontiers” (2023, arXiv 2306.16927). 13 new papers 17 Sep–7 Oct.

What’s new

17 Sep – 7 Oct 2026

13 new papers, 17 Sep – 7 Oct; 2 this week.

  1. This week · 2
  2. Do Better Visual Representations Always Lead to Better End-to-End Autonomous Driving? also fits: Reasoning VLA and VLM driving policies
  3. Odyssey: A Closed-Loop Benchmark for Long-Horizon Real-World Driving with Explicit Navigation Routes also fits: Generative simulation for driving
  4. Earlier · 11
  5. Autoware in Construction: Gap Analysis and LiDAR Perception Toward Off-Road Autonomous Driving
  6. Towards Safer Autonomous Driving in an Open World: A Dual-Process Approach also fits: Adversarial scenarios and safety testing
  7. End-to-End Learning vs. Modular Architectures: Comparative Insights into Autonomous Driving Systems
  8. A Survey on End-to-End Autonomous Driving Training from the Perspectives of Data, Strategy, and Platform
  9. When the Score Becomes the Target: Rethinking Metric Validity in Autonomous Driving also fits: Imitation-learning end-to-end planners
  10. Auditing Latent-Space Monitors for Autonomous Driving also fits: Adversarial scenarios and safety testing
  11. S2Planner: Multi-Scale Semantic Planner for End-to-End Autonomous Driving
  12. FeasibleFlow: One-Step Joint Transport of Configuration Feasibility and Trajectories for End-to-End Driving also fits: Generative simulation for driving
All 13
  1. Planning-Aligned Pretraining of BEV Representations with Sparse Action-Conditioned Targets for End-to-End Autonomous Driving also fits: Generative simulation for driving
  2. Driving on Registers, Reasoning on Risk: Risk-Aware Occupancy for Register-Based End-to-End Autonomous Driving
  3. Risk-Aware Occupancy for Safety-Oriented End-to-End Autonomous Driving also fits: Adversarial scenarios and safety testing

Foundations

Most cited by papers here

  1. TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving2022cited by 95 here
  2. End-to-end Autonomous Driving: Challenges and Frontiers2023cited by 68 here
  3. ST-P3: End-to-end Vision-based Autonomous Driving via Spatial-Temporal Feature Learning2022cited by 64 here
  4. NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking2024cited by 62 here
  5. Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baseline2022cited by 61 here

Lineage

The papers this direction builds on, oldest first.

Each paper on the line cites the one before.

  1. 2021Multi-Modal Fusion Transformer for End-to-End Autonomous Drivingcited by 60 here
  2. 2021Learning to drive from a world on railscited by 27 here
  3. 2021NEAT: Neural Attention Fields for End-to-End Autonomous Drivingcited by 40 here
  4. 2022Learning from All Vehiclescited by 33 here
  5. 2022ST-P3: End-to-end Vision-based Autonomous Driving via Spatial-Temporal Feature Learningcited by 64 here
  6. 2023VAD: Vectorized Scene Representation for Efficient Autonomous Drivingcited by 100 here
  7. 2023Rethinking the Open-Loop Evaluation of End-to-End Autonomous Driving in nuScenescited by 44 here
  8. 2023End-to-end Autonomous Driving: Challenges and Frontierscited by 68 here
  9. 2023Is Ego Status All You Need for Open-Loop End-to-End Autonomous Driving?cited by 57 here
  10. 2023DriveLM: Driving with Graph Visual Question Answeringcited by 27 here
  11. 2024VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planningcited by 49 here
  12. 2024NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarkingcited by 62 here
  13. 2024DiffusionDrive: Truncated Diffusion Model for End-to-End Autonomous Drivingcited by 52 here
11 more it builds on, not in this chain
  1. 2021End-to-end Interpretable Neural Motion Plannercited by 46 here
  2. 2021NuPlan: A closed-loop ML-based planning benchmark for autonomous vehiclescited by 47 here
  3. 2021End-to-End Urban Driving by Imitating a Reinforcement Learning Coachcited by 33 here
  4. 2022TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Drivingcited by 95 here
  5. 2022Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baselinecited by 61 here
  6. 2023Think Twice before Driving: Towards Scalable Decoders for End-to-End Autonomous Drivingcited by 41 here
  7. 2023Hidden Biases of End-to-End Driving Modelscited by 35 here
  8. 2023DriveAdapter: Breaking the Coupling Barrier of Perception and Planning in End-to-End Autonomous Drivingcited by 37 here
  9. 2024GenAD: Generative End-to-End Autonomous Drivingcited by 36 here
  10. 2024SparseDrive: End-to-End Autonomous Driving via Sparse Scene Representationcited by 53 here
  11. 2024Bench2Drive: Towards Multi-Ability Benchmarking of Closed-Loop End-To-End Autonomous Drivingcited by 54 here

The 24 most cited of 491.

Browse

30 of 282, ranked 6–35

  1. 6Multi-Modal Fusion Transformer for End-to-End Autonomous Driving202160
  2. 7Is Ego Status All You Need for Open-Loop End-to-End Autonomous Driving?202357
  3. 8Bench2Drive: Towards Multi-Ability Benchmarking of Closed-Loop End-To-End Autonomous Driving202454
  4. 9SparseDrive: End-to-End Autonomous Driving via Sparse Scene Representation202453
  5. 10NuPlan: A closed-loop ML-based planning benchmark for autonomous vehicles202147
  6. 11End-to-end Interpretable Neural Motion Planner202146
  7. 12Rethinking the Open-Loop Evaluation of End-to-End Autonomous Driving in nuScenes202344
  8. 13Think Twice before Driving: Towards Scalable Decoders for End-to-End Autonomous Driving202341
  9. 14DriveAdapter: Breaking the Coupling Barrier of Perception and Planning in End-to-End Autonomous Driving202337
  10. 15Hidden Biases of End-to-End Driving Models202335
All 30
  1. 16DriveTransformer: Unified Transformer for Scalable End-to-End Autonomous Driving202527
  2. 17End-to-End Driving with Online Trajectory Evaluation via BEV World Model202526
  3. 18Enhancing End-to-End Autonomous Driving with Latent World Model202422
  4. 19Hydra-MDP++: Advancing End-to-End Driving via Expert-Guided Hydra-Distillation202518
  5. 20FusionAD: Multi-modality Fusion for Prediction and Planning Tasks of Autonomous Driving202318
  6. 21Don't Shake the Wheel: Momentum-Aware Planning in End-to-End Autonomous Driving202517
  7. 22Towards learning-based planning:The nuPlan benchmark for real-world autonomous driving202417
  8. 23DRAMA: An Efficient End-to-end Motion Planner for Autonomous Driving with Mamba202417
  9. 24Hidden Biases of End-to-End Driving Datasets202413
  10. 25World4Drive: End-to-End Autonomous Driving via Intention-aware Physical Latent World Model202512
  11. 26Navigation-Guided Sparse Scene Representation for End-to-End Autonomous Driving202412
  12. 27HiP-AD: Hierarchical and Multi-Granularity Planning with Deformable Attention for Autonomous Driving in a Single Decoder202511
  13. 28Hydra-NeXt: Robust Closed-Loop Driving with Open-Loop Training202510
  14. 29WOD-E2E: Waymo Open Dataset for End-to-End Driving in Challenging Long-tail Scenarios202510
  15. 30iPad: Iterative Proposal-centric End-to-End Autonomous Driving20259
  16. 31Recent Advancements in End-to-End Autonomous Driving using Deep Learning: A Survey20239
  17. 32MMFN: Multi-Modal-Fusion-Net for End-to-End Driving20229
  18. 33SafetyNet: Safe planning for real-world self-driving vehicles using machine-learned policies20219
  19. 34ARTEMIS: Autoregressive End-to-End Trajectory Planning with Mixture of Experts for Autonomous Driving20258
  20. 35Drive Anywhere: Generalizable End-to-end Autonomous Driving with Multi-modal Foundation Models20238