mlsanityData to 7 Oct 2026

Rethinking the Open-Loop Evaluation of End-to-End Autonomous Driving in nuScenes

arXiv 2305.10430 ↗First posted 17 May 2023cs.CVcited by 191

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

Abstract (arXiv)

Modern autonomous driving systems are typically divided into three main tasks: perception, prediction, and planning. The planning task involves predicting the trajectory of the ego vehicle based on inputs from both internal intention and the external environment, and manipulating the vehicle accordingly. Most existing works evaluate their performance on the nuScenes dataset using the L2 error and collision rate between the predicted trajectories and the ground truth. In this paper, we reevaluate these existing evaluation metrics and explore whether they accurately measure the superiority of different methods. Specifically, we design an MLP-based method that takes raw sensor data (e.g., past trajectory, velocity, etc.) as input and directly outputs the future trajectory of the ego vehicle, without using any perception or prediction information such as camera images or LiDAR. Our simple method achieves similar end-to-end planning performance on the nuScenes dataset with other perception-based methods, reducing the average L2 error by about 20%. Meanwhile, the perception-based methods have an advantage in terms of collision rate. We further conduct in-depth analysis and provide new insights into the factors that are critical for the success of the planning task on nuScenes dataset. Our observation also indicates that we need to rethink the current open-loop evaluation scheme of end-to-end autonomous driving in nuScenes. Codes are available at https://github.com/E2E-AD/AD-MLP.

Key facts. Cited by 191 papers in the map (data through 7 Oct 2026). Placed in End-to-end system architecture, one of 9 directions in End-to-end autonomous driving. Builds on 15 of its 18 references that are in the map. First posted on arXiv 17 May 2023.

Builds on

15 of 18 references.

Closest ancestors · 3

Same direction, newest first

  1. 2022ST-P3: End-to-end Vision-based Autonomous Driving via Spatial-Temporal Feature Learning15 Jul
  2. 2022TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving31 May
  3. 2021End-to-end Interpretable Neural Motion Planner17 Jan

Other references · 12

  1. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  2. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  3. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,213
  4. 2022Planning-oriented Autonomous Drivingcited by 1,068
  5. 2023VAD: Vectorized Scene Representation for Efficient Autonomous Drivingcited by 613
  6. 2021DenseTNT: End-to-end Trajectory Prediction from Dense Goal Setscited by 292
  7. 2020Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting with a Single Convolutional Netcited by 228
  8. 2020Perceive, Predict, and Plan: Safe Motion Planning Through Interpretable Semantic Representationscited by 150
  9. 2020PnPNet: End-to-End Perception and Prediction with Tracking in the Loopcited by 143
  10. 2022Differentiable Raycasting for Self-supervised Occupancy Forecastingcited by 83
  11. 2023CAPE: Camera View Position Embedding for Multi-View 3D Object Detectioncited by 39
  12. 2021What data do we need for training an AV motion planner?cited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 7; 2024: 37; 2025: 83; 2026: 64.

191 papers.

Sort:

By area:

  1. 2023End-to-end Autonomous Driving: Challenges and Frontierscited by 485
  2. 2024DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Modelscited by 482
  3. 2024NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarkingcited by 343
  4. 2024Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllabilitycited by 337
  5. 2023DriveDreamer: Towards Real-world-driven World Models for Autonomous Drivingcited by 258
  6. 2025AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuningcited by 252
  7. 2024Bench2Drive: Towards Multi-Ability Benchmarking of Closed-Loop End-To-End Autonomous Drivingcited by 250
  8. 2023Is Ego Status All You Need for Open-Loop End-to-End Autonomous Driving?cited by 242
  9. 2024SparseDrive: End-to-End Autonomous Driving via Sparse Scene Representationcited by 239
  10. 2023Parting with Misconceptions about Learning-based Vehicle Motion Planningcited by 238
  11. 2023DriveMLM: Aligning Multi-Modal Large Language Models with Behavioral Planning States for Autonomous Drivingcited by 233
  12. 2024EMMA: End-to-End Multimodal Model for Autonomous Drivingcited by 226
38 more
  1. 2025ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Drivingcited by 190
  2. 2025ORION: A Holistic End-to-End Autonomous Driving Framework by Vision-Language Instructed Action Generationcited by 177
  3. 2025OpenDriveVLA: Towards End-to-end Autonomous Driving with Large Vision Language Action Modelcited by 172
  4. 2025SimLingo: Vision-Only Closed-Loop Autonomous Driving with Language-Action Alignmentcited by 149
  5. 2025End-to-End Driving with Online Trajectory Evaluation via BEV World Modelcited by 145
  6. 2025OmniDrive: A Holistic Vision-Language Dataset for Autonomous Driving with Counterfactual Reasoningcited by 142
  7. 2025Pseudo-Simulation for Autonomous Drivingcited by 141
  8. 2025DriveTransformer: Unified Transformer for Scalable End-to-End Autonomous Drivingcited by 125
  9. 2024DriveDreamer4D: World Models Are Effective Data Machines for 4D Driving Scene Representationcited by 123
  10. 2024textitS3Gaussian: Self-Supervised Street Gaussians for Autonomous Drivingcited by 105
  11. 2024DriveArena: A Closed-loop Generative Simulation Platform for Autonomous Drivingcited by 98
  12. 2024OpenEMMA: Open-Source Multimodal Model for End-to-End Autonomous Drivingcited by 93
  13. 2024ReconDreamer: Crafting World Models for Driving Scene Reconstruction via Online Restorationcited by 89
  14. 2024VLM-AD: End-to-End Autonomous Driving through Vision-Language Model Supervisioncited by 85
  15. 2025DriveMoE: Mixture-of-Experts for Vision-Language-Action Model in End-to-End Autonomous Drivingcited by 85
  16. 2025RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-based Reinforcement Learningcited by 76
  17. 2025ARTEMIS: Autoregressive End-to-End Trajectory Planning with Mixture of Experts for Autonomous Drivingcited by 66
  18. 2025WOD-E2E: Waymo Open Dataset for End-to-End Driving in Challenging Long-tail Scenarioscited by 60
  19. 2024Unleashing Generalization of End-to-End Autonomous Driving with Controllable Long Video Generationcited by 54
  20. 2024LidarDM: Generative LiDAR Simulation in a Generated Worldcited by 53
  21. 2024Making Large Language Models Better Planners with Reasoning-Decision Alignmentcited by 51
  22. 2025Distilling Multi-modal Large Language Models for Autonomous Drivingcited by 46
  23. 2025Raw2Drive: Reinforcement Learning with Aligned World Models for End-to-End Autonomous Driving (in CARLA v2)cited by 45
  24. 2024End-to-End Autonomous Driving through V2X Cooperationcited by 42
  25. 2025iPad: Iterative Proposal-centric End-to-End Autonomous Drivingcited by 41
  26. 2025RAP: 3D Rasterization Augmented End-to-End Planningcited by 39
  27. 2024PlanAgent: A Multi-modal Large Language Agent for Closed-loop Vehicle Motion Planningcited by 38
  28. 2025HiP-AD: Hierarchical and Multi-Granularity Planning with Deformable Attention for Autonomous Driving in a Single Decodercited by 35
  29. 2025VaViM and VaVAM: Autonomous Driving through Video Generative Modelingcited by 34
  30. 2025AutoDrive-R2: Incentivizing Reasoning and Self-Reflection Capacity for VLA Model in Autonomous Drivingcited by 32
  31. 2024Hidden Biases of End-to-End Driving Datasetscited by 30
  32. 2023The Integration of Prediction and Planning in Deep Learning Automated Driving Systems: A Reviewcited by 29
  33. 2025Semi-Supervised Vision-Centric 3D Occupancy World Model for Autonomous Drivingcited by 29
  34. 2025From Forecasting to Planning: Policy World Model for Collaborative State-Action Predictioncited by 29
  35. 2025SpaceDrive: Infusing Spatial Awareness into VLM-based Autonomous Drivingcited by 28
  36. 2024SLEDGE: Synthesizing Driving Environments with Generative Models and Rule-Based Trafficcited by 27
  37. 2024End-to-End Autonomous Driving without Costly Modularization and 3D Manual Annotationcited by 27
  38. 2024DrivingRecon: Large 4D Gaussian Reconstruction Model For Autonomous Drivingcited by 27

50 most cited of 191 All 191 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Towards learning-based planning:The nuPlan benchmark for real-world autonomous driving
  2. 2026Planning-Oriented End-to-End Autonomous Driving: Architectures, Evaluation, and Emerging Paradigms
  3. 2025Fully Unified Motion Planning for End-to-End Autonomous Driving
  4. 2021NuPlan: A closed-loop ML-based planning benchmark for autonomous vehicles
  5. 2026TaCarla: A comprehensive benchmarking dataset for end-to-end autonomous driving
  6. 2026Addressing the Waypoint-Action Gap in End-to-End Autonomous Driving via Vehicle Motion Models
  7. 2025Perception in Plan: Coupled Perception and Planning for End-to-End Autonomous Driving
  8. 2022Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baseline