mlsanityData to 7 Oct 2026

NuPlan: A closed-loop ML-based planning benchmark for autonomous vehicles

arXiv 2106.11810 ↗First posted 22 Jun 2021cs.CVcited by 485

On the map: World models → World models for autonomous driving

also in 1 more
Abstract (arXiv)

In this work, we propose the world's first closed-loop ML-based planning benchmark for autonomous driving. While there is a growing body of ML-based motion planners, the lack of established datasets and metrics has limited the progress in this area. Existing benchmarks for autonomous vehicle motion prediction have focused on short-term motion forecasting, rather than long-term planning. This has led previous works to use open-loop evaluation with L2-based metrics, which are not suitable for fairly evaluating long-term planning. Our benchmark overcomes these limitations by introducing a large-scale driving dataset, lightweight closed-loop simulator, and motion-planning-specific metrics. We provide a high-quality dataset with 1500h of human driving data from 4 cities across the US and Asia with widely varying traffic patterns (Boston, Pittsburgh, Las Vegas and Singapore). We will provide a closed-loop simulation framework with reactive agents and provide a large set of both general and scenario-specific planning metrics. We plan to release the dataset at NeurIPS 2021 and organize benchmark challenges starting in early 2022.

Key facts. Cited by 485 papers in the map (data through 7 Oct 2026). Placed in World models for autonomous driving, one of 11 directions in World models. Builds on 19 of its 23 references that are in the map. First posted on arXiv 22 Jun 2021.

Builds on

19 of 23 references.

Closest ancestors · 2

Same direction, newest first

  1. 2020One Thousand and One Hours: Self-driving Motion Prediction Dataset25 Jun
  2. 2017CARLA: An Open Urban Driving Simulator10 Nov

Other references · 17

  1. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  2. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
  3. 2020Center-based 3D Object Detection and Trackingcited by 1,143
  4. 2019Argoverse: 3D Tracking and Forecasting with Rich Mapscited by 728
  5. 2021Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Datasetcited by 532
  6. 2018ChauffeurNet: Learning to Drive by Imitating the Best and Synthesizing the Worstcited by 391
  7. 2021Multi-Modal Fusion Transformer for End-to-End Autonomous Drivingcited by 372
  8. 2021End-to-end Interpretable Neural Motion Plannercited by 240
  9. 2021MP3: A Unified Model to Map, Perceive, Predict and Plancited by 211
  10. 2021Offboard 3D Object Detection from Point Cloud Sequencescited by 144
  11. 2021Learning to Track with Object Permanencecited by 117
  12. 2019Multimodal End-to-End Autonomous Drivingcited by 110
5 more
  1. 2019Jointly Learnable Behavior and Trajectory Planning for Self-Driving Vehiclescited by 51
  2. 2019Simulation-based reinforcement learning for real-world autonomous drivingcited by 51
  3. 2020Learning to Evaluate Perception Models Using Planner-Centric Metricscited by 49
  4. 2018Learning to Drive from Simulation without Real World Labelscited by 39
  5. 2020The efficacy of Neural Planning Metrics: A meta-analysis of PKL on nuScenescited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 14; 2023: 53; 2024: 84; 2025: 149; 2026: 182.

485 papers.

Sort:

By area:

  1. 2022Planning-oriented Autonomous Drivingcited by 1,068
  2. 2023DriveLM: Driving with Graph Visual Question Answeringcited by 527
  3. 2023End-to-end Autonomous Driving: Challenges and Frontierscited by 485
  4. 2023DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenescited by 359
  5. 2024Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllabilitycited by 337
  6. 2024Hydra-MDP: End-to-end Multimodal Planning with Multi-target Hydra-Distillationcited by 244
  7. 2023Parting with Misconceptions about Learning-based Vehicle Motion Planningcited by 238
  8. 2023EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervisioncited by 216
  9. 2024A Hierarchical 3D Gaussian Representation for Real-Time Rendering of Very Large Datasetscited by 214
  10. 2025ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Drivingcited by 190
  11. 2025OpenDriveVLA: Towards End-to-end Autonomous Driving with Large Vision Language Action Modelcited by 172
  12. 2024Enhancing End-to-End Autonomous Driving with Latent World Modelcited by 161
38 more
  1. 2024OmniRe: Omni Urban Scene Reconstructioncited by 159
  2. 2023Waymax: An Accelerated, Data-Driven Simulator for Large-Scale Autonomous Driving Researchcited by 158
  3. 2024GenAD: Generalized Predictive Model for Autonomous Drivingcited by 150
  4. 2025End-to-End Driving with Online Trajectory Evaluation via BEV World Modelcited by 145
  5. 2023GameFormer: Game-theoretic Modeling and Learning of Transformer-based Interactive Prediction and Planning for Autonomous Drivingcited by 141
  6. 2025Diffusion-Based Planning for Autonomous Driving with Flexible Guidancecited by 138
  7. 20223D Object Detection for Autonomous Driving: A Comprehensive Surveycited by 132
  8. 2025DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Drivingcited by 127
  9. 2022Imitation Is Not Enough: Robustifying Imitation with Reinforcement Learning for Challenging Driving Scenarioscited by 124
  10. 2025Epona: Autoregressive Diffusion World Model for Autonomous Drivingcited by 115
  11. 2023V2X-Seq: A Large-Scale Sequential Dataset for Vehicle-Infrastructure Cooperative Perception and Forecastingcited by 114
  12. 2024DriveArena: A Closed-loop Generative Simulation Platform for Autonomous Drivingcited by 98
  13. 2024DrivingGPT: Unifying Driving World Modeling and Planning with Multi-modal Autoregressive Transformerscited by 96
  14. 2025Hydra-MDP++: Advancing End-to-End Driving via Expert-Guided Hydra-Distillationcited by 93
  15. 2024DRAMA: An Efficient End-to-end Motion Planner for Autonomous Driving with Mambacited by 87
  16. 2023The Waymo Open Sim Agents Challengecited by 86
  17. 2024PLUTO: Pushing the Limit of Imitation Learning-based Planning for Autonomous Drivingcited by 84
  18. 2024HUGSIM: A Real-Time, Photo-Realistic and Closed-Loop Simulator for Autonomous Drivingcited by 84
  19. 2024CoVLA: Comprehensive Vision-Language-Action Dataset for Autonomous Drivingcited by 74
  20. 2023FusionAD: Multi-modality Fusion for Prediction and Planning Tasks of Autonomous Drivingcited by 67
  21. 2024DrivingWorld: Constructing World Model for Autonomous Driving via Video GPTcited by 66
  22. 2025ARTEMIS: Autoregressive End-to-End Trajectory Planning with Mixture of Experts for Autonomous Drivingcited by 66
  23. 2024A Survey on Autonomous Driving Datasets: Statistics, Annotation Quality, and a Future Outlookcited by 65
  24. 2025A Comprehensive Survey on World Models for Embodied AIcited by 65
  25. 2025Robust Autonomy Emerges from Self-Playcited by 64
  26. 20253D and 4D World Modeling: A Surveycited by 64
  27. 2022Symphony: Learning Realistic and Diverse Agents for Autonomous Driving Simulationcited by 61
  28. 2024NeuroNCAP: Photorealistic Closed-loop Safety Testing for Autonomous Drivingcited by 61
  29. 2025A Survey of World Models for Autonomous Drivingcited by 60
  30. 2025Impromptu VLA: Open Weights and Open Data for Driving Vision-Language-Action Modelscited by 60
  31. 2025WOD-E2E: Waymo Open Dataset for End-to-End Driving in Challenging Long-tail Scenarioscited by 60
  32. 2023LLM-Assist: Enhancing Closed-Loop Planning with Language-Based Reasoningcited by 59
  33. 2023TrafficBots: Towards World Models for Autonomous Driving Simulation and Motion Predictioncited by 56
  34. 2024Driving Everywhere with Large Language Model Policy Adaptationcited by 53
  35. 2023CAT: Closed-loop Adversarial Training for Safe End-to-End Drivingcited by 52
  36. 2025DiffusionDriveV2: Reinforcement Learning-Constrained Truncated Diffusion Modeling in End-to-End Autonomous Drivingcited by 52
  37. 2024UniTraj: A Unified Framework for Scalable Vehicle Trajectory Predictioncited by 51
  38. 2023DTPP: Differentiable Joint Conditional Prediction and Cost Evaluation for Tree Policy Planning in Autonomous Drivingcited by 46

50 most cited of 485 All 485 (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. 2025Closing the Loop: Motion Prediction Models beyond Open-Loop Benchmarks
  3. 2024NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking
  4. 2025Results of the 2024 CommonRoad Motion Planning Competition for Autonomous Vehicles
  5. 2026An Open-Source Modular Benchmark for Diffusion-Based Motion Planning in Closed-Loop Autonomous Driving
  6. 2026SparseDriveV2: Scoring is All You Need for End-to-End Autonomous Driving
  7. 2023Rethinking the Open-Loop Evaluation of End-to-End Autonomous Driving in nuScenes
  8. 2026TaCarla: A comprehensive benchmarking dataset for end-to-end autonomous driving