mlsanityData to 7 Oct 2026

Diffusion-Based Planning for Autonomous Driving with Flexible Guidance

arXiv 2501.15564 ↗First posted 26 Jan 2025cs.RO cs.AI cs.LGcited by 138

On the map: End-to-end autonomous driving → Imitation-learning end-to-end planners

Abstract (arXiv)

Achieving human-like driving behaviors in complex open-world environments is a critical challenge in autonomous driving. Contemporary learning-based planning approaches such as imitation learning methods often struggle to balance competing objectives and lack of safety assurance,due to limited adaptability and inadequacy in learning complex multi-modal behaviors commonly exhibited in human planning, not to mention their strong reliance on the fallback strategy with predefined rules. We propose a novel transformer-based Diffusion Planner for closed-loop planning, which can effectively model multi-modal driving behavior and ensure trajectory quality without any rule-based refinement. Our model supports joint modeling of both prediction and planning tasks under the same architecture, enabling cooperative behaviors between vehicles. Moreover, by learning the gradient of the trajectory score function and employing a flexible classifier guidance mechanism, Diffusion Planner effectively achieves safe and adaptable planning behaviors. Evaluations on the large-scale real-world autonomous planning benchmark nuPlan and our newly collected 200-hour delivery-vehicle driving dataset demonstrate that Diffusion Planner achieves state-of-the-art closed-loop performance with robust transferability in diverse driving styles.

Key facts. Cited by 138 papers in the map (data through 7 Oct 2026). Placed in Imitation-learning end-to-end planners, one of 9 directions in End-to-end autonomous driving. Builds on 44 of its 53 references that are in the map. First posted on arXiv 26 Jan 2025.

Builds on

44 of 53 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024PLUTO: Pushing the Limit of Imitation Learning-based Planning for Autonomous Driving22 Apr
  2. 2024Diffusion-ES: Gradient-free Planning with Diffusion for Autonomous Driving and Zero-Shot Instruction Following9 Feb
  3. 2023GameFormer: Game-theoretic Modeling and Learning of Transformer-based Interactive Prediction and Planning for Autonomous Driving10 Mar
  4. 2021Urban Driver: Learning to Drive from Real-world Demonstrations Using Policy Gradients27 Sep

Other references · 40

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  3. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  4. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  5. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  6. 2022Scalable Diffusion Models with Transformerscited by 5,931
  7. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  8. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  9. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,730
  10. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Stepscited by 1,961
  11. 2023Consistency Modelscited by 1,778
  12. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,441
28 more
  1. 2022Diffusion Posterior Sampling for General Noisy Inverse Problemscited by 1,375
  2. 2022Planning-oriented Autonomous Drivingcited by 1,068
  3. 2022Planning with Diffusion for Flexible Behavior Synthesiscited by 1,023
  4. 2016End to End Learning for Self-Driving Carscited by 1,000
  5. 2022On Distillation of Guided Diffusion Modelscited by 721
  6. 2020VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representationcited by 528
  7. 2022Is Conditional Generative Modeling all you need for Decision-Making?cited by 504
  8. 2021NuPlan: A closed-loop ML-based planning benchmark for autonomous vehiclescited by 485
  9. 2023End-to-end Autonomous Driving: Challenges and Frontierscited by 485
  10. 2022TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Drivingcited by 477
  11. 2018ChauffeurNet: Learning to Drive by Imitating the Best and Synthesizing the Worstcited by 391
  12. 2022Wayformer: Motion Forecasting via Simple & Efficient Attention Networkscited by 279
  13. 2018Learning to Drive in a Daycited by 266
  14. 2023Is Ego Status All You Need for Open-Loop End-to-End Autonomous Driving?cited by 242
  15. 2023Parting with Misconceptions about Learning-based Vehicle Motion Planningcited by 238
  16. 2023MotionDiffuser: Controllable Multi-Agent Motion Prediction using Diffusioncited by 210
  17. 2022Guided Conditional Diffusion for Controllable Traffic Simulationcited by 189
  18. 2021Scene Transformer: A unified architecture for predicting multiple agent trajectoriescited by 165
  19. 2023Contrastive Energy Prediction for Exact Energy-Guided Diffusion Sampling in Offline Reinforcement Learningcited by 145
  20. 2020A Survey of End-to-End Driving: Architectures and Training Methodscited by 123
  21. 2021Learning to drive from a world on railscited by 114
  22. 2023Language-Guided Traffic Simulation via Scene-Level Diffusioncited by 110
  23. 2019Urban Driving with Conditional Imitation Learningcited by 84
  24. 2021SafetyNet: Safe planning for real-world self-driving vehicles using machine-learned policiescited by 68
  25. 2024Safe Offline Reinforcement Learning with Feasibility-Guided Diffusion Modelcited by 62
  26. 2024Solving Motion Planning Tasks with a Scalable Generative Modelcited by 40
  27. 2023Large Trajectory Models are Scalable Motion Predictors and Plannerscited by 23
  28. 2024Generalizing Motion Planners with Mixture of Experts for Autonomous Drivingcited by 22

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 56; 2026: 82.

138 papers.

Sort:

By area:

  1. 2025ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Drivingcited by 190
  2. 2025DiffVLA: Vision-Language Guided Diffusion Planning for Autonomous Drivingcited by 64
  3. 2025Generalized Trajectory Scoring for End-to-end Multimodal Planningcited by 63
  4. 2025DriveLaW:Unifying Planning and Video Generation in a Latent Driving Worldcited by 43
  5. 2025CaRL: Learning Scalable Planning Policies with Simple Rewardscited by 34
  6. 2025SimScale: Learning to Drive via Real-World Simulation at Scalecited by 34
  7. 2025OmniNWM: Omniscient Driving Navigation World Modelscited by 32
  8. 2025Discrete Diffusion for Reflective Vision-Language-Action Models in Autonomous Drivingcited by 24
  9. 2025Flow Matching-Based Autonomous Driving Planning with Advanced Interactive Behavior Modelingcited by 22
  10. 2025GuideFlow: Constraint-Guided Flow Matching for Planning in End-to-End Autonomous Drivingcited by 21
  11. 2025Plan-R1: Safe and Feasible Trajectory Planning as Language Modelingcited by 19
  12. 2026DriveFine: Refining-Augmented Masked Diffusion VLA for Precise and Robust Drivingcited by 18
38 more
  1. 2025BridgeDrive: Diffusion Bridge Policy for Closed-Loop Trajectory Planning in Autonomous Drivingcited by 17
  2. 2025Challenger: Affordable Adversarial Driving Video Generationcited by 16
  3. 2025PRIX: Learning to Plan from Raw Pixels for End-to-End Autonomous Drivingcited by 16
  4. 2025Skill Expansion and Composition in Parameter Spacecited by 13
  5. 2025DistillDrive: End-to-End Multi-Mode Autonomous Driving Distillation by Isomorphic Hetero-Source Planning Modelcited by 13
  6. 2025Decoupled Diffusion Sparks Adaptive Scene Generationcited by 12
  7. 2025ResAD: Normalized Residual Trajectory Modeling for End-to-End Autonomous Drivingcited by 12
  8. 2026SteerVLA: Steering Vision-Language-Action Models in Long-Tail Driving Scenarioscited by 11
  9. 2026Unleashing the Potential of Diffusion Models for End-to-End Autonomous Drivingcited by 11
  10. 2025SparseWorld: A Flexible, Adaptive, and Efficient 4D Occupancy World Model Powered by Sparse and Dynamic Queriescited by 10
  11. 2025DiffE2E: Rethinking End-to-End Driving with a Hybrid Action Diffusion and Supervised Policycited by 9
  12. 2025DiffRefiner: Coarse to Fine Trajectory Planning via Diffusion Refinement with Semantic Interaction for End to End Autonomous Drivingcited by 9
  13. 2025Percept-WAM: Perception-Enhanced World-Awareness-Action Model for Robust End-to-End Autonomous Drivingcited by 9
  14. 2025TrajDiff: End-to-end Autonomous Driving without Perception Annotationcited by 8
  15. 2025When Planners Meet Reality: How Learned, Reactive Traffic Agents Shift nuPlan Benchmarkscited by 7
  16. 2025Towards Robust Zero-Shot Reinforcement Learningcited by 7
  17. 2025Model-Based Policy Adaptation for Closed-Loop End-to-End Autonomous Drivingcited by 7
  18. 2026RAD-2: Scaling Reinforcement Learning in a Generator-Discriminator Frameworkcited by 7
  19. 2025Learning to Tune Like an Expert: Interpretable and Scene-Aware Navigation via MLLM Reasoning and CVAE-Based Adaptationcited by 6
  20. 2025Dichotomous Diffusion Policy Optimizationcited by 6
  21. 2026Generative Scenario Rollouts for End-to-End Autonomous Drivingcited by 6
  22. 2026MindVLA-U1: VLA Beats VA with Unified Streaming Architecture for Autonomous Drivingcited by 6
  23. 2025A Knowledge-Driven Diffusion Policy for End-to-End Autonomous Driving Based on Expert Routingcited by 5
  24. 2026What Matters for Scalable and Robust Learning in End-to-End Driving Planners?cited by 5
  25. 2026Beyond Self-Play and Scale: A Behavior Benchmark for Generalization in Autonomous Drivingcited by 5
  26. 2025RIFT: Group-Relative RL Fine-Tuning for Realistic and Controllable Traffic Simulationcited by 4
  27. 2025FlowDrive: Energy Flow Field for End-to-End Autonomous Drivingcited by 4
  28. 2025CoPlanner: An Interactive Motion Planner with Contingency-Aware Diffusion for Autonomous Drivingcited by 4
  29. 2025Perfect Prediction or Plenty of Proposals? What Matters Most in Planning for Autonomous Drivingcited by 4
  30. 2025WPT: World-to-Policy Transfer via Online World Model Distillationcited by 4
  31. 2026Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Drivingcited by 4
  32. 2026HAD: Combining Hierarchical Diffusion with Metric-Decoupled RL for End-to-End Drivingcited by 4
  33. 2025RealDrive: Retrieval-Augmented Driving with Diffusion Modelscited by 3
  34. 2025Train-Once Plan-Anywhere Kinodynamic Motion Planning via Diffusion Treescited by 3
  35. 2025Language Model as Planner and Formalizer under Constraintscited by 3
  36. 2025nuPlan-R: A Closed-Loop Planning Benchmark for Autonomous Driving via Reactive Multi-Agent Simulationcited by 3
  37. 2026ParkDiffusion++: Ego Intention Conditioned Joint Multi-Agent Trajectory Prediction for Automated Parking using Diffusion Modelscited by 3
  38. 2026RAD-LAD: Rule and Language Grounded Autonomous Driving in Real-Timecited by 3

50 most cited of 138 All 138 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023Interpretable Motion Planner for Urban Driving via Hierarchical Imitation Learning
  2. 2026IRL-DAL: Safe and Adaptive Trajectory Planning for Autonomous Driving via Energy-Guided Diffusion Models
  3. 2024Hybrid Imitation-Learning Motion Planner for Urban Driving
  4. 2025DIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous Driving
  5. 2026Multimodal Action Diffusion for Robust End-to-End Autonomous Driving
  6. 2025Exposing the Copycat Problem of Imitation-based Planner: A Novel Closed-Loop Simulator, Causal Benchmark and Joint IL-RL Baseline
  7. 2025Predictive Planner for Autonomous Driving with Consistency Models
  8. 2026Learning-Based Behavior Planning for Automated Driving: Real-World Integration and Deployment