mlsanityData to 7 Oct 2026

Imitation-learning end-to-end planners

287 papers2 this weekMedium confidence in this grouping: mostly one topic, with blurry edgesMedium confidence in this grouping: mostly one topic, with blurry edges · About

Keywords: driving, planning, autonomous, imitation, autonomous driving

Key facts. Imitation-learning end-to-end planners: 287 papers on arXiv since 2021 (data through 7 Oct 2026). 47 of its 287 mapped papers (16%) cite “DiffusionDrive: Truncated Diffusion Model for End-to-End Autonomous Driving” (2024, arXiv 2411.15139). 45 of its 287 mapped papers (16%) cite “Urban Driver: Learning to Drive from Real-world Demonstrations Using Policy Gradients” (2021, arXiv 2109.13333). 19 new papers 17 Sep–7 Oct.

What’s new

17 Sep – 7 Oct 2026

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

  1. This week · 2
  2. Beyond Policy Support: Interaction Constrained Offline Reinforcement Learning for Autonomous Driving also fits: Reinforcement learning for driving
  3. Beyond Waypoint Regression: Query-Based Cost Learning over Reachable Ego Futures for End-to-End Driving also fits: End-to-end system architecture
  4. Earlier · 17
  5. Closed-Loop Refinement and Execution for Learned Driving Planners
  6. Learning to Explain While Planning: Rule-Aligned Diffusion Planning for Autonomous Driving
  7. ReWAM: Reciprocal World Action Models for Interactive Autonomous Driving also fits: Cooperative and V2X driving
  8. Efficient Multi-Modal Planning with Reward-Guided Preference Optimization for Autonomous Driving also fits: Reinforcement learning for driving
  9. RoXDrive: Closed-Loop Reinforcement Learning for End-to-End Autonomous Driving via Action-Faithful Rollouts
  10. Diffusion-2BC: Hybrid Diffusion and Regression Training for Offline Behavior Cloning in Autonomous Driving
  11. Guiding End-to-End Driving Models with Endpoint-Constrained Trajectory Optimization also fits: End-to-end system architecture
  12. INTERACT: Interactive Planning for Autonomous Driving via Anchor-Conditioned Prediction and Trust-Region Refinement
All 19
  1. Evaluation Is All You Need for Multi-Modal Autonomous Driving also fits: End-to-end system architecture
  2. Sim-to-Real Aware End-to-End Learning Environment for Micromobility also fits: Reinforcement learning for driving
  3. Taming an End-to-End Autonomous Driving Policy for Urban Navigation of Quadruped Robots also fits: End-to-end system architecture
  4. BranchDrive: A Branch-Structured Dataset for Action-Conditioned Driving Prediction also fits: End-to-end system architecture
  5. Stability-Aware Imitation Learning from Model Predictive Control for Autonomous Vehicle Lateral Control: Exact Q-Loss and a Novel Training Procedure also fits: Reinforcement learning for driving
  6. CounterPlay: Counterfactual Post-Training for Self-Play Driving Policies
  7. Stabilizing Trajectory Outputs in End-to-End Autonomous Driving via SC-IMM Based Teacher Signals
  8. OPTED: On-Policy Fine-Tuning for End-to-End Driving using a Render-Free Teacher also fits: Reinforcement learning for driving
  9. MILER: Semantic Mid-Level Representation for Sim-to-Real Reinforcement Learning in Unstructured Autonomous Driving also fits: Reinforcement learning for driving

Foundations

Most cited by papers here

  1. DiffusionDrive: Truncated Diffusion Model for End-to-End Autonomous Driving2024cited by 47 here
  2. Urban Driver: Learning to Drive from Real-world Demonstrations Using Policy Gradients2021cited by 45 here
  3. VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planning2024cited by 39 here
  4. Diffusion-Based Planning for Autonomous Driving with Flexible Guidance2025cited by 35 here
  5. Imitation Is Not Enough: Robustifying Imitation with Reinforcement Learning for Challenging Driving Scenarios2022cited by 32 here

Lineage

The papers this direction builds on, oldest first.

Each paper on the line cites the one before.

  1. 2021End-to-end Interpretable Neural Motion Plannercited by 27 here
  2. 2021End-to-End Urban Driving by Imitating a Reinforcement Learning Coachcited by 27 here
  3. 2022TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Drivingcited by 66 here
  4. 2023Think Twice before Driving: Towards Scalable Decoders for End-to-End Autonomous Drivingcited by 21 here
  5. 2023End-to-end Autonomous Driving: Challenges and Frontierscited by 39 here
  6. 2024NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarkingcited by 46 here
  7. 2024DiffusionDrive: Truncated Diffusion Model for End-to-End Autonomous Drivingcited by 47 here
17 more it builds on, not in this chain
  1. 2021Multi-Modal Fusion Transformer for End-to-End Autonomous Drivingcited by 27 here
  2. 2021Learning to drive from a world on railscited by 21 here
  3. 2021NuPlan: A closed-loop ML-based planning benchmark for autonomous vehiclescited by 67 here
  4. 2021MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learningcited by 21 here
  5. 2021Urban Driver: Learning to Drive from Real-world Demonstrations Using Policy Gradientscited by 45 here
  6. 2021SafetyNet: Safe planning for real-world self-driving vehicles using machine-learned policiescited by 22 here
  7. 2022Imitation Is Not Enough: Robustifying Imitation with Reinforcement Learning for Challenging Driving Scenarioscited by 32 here
  8. 2023GameFormer: Game-theoretic Modeling and Learning of Transformer-based Interactive Prediction and Planning for Autonomous Drivingcited by 32 here
  9. 2023VAD: Vectorized Scene Representation for Efficient Autonomous Drivingcited by 61 here
  10. 2023Waymax: An Accelerated, Data-Driven Simulator for Large-Scale Autonomous Driving Researchcited by 27 here
  11. 2024VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planningcited by 39 here
  12. 2024PLUTO: Pushing the Limit of Imitation Learning-based Planning for Autonomous Drivingcited by 29 here
  13. 2024SparseDrive: End-to-End Autonomous Driving via Sparse Scene Representationcited by 28 here
  14. 2024Bench2Drive: Towards Multi-Ability Benchmarking of Closed-Loop End-To-End Autonomous Drivingcited by 22 here
  15. 2025Diffusion-Based Planning for Autonomous Driving with Flexible Guidancecited by 35 here
  16. 2025GoalFlow: Goal-Driven Flow Matching for Multimodal Trajectories Generation in End-to-End Autonomous Drivingcited by 27 here
  17. 2025Pseudo-Simulation for Autonomous Drivingcited by 21 here

The 24 most cited of 415.

Browse

30 of 287, ranked 6–35

  1. 6GameFormer: Game-theoretic Modeling and Learning of Transformer-based Interactive Prediction and Planning for Autonomous Driving202332
  2. 7PLUTO: Pushing the Limit of Imitation Learning-based Planning for Autonomous Driving202429
  3. 8GoalFlow: Goal-Driven Flow Matching for Multimodal Trajectories Generation in End-to-End Autonomous Driving202527
  4. 9Waymax: An Accelerated, Data-Driven Simulator for Large-Scale Autonomous Driving Research202327
  5. 10End-to-End Urban Driving by Imitating a Reinforcement Learning Coach202127
  6. 11Differentiable Integrated Motion Prediction and Planning with Learnable Cost Function for Autonomous Driving202220
  7. 12RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-based Reinforcement Learning202515
  8. 13Learning from All Vehicles202215
  9. 14DTPP: Differentiable Joint Conditional Prediction and Cost Evaluation for Tree Policy Planning in Autonomous Driving202312
  10. 15Model-Based Imitation Learning for Urban Driving202212
All 30
  1. 16Conditional Predictive Behavior Planning with Inverse Reinforcement Learning for Human-like Autonomous Driving202212
  2. 17GPUDrive: Data-driven, multi-agent driving simulation at 1 million FPS202410
  3. 18Gen-Drive: Enhancing Diffusion Generative Driving Policies with Reward Modeling and Reinforcement Learning Fine-tuning202410
  4. 19Hierarchical Model-Based Imitation Learning for Planning in Autonomous Driving202210
  5. 20CarPlanner: Consistent Auto-regressive Trajectory Planning for Large-scale Reinforcement Learning in Autonomous Driving20259
  6. 21Exploring Imitation Learning for Autonomous Driving with Feedback Synthesizer and Differentiable Rasterization20219
  7. 22Diffusion-ES: Gradient-free Planning with Diffusion for Autonomous Driving and Zero-Shot Instruction Following20248
  8. 23KING: Generating Safety-Critical Driving Scenarios for Robust Imitation via Kinematics Gradients20228
  9. 24Rethinking Imitation-based Planner for Autonomous Driving20237
  10. 25Learning Personalized Driving Styles via Reinforcement Learning from Human Feedback20256
  11. 26Raw2Drive: Reinforcement Learning with Aligned World Models for End-to-End Autonomous Driving (in CARLA v2)20256
  12. 27DIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous Driving20256
  13. 28RAP: 3D Rasterization Augmented End-to-End Planning20256
  14. 29Flow Matching-Based Autonomous Driving Planning with Advanced Interactive Behavior Modeling20256
  15. 30DiffusionDriveV2: Reinforcement Learning-Constrained Truncated Diffusion Modeling in End-to-End Autonomous Driving20256
  16. 31TrafficBots: Towards World Models for Autonomous Driving Simulation and Motion Prediction20236
  17. 32StyleDrive: Towards Driving-Style Aware Benchmarking of End-To-End Autonomous Driving20255
  18. 33DriveDPO: Policy Learning via Safety DPO For End-to-End Autonomous Driving20255
  19. 34Zero-Human Demonstration End-to-end Autonomous Driving with Trajectory Scorer20255
  20. 35GuideFlow: Constraint-Guided Flow Matching for Planning in End-to-End Autonomous Driving20255