mlsanityData to 7 Oct 2026

Designing Versatile Samples for Learned Trajectory Scoring

arXiv 2609.01799 ↗First posted 1 Sep 2026cs.RO cs.CVcited by 0

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

Abstract (arXiv)

Many current end-to-end driving policies emit a pool of candidate trajectories and select one, which makes selection a separable component: a scorer can be retrained while the planner, its backbone, and its trajectory generator all stay frozen. However, many strong planners concentrate their proposals around safe mode, providing limited supervision near decision boundaries. In this work, we design a training dataset that provides more informative supervision for the scorer. In particular, we construct two generators that perturb the logged human trajectory along the two axes a vehicle can be displaced: laterally toward the drivable boundary and longitudinally toward a leading vehicle. The designed dataset produces more informative positive and negative samples than the base planner's proposal pool. We attach a transformer-based scorer to two frozen generative planners, DiffusionDrive and MeanFuser, and train it on the NAVSIM navtrain dataset. The results of the experiments show that we achieve 90.1 EPDMS on DiffusionDrive and 90.4 EPDMS on MeanFuser when using ResNet-34, with 0.4 and 0.3 EPDMS respectively, from the designed training dataset.

Key facts. No citing papers in the map yet (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 36 of its 41 references that are in the map. First posted on arXiv 1 Sep 2026.

Builds on

36 of 41 references.

Closest ancestors · 4

Same direction, newest first

  1. 2026MeanFuser: Fast One-Step Multi-Modal Trajectory Generation and Adaptive Reconstruction via MeanFlow for End-to-End Autonomous Driving23 Feb
  2. 2025GoalFlow: Goal-Driven Flow Matching for Multimodal Trajectories Generation in End-to-End Autonomous Driving7 Mar
  3. 2024VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planning20 Feb
  4. 2022KING: Generating Safety-Critical Driving Scenarios for Robust Imitation via Kinematics Gradients28 Apr

Other references · 32

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020Conservative Q-Learning for Offline Reinforcement Learningcited by 1,777
  3. 2021Offline Reinforcement Learning with Implicit Q-Learningcited by 1,245
  4. 2022Planning-oriented Autonomous Drivingcited by 1,068
  5. 2023VAD: Vectorized Scene Representation for Efficient Autonomous Drivingcited by 613
  6. 2021NuPlan: A closed-loop ML-based planning benchmark for autonomous vehiclescited by 485
  7. 2022TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Drivingcited by 477
  8. 2018ChauffeurNet: Learning to Drive by Imitating the Best and Synthesizing the Worstcited by 391
  9. 2019Learning by Cheatingcited by 361
  10. 2019Exploring the Limitations of Behavior Cloning for Autonomous Drivingcited by 343
  11. 2024NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarkingcited by 343
  12. 2023UniSim: A Neural Closed-Loop Sensor Simulatorcited by 294
20 more
  1. 2024Hydra-MDP: End-to-end Multimodal Planning with Multi-target Hydra-Distillationcited by 244
  2. 2023Is Ego Status All You Need for Open-Loop End-to-End Autonomous Driving?cited by 242
  3. 2024SparseDrive: End-to-End Autonomous Driving via Sparse Scene Representationcited by 239
  4. 2023Parting with Misconceptions about Learning-based Vehicle Motion Planningcited by 238
  5. 2023NeuRAD: Neural Rendering for Autonomous Drivingcited by 146
  6. 2025End-to-End Driving with Online Trajectory Evaluation via BEV World Modelcited by 145
  7. 2025Pseudo-Simulation for Autonomous Drivingcited by 141
  8. 2023HIQL: Offline Goal-Conditioned RL with Latent States as Actionscited by 133
  9. 2025Epona: Autoregressive Diffusion World Model for Autonomous Drivingcited by 115
  10. 2024Towards learning-based planning:The nuPlan benchmark for real-world autonomous drivingcited by 103
  11. 2023Hidden Biases of End-to-End Driving Modelscited by 95
  12. 2020Counterfactual Data Augmentation using Locally Factored Dynamicscited by 93
  13. 2025Hydra-MDP++: Advancing End-to-End Driving via Expert-Guided Hydra-Distillationcited by 93
  14. 2025DriveSuprim: Towards Precise Trajectory Selection for End-to-End Planningcited by 91
  15. 2025World4Drive: End-to-End Autonomous Driving via Intention-aware Physical Latent World Modelcited by 91
  16. 2024HUGSIM: A Real-Time, Photo-Realistic and Closed-Loop Simulator for Autonomous Drivingcited by 84
  17. 2025Generalized Trajectory Scoring for End-to-end Multimodal Planningcited by 63
  18. 2026Driving on Registerscited by 38
  19. 2025SimScale: Learning to Drive via Real-World Simulation at Scalecited by 34
  20. 2022Data augmentation for efficient learning from parametric expertscited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025A Framework for Learning Scoring Rules in Autonomous Driving Planning Systems
  2. 2026Learning to Explain While Planning: Rule-Aligned Diffusion Planning for Autonomous Driving
  3. 2026SparseDriveV2: Scoring is All You Need for End-to-End Autonomous Driving
  4. 2026Test-Time Trajectory Optimization for Autonomous Driving
  5. 2026CLOVER: Closed-Loop Value Estimation and Ranking for End-to-End Autonomous Driving Planning
  6. 2026Off the Rails: Hijacking the Scoring Head in Generative End-to-End Driving Planners with Safety-Violating Adversarial Perturbations
  7. 2025RealDrive: Retrieval-Augmented Driving with Diffusion Models
  8. 2025DiffRefiner: Coarse to Fine Trajectory Planning via Diffusion Refinement with Semantic Interaction for End to End Autonomous Driving