mlsanityData to 7 Oct 2026

Test-Time Trajectory Optimization for Autonomous Driving

arXiv 2606.07170 ↗First posted 5 Jun 2026cs.ROcited by 7

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

Abstract (arXiv)

End-to-end planners for autonomous driving typically generate a set of candidate trajectories, score each one, and return the highest-scoring candidate. However, the scorer is applied only after the proposals are generated and cannot influence the set of trajectories: a weak set of candidates limits planning performance regardless of the scorer's quality. We instead treat the scorer as a learned trajectory-level reward function and search for trajectories that maximize it. Our method, TOAD, runs the Cross-Entropy Method at test time, warm-started from the planner's proposals. It requires no retraining and is plug-and-play for existing planners. Across six base planners, TOAD improves results on NAVSIM-v1 (94.7 PDMS), NAVSIM-v2 (56.3 EPDMS), and the closed-loop HUGSIM benchmark. The code will be made publicly available via the project page: https://valeoai.github.io/TOAD/.

Key facts. Cited by 7 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 55 of its 62 references that are in the map. First posted on arXiv 5 Jun 2026.

Builds on

55 of 62 references.

Closest ancestors · 11

Same direction, newest first

  1. 2026Risk-Aware World Model Predictive Control for Generalizable End-to-End Autonomous Driving26 Feb
  2. 2025GuideFlow: Constraint-Guided Flow Matching for Planning in End-to-End Autonomous Driving24 Nov
  3. 2025Zero-Human Demonstration End-to-end Autonomous Driving with Trajectory Scorer28 Oct
  4. 2025RAP: 3D Rasterization Augmented End-to-End Planning5 Oct
  5. 2025DIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous Driving5 Jul
  6. 2025Learning Personalized Driving Styles via Reinforcement Learning from Human Feedback13 Mar
  7. 2025GoalFlow: Goal-Driven Flow Matching for Multimodal Trajectories Generation in End-to-End Autonomous Driving7 Mar
  8. 2024DiffusionDrive: Truncated Diffusion Model for End-to-End Autonomous Driving22 Nov
  9. 2024VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planning20 Feb
  10. 2022Differentiable Integrated Motion Prediction and Planning with Learnable Cost Function for Autonomous Driving21 Jul
  11. 2022KING: Generating Safety-Critical Driving Scenarios for Robust Imitation via Kinematics Gradients28 Apr

Other references · 44

  1. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  2. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  3. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  4. 2022Planning-oriented Autonomous Drivingcited by 1,068
  5. 2016End to End Learning for Self-Driving Carscited by 1,000
  6. 2024Large Language Monkeys: Scaling Inference Compute with Repeated Samplingcited by 946
  7. 2023VAD: Vectorized Scene Representation for Efficient Autonomous Drivingcited by 613
  8. 2021KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3Dcited by 570
  9. 2022TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Drivingcited by 477
  10. 2019A Survey of Autonomous Driving: Common Practices and Emerging Technologiescited by 373
  11. 2024NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarkingcited by 343
  12. 2025AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuningcited by 252
32 more
  1. 2024Hydra-MDP: End-to-end Multimodal Planning with Multi-target Hydra-Distillationcited by 244
  2. 2021End-to-end Interpretable Neural Motion Plannercited by 240
  3. 2023Parting with Misconceptions about Learning-based Vehicle Motion Planningcited by 238
  4. 2025ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Drivingcited by 190
  5. 2021PandaSet: Advanced Sensor Suite Dataset for Autonomous Drivingcited by 186
  6. 2024Senna: Bridging Large Vision-Language Models and End-to-End Autonomous Drivingcited by 156
  7. 2025SimLingo: Vision-Only Closed-Loop Autonomous Driving with Language-Action Alignmentcited by 149
  8. 2025End-to-End Driving with Online Trajectory Evaluation via BEV World Modelcited by 145
  9. 2025Pseudo-Simulation for Autonomous Drivingcited by 141
  10. 2025Unified Vision-Language-Action Modelcited by 128
  11. 2025DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Drivingcited by 127
  12. 2024DrivingGPT: Unifying Driving World Modeling and Planning with Multi-modal Autoregressive Transformerscited by 96
  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. 2020Sample-efficient Cross-Entropy Method for Real-time Planningcited by 90
  17. 2024DRAMA: An Efficient End-to-end Motion Planner for Autonomous Driving with Mambacited by 87
  18. 2024HUGSIM: A Real-Time, Photo-Realistic and Closed-Loop Simulator for Autonomous Drivingcited by 84
  19. 2025DiffVLA: Vision-Language Guided Diffusion Planning for Autonomous Drivingcited by 64
  20. 2025Generalized Trajectory Scoring for End-to-end Multimodal Planningcited by 63
  21. 2025Centaur: Robust End-to-End Autonomous Driving with Test-Time Trainingcited by 41
  22. 2025iPad: Iterative Proposal-centric End-to-End Autonomous Drivingcited by 41
  23. 2026Driving on Registerscited by 38
  24. 2025SimScale: Learning to Drive via Real-World Simulation at Scalecited by 34
  25. 2026SparseDriveV2: Scoring is All You Need for End-to-End Autonomous Drivingcited by 21
  26. 2025DriveX: Omni Scene Modeling for Learning Generalizable World Knowledge in Autonomous Drivingcited by 20
  27. 2025PRIX: Learning to Plan from Raw Pixels for End-to-End Autonomous Drivingcited by 16
  28. 2026SpanVLA: Efficient Action Bridging and Learning from Negative-Recovery Samples for Vision-Language-Action Modelcited by 15
  29. 2026DriveFuture: Future-Aware Latent World Models for Autonomous Drivingcited by 15
  30. 2025MindDrive: An All-in-One Framework Bridging World Models and Vision-Language Model for End-to-End Autonomous Drivingcited by 12
  31. 2024ReGentS: Real-World Safety-Critical Driving Scenario Generation Made Stablecited by 8
  32. 2025SimpleVSF: VLM-Scoring Fusion for Trajectory Prediction of End-to-End Autonomous Drivingcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 7.

7 papers.

  1. 2026Physics-Grounded Causal Auditing of End-to-End Driving Plannerscited by 0
  2. 2026DriveReferee: Geometric Safety Verdicts Need Not Be Learned for Driving World-Action Modelscited by 0
  3. 2026Evaluation Is All You Need for Multi-Modal Autonomous Drivingcited by 0
  4. 2026INTERACT: Interactive Planning for Autonomous Driving via Anchor-Conditioned Prediction and Trust-Region Refinementcited by 0
  5. 2026Guiding End-to-End Driving Models with Endpoint-Constrained Trajectory Optimizationcited by 0
  6. 2026When the Score Becomes the Target: Rethinking Metric Validity in Autonomous Drivingcited by 0
  7. 2026Closed-Loop Refinement and Execution for Learned Driving Plannerscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026CLOVER: Closed-Loop Value Estimation and Ranking for End-to-End Autonomous Driving Planning
  2. 2026Designing Versatile Samples for Learned Trajectory Scoring
  3. 2025A Framework for Learning Scoring Rules in Autonomous Driving Planning Systems
  4. 2025Benchmarking Autonomous Driving Planners Across Leaderboards: A Unified CARLA-Based Evaluation
  5. 2024Diffusion-ES: Gradient-free Planning with Diffusion for Autonomous Driving and Zero-Shot Instruction Following
  6. 2026DriveVer: Lightweight Trajectory Evaluator as Test-Time Verifier for Autonomous Driving
  7. 2023Rethinking Closed-loop Training for Autonomous Driving
  8. 2026Efficient Multi-Modal Planning with Reward-Guided Preference Optimization for Autonomous Driving