mlsanityData to 7 Oct 2026

Don't Shake the Wheel: Momentum-Aware Planning in End-to-End Autonomous Driving

arXiv 2503.03125 ↗First posted 5 Mar 2025cs.ROcited by 84

On the map: End-to-end autonomous driving → End-to-end system architecture

Abstract (arXiv)

End-to-end autonomous driving frameworks enable seamless integration of perception and planning but often rely on one-shot trajectory prediction, which may lead to unstable control and vulnerability to occlusions in single-frame perception. To address this, we propose the Momentum-Aware Driving (MomAD) framework, which introduces trajectory momentum and perception momentum to stabilize and refine trajectory predictions. MomAD comprises two core components: (1) Topological Trajectory Matching (TTM) employs Hausdorff Distance to select the optimal planning query that aligns with prior paths to ensure coherence;(2) Momentum Planning Interactor (MPI) cross-attends the selected planning query with historical queries to expand static and dynamic perception files. This enriched query, in turn, helps regenerate long-horizon trajectory and reduce collision risks. To mitigate noise arising from dynamic environments and detection errors, we introduce robust instance denoising during training, enabling the planning model to focus on critical signals and improve its robustness. We also propose a novel Trajectory Prediction Consistency (TPC) metric to quantitatively assess planning stability. Experiments on the nuScenes dataset demonstrate that MomAD achieves superior long-term consistency (>=3s) compared to SOTA methods. Moreover, evaluations on the curated Turning-nuScenes shows that MomAD reduces the collision rate by 26% and improves TPC by 0.97m (33.45%) over a 6s prediction horizon, while closedloop on Bench2Drive demonstrates an up to 16.3% improvement in success rate.

Key facts. Cited by 84 papers in the map (data through 7 Oct 2026). Placed in End-to-end system architecture, one of 9 directions in End-to-end autonomous driving. Builds on 28 of its 38 references that are in the map. First posted on arXiv 5 Mar 2025.

Builds on

28 of 38 references.

Closest ancestors · 11

Same direction, newest first

  1. 2024DeepInteraction++: Multi-Modality Interaction for Autonomous Driving9 Aug
  2. 2024End-to-End Autonomous Driving without Costly Modularization and 3D Manual Annotation25 Jun
  3. 2024DualAD: Disentangling the Dynamic and Static World for End-to-End Driving10 Jun
  4. 2024Bench2Drive: Towards Multi-Ability Benchmarking of Closed-Loop End-To-End Autonomous Driving6 Jun
  5. 2024SparseDrive: End-to-End Autonomous Driving via Sparse Scene Representation30 May
  6. 2023Is Ego Status All You Need for Open-Loop End-to-End Autonomous Driving?5 Dec
  7. 2023End-to-end Autonomous Driving: Challenges and Frontiers29 Jun
  8. 2022ST-P3: End-to-end Vision-based Autonomous Driving via Spatial-Temporal Feature Learning15 Jul
  9. 2022Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baseline16 Jun
  10. 2021Multi-Modal Fusion Transformer for End-to-End Autonomous Driving19 Apr
  11. 2021End-to-end Interpretable Neural Motion Planner17 Jan

Other references · 17

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  3. 2022Planning-oriented Autonomous Drivingcited by 1,068
  4. 2023VAD: Vectorized Scene Representation for Efficient Autonomous Drivingcited by 613
  5. 2017End-to-end Driving via Conditional Imitation Learningcited by 479
  6. 2023GPT-Driver: Learning to Drive with GPTcited by 344
  7. 2019Exploring the Limitations of Behavior Cloning for Autonomous Drivingcited by 343
  8. 2024VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planningcited by 287
  9. 2024Hydra-MDP: End-to-end Multimodal Planning with Multi-target Hydra-Distillationcited by 244
  10. 2024GenAD: Generative End-to-End Autonomous Drivingcited by 225
  11. 2021End-to-End Urban Driving by Imitating a Reinforcement Learning Coachcited by 191
  12. 2023Benchmarking Robustness of 3D Object Detection to Common Corruptions in Autonomous Drivingcited by 112
5 more
  1. 2020Survey of Deep Reinforcement Learning for Motion Planning of Autonomous Vehiclescited by 101
  2. 2023PPAD: Iterative Interactions of Prediction and Planning for End-to-end Autonomous Drivingcited by 33
  3. 2022Perceive, Interact, Predict: Learning Dynamic and Static Clues for End-to-End Motion Predictioncited by 28
  4. 2024GraphAD: Interaction Scene Graph for End-to-end Autonomous Drivingcited by 25
  5. 2024ComDrive: Comfort-Oriented End-to-End Autonomous Drivingcited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 35; 2026: 49.

84 papers.

Sort:

By area:

  1. 2025ORION: A Holistic End-to-End Autonomous Driving Framework by Vision-Language Instructed Action Generationcited by 177
  2. 2025DriveMoE: Mixture-of-Experts for Vision-Language-Action Model in End-to-End Autonomous Drivingcited by 85
  3. 2025Raw2Drive: Reinforcement Learning with Aligned World Models for End-to-End Autonomous Driving (in CARLA v2)cited by 45
  4. 2025DriveDPO: Policy Learning via Safety DPO For End-to-End Autonomous Drivingcited by 39
  5. 2025Vision-Language-Action Models for Autonomous Driving: Past, Present, and Futurecited by 32
  6. 2026DriveWorld-VLA: Unified Latent-Space World Modeling with Vision-Language-Action for Autonomous Drivingcited by 31
  7. 2025SpaceDrive: Infusing Spatial Awareness into VLM-based Autonomous Drivingcited by 28
  8. 2026Drive-JEPA: Video JEPA Meets Multimodal Trajectory Distillation for End-to-End Drivingcited by 26
  9. 2025MindDrive: A Vision-Language-Action Model for Autonomous Driving via Online Reinforcement Learningcited by 25
  10. 2025ImagiDrive: A Unified Imagination-and-Planning Framework for Autonomous Drivingcited by 24
  11. 2025ReasonPlan: Unified Scene Prediction and Decision Reasoning for Closed-loop Autonomous Drivingcited by 22
  12. 2025GuideFlow: Constraint-Guided Flow Matching for Planning in End-to-End Autonomous Drivingcited by 21
38 more
  1. 2026UniDrive-WM: Unified Understanding, Planning and Generation World Model for Autonomous Drivingcited by 20
  2. 2025DIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous Drivingcited by 17
  3. 2026UniDriveVLA: Unifying Understanding, Perception, and Action Planning for Autonomous Drivingcited by 17
  4. 2026DriveFuture: Future-Aware Latent World Models for Autonomous Drivingcited by 15
  5. 2026ResWorld: Temporal Residual World Model for End-to-End Autonomous Drivingcited by 14
  6. 2025ResAD: Normalized Residual Trajectory Modeling for End-to-End Autonomous Drivingcited by 12
  7. 2025MindDrive: An All-in-One Framework Bridging World Models and Vision-Language Model for End-to-End Autonomous Drivingcited by 12
  8. 2026EponaV2: Driving World Model with Comprehensive Future Reasoningcited by 12
  9. 2025GS-Occ3D: Scaling Vision-only Occupancy Reconstruction with Gaussian Splattingcited by 11
  10. 2026DynVLA: Learning World Dynamics for Action Reasoning in Autonomous Drivingcited by 11
  11. 2026AutoMoT: A Unified Vision-Language-Action Model with Asynchronous Mixture-of-Transformers for End-to-End Autonomous Drivingcited by 9
  12. 2025TakeAD: Preference-based Post-optimization for End-to-end Autonomous Driving with Expert Takeover Datacited by 8
  13. 2026SafeDrive: Fine-Grained Safety Reasoning for End-to-End Driving in a Sparse Worldcited by 7
  14. 2025Fully Unified Motion Planning for End-to-End Autonomous Drivingcited by 6
  15. 2025FocalAD: Local Motion Planning for End-to-End Autonomous Drivingcited by 6
  16. 2025HENet++: Hybrid Encoding and Multi-task Learning for 3D Perception and End-to-end Autonomous Drivingcited by 6
  17. 2026Generative Scenario Rollouts for End-to-End Autonomous Drivingcited by 6
  18. 2026GraphWorld: Long-Horizon Planning with World Models for End-to-End Autonomous Drivingcited by 6
  19. 2025GEMINUS: Dual-aware Global and Scene-Adaptive Mixture-of-Experts for End-to-End Autonomous Drivingcited by 5
  20. 2025CogDriver: Integrating Cognitive Inertia for Temporally Coherent Planning in Autonomous Drivingcited by 5
  21. 2025DriveE2E: Closed-Loop Benchmark for End-to-End Autonomous Driving through Real-to-Simulationcited by 5
  22. 2025VR-Drive: Viewpoint-Robust End-to-End Driving with Feed-Forward 3D Gaussian Splattingcited by 5
  23. 2025Spatial Retrieval Augmented Autonomous Drivingcited by 5
  24. 2025CogAD: Cognitive-Hierarchy Guided End-to-End Autonomous Drivingcited by 4
  25. 2025WPT: World-to-Policy Transfer via Online World Model Distillationcited by 4
  26. 2025KnowVal: A Knowledge-Augmented and Value-Guided Autonomous Driving Systemcited by 4
  27. 2026FlowAD: Ego-Scene Interactive Modeling for Autonomous Drivingcited by 4
  28. 2025Echo Planning for Autonomous Driving: From Current Observations to Future Trajectories and Backcited by 3
  29. 2025Foundation Models for Trajectory Planning in Autonomous Driving: A Review of Progress and Open Challengescited by 3
  30. 2026UniDWM: Towards a Unified Driving World Model via Multifaceted Representation Learningcited by 3
  31. 2026Latent World Models for Automated Driving: A Unified Taxonomy, Evaluation Framework, and Open Challengescited by 3
  32. 2026Bench2Drive-Robust: Benchmarking Closed-Loop Autonomous Driving under Deployment Perturbationscited by 3
  33. 2026VLGA: Vision-Language-Geometry-Action Models for Autonomous Drivingcited by 3
  34. 2025Map-World: Masked Action planning and Path-Integral World Model for Autonomous Drivingcited by 2
  35. 2026UniUncer: Unified Dynamic Static Uncertainty for End to End Drivingcited by 2
  36. 2026DynFlowDrive: Flow-Based Dynamic World Modeling for Autonomous Drivingcited by 2
  37. 2026CLEAR: Closed-Loop Reinforcement Learning at Scale for End-to-End Autonomous Drivingcited by 2
  38. 2025CodeMerge: Codebook-Guided Model Merging for Robust Test-Time Adaptation in Autonomous Drivingcited by 1

50 most cited of 84 All 84 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026MomWorld: Momentum-Aware Latent World Model for Long-Horizon Autonomous Driving
  2. 2026MomADv2: Reliable Temporal Memory for End-to-End Autonomous Driving
  3. 2025Perception in Plan: Coupled Perception and Planning for End-to-End Autonomous Driving
  4. 2026A Reliable Context-Aware and Temporal Planning Framework for Autonomous Driving
  5. 2025SUPER-AD: Semantic Uncertainty-aware Planning for End-to-End Robust Autonomous Driving
  6. 2026What Matters for Scalable and Robust Learning in End-to-End Driving Planners?
  7. 2025TrajDiff: End-to-end Autonomous Driving without Perception Annotation
  8. 2022Distribution-aware Goal Prediction and Conformant Model-based Planning for Safe Autonomous Driving