mlsanityData to 7 Oct 2026

Producing and Leveraging Online Map Uncertainty in Trajectory Prediction

arXiv 2403.16439 ↗First posted 25 Mar 2024cs.RO cs.CV cs.LGcited by 32

Not on the map. Why?

Abstract (arXiv)

High-definition (HD) maps have played an integral role in the development of modern autonomous vehicle (AV) stacks, albeit with high associated labeling and maintenance costs. As a result, many recent works have proposed methods for estimating HD maps online from sensor data, enabling AVs to operate outside of previously-mapped regions. However, current online map estimation approaches are developed in isolation of their downstream tasks, complicating their integration in AV stacks. In particular, they do not produce uncertainty or confidence estimates. In this work, we extend multiple state-of-the-art online map estimation methods to additionally estimate uncertainty and show how this enables more tightly integrating online mapping with trajectory forecasting. In doing so, we find that incorporating uncertainty yields up to 50% faster training convergence and up to 15% better prediction performance on the real-world nuScenes driving dataset.

Key facts. Cited by 32 papers in the map (data through 7 Oct 2026). Builds on 37 of its 41 references that are in the map. First posted on arXiv 25 Mar 2024.

Builds on

37 of 41 references.

References · 37

  1. 2017Attention Is All You Needcited by 59,932
  2. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  3. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,213
  4. 2022Planning-oriented Autonomous Drivingcited by 1,068
  5. 2020Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3Dcited by 1,040
  6. 2022BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representationcited by 844
  7. 2019Argoverse: 3D Tracking and Forecasting with Rich Mapscited by 728
  8. 2023Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecastingcited by 701
  9. 2023VAD: Vectorized Scene Representation for Efficient Autonomous Drivingcited by 613
  10. 2021Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Datasetcited by 532
  11. 2020VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representationcited by 528
  12. 2020Learning Lane Graph Representations for Motion Forecastingcited by 380
25 more
  1. 2020TNT: Target-driveN Trajectory Predictioncited by 345
  2. 2021AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecastingcited by 327
  3. 2022MapTR: Structured Modeling and Learning for Online Vectorized HD Map Constructioncited by 311
  4. 2021DenseTNT: End-to-end Trajectory Prediction from Dense Goal Setscited by 292
  5. 2021HDMapNet: An Online HD Map Construction and Evaluation Frameworkcited by 280
  6. 2019CoverNet: Multimodal Behavior Prediction using Trajectory Setscited by 259
  7. 2022VectorMapNet: End-to-end Vectorized HD Map Learningcited by 243
  8. 2023Parting with Misconceptions about Learning-based Vehicle Motion Planningcited by 238
  9. 2019Human Motion Trajectory Prediction: A Surveycited by 231
  10. 2023Scene as Occupancycited by 208
  11. 2021Multimodal Motion Prediction with Stacked Transformerscited by 207
  12. 2023MapTRv2: An End-to-End Framework for Online Vectorized HD Map Constructioncited by 192
  13. 2021GOHOME: Graph-Oriented Heatmap Output for future Motion Estimationcited by 146
  14. 2023StreamMapNet: Streaming Mapping Network for Vectorized Online HD Map Constructioncited by 143
  15. 2021HOME: Heatmap Output for future Motion Estimationcited by 122
  16. 2021Multimodal Trajectory Prediction Conditioned on Lane-Graph Traversalscited by 112
  17. 2021THOMAS: Trajectory Heatmap Output with learned Multi-Agent Samplingcited by 101
  18. 2021Structured Bird's-Eye-View Traffic Scene Understanding from Onboard Imagescited by 98
  19. 2023PivotNet: Vectorized Pivot Learning for End-to-end HD Map Constructioncited by 84
  20. 2023End-to-End Vectorized HD-map Construction with Piecewise Bezier Curvecited by 80
  21. 2022BEVPoolv2: A Cutting-edge Implementation of BEVDet Toward Deploymentcited by 79
  22. 2023InstaGraM: Instance-level Graph Modeling for Vectorized HD Map Learningcited by 40
  23. 2022SuperFusion: Multilevel LiDAR-Camera Fusion for Long-Range HD Map Generationcited by 39
  24. 2023trajdata: A Unified Interface to Multiple Human Trajectory Datasetscited by 25
  25. 2022Expanding the Deployment Envelope of Behavior Prediction via Adaptive Meta-Learningcited by 23

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 7; 2025: 19; 2026: 6.

32 papers.

Sort:

By area:

  1. 2024DiffusionDrive: Truncated Diffusion Model for End-to-End Autonomous Drivingcited by 324
  2. 2025RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-based Reinforcement Learningcited by 76
  3. 2025Toward Real-world BEV Perception: Depth Uncertainty Estimation via Gaussian Splattingcited by 20
  4. 2025Trajectory Prediction for Autonomous Driving: Progress, Limitations, and Future Directionscited by 14
  5. 2025Data Scaling Laws for End-to-End Autonomous Drivingcited by 14
  6. 2025UncAD: Towards Safe End-to-end Autonomous Driving via Online Map Uncertaintycited by 14
  7. 2024Unveiling the Hidden: Online Vectorized HD Map Construction with Clip-Level Token Interaction and Propagationcited by 12
  8. 2025MapDiffusion: Generative Diffusion for Vectorized Online HD Map Construction and Uncertainty Estimation in Autonomous Drivingcited by 12
  9. 2024DTCLMapper: Dual Temporal Consistent Learning for Vectorized HD Map Constructioncited by 10
  10. 2025Multi-modal Knowledge Distillation-based Human Trajectory Forecastingcited by 10
  11. 2024MemFusionMap: Working Memory Fusion for Online Vectorized HD Map Constructioncited by 9
  12. 2024Accelerating Online Mapping and Behavior Prediction via Direct BEV Feature Attentioncited by 8
20 more
  1. 2025Delving into Mapping Uncertainty for Mapless Trajectory Predictioncited by 6
  2. 2025Generative Active Learning for Long-tail Trajectory Prediction via Controllable Diffusion Modelcited by 6
  3. 2025Stability Under Scrutiny: Benchmarking Representation Paradigms for Online HD Mappingcited by 6
  4. 2024CUQDS: Conformal Uncertainty Quantification under Distribution Shift for Trajectory Predictioncited by 5
  5. 2025RTMap: Real-Time Recursive Mapping with Change Detection and Localizationcited by 5
  6. 2025AID4AD: Aerial Image Data for Automated Driving Perceptioncited by 4
  7. 2025WPT: World-to-Policy Transfer via Online World Model Distillationcited by 4
  8. 2025Uncertainty-Instructed Structure Injection for Generalizable HD Map Constructioncited by 3
  9. 2025Mimir: Hierarchical Goal-Driven Diffusion with Uncertainty Propagation for End-to-End Autonomous Drivingcited by 3
  10. 2025Using Language and Road Manuals to Inform Map Reconstruction for Autonomous Drivingcited by 2
  11. 2025DiffSemanticFusion: Semantic Raster BEV Fusion for Autonomous Driving via Online HD Map Diffusioncited by 2
  12. 2026UniUncer: Unified Dynamic Static Uncertainty for End to End Drivingcited by 2
  13. 2025SUPER-AD: Semantic Uncertainty-aware Planning for End-to-End Robust Autonomous Drivingcited by 1
  14. 2026Unified Map Prior Encoder for Mapping and Planningcited by 1
  15. 2024LASER: Script Execution by Autonomous Agents for On-demand Traffic Simulationcited by 0
  16. 2025GContextFormer: A global context-aware hybrid multi-head attention approach with scaled additive aggregation for multimodal trajectory predictioncited by 0
  17. 2026Uncertainty-Aware Trajectory Prediction: A Unified Framework Harnessing Positional and Semantic Uncertaintiescited by 0
  18. 2026A Collaborative Multi-Modality Interaction for VLA-based End-to-End Autonomous Drivingcited by 0
  19. 2026Auditing Latent-Space Monitors for Autonomous Drivingcited by 0
  20. 2026MapLightning: Online Vectorized HD Map Construction with 1D Map Tokenscited by 0