mlsanityData to 7 Oct 2026

Uncertainty estimation for Cross-dataset performance in Trajectory prediction

arXiv 2205.07310 ↗First posted 15 May 2022cs.CVcited by 13

Not on the map. Why?

Abstract (arXiv)

While a lot of work has been carried on developing trajectory prediction methods, and various datasets have been proposed for benchmarking this task, little study has been done so far on the generalizability and the transferability of these methods across dataset. In this paper, we observe the performance of two of the latest state-of-the-art trajectory prediction methods across four different datasets (Argoverse, NuScenes, Interaction, Shifts). This analysis allows to gain some insights on the generalizability proprieties of most recent trajectory prediction models and to analyze which dataset is more representative of real driving scenes and therefore enables better transferability. Furthermore we present a novel method to estimate prediction uncertainty and show how it could be used to achieve better performance across datasets.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 50 of its 60 references that are in the map. First posted on arXiv 15 May 2022.

Builds on

50 of 60 references.

References · 50

  1. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  2. 2019Argoverse: 3D Tracking and Forecasting with Rich Mapscited by 728
  3. 2019MultiPath: Multiple Probabilistic Anchor Trajectory Hypotheses for Behavior Predictioncited by 417
  4. 2020Learning Lane Graph Representations for Motion Forecastingcited by 380
  5. 2020TNT: Target-driveN Trajectory Predictioncited by 345
  6. 2021AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecastingcited by 327
  7. 2017DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agentscited by 310
  8. 2018SoPhie: An Attentive GAN for Predicting Paths Compliant to Social and Physical Constraintscited by 296
  9. 2021DenseTNT: End-to-end Trajectory Prediction from Dense Goal Setscited by 292
  10. 2018Multimodal Trajectory Predictions for Autonomous Driving using Deep Convolutional Networkscited by 289
  11. 2019CoverNet: Multimodal Behavior Prediction using Trajectory Setscited by 259
  12. 2021MultiPath++: Efficient Information Fusion and Trajectory Aggregation for Behavior Predictioncited by 246
38 more
  1. 2020It Is Not the Journey but the Destination: Endpoint Conditioned Trajectory Predictioncited by 235
  2. 2019INTERACTION Dataset: An INTERnational, Adversarial and Cooperative moTION Dataset in Interactive Driving Scenarios with Semantic Mapscited by 231
  3. 2017Geometric Loss Functions for Camera Pose Regression with Deep Learningcited by 224
  4. 2018Convolutional Social Pooling for Vehicle Trajectory Predictioncited by 221
  5. 2021MP3: A Unified Model to Map, Perceive, Predict and Plancited by 211
  6. 2019Multiple Futures Predictioncited by 178
  7. 2020From Goals, Waypoints & Paths To Long Term Human Trajectory Forecastingcited by 166
  8. 2021GOHOME: Graph-Oriented Heatmap Output for future Motion Estimationcited by 146
  9. 2021Latent Variable Sequential Set Transformers For Joint Multi-Agent Motion Predictioncited by 131
  10. 2021HOME: Heatmap Output for future Motion Estimationcited by 122
  11. 2019Rules of the Road: Predicting Driving Behavior with a Convolutional Model of Semantic Interactionscited by 117
  12. 2020Implicit Latent Variable Model for Scene-Consistent Motion Forecastingcited by 116
  13. 2021LaneRCNN: Distributed Representations for Graph-Centric Motion Forecastingcited by 112
  14. 2021Multimodal Trajectory Prediction Conditioned on Lane-Graph Traversalscited by 112
  15. 2021THOMAS: Trajectory Heatmap Output with learned Multi-Agent Samplingcited by 101
  16. 2021Shifts: A Dataset of Real Distributional Shift Across Multiple Large-Scale Taskscited by 100
  17. 2019Multi-Head Attention for Multi-Modal Joint Vehicle Motion Forecastingcited by 87
  18. 2022Occupancy Flow Fields for Motion Forecasting in Autonomous Drivingcited by 62
  19. 2017Probabilistic Vehicle Trajectory Prediction over Occupancy Grid Map via Recurrent Neural Networkcited by 56
  20. 2018Sequence-to-Sequence Prediction of Vehicle Trajectory via LSTM Encoder-Decoder Architecturecited by 55
  21. 2021Vehicle trajectory prediction works, but not everywherecited by 39
  22. 2021Divide-and-Conquer for Lane-Aware Diverse Trajectory Predictioncited by 37
  23. 2019Learning an Uncertainty-Aware Object Detector for Autonomous Drivingcited by 34
  24. 2021CoordiNet: uncertainty-aware pose regressor for reliable vehicle localizationcited by 34
  25. 2020Map-Adaptive Goal-Based Trajectory Predictioncited by 29
  26. 2019Scene Compliant Trajectory Forecast with Agent-Centric Spatio-Temporal Gridscited by 24
  27. 2021Injecting Planning-Awareness into Prediction and Detection Evaluationcited by 21
  28. 2021A Survey on Deep-Learning Approaches for Vehicle Trajectory Prediction in Autonomous Drivingcited by 21
  29. 2022Control-Aware Prediction Objectives for Autonomous Drivingcited by 18
  30. 2021Propagating State Uncertainty Through Trajectory Forecastingcited by 17
  31. 2021MTP: Multi-Hypothesis Tracking and Prediction for Reduced Error Propagationcited by 14
  32. 2021Rethinking Trajectory Forecasting Evaluationcited by 11
  33. 2022Assessing Cross-dataset Generalization of Pedestrian Crossing Predictorscited by 11
  34. 2022Pedestrian Detection: Domain Generalization, CNNs, Transformers and Beyondcited by 8
  35. 2022Context-Aware Scene Prediction Network (CASPNet)cited by 7
  36. 2021Transformer based trajectory predictioncited by 5
  37. 2021Estimating Uncertainty For Vehicle Motion Prediction on Yandex Shifts Datasetcited by 3
  38. 2020PrognoseNet: A Generative Probabilistic Framework for Multimodal Position Prediction given Context Informationcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 3; 2024: 5; 2025: 1; 2026: 2.

13 papers.

Sort:

By area:

  1. 2024UniTraj: A Unified Framework for Scalable Vehicle Trajectory Predictioncited by 51
  2. 2022Behavioral Intention Prediction in Driving Scenes: A Surveycited by 30
  3. 2023trajdata: A Unified Interface to Multiple Human Trajectory Datasetscited by 25
  4. 2022Expanding the Deployment Envelope of Behavior Prediction via Adaptive Meta-Learningcited by 23
  5. 2024T4P: Test-Time Training of Trajectory Prediction via Masked Autoencoder and Actor-specific Token Memorycited by 20
  6. 2023Improving Transferability for Cross-domain Trajectory Prediction via Neural Stochastic Differential Equationcited by 12
  7. 2024Stochasticity in Motion: An Information-Theoretic Approach to Trajectory Predictioncited by 4
  8. 2025Interaction-Merged Motion Planning: Effectively Leveraging Diverse Motion Datasets for Robust Planningcited by 4
  9. 2023How Does Traffic Environment Quantitatively Affect the Autonomous Driving Prediction?cited by 3
  10. 2024Cross-Dataset Gaze Estimation by Evidential Inter-intra Fusioncited by 1
  11. 2024BEVal: A Cross-dataset Evaluation Study of BEV Segmentation Models for Autonomous Drivingcited by 0
  12. 2026Unveiling Transferability in Trajectory Prediction via Latent Scene Embeddingscited by 0
1 more
  1. 2026Kernel-Based Metrics Learning for Uncertain Opponent Vehicle Trajectory Prediction in Autonomous Racingcited by 0