mlsanityData to 14 Oct 2026

Motion Forecasting for Autonomous Vehicles: A Survey

arXiv 2502.08664 ↗First posted 10 Feb 2025cs.RO cs.AIcited by 8

Not on the map. Why?

Abstract (arXiv)

In recent years, the field of autonomous driving has attracted increasingly significant public interest. Accurately forecasting the future behavior of various traffic participants is essential for the decision-making of Autonomous Vehicles (AVs). In this paper, we focus on both scenario-based and perception-based motion forecasting for AVs. We propose a formal problem formulation for motion forecasting and summarize the main challenges confronting this area of research. We also detail representative datasets and evaluation metrics pertinent to this field. Furthermore, this study classifies recent research into two main categories: supervised learning and self-supervised learning, reflecting the evolving paradigms in both scenario-based and perception-based motion forecasting. In the context of supervised learning, we thoroughly examine and analyze each key element of the methodology. For self-supervised learning, we summarize commonly adopted techniques. The paper concludes and discusses potential research directions, aiming to propel progress in this vital area of AV technology.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 58 of its 90 references that are in the map. First posted on arXiv 10 Feb 2025.

Builds on

58 of 90 references.

References · 58

  1. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  2. 2022Planning-oriented Autonomous Drivingcited by 1,087
  3. 2019Argoverse: 3D Tracking and Forecasting with Rich Mapscited by 732
  4. 2023Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecastingcited by 707
  5. 2021Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Datasetcited by 537
  6. 2020VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representationcited by 530
  7. 2019MultiPath: Multiple Probabilistic Anchor Trajectory Hypotheses for Behavior Predictioncited by 420
  8. 2020Learning Lane Graph Representations for Motion Forecastingcited by 382
  9. 2020TNT: Target-driveN Trajectory Predictioncited by 347
  10. 2021AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecastingcited by 331
  11. 2021DenseTNT: End-to-end Trajectory Prediction from Dense Goal Setscited by 295
  12. 2022Wayformer: Motion Forecasting via Simple & Efficient Attention Networkscited by 280
38 more
  1. 2018The highD Dataset: A Drone Dataset of Naturalistic Vehicle Trajectories on German Highways for Validation of Highly Automated Driving Systemscited by 277
  2. 2022Motion Transformer with Global Intention Localization and Local Movement Refinementcited by 270
  3. 2019CoverNet: Multimodal Behavior Prediction using Trajectory Setscited by 259
  4. 2019INTERACTION Dataset: An INTERnational, Adversarial and Cooperative moTION Dataset in Interactive Driving Scenarios with Semantic Mapscited by 231
  5. 2020Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting with a Single Convolutional Netcited by 228
  6. 2018Convolutional Social Pooling for Vehicle Trajectory Predictioncited by 221
  7. 2023MotionDiffuser: Controllable Multi-Agent Motion Prediction using Diffusioncited by 213
  8. 2021IntentNet: Learning to Predict Intention from Raw Sensor Datacited by 158
  9. 2023MotionLM: Multi-Agent Motion Forecasting as Language Modelingcited by 156
  10. 2020PnPNet: End-to-End Perception and Prediction with Tracking in the Loopcited by 144
  11. 2023GameFormer: Game-theoretic Modeling and Learning of Transformer-based Interactive Prediction and Planning for Autonomous Drivingcited by 141
  12. 2023MTR++: Multi-Agent Motion Prediction with Symmetric Scene Modeling and Guided Intention Queryingcited by 140
  13. 2019Multi-Agent Tensor Fusion for Contextual Trajectory Predictioncited by 131
  14. 2021Latent Variable Sequential Set Transformers For Joint Multi-Agent Motion Predictioncited by 131
  15. 2024A Comprehensive Survey of Small Language Models in the Era of Large Language Models: Techniques, Enhancements, Applications, Collaboration with LLMs, and Trustworthinesscited by 127
  16. 2021HOME: Heatmap Output for future Motion Estimationcited by 122
  17. 2021LaneRCNN: Distributed Representations for Graph-Centric Motion Forecastingcited by 113
  18. 2021Multimodal Trajectory Prediction Conditioned on Lane-Graph Traversalscited by 113
  19. 2022HDGT: Heterogeneous Driving Graph Transformer for Multi-Agent Trajectory Prediction via Scene Encodingcited by 110
  20. 2019Spatially-Aware Graph Neural Networks for Relational Behavior Forecasting from Sensor Datacited by 104
  21. 2021THOMAS: Trajectory Heatmap Output with learned Multi-Agent Samplingcited by 101
  22. 2022M2I: From Factored Marginal Trajectory Prediction to Interactive Predictioncited by 81
  23. 2019What the Constant Velocity Model Can Teach Us About Pedestrian Motion Predictioncited by 80
  24. 2020PiP: Planning-informed Trajectory Prediction for Autonomous Drivingcited by 80
  25. 2021Multi-modal Motion Prediction with Transformer-based Neural Network for Autonomous Drivingcited by 73
  26. 2023Forecast-MAE: Self-supervised Pre-training for Motion Forecasting with Masked Autoencoderscited by 73
  27. 2023Traj-MAE: Masked Autoencoders for Trajectory Predictioncited by 42
  28. 2023ADAPT: Efficient Multi-Agent Trajectory Prediction with Adaptationcited by 41
  29. 2022JFP: Joint Future Prediction with Interactive Multi-Agent Modeling for Autonomous Drivingcited by 40
  30. 2024SmartRefine: A Scenario-Adaptive Refinement Framework for Efficient Motion Predictioncited by 34
  31. 2022SSL-Lanes: Self-Supervised Learning for Motion Forecasting in Autonomous Drivingcited by 32
  32. 2023FEND: A Future Enhanced Distribution-Aware Contrastive Learning Framework for Long-tail Trajectory Predictioncited by 31
  33. 2023QCNeXt: A Next-Generation Framework For Joint Multi-Agent Trajectory Predictioncited by 31
  34. 2023SEPT: Towards Efficient Scene Representation Learning for Motion Predictioncited by 27
  35. 2022PreTraM: Self-Supervised Pre-training via Connecting Trajectory and Mapcited by 25
  36. 2023Large Trajectory Models are Scalable Motion Predictors and Plannerscited by 23
  37. 2024T4P: Test-Time Training of Trajectory Prediction via Masked Autoencoder and Actor-specific Token Memorycited by 20
  38. 2020IDE-Net: Interactive Driving Event and Pattern Extraction from Human Datacited by 19

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 6.

8 papers.

  1. 2025DRoPE: Directional Rotary Position Embedding for Efficient Agent Interaction Modelingcited by 9
  2. 2026KLDrive: Fine-Grained 3D Scene Reasoning for Autonomous Driving based on Knowledge Graphcited by 2
  3. 2025Semi-SMD: Semi-Supervised Metric Depth Estimation via Surrounding Cameras for Autonomous Drivingcited by 1
  4. 2026MotionScale: Reconstructing Appearance, Geometry, and Motion of Dynamic Scenes with Scalable 4D Gaussian Splattingcited by 1
  5. 2026Digital-Twin Losses for Lane-Compliant Trajectory Prediction at Urban Intersectionscited by 0
  6. 2026Driving, Fast or Slow? Neuro-Symbolic Guidance for Motion Prediction in Multi-Modal Ground Mobilitycited by 0
  7. 2026Reasonable Motion: A General ASP Foundation for Environment Constrained Movement Trajectory Computationcited by 0
  8. 2026SD-RouteFusion: Ego-Trajectory Prediction with SD-Map Route Conditioningcited by 0