mlsanityData to 7 Oct 2026

Vision-based Multi-future Trajectory Prediction: A Survey

arXiv 2302.10463 ↗First posted 21 Feb 2023cs.RO cs.CV cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

Vision-based trajectory prediction is an important task that supports safe and intelligent behaviours in autonomous systems. Many advanced approaches have been proposed over the years with improved spatial and temporal feature extraction. However, human behaviour is naturally diverse and uncertain. Given the past trajectory and surrounding environment information, an agent can have multiple plausible trajectories in the future. To tackle this problem, an essential task named multi-future trajectory prediction (MTP) has recently been studied. This task aims to generate a diverse, acceptable and explainable distribution of future predictions for each agent. In this paper, we present the first survey for MTP with our unique taxonomies and a comprehensive analysis of frameworks, datasets and evaluation metrics. We also compare models on existing MTP datasets and conduct experiments on the ForkingPath dataset. Finally, we discuss multiple future directions that can help researchers develop novel multi-future trajectory prediction systems and other diverse learning tasks similar to MTP.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 87 of its 150 references that are in the map. First posted on arXiv 21 Feb 2023.

Builds on

87 of 150 references.

References · 87

  1. 2020End-to-End Object Detection with Transformerscited by 7,384
  2. 2022Generative Adversarial Networkscited by 5,603
  3. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  4. 2017CARLA: An Open Urban Driving Simulatorcited by 2,431
  5. 2016InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Netscited by 858
  6. 2019Argoverse: 3D Tracking and Forecasting with Rich Mapscited by 728
  7. 2018Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networkscited by 687
  8. 2021Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Datasetcited by 532
  9. 2020VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representationcited by 528
  10. 2017Non-Autoregressive Neural Machine Translationcited by 457
  11. 2019MultiPath: Multiple Probabilistic Anchor Trajectory Hypotheses for Behavior Predictioncited by 417
  12. 2020Learning Lane Graph Representations for Motion Forecastingcited by 380
38 more
  1. 2020TNT: Target-driveN Trajectory Predictioncited by 345
  2. 2021AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecastingcited by 327
  3. 2020Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Predictioncited by 324
  4. 2017DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agentscited by 310
  5. 2018SoPhie: An Attentive GAN for Predicting Paths Compliant to Social and Physical Constraintscited by 296
  6. 2017Toward Multimodal Image-to-Image Translationcited by 295
  7. 2021DenseTNT: End-to-end Trajectory Prediction from Dense Goal Setscited by 292
  8. 2018Multimodal Trajectory Predictions for Autonomous Driving using Deep Convolutional Networkscited by 289
  9. 2019CoverNet: Multimodal Behavior Prediction using Trajectory Setscited by 259
  10. 2021MultiPath++: Efficient Information Fusion and Trajectory Aggregation for Behavior Predictioncited by 246
  11. 2020It Is Not the Journey but the Destination: Endpoint Conditioned Trajectory Predictioncited by 235
  12. 2017Beam Search Strategies for Neural Machine Translationcited by 232
  13. 2019Human Motion Trajectory Prediction: A Surveycited by 231
  14. 2019INTERACTION Dataset: An INTERnational, Adversarial and Cooperative moTION Dataset in Interactive Driving Scenarios with Semantic Mapscited by 231
  15. 2019Social-BiGAT: Multimodal Trajectory Forecasting using Bicycle-GAN and Graph Attention Networkscited by 228
  16. 2020Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Predictioncited by 218
  17. 2021Multimodal Motion Prediction with Stacked Transformerscited by 207
  18. 2017Social Attention: Modeling Attention in Human Crowdscited by 185
  19. 2022Stochastic Trajectory Prediction via Motion Indeterminacy Diffusioncited by 184
  20. 2020Transformer Networks for Trajectory Forecastingcited by 180
  21. 2019Multiple Futures Predictioncited by 178
  22. 2022PromptCast: A New Prompt-based Learning Paradigm for Time Series Forecastingcited by 170
  23. 2020From Goals, Waypoints & Paths To Long Term Human Trajectory Forecastingcited by 166
  24. 2021GOHOME: Graph-Oriented Heatmap Output for future Motion Estimationcited by 146
  25. 2019The inD Dataset: A Drone Dataset of Naturalistic Road User Trajectories at German Intersectionscited by 137
  26. 2020Human Trajectory Forecasting in Crowds: A Deep Learning Perspectivecited by 128
  27. 2021HOME: Heatmap Output for future Motion Estimationcited by 122
  28. 2021SGCN:Sparse Graph Convolution Network for Pedestrian Trajectory Predictioncited by 97
  29. 2019Overcoming Limitations of Mixture Density Networks: A Sampling and Fitting Framework for Multimodal Future Predictioncited by 96
  30. 2022M2I: From Factored Marginal Trajectory Prediction to Interactive Predictioncited by 81
  31. 2020TPNet: Trajectory Proposal Network for Motion Predictioncited by 80
  32. 2019What the Constant Velocity Model Can Teach Us About Pedestrian Motion Predictioncited by 78
  33. 2019Social Ways: Learning Multi-Modal Distributions of Pedestrian Trajectories with GANscited by 78
  34. 2019The Garden of Forking Paths: Towards Multi-Future Trajectory Predictioncited by 72
  35. 2022SocialVAE: Human Trajectory Prediction using Timewise Latentscited by 65
  36. 2022ScePT: Scene-consistent, Policy-based Trajectory Predictions for Planningcited by 63
  37. 2021Stepwise Goal-Driven Networks for Trajectory Predictioncited by 62
  38. 2021MG-GAN: A Multi-Generator Model Preventing Out-of-Distribution Samples in Pedestrian Trajectory Predictioncited by 61

50 most cited of 87 All 87 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 1; 2025: 4; 2026: 2.

8 papers.

  1. 2025Diffusion Forcing for Multi-Agent Interaction Sequence Modelingcited by 4
  2. 2023GSGFormer: Generative Social Graph Transformer for Multimodal Pedestrian Trajectory Predictioncited by 1
  3. 2024Graph Neural Networks in Intelligent Transportation Systems: Advances, Applications and Trendscited by 1
  4. 2025TS-Mob: Social and Geographical-Aware Time Series Foundation-Model Framework for Human Mobility Predictioncited by 0
  5. 2025BEVTraj: Map-Free End-to-End Trajectory Prediction in Bird's-Eye View with Deformable Attention and Sparse Goal Proposalscited by 0
  6. 2025GContextFormer: A global context-aware hybrid multi-head attention approach with scaled additive aggregation for multimodal trajectory predictioncited by 0
  7. 2026Agent-Centric Animal Pose Forecastingcited by 0
  8. 2026ACME: A Multi-Cultural, Multi-Embodiment Social-Navigation Datasetcited by 0