mlsanityData to 14 Oct 2026

SSL-Lanes: Self-Supervised Learning for Motion Forecasting in Autonomous Driving

arXiv 2206.14116 ↗First posted 28 Jun 2022cs.CV cs.AI cs.ROcited by 32

Not on the map. Why?

Abstract (arXiv)

Self-supervised learning (SSL) is an emerging technique that has been successfully employed to train convolutional neural networks (CNNs) and graph neural networks (GNNs) for more transferable, generalizable, and robust representation learning. However its potential in motion forecasting for autonomous driving has rarely been explored. In this study, we report the first systematic exploration and assessment of incorporating self-supervision into motion forecasting. We first propose to investigate four novel self-supervised learning tasks for motion forecasting with theoretical rationale and quantitative and qualitative comparisons on the challenging large-scale Argoverse dataset. Secondly, we point out that our auxiliary SSL-based learning setup not only outperforms forecasting methods which use transformers, complicated fusion mechanisms and sophisticated online dense goal candidate optimization algorithms in terms of performance accuracy, but also has low inference time and architectural complexity. Lastly, we conduct several experiments to understand why SSL improves motion forecasting. Code is open-sourced at urlhttps://github.com/AutoVision-cloud/SSL-Lanes.

Key facts. Cited by 32 papers in the map (data through 14 Oct 2026). Builds on 46 of its 54 references that are in the map. First posted on arXiv 28 Jun 2022.

Builds on

46 of 54 references.

References · 46

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  4. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  5. 2016Layer Normalizationcited by 5,669
  6. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  7. 2019Similarity of Neural Network Representations Revisitedcited by 1,755
  8. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,591
  9. 2016Context Encoders: Feature Learning by Inpaintingcited by 1,428
  10. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,382
  11. 2019Objects as Pointscited by 1,175
  12. 2016Colorful Image Colorizationcited by 1,114
34 more
  1. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,102
  2. 2015Unsupervised Visual Representation Learning by Context Predictioncited by 1,066
  3. 2019Strategies for Pre-training Graph Neural Networkscited by 971
  4. 2019Argoverse: 3D Tracking and Forecasting with Rich Mapscited by 732
  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. 2018ChauffeurNet: Learning to Drive by Imitating the Best and Synthesizing the Worstcited by 397
  9. 2020Learning Lane Graph Representations for Motion Forecastingcited by 382
  10. 2020TNT: Target-driveN Trajectory Predictioncited by 347
  11. 2020Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Predictioncited by 325
  12. 2021DenseTNT: End-to-end Trajectory Prediction from Dense Goal Setscited by 295
  13. 2021Graph Self-Supervised Learning: A Surveycited by 289
  14. 2019CoverNet: Multimodal Behavior Prediction using Trajectory Setscited by 259
  15. 2021MultiPath++: Efficient Information Fusion and Trajectory Aggregation for Behavior Predictioncited by 246
  16. 2021End-to-end Interpretable Neural Motion Plannercited by 242
  17. 2021Multimodal Motion Prediction with Stacked Transformerscited by 208
  18. 2021IntentNet: Learning to Predict Intention from Raw Sensor Datacited by 158
  19. 2016Learning Features by Watching Objects Movecited by 138
  20. 2021Latent Variable Sequential Set Transformers For Joint Multi-Agent Motion Predictioncited by 131
  21. 2021Self-supervised Learning is More Robust to Dataset Imbalancecited by 123
  22. 2021HOME: Heatmap Output for future Motion Estimationcited by 122
  23. 2020When Does Self-Supervision Help Graph Convolutional Networks?cited by 121
  24. 2021LaneRCNN: Distributed Representations for Graph-Centric Motion Forecastingcited by 113
  25. 2020Self-supervised Learning on Graphs: Deep Insights and New Directioncited by 108
  26. 2021TPCN: Temporal Point Cloud Networks for Motion Forecastingcited by 94
  27. 2019Multi-Head Attention for Multi-Modal Joint Vehicle Motion Forecastingcited by 87
  28. 2020What-If Motion Prediction for Autonomous Drivingcited by 80
  29. 2018Multi-Modal Trajectory Prediction of Surrounding Vehicles with Maneuver based LSTMscited by 77
  30. 2021Multi-modal Motion Prediction with Transformer-based Neural Network for Autonomous Drivingcited by 73
  31. 2021Learning to Predict Vehicle Trajectories with Model-based Planningcited by 63
  32. 2020Self-supervised Auxiliary Learning with Meta-paths for Heterogeneous Graphscited by 38
  33. 2022Bootstrap Motion Forecasting With Self-Consistent Constraintscited by 23
  34. 2021Self-Supervised Simultaneous Multi-Step Prediction of Road Dynamics and Cost Mapcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 3; 2023: 7; 2024: 15; 2025: 5; 2026: 2.

32 papers.

Sort:

By area:

  1. 2023Forecast-MAE: Self-supervised Pre-training for Motion Forecasting with Masked Autoencoderscited by 73
  2. 2024A Clinical Benchmark of Public Self-Supervised Pathology Foundation Modelscited by 66
  3. 2024UniTraj: A Unified Framework for Scalable Vehicle Trajectory Predictioncited by 52
  4. 2022FJMP: Factorized Joint Multi-Agent Motion Prediction over Learned Directed Acyclic Interaction Graphscited by 41
  5. 2023BAT: Behavior-Aware Human-Like Trajectory Prediction for Autonomous Drivingcited by 28
  6. 2024SIMPL: A Simple and Efficient Multi-agent Motion Prediction Baseline for Autonomous Drivingcited by 27
  7. 2023Pre-training on Synthetic Driving Data for Trajectory Predictioncited by 18
  8. 2022Motion Style Transfer: Modular Low-Rank Adaptation for Deep Motion Forecastingcited by 12
  9. 2024MFTraj: Map-Free, Behavior-Driven Trajectory Prediction for Autonomous Drivingcited by 12
  10. 2022Exploiting map information for self-supervised learning in motion forecastingcited by 8
  11. 2025Motion Forecasting for Autonomous Vehicles: A Surveycited by 8
  12. 2024JointMotion: Joint Self-Supervision for Joint Motion Predictioncited by 7
20 more
  1. 2024SmartPretrain: Model-Agnostic and Dataset-Agnostic Representation Learning for Motion Predictioncited by 7
  2. 2023RMP: A Random Mask Pretrain Framework for Motion Predictioncited by 6
  3. 2024FutureNet-LOF: Joint Trajectory Prediction and Lane Occupancy Field Prediction with Future Context Encodingcited by 6
  4. 2023iPLAN: Intent-Aware Planning in Heterogeneous Traffic via Distributed Multi-Agent Reinforcement Learningcited by 5
  5. 2023Improving Autonomous Driving Safety with POP: A Framework for Accurate Partially Observed Trajectory Predictionscited by 5
  6. 2025Future-Aware Interaction Network For Motion Forecastingcited by 4
  7. 2024Forecast-PEFT: Parameter-Efficient Fine-Tuning for Pre-trained Motion Forecasting Modelscited by 3
  8. 2024Multi-scale Temporal Fusion Transformer for Incomplete Vehicle Trajectory Predictioncited by 3
  9. 2024RealTraj: Towards Real-World Pedestrian Trajectory Forecastingcited by 3
  10. 2025Towards Generalizable Trajectory Prediction Using Dual-Level Representation Learning And Adaptive Promptingcited by 3
  11. 2025OmniTraj: Pre-Training on Heterogeneous Data for Adaptive and Zero-Shot Human Trajectory Predictioncited by 3
  12. 2024ADM: Accelerated Diffusion Model via Estimated Priors for Robust Motion Prediction under Uncertaintiescited by 2
  13. 2024A Structure-Aware Lane Graph Transformer Model for Vehicle Trajectory Predictioncited by 2
  14. 2024PPT: Pretraining with Pseudo-Labeled Trajectories for Motion Forecastingcited by 2
  15. 2023Enhancing Trajectory Prediction through Self-Supervised Waypoint Noise Predictioncited by 1
  16. 2024Interpretable Interaction Modeling for Trajectory Prediction via Agent Selection and Physical Coefficientcited by 1
  17. 2024Noise-Free Explanation for Driving Action Predictioncited by 0
  18. 2025Driving behavior recognition via self-discovery learningcited by 0
  19. 2026TaPD: Temporal-adaptive Progressive Distillation for Observation-Adaptive Trajectory Forecasting in Autonomous Drivingcited by 0
  20. 2026MoCAR: Motion-code Coordinate-aware AutoRegression for Continuous Trajectory Forecastingcited by 0