mlsanityData to 14 Oct 2026

Dynamic Scenario Representation Learning for Motion Forecasting with Heterogeneous Graph Convolutional Recurrent Networks

arXiv 2303.04364 ↗First posted 8 Mar 2023cs.AI cs.CV cs.LGcited by 28

Not on the map. Why?

Abstract (arXiv)

Due to the complex and changing interactions in dynamic scenarios, motion forecasting is a challenging problem in autonomous driving. Most existing works exploit static road graphs to characterize scenarios and are limited in modeling evolving spatio-temporal dependencies in dynamic scenarios. In this paper, we resort to dynamic heterogeneous graphs to model the scenario. Various scenario components including vehicles (agents) and lanes, multi-type interactions, and their changes over time are jointly encoded. Furthermore, we design a novel heterogeneous graph convolutional recurrent network, aggregating diverse interaction information and capturing their evolution, to learn to exploit intrinsic spatio-temporal dependencies in dynamic graphs and obtain effective representations of dynamic scenarios. Finally, with a motion forecasting decoder, our model predicts realistic and multi-modal future trajectories of agents and outperforms state-of-the-art published works on several motion forecasting benchmarks.

Key facts. Cited by 28 papers in the map (data through 14 Oct 2026). Builds on 32 of its 36 references that are in the map. First posted on arXiv 8 Mar 2023.

Builds on

32 of 36 references.

References · 32

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2017Graph Attention Networkscited by 8,923
  3. 2017Inductive Representation Learning on Large Graphscited by 6,320
  4. 2018How Powerful are Graph Neural Networks?cited by 4,393
  5. 2017Neural Message Passing for Quantum Chemistrycited by 3,487
  6. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
  7. 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,102
  8. 2019Argoverse: 3D Tracking and Forecasting with Rich Mapscited by 732
  9. 2023Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecastingcited by 707
  10. 2018Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networkscited by 690
  11. 2020VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representationcited by 530
  12. 2019MultiPath: Multiple Probabilistic Anchor Trajectory Hypotheses for Behavior Predictioncited by 420
20 more
  1. 2018ChauffeurNet: Learning to Drive by Imitating the Best and Synthesizing the Worstcited by 397
  2. 2020Learning Lane Graph Representations for Motion Forecastingcited by 382
  3. 2020TNT: Target-driveN Trajectory Predictioncited by 347
  4. 2021DenseTNT: End-to-end Trajectory Prediction from Dense Goal Setscited by 295
  5. 2018Multimodal Trajectory Predictions for Autonomous Driving using Deep Convolutional Networkscited by 289
  6. 2021MultiPath++: Efficient Information Fusion and Trajectory Aggregation for Behavior Predictioncited by 246
  7. 2019Graph Neural Networks with convolutional ARMA filterscited by 185
  8. 2021IntentNet: Learning to Predict Intention from Raw Sensor Datacited by 158
  9. 2021GOHOME: Graph-Oriented Heatmap Output for future Motion Estimationcited by 146
  10. 2021Latent Variable Sequential Set Transformers For Joint Multi-Agent Motion Predictioncited by 131
  11. 2019Rules of the Road: Predicting Driving Behavior with a Convolutional Model of Semantic Interactionscited by 117
  12. 2021LaneRCNN: Distributed Representations for Graph-Centric Motion Forecastingcited by 113
  13. 2021THOMAS: Trajectory Heatmap Output with learned Multi-Agent Samplingcited by 101
  14. 2021TPCN: Temporal Point Cloud Networks for Motion Forecastingcited by 94
  15. 2019Multi-Head Attention for Multi-Modal Joint Vehicle Motion Forecastingcited by 87
  16. 2020What-If Motion Prediction for Autonomous Drivingcited by 80
  17. 2021Learning to Predict Vehicle Trajectories with Model-based Planningcited by 63
  18. 2022Bootstrap Motion Forecasting With Self-Consistent Constraintscited by 23
  19. 2022BANet: Motion Forecasting with Boundary Aware Networkcited by 10
  20. 2017Graph-based Isometry Invariant Representation Learningcited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 13; 2025: 7; 2026: 5.

28 papers.

Sort:

By area:

  1. 2024HPNet: Dynamic Trajectory Forecasting with Historical Prediction Attentioncited by 38
  2. 2023Real-Time Motion Prediction via Heterogeneous Polyline Transformer with Relative Pose Encodingcited by 33
  3. 2023SEPT: Towards Efficient Scene Representation Learning for Motion Predictioncited by 27
  4. 2024SIMPL: A Simple and Efficient Multi-agent Motion Prediction Baseline for Autonomous Drivingcited by 27
  5. 2023SceneDM: Scene-level Multi-agent Trajectory Generation with Consistent Diffusion Modelscited by 24
  6. 2024Optimizing Diffusion Models for Joint Trajectory Prediction and Controllable Generationcited by 18
  7. 2024Diffusion-Based Environment-Aware Trajectory Predictioncited by 14
  8. 2024Motion Forecasting in Continuous Drivingcited by 11
  9. 2024Efficient Motion Prediction: A Lightweight & Accurate Trajectory Prediction Model With Fast Training and Inference Speedcited by 10
  10. 2025DONUT: A Decoder-Only Model for Trajectory Predictioncited by 7
  11. 2025GoIRL: Graph-Oriented Inverse Reinforcement Learning for Multimodal Trajectory Predictioncited by 7
  12. 2024FutureNet-LOF: Joint Trajectory Prediction and Lane Occupancy Field Prediction with Future Context Encodingcited by 6
16 more
  1. 2024Multi-Agent Trajectory Prediction with Difficulty-Guided Feature Enhancement Networkcited by 6
  2. 2025Future-Aware Interaction Network For Motion Forecastingcited by 4
  3. 2024Controllable Diverse Sampling for Diffusion Based Motion Behavior Forecastingcited by 3
  4. 2024ProIn: Learning to Predict Trajectory Based on Progressive Interactions for Autonomous Drivingcited by 3
  5. 2024Forecast-PEFT: Parameter-Efficient Fine-Tuning for Pre-trained Motion Forecasting Modelscited by 3
  6. 2025C-MAG: Cascade Multimodal Attributed Graphs for Supply Chain Link Predictioncited by 3
  7. 2024A Structure-Aware Lane Graph Transformer Model for Vehicle Trajectory Predictioncited by 2
  8. 2025HAMF: A Hybrid Attention-Mamba Framework for Joint Scene Context Understanding and Future Motion Representation Learningcited by 2
  9. 2025LANet: A Lane Boundaries-Aware Approach For Robust Trajectory Predictioncited by 1
  10. 2026HiMAP: History-aware Map-occupancy Prediction with Fallbackcited by 1
  11. 2024Vectorized Representation Dreamer (VRD): Dreaming-Assisted Multi-Agent Motion-Forecastingcited by 0
  12. 2025Unifying Structural Proximity and Equivalence for Enhanced Dynamic Network Embeddingcited by 0
  13. 2026ECTraj: Enhanced Consistency Training for Multi-Agent Trajectory Predictioncited by 0
  14. 2026Unveiling Transferability in Trajectory Prediction via Latent Scene Embeddingscited by 0
  15. 2026A Unified Framework for Trajectory Prediction with Explicit Planning and Reaction Decompositioncited by 0
  16. 2026MoCAR: Motion-code Coordinate-aware AutoRegression for Continuous Trajectory Forecastingcited by 0