VectorNet: Encoding HD Maps and Agent Dynamics From Vectorized Representation

@article{Gao2020VectorNetEH,
  title={VectorNet: Encoding HD Maps and Agent Dynamics From Vectorized Representation},
  author={Jiyang Gao and Chen Sun and Hang Zhao and Y. Shen and Dragomir Anguelov and Congcong Li and C. Schmid},
  journal={2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2020},
  pages={11522-11530}
}
  • Jiyang Gao, Chen Sun, +4 authors C. Schmid
  • Published 2020
  • Computer Science, Mathematics
  • 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • Behavior prediction in dynamic, multi-agent systems is an important problem in the context of self-driving cars, due to the complex representations and interactions of road components, including moving agents (e.g. pedestrians and vehicles) and road context information (e.g. lanes, traffic lights). This paper introduces VectorNet, a hierarchical graph neural network that first exploits the spatial locality of individual road components represented by vectors and then models the high-order… CONTINUE READING
    25 Citations
    Learning Lane Graph Representations for Motion Forecasting
    • 12
    • Highly Influenced
    • PDF
    LaneRCNN: Distributed Representations for Graph-Centric Motion Forecasting
    • Highly Influenced
    • PDF
    Motion Prediction using Trajectory Sets and Self-Driving Domain Knowledge
    • 1
    • PDF
    Interaction-Based Trajectory Prediction Over a Hybrid Traffic Graph
    • PDF
    Motion Prediction for Autonomous Vehicles from Lyft Dataset using Deep Learning
    Learning Representations for Safe Autonomous Movement
    • Highly Influenced
    • PDF
    PRANK: motion Prediction based on RANKing
    • Highly Influenced
    • PDF

    References

    SHOWING 1-10 OF 34 REFERENCES
    Rules of the Road: Predicting Driving Behavior With a Convolutional Model of Semantic Interactions
    • J. Hong, B. Sapp, J. Philbin
    • Computer Science
    • 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
    • 2019
    • 57
    • PDF
    Social LSTM: Human Trajectory Prediction in Crowded Spaces
    • 1,053
    • Highly Influential
    • PDF
    Multimodal Trajectory Predictions for Autonomous Driving using Deep Convolutional Networks
    • 108
    • PDF
    Multiple Futures Prediction
    • 68
    • PDF
    PRECOG: PREdiction Conditioned on Goals in Visual Multi-Agent Settings
    • 92
    • PDF
    Learning Social Etiquette: Human Trajectory Understanding In Crowded Scenes
    • 318
    • PDF
    Relational Action Forecasting
    • 34
    • PDF
    VideoBERT: A Joint Model for Video and Language Representation Learning
    • 202
    • PDF
    PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
    • 2,234
    • PDF
    IntentNet: Learning to Predict Intention from Raw Sensor Data
    • 109
    • Highly Influential
    • PDF