Corpus ID: 227254503

From Goals, Waypoints & Paths To Long Term Human Trajectory Forecasting

@article{Mangalam2020FromGW,
  title={From Goals, Waypoints & Paths To Long Term Human Trajectory Forecasting},
  author={K. Mangalam and Yang An and Harshayu Girase and J. Malik},
  journal={ArXiv},
  year={2020},
  volume={abs/2012.01526}
}
  • K. Mangalam, Yang An, +1 author J. Malik
  • Published 2020
  • Computer Science
  • ArXiv
  • Human trajectory forecasting is an inherently multi-modal problem. Uncertainty in future trajectories stems from two sources: (a) sources that are known to the agent but unknown to the model, such as long term goals and (b)sources that are unknown to both the agent & the model, such as intent of other agents & irreducible randomness indecisions. We propose to factorize this uncertainty into its epistemic & aleatoric sources. We model the epistemic un-certainty through multimodality in long term… CONTINUE READING

    Figures and Tables from this paper

    References

    SHOWING 1-10 OF 46 REFERENCES
    Trajectory Forecasts in Unknown Environments Conditioned on Grid-Based Plans
    • 16
    • Highly Influential
    • PDF
    TNT: Target-driveN Trajectory Prediction
    • 7
    • Highly Influential
    • PDF
    Trajectron++: Dynamically-Feasible Trajectory Forecasting with Heterogeneous Data
    • 31
    • Highly Influential
    • PDF
    It Is Not the Journey but the Destination: Endpoint Conditioned Trajectory Prediction
    • 16
    • PDF
    Social Attention: Modeling Attention in Human Crowds
    • 209
    • PDF
    Conditional Generative Neural System for Probabilistic Trajectory Prediction
    • 29
    • PDF
    DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agents
    • 379
    • Highly Influential
    • PDF
    The Garden of Forking Paths: Towards Multi-Future Trajectory Prediction
    • 22
    • Highly Influential
    • PDF
    Social LSTM: Human Trajectory Prediction in Crowded Spaces
    • 1,043
    • PDF
    Long-term Human Motion Prediction with Scene Context
    • 9
    • PDF