Corpus ID: 214802528

Trajectron++: Dynamically-Feasible Trajectory Forecasting With Heterogeneous Data.

@article{Salzmann2020TrajectronDT,
  title={Trajectron++: Dynamically-Feasible Trajectory Forecasting With Heterogeneous Data.},
  author={Tim Salzmann and B. Ivanovic and P. Chakravarty and M. Pavone},
  journal={arXiv: Robotics},
  year={2020}
}
  • Tim Salzmann, B. Ivanovic, +1 author M. Pavone
  • Published 2020
  • Engineering, Computer Science
  • arXiv: Robotics
  • Reasoning about human motion is an important prerequisite to safe and socially-aware robotic navigation. As a result, multi-agent behavior prediction has become a core component of modern human-robot interactive systems, such as self-driving cars. While there exist many methods for trajectory forecasting, most do not enforce dynamic constraints and do not account for environmental information (e.g., maps). Towards this end, we present Trajectron++, a modular, graph-structured recurrent model… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 43 REFERENCES
    Social Attention: Modeling Attention in Human Crowds
    162
    Learning Structured Output Representation using Deep Conditional Generative Models
    831
    nuScenes: A Multimodal Dataset for Autonomous Driving
    277