Corpus ID: 208617538

Visual Reaction: Learning to Play Catch with Your Drone

@article{Zeng2019VisualRL,
  title={Visual Reaction: Learning to Play Catch with Your Drone},
  author={Kuo-Hao Zeng and Roozbeh Mottaghi and Luca Weihs and Ali Farhadi},
  journal={ArXiv},
  year={2019},
  volume={abs/1912.02155}
}
  • Kuo-Hao Zeng, Roozbeh Mottaghi, +1 author Ali Farhadi
  • Published in ArXiv 2019
  • Computer Science
  • In this paper we address the problem of visual reaction: the task of interacting with dynamic environments where the changes in the environment are not necessarily caused by the agents itself. Visual reaction entails predicting the future changes in a visual environment and planning accordingly. We study the problem of visual reaction in the context of playing catch with a drone in visually rich synthetic environments. This is a challenging problem since the agent is required to learn (1) how… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 71 REFERENCES

    Asynchronous Methods for Deep Reinforcement Learning

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    An introduction to Kalman filter

    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL

    Improved vrnns for video prediction

    • Lluís Castrejón, Nicolas Ballas, Aaron C. Courville
    • In ICCV,
    • 2019
    VIEW 1 EXCERPT

    Learning Latent Dynamics for Planning from Pixels

    VIEW 1 EXCERPT

    Relational Action Forecasting

    VIEW 1 EXCERPT

    Learning Spatial-Aware Regressions for Visual Tracking

    VIEW 1 EXCERPT