Visual Reaction: Learning to Play Catch With Your Drone

@article{Zeng2020VisualRL,
  title={Visual Reaction: Learning to Play Catch With Your Drone},
  author={Kuo-Hao Zeng and R. Mottaghi and Luca Weihs and A. Farhadi},
  journal={2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2020},
  pages={11570-11579}
}
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… Expand
3 Citations
AllenAct: A Framework for Embodied AI Research
  • 11
  • PDF
Learning About Objects by Learning to Interact with Them
  • 3
  • PDF

References

SHOWING 1-10 OF 73 REFERENCES
Target-driven visual navigation in indoor scenes using deep reinforcement learning
  • 768
  • PDF
Unsupervised Learning for Physical Interaction through Video Prediction
  • 658
  • PDF
Activity Forecasting
  • 550
  • PDF
An Uncertain Future: Forecasting from Static Images Using Variational Autoencoders
  • 365
  • PDF
Learning to Act by Predicting the Future
  • 213
  • PDF
Anticipating Visual Representations from Unlabeled Video
  • 309
  • PDF
AI2-THOR: An Interactive 3D Environment for Visual AI
  • 251
  • PDF
Visual Semantic Navigation using Scene Priors
  • 86
  • PDF
...
1
2
3
4
5
...