Corpus ID: 212634254

Learning Visuomotor Policies for Aerial Navigation Using Cross-Modal Representations

@article{Bonatti2019LearningVP,
  title={Learning Visuomotor Policies for Aerial Navigation Using Cross-Modal Representations},
  author={Rogerio Bonatti and Ratnesh Madaan and Vibhav Vineet and S. Scherer and A. Kapoor},
  journal={arXiv: Computer Vision and Pattern Recognition},
  year={2019}
}
  • Rogerio Bonatti, Ratnesh Madaan, +2 authors A. Kapoor
  • Published 2019
  • Computer Science
  • arXiv: Computer Vision and Pattern Recognition
  • Machines are a long way from robustly solving open-world perception-control tasks, such as first-person view (FPV) aerial navigation. While recent advances in end-to-end Machine Learning, especially Imitation and Reinforcement Learning appear promising, they are constrained by the need of large amounts of difficult-to-collect labeled real-world data. Simulated data, on the other hand, is easy to generate, but generally does not render safe behaviors in diverse real-life scenarios. In this work… CONTINUE READING
    3 Citations

    References

    SHOWING 1-10 OF 39 REFERENCES
    (CAD)$^2$RL: Real Single-Image Flight without a Single Real Image
    • 404
    • PDF
    Adversarial discriminative sim-to-real transfer of visuo-motor policies
    • 23
    Generalization through Simulation: Integrating Simulated and Real Data into Deep Reinforcement Learning for Vision-Based Autonomous Flight
    • 32
    • PDF
    Beauty and the Beast: Optimal Methods Meet Learning for Drone Racing
    • 47
    • Highly Influential
    • PDF
    DroNet: Learning to Fly by Driving
    • 148
    • PDF
    Deep Drone Racing: From Simulation to Reality With Domain Randomization
    • 33
    • PDF
    Learning monocular reactive UAV control in cluttered natural environments
    • 300
    • PDF
    Perception, Guidance, and Navigation for Indoor Autonomous Drone Racing Using Deep Learning
    • 53
    Virtual-to-real deep reinforcement learning: Continuous control of mobile robots for mapless navigation
    • L. Tai, G. Paolo, M. Liu
    • Computer Science, Engineering
    • 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
    • 2017
    • 256
    • PDF