GapFlyt: Active Vision Based Minimalist Structure-less Gap Detection For Quadrotor Flight: Wiki

GapFlyt by Perception & Robotics Group at the Department of Computer Science, University of Maryland- College Park.

Check out the Wiki for the Hardware and Software setup.

Check out our Youtube video which depicts the proposed framework of a bio-inspired perceptual design for quadrotors.

We use this bio-inspired philosophy to design a minimalist sensori-motor framework for a quadrotor to fly though unknown gaps without a 3D reconstruction of the scene using only a monocular camera and onboard sensing. We successfully evaluate and demonstrate the proposed approach in many real-world experiments with different settings and window shapes, achieving a success rate of 85% at 2.5m/s, even with a minimum tolerance of just 5cm.

• Project Page
• IEEE-RAL 2018 Paper
• arXiv Preprint
• Supplementary

Publication:

Nitin J Sanket*, Chahat Deep Singh*, Kanishka Ganguly, Cornelia Fermuller, Yiannis Aloimonos
(* Equal Contribution)

@article{sanket2018gapflyt,
  title={GapFlyt: Active Vision Based Minimalist Structure-less Gap Detection For Quadrotor Flight},
  author={Sanket, Nitin J and Singh, Chahat and Ganguly, Kanishka and Ferm{\"u}ller, Cornelia and Aloimonos, Yiannis},
  journal={IEEE Robotics and Automation Letters},
  year={2018},
  publisher={IEEE}
}

Maintainers:

• Nitin J Sanket
• Chahat Deep Singh

License:

Copyright (c) 2018 Perception and Robotics Group (PRG)