Autonomous drone hunter operating by deep learning and all-onboard computations in GPS-denied environments.

Journal: PloS one
Published Date:

Abstract

This paper proposes a UAV platform that autonomously detects, hunts, and takes down other small UAVs in GPS-denied environments. The platform detects, tracks, and follows another drone within its sensor range using a pre-trained machine learning model. We collect and generate a 58,647-image dataset and use it to train a Tiny YOLO detection algorithm. This algorithm combined with a simple visual-servoing approach was validated on a physical platform. Our platform was able to successfully track and follow a target drone at an estimated speed of 1.5 m/s. Performance was limited by the detection algorithm's 77% accuracy in cluttered environments and the frame rate of eight frames per second along with the field of view of the camera.

Authors

  • Philippe Martin Wyder
    Department of Mechanical Engineering, Columbia University, New York, New York, United States of America.
  • Yan-Song Chen
    Department of Computer Science, Columbia University, New York, New York, United States of America.
  • Adrian J Lasrado
    Department of Mechanical Engineering, Columbia University, New York, New York, United States of America.
  • Rafael J Pelles
    Department of Mechanical Engineering, Columbia University, New York, New York, United States of America.
  • Robert Kwiatkowski
    Department of Computer Science, Columbia University, New York, New York, United States of America.
  • Edith O A Comas
    Department of Computer Science, Columbia University, New York, New York, United States of America.
  • Richard Kennedy
    Department of Medicine, University of Alabama at Birmingham, Birmingham, AL, USA.
  • Arjun Mangla
    Department of Computer Science, Columbia University, New York, New York, United States of America.
  • Zixi Huang
    Department of Electrical Engineering, Columbia University, New York, New York, United States of America.
  • Xiaotian Hu
    Department of Electrical Engineering, Columbia University, New York, New York, United States of America.
  • Zhiyao Xiong
    Department of Mechanical Engineering, Columbia University, New York, New York, United States of America.
  • Tomer Aharoni
    Department of Computer Science, Columbia University, New York, New York, United States of America.
  • Tzu-Chan Chuang
    Department of Computer Science, Columbia University, New York, New York, United States of America.
  • Hod Lipson
    Columbia University, Department of Mechanical Engineering, New York, NY 10027, USA.