Drone Autonomous Landing on a Moving Maritime Platform Using Machine Learning Classifiers

  • Udi Shriki Open University, Israel
  • Oren Gal Technion - Israel Institute of Technology, Haifa, Israel
  • Yerach Doytsher Technion - Israel Institute of Technology, Haifa, Israel
Keywords: Drone, Stochastic Gradient Descent, neural network

Abstract

Quadcopters are four rotor Vertical Take-Off and Landing (VTOL) Unmanned Aerial Vehicle (UAV) with agile manoeuvring ability, small form factor and light weight – which makes it possible to carry on small platforms.  Quadcopters are also used in marine environment for similar reasons – especially the ability to carry on small boats, instead of using helicopters on larger boats. Pilots of both manned and unmanned aerial vehicles over sea, face the challenge of landing their aircraft on a boat that is continuously rocking in all three axes (pitch, roll, yaw) and with movement of the boat, usually at steady course and speed. In this paper, we present a new approach for autonomous landing a quadcopter on a moving marine platform. Our approach is based on computer-vision algorithms using markers identification as input for the decision by Stochastic Gradient Descent (SGD) classifier with Neural Network decision making module. We use OpenCV with its built-in ArUco module to analyze the camera images and recognize platform/markers, then we use Sci-Kit Learn implementation of SGD classifier to predict landing optimum angle and compare results to manually decide by simple calculations. Our research includes real-time experiments using Parrot Bebop2 quadcopter and the Parrot Sphinx Simulator.

Published
2020-12-07
How to Cite
Shriki, U., Gal, O., & Doytsher, Y. (2020). Drone Autonomous Landing on a Moving Maritime Platform Using Machine Learning Classifiers. International Journal of Data Science and Advanced Analytics (ISSN 2563-4429), 2(2), 30-35. Retrieved from http://ijdsaa.com/index.php/welcome/article/view/80
Section
Articles