Abstract— Detecting Unmanned Aerial Vehicles (UAVs), also known as drones, is becoming more difficult as technologies keep advancing. The low price, smaller size, and high speed of UAVs make them hard to detect. The goal of this study is to critically review and evaluate the UAVs sensor-based detection systems using Machine Learning (ML) algorithms. The study reviews several sensor-based detection systems (acoustic, thermal infra-red, radio frequency, and radar), and makes recommendations for future enhancements using machine learning-based techniques. One of the findings of this study is the small amount of data used by researchers, due to the lack of publicly available datasets, which added limitations to the research and may have produced inaccurate results. Another important finding is the closed environments (labs) that most researchers have conducted their research in, which are far from real case scenarios. Finally, this research makes recommendations on how to improve the process and obtain more accurate results. Classification and identification of UAVs are beyond the scope of this paper.

Index Terms—unmanned aerial vehicle, sensor-based detection, machine learning

Cite: Romil S. Al-Adwan and Osama M. Al-Habahbeh, "Unmanned Aerial Vehicles Sensor-Based Detection Systems Using Machine Learning Algorithms," International Journal of Mechanical Engineering and Robotics Research, Vol. 11, No. 9, pp. 662-668, September 2022. DOI: 10.18178/ijmerr.11.9.662-668

Copyright © 2022 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC BY-NC-ND 4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.