electronics Review Drone Deep Reinforcement Learning: A Review Ahmad Taher Azar 1,2, * , , Anis Koubaa 1 , Nada Ali Mohamed 3 , Habiba A. Ibrahim 4 , Zahra Fathy Ibrahim 3 , Muhammad Kazim 1,5 , Adel Ammar 1 , Bilel Benjdira 1 , Alaa M. Khamis 6 , Ibrahim A. Hameed 7 and Gabriella Casalino 8   Citation: Azar, A.T.; Koubaa, A.; Ali Mohamed, N.; Ibrahim, H.A.; Ibrahim, Z.F.; Kazim, M.; Ammar, A.; Benjdira, B.; Khamis, A.; Hameed, I.A.; et al. Drone Deep Reinforcement Learning: A Review. Electronics 2021, 10, 999. https://doi.org/10.3390/ electronics10090999 Academic Editor: Mohamed Benbouzid and Juan M. Corchado Received: 5 March 2021 Accepted: 17 April 2021 Published: 22 April 2021 Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affil- iations. Copyright: © 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https:// creativecommons.org/licenses/by/ 4.0/). 1 College of Computer & Information Sciences, Prince Sultan University, Riyadh 11586, Saudi Arabia; akoubaa@psu.edu.sa (A.K.); mkazim@psu.edu.sa (M.K.); aammar@psu.edu.sa (A.A.); bbenjdira@psu.edu.sa (B.B.) 2 Faculty of Computers and Artificial Intelligence, Benha University, Benha 13518, Egypt 3 School of Engineering and Applied Sciences, Nile University Campus, Sheikh Zayed District, Juhayna Square, 6th of October City, Giza 60411, Egypt; N.Ali@nu.edu.eg (N.A.M.); Z.Fathy@nu.edu.eg (Z.F.I.) 4 Smart Engineering Systems Research Center (SESC), Nile University, Sheikh Zayed City, Giza 12588, Egypt; h.ibrahim@nu.edu.eg 5 Research Institute of Intelligent Control and Systems, Harbin Institute of Technology, Harbin 150080, China; 6 General Motors Canada, 500 Wentworth St W, Oshawa ON L1J 6J2, Canada; alaakhamis@gmail.com 7 Department of ICT and Natural Sciences, Norwegian University of Science and Technology, Larsgårdsvegen, 2, 6009 Ålesund, Norway; ibib@ntnu.no 8 Department of Informatics, University of Bari, 70125 Bari, Italy; gabriella.casalino@uniba.it * Correspondence: aazar@psu.edu.sa or ahmad.azar@fci.bu.edu.eg Abstract: Unmanned Aerial Vehicles (UAVs) are increasingly being used in many challenging and diversified applications. These applications belong to the civilian and the military fields. To name a few; infrastructure inspection, traffic patrolling, remote sensing, mapping, surveillance, rescuing humans and animals, environment monitoring, and Intelligence, Surveillance, Target Acquisition, and Reconnaissance (ISTAR) operations. However, the use of UAVs in these applications needs a substantial level of autonomy. In other words, UAVs should have the ability to accomplish planned missions in unexpected situations without requiring human intervention. To ensure this level of autonomy, many artificial intelligence algorithms were designed. These algorithms targeted the guidance, navigation, and control (GNC) of UAVs. In this paper, we described the state of the art of one subset of these algorithms: the deep reinforcement learning (DRL) techniques. We made a detailed description of them, and we deduced the current limitations in this area. We noted that most of these DRL methods were designed to ensure stable and smooth UAV navigation by training computer-simulated environments. We realized that further research efforts are needed to address the challenges that restrain their deployment in real-life scenarios. Keywords: unmanned aerial vehicles; UAVs; guidance; navigation; control; machine learning; deep reinforcement learning (DRL); literature review 1. Introduction In recent years, the huge advancement in information technology and artificial intelli- gence largely impacted intelligent autonomous systems, which are becoming ubiquitous. Such evolution includes Unmanned Aerial Vehicles (UAVs) consisting of fully autonomous, semi-autonomous, and pilot-based or remote control-based flying vehicles. UAVs are a class of aircraft that can fly without a necessary need for an onboard human pilot [1]. They are commonly known as drones, and they can fly with various degrees of autonomy: either under remote control by a human operator or autonomously by onboard computers [2]. These drones can fly within Visual Line of Sight (VLOS) for limited distances or Beyond Visual Line of Sight (BVLOS), covering far greater distances. UAVs have been around for decades and were mainly used for military purposes. After that, they found their role in each field, either in industry, military, or even enter- Electronics 2021, 10, 999. https://doi.org/10.3390/electronics10090999 https://www.mdpi.com/journal/electronics