Autonomous Unmanned Aerial Vehicle navigation using Reinforcement Learning: A systematic review

There is an increasing demand for using Unmanned Aerial Vehicle (UAV), known as drones, in different applications such packages delivery, traffic monitoring, search and rescue operations, military combat engagements. In all of these applications, the UAV used to navigate environment autonomously - without human interaction, perform specific tasks avoid obstacles. Autonomous navigation commonly accomplished Reinforcement Learning (RL), where agents act experts a domain while avoiding Understanding algorithmic limitations plays essential role choosing appropriate RL algorithm solve problem effectively. Consequently, this study first identifies main discusses frameworks simulation software. Next, algorithms are classified discussed based on environment, characteristics, abilities, problems, which will help practitioners researchers select their use cases. Moreover, identified gaps opportunities drive research.