A Methodology For Drones to Learn How to Navigate And Avoid Obstacles Using Decision Trees

Abstract

Over the last decade, drones and UAVs have attracted great research interest mainly due to their abilities and their potential to be used in various applications and domains. One of the most important operations that Drones must perform efficiently concerns the navigation in real-world environments. This typically includes the ability of path planning and obstacle avoidance. It is crucial that drones have the ability to perform automatically and efficiently procedures related to the avoidance of objects while navigating in environments. In this work, we present a methodology for assisting a drone to navigate in unknown environments and avoid obstacles. The methodology is based on a training-by-human concept where the drone learns how to avoid obstacles by example cases that are provided to it and it is trained on them. The results are quite interesting and indicate that the methodology is efficient and can assist drones and robotics systems to learn how to navigate and avoid obstacles in environments.