I. Introduction
The use of drones has become commonplace in both industry and academia. Using drones in all kinds of missions like deliverers, photographing in all kinds of events especially that the drone has the ability to reach places that for humans would be a great danger to reach and for ground robots it is an impossible task. With all the progress in the field of drones, we still do not see drones that navigate in closed places close to people, for example a drone inside a mall that takes customers to McDonald’s or shows a discount on products inside a supermarket. This task is considered a difficult task because the following challenges need to be overcome:
Lack of GPS information: unlike outdoor, we cannot use GPS data in indoor localization, both because the reception is weak and because of its limited accuracy.
Limited battery lifetime: typical drones are powered by on-board batteries. Hence, the performance of drones is critically constrained by limited battery lifetime. Talking of low-cost drones, many drones are only suitable for short-time controlling, which considerably limit their applicability.
Weight and lack of sensors: safe toy-drones cannot carry heavy sensors such as Ultrasonic or 3D cameras, or range finders, except tiny analog single RGB camera. This is not only a technological problem: a low-weight drone cannot carry heavy sensors.