Drones, say goodbye to pilots. With the goal of achieving autonomous flight of these aerial vehicles, researchers developed a vision and learning system to control and navigate them without relying on a GPS signal or trained personnel. The method estimates the position and orientation of the vehicle, allowing it to recognize its environment, replacing the GPS location system with low-cost sensors such as accelerometers, gyroscopes, and camcorders.
The system uses video cameras on the vehicle for visual information, and applies an algorithm to locate and orient the drone during its flight to use such information. To do this, a function that allows it to draw a specific route on a map using aerial view was also adapted, similar to Google Maps.
In the future, the researchers want to make the drone capable of being operated from wearable devices, and used in various civil applications such as surveillance.