Drones Learn Autonomous Flying by Imitating Cars and Bikes
The algorithm DroNet allows drones to fly completely by themselves through the streets of a city and in indoor environments. It produces two outputs for each single input image: a steering angle to keep the drone navigating while avoiding obstacles, and a collision probability to let the drone recognize dangerous situations and promptly react to them.
The algorithm learns to solve complex tasks from a set of ‘training examples’ that shows the drone how to do certain things and cope with difficult situations, much like children learn from their parents or teachers. In this case, cars and bikes are the drones’ teachers.