This post is also available in: heעברית (Hebrew)

Autonomous drones can hardly find their way through an unknown environment without a map. Expert human pilots are needed to release the full potential of drones.

In a new study, researchers at the Robotics and Perception Group at the University of Zurich have trained an autonomous quadrotor to fly through previously unseen environments such as forests, buildings, ruins, and trains, keeping speeds of up to 40 km/h and without crashing into trees, walls or other obstacles. All this was achieved relying only on the quadrotor’s onboard cameras and computation.

The drone’s neural network learned to fly by watching a sort of “simulated expert” – an algorithm that flew a computer-generated drone through a simulated environment full of complex obstacles. At all times, the algorithm had complete information on the state of the quadrotor and readings from its sensors, and could rely on enough time and computational power to always find the best trajectory.

The data from the “simulated expert” were used to teach the neural network how to predict the best trajectory based only on the data from the sensors. This is a considerable advantage over existing systems, which first use sensor data to create a map of the environment and then plan trajectories within the map – two steps that require time and make it impossible to fly at high-speeds, according to eurekalert.org. 

After being trained in simulation, the system was tested in the real world, where it was able to fly in a variety of environments without collisions at speeds of up to 40 km/h. 

The technology could be applied for improving the performance of autonomous cars, or could even open the door to a new way of training AI systems for operations in domains where collecting data is difficult or impossible, for example on other planets.