A new orientation system for drones that emulates the human visual system and sense of balance has been unveiled today.
The technology, developed by researchers at the University of Zurich, should make it possible to launch drones by simply tossing them into the air or recover stable flight after a system failure, as well as allowing them to identify safe landing sites and land automatically in an emergency.
The group’s drones are equipped with a single camera and acceleration sensors and as soon as stable flight is lost computer-vision software analyses images from the camera to identify distinctive landmarks in the environment and restore balance.
“Our system works similarly to a tight-rope walker. When you balance on a rope, you fixate on some static points in the environment and shift your weight accordingly to restore balance,” said Matthias Faessler, co-inventor of the technology.
The same software is able to build a 3D model of the drone’s environment, which is used to group terrain into ‘risky’ and ‘safe’ landing sites so that if an emergency landing is required the drone will automatically aim for a flat, safe landing spot without any human intervention.
This ability addresses growing safety concerns due to the fact that drones can run out of power, forcing them to land immediately. Drones can also lose their positional information if they lose GPS signal, which can happen when they fly close to buildings that block their feed from the satellite.
The solution devised by the group at UZH runs on a smartphone processor on-board the drone, creating an essential back-up system that can operate independently of any communication or interaction with the operator.
“Our new technology allows safe operation of drones beyond the operator’s line of sight, which is crucial for commercial use of drones, such as parcel delivery,” said professor Davide Scaramuzza, co-inventor and Director of the Robotics and Perception Group at the university.