Low Level Navigation Made Easy for Drones

A drone has always had to fly high over building tops because it didn’t have the ability to navigate through busy streets which would have cars, trucks and bicycles floating through them. Now the researchers at the University of Zurich have come up with an algorithm which will allow drones to fly through streets and handle traffic.

Davide Scaramuzza, Professor for Robotics and Perception at the University of Zurich, was involved in the creation of DroNet. The creation of this algorithm was a joint venture for the University of Zurich with the National Centre of Competence in Research NCCR Robotics. Scaramuzza says that DroNet recognizes static and dynamic obstacles and can slow down to avoid crashing into them. With this algorithm we have taken a step forward towards integrating autonomously navigating drones into our everyday life.

The drone uses a regular camera like that of a smartphone, instead of the standard practice of outfitting drones with super specialized sensors. The feed from the camera is run through the software and allows the drone to navigate without the peril of crashing into buildings, vehicles and pedestrians. This is a science project that will ensure that drones can handle low level navigation within city streets with ease.