Teaching drones to navigate city streets
Researchers from the University of Zurich and the National Centre of Competence in Research (NCCR) Robotics are working on a system called “DroNet” – which they describe as a convolutional neural network that can safely drive a drone through the streets of a city.
According to a research paper published on the University of Zurich’s website yesterday (23 January), the system would “train” drones to navigate city streets using data collected by cars and bicycles – and thereby “imitating” their “expert behavior”.
The research paper comes from the University’s Robotics and Perception Group, which is led by Prof. Davide Scaramuzza. The lab was founded in February 2012 and is part of the Department of Informatics at the University of Zurich, and the Institute of Neuroinformatics, a joint institute affiliated with both the University of Zurich and ETH Zurich.
Click here to see a YouTube video about the DroNet concept.
