Forum for Science, Industry and Business

Sponsored by:     3M 
Search our Site:

 

Drones learn to navigate autonomously by imitating cars and bicycles

23.01.2018

Developed by UZH researchers, the algorithm DroNet allows drones to fly completely by themselves through the streets of a city and in indoor environments. Therefore, the algorithm had to learn traffic rules and adapt training examples from cyclists and car drivers.

All today’s commercial drones use GPS, which works fine above building roofs and in high altitudes. But what, when the drones have to navigate autonomously at low altitude among tall buildings or in the dense, unstructured city streets with cars, cyclists or pedestrians suddenly crossing their way? Until now, commercial drones are not able to quickly react to such unforeseen events.


By imitating cars and bycicles, the drone automatically learned to respect the safety rules.

UZH


http://rpg.ifi.uzh.ch/dronet.html

UZH

Integrate autonomously navigating drones

Researchers of the University of Zurich and the National Centre of Competence in Research NCCR Robotics developed DroNet, an algorithm that can safely drive a drone through the streets of a city. Designed as a fast 8-layers residual network, 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 recognise dangerous situations and promptly react to them.

“DroNet recognises 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”, says Davide Scaramuzza, Professor for Robotics and Perception at the University of Zurich.

Powerful artificial intelligence algorithm

Instead of relying on sophisticated sensors, the drone developed by Swiss researchers uses a normal camera like that of every smartphone, and a very powerful artificial intelligence algorithm to interpret the scene it observes and react accordingly. The algorithm consists of a so-called Deep Neural Network. “This is a computer algorithm that learns to solve complex tasks from a set of ‘training examples’ that show the drone how to do certain things and cope with some difficult situ-ations, much like children learn from their parents or teachers”, says Prof. Scaramuzza.

Cars and bicycles are the drones’ teachers

One of the most difficult challenges in Deep Learning is to collect several thousand ‘training examples’. To gain enough data to train their algorithms, Prof. Scaramuzza and his team collected data from cars and bicycles, that were driving in urban environments. By imitating them, the drone automatically learned to respect the safety rules, such as “How follow the street without crossing into the oncoming lane”, and “How to stop when obstacles like pedestrians, construction works, or other vehicles, block their ways”.

Even more interestingly, the research-ers showed that their drones learned to not only navigate through city streets, but also in completely different environments, where they were never taught to do so. Indeed, the drones learned to fly autonomously in indoor environments, such as parking lots and office’s corridors.

Toward fully autonomous drones

This research opens potential for monitoring and surveillance or parcel delivery in cluttered city streets as well as rescue operations in disastered urban areas. Nevertheless, the research team warns from exaggerated expectations of what lightweight, cheap drones can do. “Many technological issues must still be overcome before the most ambitious applications can become reality,” says PhD Student Antonio Loquercio.

Literature:
Antonio Loquercio, Ana Isabel Maqueda, Carlos Roberto del Blanco, and Davide Scaramuz-za. DroNet: Learning to Fly by Driving. IEEE Robotics and Automation Letters, 22. January 22, 2018. DOI: 10.1109/LRA.2018.2795643

Paper, video, and research page: http://rpg.ifi.uzh.ch/dronet.html

Contact:
Prof. Dr. Davide Scaramuzza
University of Zurich
Director of the Robotics and Perception Group
Tel: +41 44 635 24 07
E-Mail: press.scaramuzza@ifi.uzh.ch

Weitere Informationen:

http://www.media.uzh.ch/en/Press-Releases/2018/DroNet_drone.html

Melanie Nyfeler | Universität Zürich

Further reports about: Robotics algorithm artificial bicycles drone high altitudes pedestrians urban environments

More articles from Information Technology:

nachricht Putting food-safety detection in the hands of consumers
15.11.2018 | Massachusetts Institute of Technology

nachricht Next stop Morocco: EU partners test innovative space robotics technologies in the Sahara desert
09.11.2018 | Deutsches Forschungszentrum für Künstliche Intelligenz GmbH, DFKI

All articles from Information Technology >>>

The most recent press releases about innovation >>>

Die letzten 5 Focus-News des innovations-reports im Überblick:

Im Focus: A Chip with Blood Vessels

Biochips have been developed at TU Wien (Vienna), on which tissue can be produced and examined. This allows supplying the tissue with different substances in a very controlled way.

Cultivating human cells in the Petri dish is not a big challenge today. Producing artificial tissue, however, permeated by fine blood vessels, is a much more...

Im Focus: A Leap Into Quantum Technology

Faster and secure data communication: This is the goal of a new joint project involving physicists from the University of Würzburg. The German Federal Ministry of Education and Research funds the project with 14.8 million euro.

In our digital world data security and secure communication are becoming more and more important. Quantum communication is a promising approach to achieve...

Im Focus: Research icebreaker Polarstern begins the Antarctic season

What does it look like below the ice shelf of the calved massive iceberg A68?

On Saturday, 10 November 2018, the research icebreaker Polarstern will leave its homeport of Bremerhaven, bound for Cape Town, South Africa.

Im Focus: Penn engineers develop ultrathin, ultralight 'nanocardboard'

When choosing materials to make something, trade-offs need to be made between a host of properties, such as thickness, stiffness and weight. Depending on the application in question, finding just the right balance is the difference between success and failure

Now, a team of Penn Engineers has demonstrated a new material they call "nanocardboard," an ultrathin equivalent of corrugated paper cardboard. A square...

Im Focus: Coping with errors in the quantum age

Physicists at ETH Zurich demonstrate how errors that occur during the manipulation of quantum system can be monitored and corrected on the fly

The field of quantum computation has seen tremendous progress in recent years. Bit by bit, quantum devices start to challenge conventional computers, at least...

All Focus news of the innovation-report >>>

Anzeige

Anzeige

VideoLinks
Industry & Economy
Event News

“3rd Conference on Laser Polishing – LaP 2018” Attracts International Experts and Users

09.11.2018 | Event News

On the brain’s ability to find the right direction

06.11.2018 | Event News

European Space Talks: Weltraumschrott – eine Gefahr für die Gesellschaft?

23.10.2018 | Event News

 
Latest News

Massive impact crater from a kilometer-wide iron meteorite discovered in Greenland

15.11.2018 | Earth Sciences

When electric fields make spins swirl

15.11.2018 | Physics and Astronomy

Discovery of a cool super-Earth

15.11.2018 | Physics and Astronomy

VideoLinks
Science & Research
Overview of more VideoLinks >>>