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 Virtual reality can assist with the evaluation of future transport concepts
13.07.2020 | Fraunhofer-Institut für Arbeitswirtschaft und Organisation IAO

nachricht New method for simulating yarn-cloth patterns to be unveiled at ACM SIGGRAPH
09.07.2020 | Association for Computing Machinery

All articles from Information Technology >>>

The most recent press releases about innovation >>>

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

Im Focus: Electron cryo-microscopy: Using inexpensive technology to produce high-resolution images

Biochemists at Martin Luther University Halle-Wittenberg (MLU) have used a standard electron cryo-microscope to achieve surprisingly good images that are on par with those taken by far more sophisticated equipment. They have succeeded in determining the structure of ferritin almost at the atomic level. Their results were published in the journal "PLOS ONE".

Electron cryo-microscopy has become increasingly important in recent years, especially in shedding light on protein structures. The developers of the new...

Im Focus: The spin state story: Observation of the quantum spin liquid state in novel material

New insight into the spin behavior in an exotic state of matter puts us closer to next-generation spintronic devices

Aside from the deep understanding of the natural world that quantum physics theory offers, scientists worldwide are working tirelessly to bring forth a...

Im Focus: Excitation of robust materials

Kiel physics team observed extremely fast electronic changes in real time in a special material class

In physics, they are currently the subject of intensive research; in electronics, they could enable completely new functions. So-called topological materials...

Im Focus: Electrons in the fast lane

Solar cells based on perovskite compounds could soon make electricity generation from sunlight even more efficient and cheaper. The laboratory efficiency of these perovskite solar cells already exceeds that of the well-known silicon solar cells. An international team led by Stefan Weber from the Max Planck Institute for Polymer Research (MPI-P) in Mainz has found microscopic structures in perovskite crystals that can guide the charge transport in the solar cell. Clever alignment of these "electron highways" could make perovskite solar cells even more powerful.

Solar cells convert sunlight into electricity. During this process, the electrons of the material inside the cell absorb the energy of the light....

Im Focus: The lightest electromagnetic shielding material in the world

Empa researchers have succeeded in applying aerogels to microelectronics: Aerogels based on cellulose nanofibers can effectively shield electromagnetic radiation over a wide frequency range – and they are unrivalled in terms of weight.

Electric motors and electronic devices generate electromagnetic fields that sometimes have to be shielded in order not to affect neighboring electronic...

All Focus news of the innovation-report >>>

Anzeige

Anzeige

VideoLinks
Industry & Economy
Event News

Contact Tracing Apps against COVID-19: German National Academy Leopoldina hosts international virtual panel discussion

07.07.2020 | Event News

International conference QuApps shows status quo of quantum technology

02.07.2020 | Event News

Dresden Nexus Conference 2020: Same Time, Virtual Format, Registration Opened

19.05.2020 | Event News

 
Latest News

Black phosphorus-based van der Waals heterostructures for mid-infrared light-emission applications

13.07.2020 | Physics and Astronomy

Polarization of Br2 molecule in vanadium oxide cluster cavity and new alkane bromination

13.07.2020 | Life Sciences

Researchers present concept for a new technique to study superheavy elements

13.07.2020 | Life Sciences

VideoLinks
Science & Research
Overview of more VideoLinks >>>