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.
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 situations, 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 to 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 researchers 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 disaster 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.
The Latest on: Automated drones
Italy power plant deploys automated drone full-time
on May 23, 2018 at 8:08 am
In Italy, a multinational power company had deployed a drone full-time. Enel, an integrated power company in the global, power, gas and renewables markets has acquired a multirotor unmanned aircraft system to support operations and maintenance activities ... […]
Airobotics Drones Survey $1 Billion Israeli Port Project
on May 23, 2018 at 7:49 am
Airobotics’ automated, autonomous drones streamline workflows, eliminate logistical overhead, increase response times and data acquisition pace. “Airobotics’ full automation overcomes limitations posed by manually operated drones, by having the ... […]
Drones: The view from above
on May 23, 2018 at 6:41 am
Quite simply, drones have changed the way that construction sites operate ... the Falcon 8 can recognise any potential issues and make automatic adjustments to maintain stability and accuracy. It also offers users a choice of HD imaging, thermal and ... […]
Drone walnut pollination
on May 23, 2018 at 6:09 am
"The automatic pollen distribution kit was designed by Aermatica3D. The drone can cover 10 hectares per hour. CACI from Imola and Vitroplant from Cesena gave their support during the various harvesting, management and pollen certification phases." […]
This Huge Construction Project is Surveyed by Drones – Without Human Pilots
on May 22, 2018 at 7:34 am
... the mapping and surveying of this project will be handled in part by drones without a human pilot. “Airobotics, the Israeli startup that built the world’s first fully automated drone, announced today its partnership with Shapir-Ashtrom to survey ... […]
Drone industry deals with preemption loss
on May 21, 2018 at 7:00 am
The administration’s drone integration pilot program (IPP ... design a driverless car that is as safe as the safest drivers is starting to sink in among automated car development companies, according to Andy Schaudt, director of Virginia Tech’s ... […]
Aero-TV: IXI Dronekiller - For When Good Drones Go Bad
on May 20, 2018 at 9:04 pm
Mobile units with the Drone Hunter provide gap-filling coverage and pursuit capabilities that complement larger, more costly fixed-location automated UAS defense systems. Aero-TV is a production of the Internationally syndicated Aero-News Network. […]
Here’s what’s needed for self-flying taxis and delivery drones to really take off
on May 20, 2018 at 12:51 pm
the FAA does not currently permit drones to be flown over crowds. Once testing is complete, NASA will hand over the UTM to the FAA to implement alongside existing air traffic control for human-piloted aircraft. Automated UAS air traffic control has a long ... […]
Drone pilots' pay plummets 90% in 'race to the bottom'
on May 18, 2018 at 10:35 pm
Technology itself is proving to be one of the biggest competitive threats. As drones become more automated and easier to operate, some would-be customers are instead buying their own aerial robots to fly by themselves. That's driving companies such as ... […]
10 Ways Automated Delivery Will Affect The Communications Industry
on May 18, 2018 at 5:30 am
Nowadays, it has become so easy to get anything and everything delivered right to your door. The rise of drone technology has automated the process and provided instant gratification to the masses. With automated delivery expected to grow by 14.6% in the ... […]
via Google News and Bing News