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
via Google News
The Latest on: Automated drones
- Sask. Highway Patrol chief was fired for purchase of silencers, drones, high-power rifle scopeon June 25, 2020 at 4:57 pm
Saskatchewan's Minister of Highways said the chief of the province's highway patrol was fired for purchasing silencers, a drone and a high-power rifle scope.
- Industrial property of the future will have ‘McDonald’s-style’ drive-through and drone deliveries: reporton June 24, 2020 at 11:30 pm
Warehouses are set to undergo a radical shift from being the boring beige boxes in far-flung suburbs to smaller-scale, customer-friendly buildings, potentially incorporating a drive-through layout ...
- Military Drones Market 2020 – 2030: Northrop Grumman, Lockheed Martin, Boeing, AeroVironmenton June 24, 2020 at 6:55 am
The Global Military Drones Market Research Report Forecast 2020 – 2030 is a valuable source of insightful data ...
- Samsung’s new drone-based solution measures configurations in 5G and 4G networkson June 23, 2020 at 5:47 pm
Samsung Electronics announced a successful demonstration of its new drone-based antenna configuration measurement solution for 4G and 5G networks in the company’s campus. This automated solution will ...
- Automated laser-scanning 'hunter drone' seeks out fossils, minerals and biological targetson June 23, 2020 at 11:06 am
Science fiction came up with machine-intelligent hunter drones and they have now become science fact with a new HKU-codeveloped autonomous 'hunter drone' that seeks out targets at night using a ...
- Samsung boasts of measuring 5G with droneson June 22, 2020 at 7:44 am
Samsung Electronics Co., Ltd. today announced a successful demonstration of its new drone-based antenna configuration measurement solution for 4G and 5G networks in the company's campus. This ...
- Samsung Demonstrates New Drone-Based AI Solution to Optimize 5G Network Performanceon June 22, 2020 at 6:00 am
today announced a successful demonstration of its new drone-based antenna configuration measurement solution fo ...
- Samsung trials drone-based 5G network inspection serviceon June 22, 2020 at 6:00 am
Samsung will later update the solution to allow field engineers to adjust the antennas of base stations from their smartphones on the ground.
- Pak drone loaded with automatic rifle, grenades shot down by BSF along IB in Jammuon June 20, 2020 at 7:32 am
A Pakistani drone, loaded with a sophisticated rifle and seven grenades, was shot down by the Border Security Force along the International Border in Kathua district of Jammu and Kashmir on Saturday, ...
via Bing News