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
- VW's China unit to test passenger drone prototypeon August 1, 2022 at 1:30 pm
Test flights of the prototype will begin later this year and an improved version will undergo advanced test flights starting in the summer of 2023, VW said. The final version of the drone is expected ...
- PPL to use drones to inspect power lineson July 30, 2022 at 5:46 am
PPL Electric Utilities will be using drones to inspect power lines across the region. “Essentially, we are looking for hot spots that can signal future problems,” said PPL spokeswoman Jane George.
- How Do You Keep Thousands Of Solar Panels Clean? Use A Droneon July 29, 2022 at 7:11 am
But Israeli startup Solar Drone is tackling the problem from the air, with drones. They’re programmed to fly over solar farms, hosing down each panel with a high-pressure jet of cleaning fluid, then ...
- Make way for the drone superhighway, says UKon July 29, 2022 at 1:22 am
News that the UK is building the world’s biggest automated drone superhighway has grabbed my attention this week, at a time when tech scribes’ job is often to sift out the ‘world leading’ rhetoric to ...
- Beam Global Receives $900k Battery Order to Power Autonomous Delivery Droneson July 28, 2022 at 5:00 am
Beam Global, (Nasdaq: BEEM, BEEMW), the leading provider of innovative sustainable products and technologies for electric vehicle (EV) charging, energy storage, energy security and outdoor media, ...
- Percepto partners with Hellenic Drones to conquer Greek and Cypriot drone marketson July 26, 2022 at 6:35 am
Percepto, pioneering autonomous inspection by industrial robotics, today announced it has signed a new partnership with value-added seller Hellenic Drones to distribute its drone-in-a-box technology ...
- How drone autonomy unlocks a new era of AI opportunitieson July 23, 2022 at 8:10 pm
Autonomous drone technology lets us digitize and analyze the physical world, observing and improving our world’s critical infrastructure.
- Faster, cheaper, greener: Are drone deliveries the future of logistics?on July 23, 2022 at 12:00 am
Drones have the potential to reshape last-mile delivery, reducing the environmental impact of shipping and reaching more remote areas. View on euronews ...
- Drone News of the Week July 22: DRONELIFE Headlines, All in One Place to Read or Listenon July 22, 2022 at 3:00 am
Read or listen to all of the headlines in one place: excerpts from the DRONELIFE drone news of the week, July 22. Click on the titles below for the full story. Continue reading below, or listen: Dron ...
via Bing News