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
- New Technology Uses Drones to Measure Acreage of Damaged Riceon October 21, 2021 at 5:42 pm
A new technology has been developed that makes it easier to measure the acreage of rice plants that have been damaged due to rain or wind. The Korea Seed and Variety Service on Thursday demonstrated ...
- Alphabet drone delivery arm Wing set to deliver in citieson October 21, 2021 at 9:18 am
Wing, the drone delivery subsidiary of Alphabet, just announced a partnership with Walgreens to deliver in densely populated areas.
- DHL Express Malaysia and Pen Aviation sign MOU for cargo drone deliveryon October 21, 2021 at 5:29 am
DHL Express Malaysia & Pen Aviation seal a strategic partnership to participate in aproof of commercialisation (POC) for time-critical deliveries with unmanned aerialvehicles DHL Express, the world’s ...
- Walgreens testing drone deliveries in Texason October 20, 2021 at 9:14 am
Walgreens is testing drone deliveries in Texas in partnership with Wing, a Google affiliate company. The companies announced Wednesday the drone deliveries would start next week in the city of Frisco ...
- Walgreens will deploy Wing drone deliveries in the Dallas-Fort Worth areaon October 20, 2021 at 7:00 am
Alphabet today announced that Walgreens is partnering with Wing to bring drone-based deliveries to a portion of Texas’s Dallas-Forth Worth region. The drugstore giant will be the first to take ...
- Alphabet's Wing to start drone deliveries on outskirts of Texas metro areaon October 20, 2021 at 7:00 am
Wing, the drone delivery division of Google parent company Alphabet, said Wednesday that it's expanded its operations to parts of It's a significant expansion into a more complex urban area, though ...
- Drones for Organ Transport: Revolutionizing the Field of Transplantson October 19, 2021 at 10:08 am
The use of drones for organ transport could revolutionize the field and save lives. Bromont Unither transports lungs in Toronto, Canada, to demonstrate how it works. by DRONELIFE Staff Writer Ian M.
- Proven Drone-Based Automatic Dent Inspection Maps an Entire Rafale Fighter Jet in Just One Houron October 15, 2021 at 3:00 pm
In early 2020, the French Defense Innovation Agency launched a program in partnership with 8tree, Donecle and Dassault to explore automated drone-based dent-inspection of the Rafale military aircraft.
- QuadAir Drone Reviews – Read before buying a Quad air drone?on October 15, 2021 at 7:46 am
Drones are becoming an integral part of society. They can reach remote and rural communities. It is hard to stress enough the relaxing feeling that comes from watching them fly. Consumers can’t forget ...
via Bing News