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
- NASA Tests Urban Drone Traffic Management in Nevada, Texas on February 20, 2019 at 9:02 pm
The drone flights will take place in and around ... vehicle-to-vehicle communication and collision avoidance, and automated safe landing technologies. “We are very excited to partner with ... […]
- NEC Supports the Safety of Automated Driving with Demonstration of Adaptive Network Control Technology on February 20, 2019 at 6:28 pm
automated guided vehicles in factories and warehouses, security robots, and drones for inspection and delivery. In automated driving, where safety is of the utmost importance, a vehicle needs to be co... […]
- NASA's drone traffic control system moves into the final phase of testing on February 20, 2019 at 5:05 pm
drone-to-drone communication and automated landing will be put through their paces. The results of the trials will then be used to develop rules and procedures for drone traffic in busy areas. […]
- NASA Testing Drone Traffic Management Tool in Las Vegas, Texas on February 20, 2019 at 2:02 pm
Nevada to showcase the UAS Traffic Management platform's drone traffic management functions in urban areas. In addition, NASA will demonstrate a vehicle-to-vehicle communication and collision avoidanc... […]
- NASA to test urban drone traffic management in Texas and Nevada on February 20, 2019 at 4:03 am
Drones are piloted by a range of users, including amateur enthusiasts, pizza delivery companies and the military. Technologies set to be demonstrated include automated safe landing and vehicle-to-vehi... […]
- NASA is close to finalizing its drone traffic control system for cities on February 20, 2019 at 3:32 am
NASA is ready to put its drone traffic management system to the ultimate test ... vehicle-to-vehicle communication and collision avoidance, as well as automated safe landing technologies. All those wi... […]
- Atlanta-based drone solution company raises $7M on February 19, 2019 at 12:18 pm
Atlanta-based Pointivo, a software company that utilizes AI and computer vision to provide automated analytics for drone and other aerial platforms, has raised $7 million in a Series A round led by lo... […]
- Automated Weapon System Market: Industry Size, Growth, Analysis and Forecast of 2025 on February 18, 2019 at 9:44 pm
Automated weapon systems are specifically designed to engage with military targets without any human intervention. There has been a growing demand for drones over the years due to the modernization of ... […]
- Trump administration releases proposed drone rules and regulatory changes on February 18, 2019 at 2:04 pm
the FAA asked in its proposal, which also seeks comments on whether drones should be required to fly as part of an “unmanned traffic management system,” a type of automated version of air traffic cont... […]
via Bing News