It does not need a pilot, a pre-programmed route or a GPS signal – you just need to tell it what to do. The innovative flying robot from the Czech team of the Czech Technical University FEL and the company Fly4Future scored points in the prestigious European Fully Autonomous Flight 2.0 competition. It performed best in a simulated rescue operation, where it independently searched for an injured person and delivered help to him.
The Czech team succeeded in the finals of the competition in Germany with a drone that can accept instructions in human language and complete the task without GPS and manual control. It was developed by a team of the company Fly4Future and the Faculty of Electrical Engineering of the Czech Technical University in Prague (FEL CVUT). The fourteen-month Fully Autonomous Flight 2.0 competition organized by the German Federal Agency for Breakthrough Innovation SPRIND had a budget of over five million euros (121 million CZK). Each of the final teams received a grant of 500,000 euros (12 million CZK) for the development of the system, the faculty said in a press release today.
The competition tasks simulated real-life use, for example, in a delivery service, during a rescue operation or in a security control room. The F4F & CTU SkyGraph team won the task of finding and helping an injured person. The basic condition was that the drone was not allowed to use GPS and had to handle the mission completely autonomously after takeoff.
The organizers named the Austrian HERMES from the University of Klagenfurt as the overall winner. The German team UBASWARM, which connects the Technical University of Berlin and the Berlin technology startup Autonx, as well as the Swiss team Avientus RadNav, also advanced to the final demonstration of the system for invited investors and representatives of European security and defense forces. In this final demonstration of the competition tasks, the Czech team succeeded best of all the finalists, the faculty said.
"Today, the deployment of similar robotic systems often requires a team of specialists who prepare the mission and precisely program its course. Our goal is for the user to simply describe the desired result and the system to prepare a way to achieve it itself. This significantly reduces costs and operator demands and paves the way for the practical use of flying robots in industry, logistics, security or rescue operations," said the head of the Czech team, Martin Saska.
One of the final tasks was to leave a parcel by a blue bicycle in front of a house. The Czech team's drone mistook blue for green in variable lighting conditions. The team needs to refine its visual distinction between similar colors.
In the next task, the drone was supposed to find an injured person in a red T-shirt and deliver a medical package to him. The extra, who was lying partially hidden behind a building and leaning against a tree, was discovered by the system on its own. However, it did not find enough space immediately next to him for a safe landing, and therefore refused the maneuver. On another attempt, it landed on a nearby roof. The test showed that the robot also needs to know the broader meaning of the mission, but the Czech team presented the best solution in the task.
"I was pleased that we won this task, because many Fly4Future clients are asking for a similar system, and we also recently won a large national project focused on solving the problem of fires in buildings, where finding and rescuing people is always a priority," added the team's technical leader Tomáš Báča. Fly4Future is gradually integrating the technology into its robotic platforms and preparing them for commercial use.