The first of the projects presented by Prof. Martin Saska, head of MRS, and his colleagues is the development of a secure drone for monitoring and protecting critical infrastructure—such as nuclear power plants, military facilities, and key industrial sites.
"The goal is to develop an advanced flying robot with onboard artificial intelligence, whose components and software come from domestic or European companies and research institutions. It is therefore completely independent of non-European components that may pose a potential threat of industrial and security espionage," explained Prof. Saska, adding that the research on secure robotic systems is based on Czech know-how. More than a hundred researchers from the MRS group and the CTU spin-off Fly4Future are involved in the project.
"The biggest challenge is ensuring the absolute security of the robotic platform. Any component in a drone that collects data from critical infrastructure can be a potential threat and could be exploited for espionage. There have been cases where seemingly harmless chips in drones connected to networks and transmitted collected data even weeks after deployment. For example, in the United States, drones compliant with the NDAA are not allowed to contain even a single component originating from countries with interests in espionage. Similarly, we are developing a unique solution that will be fully under our control at the European level,” Prof. Saska explained.
A secure and unique solution in practice
The project is now in its second year, and the team has already achieved a number of interesting results. “In cooperation with Fly4Future, we have managed to develop a reliable platform that is resistant to weather conditions and is also modular and open. This means it can be equipped with various sensors. The client can choose what type of sensor, computer, or camera they need, and we are able to integrate everything very quickly,” said the researcher.
And that’s not all. The team has already integrated a secure flight controller, a computer, and a communication module—mesh communication—into the platform. “This is critical in these applications, and virtually no other solution on the market offers it to this extent. Moreover, our product has been designed from the beginning as a multi-robot system. Cooperation between teams of flying robots is key for complex missions in large areas where tasks need to be performed quickly, and competing solutions practically do not support this,” emphasized Prof. Saska.
The team also regularly tests the drones in the field—over open-pit mines in northern Czechia. “The advantage of testing in these areas is that they offer a truly large scale. This is where the benefits of multi-robot systems become apparent. The mines span dozens of kilometers and present a diverse environment. There are tunnels, pits, dust, and often poor GPS signals, as drones fly close to rock formations. So it is an interesting and highly demanding environment for us to operate in,” added Prof. Martin Saska.
Drone swarms as the perfect solution for challenging terrain
The second research project presented, which focuses on developing drones capable of flying in dynamic swarms and responding quickly and flexibly to changes, began this January. Its goals also overlap with monitoring critical infrastructure, exploring complex terrains, and deployment in crisis situations.
Fast swarm flight is important in applications where drones must fly close to each other and continuously react to one another. In addition to many civil applications and fundamental research inspired by nature, the FEE CTU team is also integrating requirements related to national security and defense into swarm research within TAČR PRODEF projects, including resilience to GPS outages and communication failures.
To achieve this globally unique goal, the team draws inspiration from nature. “Specifically, we are now focusing on studying birds. We collaborated with Dr. Martin Šálek from the Institute of Vertebrate Biology of the Czech Academy of Sciences, who helped us capture unique, highly dynamic data on the movement of flocking birds. We then analyzed this data in cooperation with the team of Prof. Iain Couzin, who leads one of Europe’s largest centers for the study of collective behavior in nature at the University of Konstanz. Together, we are trying to understand how high dynamics in flocks actually work—how birds can maneuver at high speeds, avoid obstacles, and never collide. What information they use. We directly translate these findings into artificial intelligence that controls robotic swarms. Our goal is for drones to fly in groups as reliably, quickly, and dynamically as birds,” explained Prof. Saska.
How is the transfer of data from bird behavior analysis into machines carried out? “We try to determine how birds perceive nearby individuals in a flock and how they use this information for coordinated maneuvers. The acquired data is used to train neural networks and other components of onboard intelligence used to control flying robots. In addition, we are developing sensors as fast as those of birds, capable of reacting to rapid events in their surroundings. This technology of very fast cameras is also directly inspired by nature,” the scientist explained.
First major success
Despite the fact that the project has been running for only a quarter of a year, the team has already achieved its first significant research success, according to Prof. Saska.
“We hypothesized that birds in flocks use more than just the relative positions of their neighbors. In collective robotics, only position has typically been used. Through our study of birds, we have now discovered that they try to predict the future movement of other individuals in the flock. This allows them to fly close together and move very dynamically,” emphasized Prof. Saska.
“We have already conducted an experiment in which a drone also tries to estimate what its neighbor will do and reacts accordingly, enabling faster actions. As a result, they are capable of dynamic and highly precise formation flight. The improvement in maneuverability reached up to 60 percent, which is an incredible advancement—achieved in just one month. I believe that thanks to this close collaboration between biologists, roboticists, and drone experts, we can soon achieve truly groundbreaking results in the field of dynamic swarms and also contribute to understanding processes in natural flocks,” concluded Prof. Saska.
