Sunday, December 3, 2023

Watch a swarm of drones autonomously track a human through a dense forest

Must read

Scientists at Zhejiang University of China have revealed a drone swarm capable of navigating through dense bamboo forest without human guidance.

The group of 10 palm-sized drones communicate with each other to stay in formation, sharing data collected by onboard deep-sensing cameras to map their surroundings. This method means that if the road in front of one drone is blocked, it can use information gathered by its neighbors to hit a new route. The researchers note that this technique can also be used by the swarm to track a person walking through the same environment. If one drone loses sight of the target, others may take the trail.

In the future, write the scientists in an article published in the magazine Scientific Robotics, drone swarms like this could be used for disaster relief and environmental surveys.

“In natural disasters such as earthquakes and floods, a swarm of drones can search for, guide and deliver emergency supplies to trapped people,” they write. “For example, in wildfires, clever multi-cops can quickly gather information from a close-up view of the front without the risk of human injury.”

However, experts say the work also has clear military potential. A number of nations – most notably the United States, China, Russia, Israel, and the United Kingdom – are currently developing drones that could be used in warfare. Military personnel tend to call surveillance and reconnaissance as the most common applications for this work, but the same technology could undoubtedly be used to track and attack both fighters and civilians.

An illustration of the paper showing how several drones can be used to track a target even if the view of one drone is blocked.
Image: Scientific Robotics / Xin Zhou et al

Elke Schwarz, a senior lecturer at Queen Mary University of London, whose specialties include the use of drones in combat, says this research has clear military potential.

“The ability to navigate disorderly environments, for example, is desirable for a range of military purposes, including urban warfare,” Schwarz recounts. The Edge. “How is the ability to ‘follow a man’ – here I can see how this converges with projects that aim to develop lethal drone capabilities that minimize risk to ground soldiers in urban environments.”

The recent war between Russia and Ukraine has shown how fast drone technology can be adapted for the battlefield and what a devastating effect it can have. Both sides in the conflict use cheap consumer drones for notification and, sometimes, offense. One method involves using drones to drop shells on opposing forces. Recent video showed Ukrainian troops using what appears to be a DJI Phantom 3 drone (price tag: $ 500) to drop a grenade through the sunroof of a car allegedly driven by Russian soldiers.

What makes drone swarms perhaps more dangerous than single machines, however, is not only their numbers but their autonomy. No single person can simultaneously control a swarm of 10 drones, but if this task can be downloaded to algorithms, then military planners are more likely to accept the use of this kind of autonomous system in war.

Drones in the swarm are capable of navigating through spaces as small as 30 centimeters.
Image: Scientific Robotics / Xin Zhou et al

Currently, drone swarms are limited in their application. The most common real-world use case is the creation of complex light shows. But in these scenarios, drones follow predetermined trajectories in open spaces, using tracking technology such as GPS to locate themselves.

Zhejiang University research is progressing on this using only onboard sensors and algorithms to control the flight of drones without prior mapping of their environment. “This is the first time that a swarm of drones have successfully flown outside in an unstructured environment, in the wild,” said Enrica Soria, a drone researcher at the Swiss Federal Institute of Technology in Lausanne. told AFP. Soria added that the work was “impressive”.

In their article, the scientists note that approaches to drone swarms tend to follow one of two programming paradigms: either “bird” or “insect”. In an “insect” swarm, the focus is on fast, reactive movements that require less planning while a “bird” swarm attempts to direct drones along long, flowing paths (the latter being the researchers’ approach). Both methods have their advantages, as thinking like an insect requires less computing power, but planning like a bird is more energy efficient. But, as the computing capacity of hardware improves, programming of bird-like behavior has become more affordable.

Schwarz notes that while the focus in such drone swarm research is often on these technological achievements, this may obscure the more difficult questions of as such work should be deployed. She cites the observations of 20th-century American mathematician Norbert Wiener, whose work laid the foundations for the development of AI.

Says Schwarz: “[Weiner] said – in the 1960s – that there is a catastrophic focus and obsession with “knowledge” that tends to overshadow the moral question we should be asking: what is it for.


More articles

Latest article