Watch a swarm of DRONES navigate through dense forest with incredible precision

Scientists have taken inspiration from science fiction blockbusters including Blade Runner 2049, to train swarms of drones to navigate through dense forests with expert precision

From Blade Runner 2049 to Star Wars: Episode III, many of the most popular science fiction blockbusters feature swarms of flying cars.

Now, scientists have taken inspiration from these films, to train swarms of drones to navigate through dense forests with expert precision.

The team from Zhejiang University captured incredible footage of 10 bright blue drones swerving through a bamboo forest in China.

Referring to the science fiction blockbusters, the team, led by Xin Zhou, wrote: ‘Here, we take a step forward (to) such a future.’

Scientists have taken inspiration from science fiction blockbusters including Blade Runner 2049, to train swarms of drones to navigate through dense forests with expert precision

Scientists have taken inspiration from science fiction blockbusters including Blade Runner 2049, to train swarms of drones to navigate through dense forests with expert precision

In the 2017 blockbuster, Blade Runner 2049, bustling yet orderly flying cars expertly navigate among skyscrapers

How could the drone swarms be used?

Since these drones do not rely on any outside infrastructure, such as GPS, swarms could be used during natural disasters.

For example, they could be sent into earthquake-hit areas to survey damage and identify where to send help, or into buildings where it’s unsafe to send people.

It’s certainly possible to use single drones in such scenarios, but a swarm approach would be far more efficient, especially given limited flight times.

Another possible use is having the swarm collectively lift and deliver heavy objects.

There’s also a darker side: swarms could be weaponized by militaries, just as remote-piloted single drones are today.

The palm-sized robots were purpose-built, with depth cameras, altitude sensors and an on-board computer.

The biggest advance was a clever algorithm that incorporates collision avoidance, flight efficiency and coordination within the swarm.

The team tested their drones in different scenarios – swarming through the bamboo forest, avoiding other drones in a high-traffic experiment, and having the robots follow a person’s lead.

‘Our work was inspired by birds that fly smoothly in a free swarm through even very dense woods,’ Zhou wrote in a blog post.

The challenge, he said, was balancing competing demands: the need for small, lightweight machines, but with high-computational power, and plotting safe trajectories without greatly prolonging flight time.

Since these drones do not rely on any outside infrastructure, such as GPS, swarms could be used during natural disasters.

For example, they could be sent into earthquake-hit areas to survey damage and identify where to send help, or into buildings where it’s unsafe to send people.

It’s certainly possible to use single drones in such scenarios, but a swarm approach would be far more efficient, especially given limited flight times.

Another possible use is having the swarm collectively lift and deliver heavy objects.

There’s also a darker side: swarms could be weaponized by military forces, just as remote-piloted single drones are today.

The Pentagon has repeatedly expressed interest and is carrying out its own tests.

‘Military research is not shared with the rest of the world just openly, and so it’s difficult to imagine at what stage they are with their development,’ Enrica Soria, a roboticist at the Swiss Federal Institute of Technology Lausanne, who was not involved in the research, told AFP.

But advances shared in scientific journals could certainly be put to military use.

Drone swarms have been tested in the past, but either in open environments without obstacles, or with the location of those obstacles programmed in.

The palm-sized robots were purpose-built, with depth cameras, altitude sensors and an on-board computer.  The biggest advance was a clever algorithm that incorporates collision avoidance, flight efficiency and coordination within the swarm

The palm-sized robots were purpose-built, with depth cameras, altitude sensors and an on-board computer. The biggest advance was a clever algorithm that incorporates collision avoidance, flight efficiency and coordination within the swarm

‘This is the first time there’s a swarm of drones successfully flying outside in an unstructured environment, in the wild,’ Ms Soria said, adding the experiment was ‘impressive.’

For Ms Soria, it could only be a few years before we see such drones deployed in real-life work.

First, though, they will need to be tested in ultra-dynamic environments like cities, where they’ll constantly come up against people and vehicles.

Regulations will also need to catch up, which takes additional time, Ms Soria said.

HOW CLOSE IS A NEAR MISS BETWEEN AIRCRAFT AND DRONES?

Near miss is a common term used to describe encounters between different airborne vehicles.

Governed by Airprox, there is no specific distance stated, instead it is gauged by the opinions of the pilot, air traffic controller and the drone operator.

Earlier this year a ‘near-miss’ report was filed between a police drone and two fighter jets traveling at 520 mph.

Governed by Airprox, there is no specific distance stated, instead it is gauged by the opinions of the pilot, air traffic controller and the drone operator

Governed by Airprox, there is no specific distance stated, instead it is gauged by the opinions of the pilot, air traffic controller and the drone operator

The Devon and Cornwall officer was convinced there would be a collision as the military jet came into view.

The Airprox board reported the 13lbs device was flying at an altitude of around 300ft when the pilot heard a fast jet approaching.

The F-15 pilot, who was flying at an altitude of 500ft, could not see the drone but the drone pilot said the risk of a collision was ‘high’.

.

Leave a Reply

Your email address will not be published.