WHY THIS MATTERS IN BRIEF
This technological leap shows just how far drone and autonomous navigation and manoeuvrability tech has come in just a few years.
Love the Exponential Future? Join our XPotential Community, future proof yourself with courses from XPotential University, connect, watch a keynote, read our codexes, or browse my blog.
A new Artificial Intelligence (AI) based navigation system has been unveiled that enables swarms of lightweight drones to fly together without crashing into one another or obstacles – even in challenging places such as forests. And, as you can see from the video it’s a spectacle to behold. It’s also slightly scary given the fact that China is also trying to develop drone swarms capable of travelling at hypersonic speed that can evade the latest and most sophisticated drone defence systems … but that’s all another story.
While most drones can compute their location and find a path to follow using a multitude of sensors, which can be expensive and unwieldy, shrinking down a drone often involves getting rid of key components which then impact its ability to travel safely, so Xin Zhou at Zhejiang University in China and his colleagues have developed a completely new method that lets them reduce the drones size and hardware requirements while keeping its computing nous intact.
Watch the drones in action
In the experiment the palm sized 300 gram drones use off the shelf computer components powered by a 100 gram battery that can keep them aloft for up to 11 minutes, and they have a camera that feeds real time footage to their on board processing units.
A localisation algorithm then creates a 3D image of the scene and regularly sets the drone targets to reach within that scene. It looks out for obstacles, and other drones, then readjusts the flight pattern in real time accordingly. Then it plans the most computationally efficient route through the area.
This algorithm accounts for the largest share of the drone’s processing power, but it doesn’t require the specialist processors that other drone navigation systems do, and that’s a breakthrough in itself. Perhaps most importantly though the algorithm doesn’t require GPS signals to locate itself, meaning it can be used in a broader range of places where such signals are low or even non-existent.
“To achieve a quality map, built from a distributed collection of robots, of the detail demonstrated is an excellent piece of engineering,” says Jonathan Aitken at the University of Sheffield, UK. “To couple this with the additional successful navigation and avoidance of obstacles, and critically other members of the swarm, is an excellent achievement.”
Journal reference: Science Robotics, DOI: 10.1126/scirobotics.abm5954
