AI drone beats human champions in racing
Remember the days when computers beat humans at board games?
Like when IBM’s Deep Blue defeated world chess champion Gary Kasparov in 1996?
Or when Google’s 2016 AlphaGo defeated Lee Sedol, a top player in the tricky game of Go?
Well, computers have now evolved from board games to real sports! A team from the University of Zurich and Intel has built a drone that beats human champions in racing!
This super intelligent drone is called Swift. It competed in drone races, competing against three human champions.
Drone racing is a sport in which small, flying robots called drones race at high speeds of over 60 miles per hour. Pilots control these drones remotely using a special headset that allows them to see what the drone sees.
Speed wasn’t the only challenge for Swift. Unlike board games, real-world sports like drone racing are full of surprises.
The drone has to navigate the route, adapting to changes in the environment. Davide Scaramuzza, the team’s leader, said that flying a drone is far more unpredictable than playing board games on a computer.
Before Swift, computer-controlled drones were slower racing planes than human-flown drones. But Swift is different.
It uses a camera to see where it’s going, just like human racers do. It has special sensors that measure how fast it moves and rotates. And then his “brain” (a kind of computer program) decides how the race can be ended as quickly as possible.
How did Swift learn to fly so well? It was practiced in a computer simulation. Think of it like a video game where the drone can learn from its mistakes without actually taking any damage. This is a method known as “Reinforcement Learning”.
And to ensure the drone is fit for the real world, the researchers used data from actual flights to improve the simulation.
After a month of this virtual training, Swift was ready to compete against real people.
It competed against Alex Vanover, the 2019 Drone Racing League champion, Thomas Bitmatta, the 2019 MultiGP Drone Racing champion, and Marvin Schaepper, a three-time Swiss champion.
The race took place on a special track near Zurich that featured various gates and even some tricky moves like the Split-S – an intricate, acrobatic move.
Swift actually set the fastest lap, beating the human pilots! However, there were some limitations. For example, if the lighting changed too much, Swift would get a little confused. But humans could adapt better to these changes.
Why is that so important? Because fast drones are not just for racing. You can help in many other ways too!
For example, you could quickly scan forests to look for fires or walk through buildings to find people trapped inside. They could even be used in movies to film fast-paced action scenes.
So this isn’t just a win in the sports world; It’s a big step in how drones can improve our lives!
The study was published in the journal Nature.
follow us on Twitter for more articles on this topic.
