This Parkour Robot Easily Bounces Its Way Over Obstacles
Researchers at the University of California, Berkeley, have updated their parkour robot, and the results would make any free-runner green with envy.
Late last year, we wrote about Duncan Haldane’s Salto robot. It was impressive: weighing mere ounces and standing just a few inches tall, it crouched low, jumped high, and could quickly prepare for another jump. That meant that it could, say, bounce itself off walls.
The only problem was that the small spinning tail it used to control its aerial orientation could control it only along one axis—known as pitch, as on an airplane. That meant it could only jump forward and backward, and then only for few hops at a time, because if it went off balance along the other two axes it would fall to the left or right.
Now, though, IEEE Spectrum reports that Salto has been upgraded: say hello to Salto-1P. The addition of two small thrusters, like propellers from a quadcopter drone, allows it to adjust its orientation in the two other directions, known as roll and yaw, as it moves through the air. It can also crouch lower, enabling it to jump a little farther. (It’s worth noting that it’s not autonomous—a computer is working out how it should move and wirelessly beaming it instructions.)
You can see the impressive results of those upgrades in the clips above. Now, Salto-1P can bounce forward and backward many times over, move side to side to cover the entire floor of a room, and even traverse obstacles like foam blocks and a ramp.
(Read more: IEEE Spectrum, “This Super-Springy Robot Can Do Parkour”)
Keep Reading
Most Popular
Large language models can do jaw-dropping things. But nobody knows exactly why.
And that's a problem. Figuring it out is one of the biggest scientific puzzles of our time and a crucial step towards controlling more powerful future models.
The problem with plug-in hybrids? Their drivers.
Plug-in hybrids are often sold as a transition to EVs, but new data from Europe shows we’re still underestimating the emissions they produce.
Google DeepMind’s new generative model makes Super Mario–like games from scratch
Genie learns how to control games by watching hours and hours of video. It could help train next-gen robots too.
How scientists traced a mysterious covid case back to six toilets
When wastewater surveillance turns into a hunt for a single infected individual, the ethics get tricky.
Stay connected
Get the latest updates from
MIT Technology Review
Discover special offers, top stories, upcoming events, and more.