Skip to main content

Meet the Skydio R1: A portable A.I. camera drone that truly flies itself

Introducing the Skydio Autonomy Engine

Another drone with built-in camera isn’t all that exciting, right? Try telling that to the Massachusetts Institute of Technology engineering graduates at Skydio who this week introduced their new R1 flying action cam. Utilizing 13 cameras to view the world and an Nvidia Jetson chip more commonly used in self-driving cars, the R1 promises to be the smartest flying 4K camera you ever tried — with its guiding mission being to keep you in the frame at all times while dodging any obstacles around it.

“The R1 was designed for full autonomy,” Skydio’s CEO and co-founder Adam Bry told Digital Trends. “With other drones the autonomy features are targeted as pilot assistance, and they’re generally designed with the notion that there’s still a pilot ready to take over at a moment’s notice. Getting beyond this is very technically challenging, but that’s what we’ve been focused on for the last four years — and that’s what makes R1 special.”

The system is based on state-of-the-art computer vision algorithms, which are able to look at raw images and simultaneously balance obstacle avoidance and the need to capture amazing video. Navigating by sight is a frankly amazing challenge, and it is one that R1 seems to be able to pull off pretty darn effortlessly, all while traveling at speeds of more than 20 mph.

Skydio R1: Running Hurdles with Olympian Mikel Thomas

At $2,499, it’s not cheap, and its battery life is limited to 16 minutes, but if you’re in the market for a great action cam, the R1 should totally be at the top of your list. Whether you’re an athlete hoping for a hands-free recording of your practices or an outdoors enthusiast who hopes to capture some stunning vistas, this looks like a brilliant bit of tech.

“There’s potential for a broad range of applications, but initially, we see this as a product that sports enthusiasts, adventurers, creators and early adopters will love,” Bry continued. “There are always going to be people that enjoy flying a drone, but the R1 is less about flying a drone manually and more about being able to create content that you wouldn’t normally be able to create.”

We can’t wait to put it through its obstacle-avoiding paces!

Editors' Recommendations

Luke Dormehl
I'm a UK-based tech writer covering Cool Tech at Digital Trends. I've also written for Fast Company, Wired, the Guardian…
Just drag and drop: Using A.I., Skylum AirMagic edits drone photos for you
skylum airmagic launches 1

Drones took photography to literal new heights, but when it comes to photo editing, aerial images tend to have a few quirks to correct. On Thursday, March 7, Skylum launched an artificially intelligent photo editor designed specifically for aerial shots called AirMagic.

Like Skylum’s A.I.-powered photo editor Photolemur, AirMagic requires little input to actually edit images. Photographers drag the images into the app and the software does the rest, relying on machine learning to determine what should be adjusted and how. Because the software is trained specifically for aerial images, the company says the program is better able to capture the issues that frequently pop up in aerial photography, such as haze, contrast, sharpness, saturation, and chromatic aberration.

Read more
SimCam security camera’s DIY A.I. recognizes faces, monitors pets and objects
simcam ai home security camera ces 2019 bg1

SimCam, 1st on-device AI Camera for Smart Home Security

SimCam Lab introduced the SimCam home security and home automation camera with trainable artificial intelligence at CES 2019. The SimCam uses A.I. for facial recognition, pet monitoring, and more via location training. You can also integrate the SimCam with Amazon Alexa or Google Assistant for voice command control and to connect with other smart home ecosystem devices.

Read more
Meet the game-changing pitching robot that can perfectly mimic any human throw
baseball hitter swings and misses

Who’s your favorite baseball pitcher? Shane McClanahan? Sandy Alcantara? Justin Verlander? Whoever you said, two of the top sports-tech companies in the U.S. -- Rapsodo and Trajekt Sports -- have teamed up to build a robot version of them, and the results are reportedly uncannily accurate.

Okay, so we’re not talking about walking-talking-pitching standalone robots, as great a sci-fi-tinged MLB ad as that would be. However, Rapsodo and Trajekt have combined their considerable powers to throw a slew of different technologies at the problem of building a machine that's able to accurately simulate the pitching style of whichever player you want to practice batting against -- and they may just have pulled it off, too.

Read more