[Matt], [Andrew], [Noah], and [Tim] have a pretty interesting build for their capstone project at Ohio Northern University. They’re using a Microsoft Kinect, and a Leap Motion to create a natural user interface for controlling humanoid robots.
The robot the team is using for this project is a tracked humanoid robot they’ve affectionately come to call Johnny Five. Johnny takes commands from a computer, Kinect, and Leap motion to move the chassis, arm, and gripper around in a way that’s somewhat natural, and surely a lot easier than controlling a humanoid robot with a keyboard.
The team has also released all their software onto Github under an open source license. You can grab that over on the Gits, or take a look at some of the pics and videos from the Columbus Mini Maker Faire.
[Eric] just sent in this awesome Kinect hack that he and a few friends worked on. Playing Super Smash Bros with a Kinect.
The system makes use of two Kinects, and three PCs. The first Kinect records each individual players moves, while the second Kinect watches both players “fight” each other. The first PC runs an Nintendo 64 emulator to play the game.
The second PC runs a camera with OpenCV to add another cool but perhaps unnecessary feature, you see, even the character selection is a physical process, adding to the idea of playing the entire game with your body. A glass table allows players to set their 3D printed token onto the glass, effectively placing it on the character they would like to use.
And when the match ends, a windshield wiper knocks off the losing player’s token from the table.
The third PC is responsible for running both Kinects, which then has to send the resulting commands back to first PC over a TCP connection for input into the game.
They introduced it to the public at MHacks Fall 2014, a hacking competition sponsored by Dell and Intel. Video Below.
Continue reading “Super Smash Bros Gets A Revamp With The Microsoft Kinect”
This animatronic teddy bear is the stuff of nightmares… or dreams if you’re into mutant robot toys. In either case, this project by [Erwin Ried] is charming and creepy, as he gives life to an unassuming stuffed animal by implanting it with motorized parts.
[Erwin] achieves several degrees of motion throughout the bear’s body by filling the skin with a series of 3D printed bones, conjoined by servo motors at its shoulders, elbows and neck. The motors are controlled via an Arduino running slave to a custom application written in C#. This application uses the motion tracking and facial recognition features of the Xbox Kinect, mapping the input from the puppeteer’s movement to the motors of the doll’s skeleton. Additionally, two red LEDs illuminate under the bear’s cheeks in response to the facial expression of the person controlling it, as an additional reminder that teddy feels what you feel.
In [Erwin’s] video, he demonstrates what his application sees through the Kinect’s camera side-by-side with the mechanical skeleton its controlling. The finished product isn’t something I’d soon cuddle up to at night, but looks amazing and is fun to watch in action :
Continue reading “Robotic Terminator Teddy Will Protect You While You Sleep”
Ever feel like someone is watching you? Like, somewhere in the back of your mind, you can feel the peering eyes of something glancing at you? Tapping into that paranoia, is this Computer Science graduate project that was created during a “Tangible Interactive Computing” class at the University of Maryland by two bright young students named [Josh
As you’ve probably gathered from the title, this project uses a Microsoft Kinect to track the movement of nearby people. The output is then translated into actionable controls of the mounted eyeballs producing a creepy vibe radiating out from the feline, robot poster.
Continue reading “Creepy Cat Eyes With A Microsoft Kinect”
The Kinect has long been able to create realistic 3D models of real, physical spaces. Combining these Kinect-mapped spaces with an Oculus Rift is something brand new entirely.
[Thomas] and his fellow compatriots within the Kintinuous project are modeling an office space with the old XBox 360 Kinect’s RGB+D sensors. then using an Oculus Rift to inhabit that space. They’re not using the internal IMU in the Oculus to position the camera in the virtual space, either: they’re using live depth sensing from the Kinect to feed the Rift screens.
While Kintinuous is very, very good at mapping large-scale spaces, the software itself if locked up behind some copyright concerns the authors and devs don’t have control over. This doesn’t mean the techniques behind Kintinuous are locked up, however: anyone is free to read the papers (here’s one, and another, PDF of course) and re-implement Kintinuous as an open source project. That’s something that would be really cool, and we’d encourage anyone with a bit of experience with point clouds to give it a shot.
Continue reading “Virtual Physical Reality With Kintinuous And An Oculus Rift”
The old gen 1 Kinect has seen a fair bit of use in the field of making 3D scans out of real world scenes. Now that Xbox 360 Kinects are winding up at yard sales and your local Goodwill, you might even have a chance to pick one up for pocket change. Until now, though, scanning objects in 3D has only been practical in a studio or workshop setting; for a mobile, portable scanner, you’d need to lug around a computer, a power supply, and it’s not really something you can fit in a back pack.
Now, finally, that may be changing. [xxorde] can now get depth data from a Kinect sensor with a Raspberry Pi. And with just about every other ARM board out there as well. It’s a kernel driver that’s small, fast, and does just one thing: turns the Kinect into a webcam that displays depth data.
Of course, a portabalized Kinect 3D scanner has been done before, but that was with an absurdly expensive Gumstix board. With a Raspi or BeagleBone Black, this driver has the beginnings of a very cheap 3D scanner that would be much more useful than the current commercial or DIY desktop scanners.
No, that isn’t a scene from a horror movie up there, it’s [Oliver Kreylos’] avatar in a 3D office environment. If he looks a bit strange, it’s because he’s wearing an Oculus Rift, and his image is being stitched together from 3 Microsoft Kinect cameras.
[Oliver] has created a 3D environment which is incredibly realistic, at least to the wearer. He believes the secret is in the low latency of the entire system. When coupled with a good 3D environment, like the office shown above, the mind is tricked into believing it is really in the room. [Oliver] mentions that he finds himself subconsciously moving to avoid bumping into a table leg that he knows isn’t there. In [Oliver’s] words, “It circumnavigates the uncanny valley“.
Instead of pulling skeleton data from the 3 Kinect cameras, [Oliver] is using video and depth data. He’s stitching and processing this data on an i7 Linux box with an Nvidia Geforce GTX 770 video card. Powerful hardware for sure, but not the cutting edge monster rig one might expect. [Oliver] also documented his software stack. He’s using Vrui VR Toolkit, the Kinect 3D Video Capture Project, and the Collaboration Infrastructure.
We can’t wait to see what [Oliver] does when he gets his hands on the Kinect One (and some good Linux drivers for it).
Continue reading “Virtual Reality Gets Real With 3 Kinect Cameras”