Here Are The (Rumored) Specs for the Next Generation Kinect Sensor

Kinect changed the game for robotics, will the Kinect 2 change it again?

2 min read
Here Are The (Rumored) Specs for the Next Generation Kinect Sensor

PrimeSense may be busy making its next-gen sensor smaller and not more powerful, but Microsoft isn't looking to stuff Kinect into mobile devices. The next generation Kinect is going to be an integral part of Microsoft's next gaming console, (widely expected to be released at E3 in June), and there's a rumor that it will come with some beefed-up specs, which we've got for you in a nice handy table. Will it make your robot better, smarter, and faster? Well, maybe.

We should reiterate that these specifications are rumored. A leak website got them from I know not where, but people with more experience than I have deemed them apparently legitimate. Here's the rundown on the new sensor (currently known as "Durango"), from VGLeaks:

The biggest disappointment here for robotics is likely the unchanged depth resolution. With a minimum resolvable depth of just 0.4 meter, robots that are too small to use Kinect to help them execute grasping tasks with arms and grippers close to their sensors aren't going to get much help from the Kinect 2.

However, we're definitely liking the increased resolution of the depth data, which should enable resolving smaller objects and features from longer distances, better separation of objects occluding one another, and better curve and edge recognition. According to the rumors we're basing all of this on, "at 3.5 m it can resolve objects two to three times smaller than the current sensor." Also, the USB 3.0 interface should make it possible for users to access all of these data, which was an issue with USB 2.0. 

There are also rumors of improved skeletal tracking, which can track six people (up from two), can identify occluded joints, identify some joint rotations, and pick out thumbs and fingers well enough to be able to tell an open hand from a closed one.

Again, these are rumors, but they seem pretty legit. We'll be on the ground at E3 in June to get you all the details as the announcement happens.

[ TNW ] via [ VGLeaks ]

Thanks Travis!

The Conversation (0)

How the U.S. Army Is Turning Robots Into Team Players

Engineers battle the limits of deep learning for battlefield bots

11 min read
Robot with threads near a fallen branch

RoMan, the Army Research Laboratory's robotic manipulator, considers the best way to grasp and move a tree branch at the Adelphi Laboratory Center, in Maryland.

Evan Ackerman

This article is part of our special report on AI, “The Great AI Reckoning.

"I should probably not be standing this close," I think to myself, as the robot slowly approaches a large tree branch on the floor in front of me. It's not the size of the branch that makes me nervous—it's that the robot is operating autonomously, and that while I know what it's supposed to do, I'm not entirely sure what it will do. If everything works the way the roboticists at the U.S. Army Research Laboratory (ARL) in Adelphi, Md., expect, the robot will identify the branch, grasp it, and drag it out of the way. These folks know what they're doing, but I've spent enough time around robots that I take a small step backwards anyway.

The robot, named RoMan, for Robotic Manipulator, is about the size of a large lawn mower, with a tracked base that helps it handle most kinds of terrain. At the front, it has a squat torso equipped with cameras and depth sensors, as well as a pair of arms that were harvested from a prototype disaster-response robot originally developed at NASA's Jet Propulsion Laboratory for a DARPA robotics competition. RoMan's job today is roadway clearing, a multistep task that ARL wants the robot to complete as autonomously as possible. Instead of instructing the robot to grasp specific objects in specific ways and move them to specific places, the operators tell RoMan to "go clear a path." It's then up to the robot to make all the decisions necessary to achieve that objective.

Keep Reading ↓ Show less