Video Friday: Atlas Unboxing, RHex Plays Fetch, and Terminators Get Real

Atlas has entered the building, and so have lots of other robots, because they all know that it’s Video Friday

3 min read
Video Friday: Atlas Unboxing, RHex Plays Fetch, and Terminators Get Real

I’m still waiting for an Atlas robot to arrive on my doorstep from Boston Dynamics (since I’m a famous and occasionally handsome Internet journalist, I’m assuming they’re sending me one for free), but some other robotics groups have gotten theirs first. This hopefully means that we’re about to see a huge number of videos show up on YouTube featuring Atlases doing all of the stuff that Boston Dynamics doesn’t want you to see. Like those butt scoots from the simulation challenge. Check out some of the very first videos of Atlas in the wild, and more (more!), because it’s Video Friday.

Atlas robots are starting to arrive! Here’s MIT’s:

Best. Present. Ever.

[ MIT CSAIL ]

Meanwhile, Hong Kong University already has their Atlas playing rock, paper, scissors using a Leap motion controller and a Sandia hand:

[ HKU ]

iRobot has finally finished swallowing Evolution Robotics, and the Mint (which we’re big fans of) has been rebranded as the iRobot Bravaa Braava.

We’ve confirmed with iRobot that the Braava is mechanically and functionally the same as Mint, so if you already have a Mint, this re-release doesn’t make your existing robot any less Minty. And now the Evolution is fully integrated, we’re looking forward to some new implementations of the localization technology that makes Mint (and Braava) so smart.

[ iRobot Braava ]

The following video is a dramatization:

The following video is not a dramatization, and is what you should use if you want to humiliate some humans at things like this:

[ R2B2 ]

[ Adept Quattro ]

Every robot needs googly eyes. Every single one. This video of RHex frolicking illustrates why. It also illustrates a bunch of other stuff, but GOOGLY EYES.

Every week we take the robots out for a hike, both because it is fun but also to make sure the robot and operator are working well. This week we made a fun video that shows off some of RHex’s potential to interact with the world in interesting ways. The story in this video stems from some cool research happening in our lab, where students are using a panning camera mounted on the robot to track objects and landmarks as a method of controlling the motion of the robot. This type of control could lead to the behaviors seen in the above video. Currently the motions of the robot are controlled by a person using a joystick, but imagine how fantastic it would be to have a robot able to track and follow a ball autonomously! The ability to track objects, combined with RHex’s agility over rough terrain has many applications in search and rescue scenarios, exploration of dangerous environments, and assisting humans in a multitude of tasks.

[ Kod*lab ]

Thanks Aaron!

Not falling off a ball is probably just about exactly as hard as it looks for Thymio II:

Thymio’s little pointy hat is actually a weight that helps stabilize the robot and increases friction between the ball and the wheels. It’s also super cute.

[ Thymio II ]

Here’s five minutes of RoboCup 2013 highlights, featuring UT Austin’s Standard Platform team:

[ Austin Villa ]

In this week’s Rover Report, Curiosity is making tracks towards Mount Sharp while getting mooned.

[ MSL ]

Northrop Grumman has a sort of sizzle reel of the X-47B carrier landing trials. There’s some new footage, but more importantly, it’s MUCH MORE ROCKIN’.

Seriously. That thing is like some sort of CGI space fighter, man. The future is here.

[ X-47B ]

And because there’s no better way to end a week than with a real live killer robot, this is a Terminator T-1. Zero percent CGI, 100 percent awesome, from the Stan Winston School.

Via [ Gizmodo ]

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
LightGreen

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