According to my (mind-bendingly sophisticated) calculations, in just two weeks from now, it'll officially be National Robotics Week in the United States. I'm mentioning this now because I'm assuming that you're very busy and important, and that you'll need that much lead time to make it to all of the activities. All of them. Road trip!

To get you pumped up, here's the week's worth of robot vids.

MorpHex MKII has somehow ingested even more servos, and is DEATH to smiling yellow balloons. Also, it rolls.

[ Zenta ]

We saw a demo like this with industrial robots and slot cars at IREX, but somehow, little trains are a heck of a lot more fun:

Via [ Gizmodo ]

SenseFly's eBee map-making drone has made a lovely map of, um, some rocky canyon-y place that does a lovely job of being three dimensional:

That is one cool mesh right there. Damn.

[ SenseFly ]

Are you ready to be swarmed by robot insects? Time to DASH!

[ DASH Robotics ]

Team BlackSheep took their FPV flying robots to Hong Kong. We're especially interested in this, because we'll be in Hong Kong in just a few months for ICRA 2014.

[ Team BlackSheep ]

Isn't it great that robots can learn how to be flawless at a task by watching humans fail at it over and over?

This video presents an imitation learning approach for a fluid pouring task, which consists of grasping a bottle containing a fluid and pouring a specified amount of the fluid into a container placed on a rotating table. The robot learns how to do this task from human demonstrations. In addition to learning from successful demonstrations, our approach allows learning from errors made by humans and how they recovered from these errors in subsequent trials. We report experimental results consisting of a 5 DOF robot using the learned parameters to successfully perform the pouring task to illustrate our approach.

[ Maryland Robotics Center ]

UMD's Robo Raven has nearly doubled the number of solar cells on its wings. We don't have any hard numbers on performance improvements, except for "more power than ever before."

[ UMD ]


[ Crabster CR200 ]

I know it just looks like a lot of featureless snow and ice, and it is, but this is what the South Pole looks like, I guess. And someone bothered to lug an AR Drone out there to fly it around:

[ Parrot ]

Continuing with our two-video theme of robots flying in cold places, here's a drone flying through some spectacular ice caves:

And a little behind the scenes:

[ Firefight Films ]

We'll finish the week with a TED Talk featuring Edward Snowden, which has a place in our Video Friday because he gives it on stage in Vancouver, Canada, from somewhere in Russia, through a Suitable Technologies Beam Pro:

This sort of politics isn't really the purview of this blog, but we will mention that the NSA has a response to Edward Snowden's talk in a TED Talk of their own, here.

[ TED ]

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

“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.

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

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