Close
ATRIAS MARLO bipedal robot walking in the forest
Where'd you get dem shoes robot?
Image: Michigan Robotics/Dynamic Legged Locomotion Lab

Video Friday is your weekly selection of awesome robotics videos, collected by your nebulous Automaton bloggers. We’ll also be posting a weekly calendar of upcoming robotics events for the next two months; here’s what we have so far (send us your events!):

RSS 2016 – June 18-22, 2016 – Ann Arbor, Mich., USA
European Land Robot Trial – June 20-24, 2016 – Eggendorf, Austria
Automatica 2016 – June 21-25, 2016 – Munich, Germany
ISR 2016 – June 21-22, 2016 – Munich, Germany
ICROM 2016 – June 23-25, 2016 – Singapore
The Rise of Machine Learning – June 24, 2016 – San Francisco, Calif., USA
UK Robotics Week – June 25-1, 2016 – United Kingdom
Hamlyn Symposium on Medical Robotics – June 25-28, 2016 – London, England
TAROS 2016 – June 28-30, 2016 – Sheffield, United Kingdom
RoboCup 2016 – June 30-4, 2016 – Leipzig, Germany


Let us know if you have suggestions for next week, and enjoy today’s videos.

Can robotic machine tending really be this easy?

Impressive. Tend.ai CEO Mark Silliman tells us how the system works:

Tend.ai makes “cloud robotics for machine tending” a reality. Our system uses artificial intelligence powered by cloud computing to read machines’ displays and press machines’ buttons just like a human would. No modification or networking of machines is required. It’s compatible with both Universal and Rethink robots (as well as many more soon). You can train, control, and monitor any robot from any device (e.g. your mobile phone), and use standard webcams (< $100) for vision. As a demo of what our system can do, we built the world’s first fully automated 3D printing solution.

[ Tend.ai ]

Mamma mia! Finally a new video from Moley Robotics, which gives a little bit of insight into their robot risotto plans:

So far, this looks mostly like “add prepared ingredients to single pot and stir.” We’re holding out for a few more kitchen skills than that. 

[ Moley Robotics ]

I’ve been waiting for this video ALL YEAR:

McGill Robotics: where the only thing better than the robots is the acting.

[ McGill RoboSub ]

Con Edison is saving a ridiculous amount of money to inspect steam boilers in New York City by using the indestructible drones from our friends at Flyability rather than having human workers assemble 10-story scaffolding to do the inspections themselves:

[ Flyability ] via [ Con Edison ]

It takes kind of a lot of abuse to get MARLO to fall over:

Also, Michigan has reacted to our continual teasing about MARLO’s mobile gantry by replacing it with a much more versatile biomechanical system:

I gotta get me a pair of dem shoes.

[ MARLO ]

There’s a reason that Clearpath makes rugged UGVs like Jackal: they’re based near Toronto, where as far as I’ve experienced, there are blizzards 100 percent of the time.

#nakedpr2

[ Clearpath ]

Usually, when birds of prey attack quadrotors, it’s over for the quadrotor pretty quickly. A flying wing is more resilient, and this one gets beat on by an eagle for 2 minutes straight before limping back home with a ruptured battery pack.

[ Team BlackSheep ]

“It’s not like Arnold-Schwarzenegger-with-the-leather-jacket-‘I’ll be back’ robot.” We can agree with that.

[ Pepper ]

At Hannover Faire, Kuka robots and humans worked side by side to fake-build powertrains for Volkswagen:

[ Volkswagen ]

SPRK+ is a beefed up version of Sphero SPRK designed to be abused in the way that only educational robots are abused:

[ Sphero ]

“Humans automatically learn to anticipate actions through experience, which is what made us interested in trying to imbue computers with the same sort of common sense,” says CSAIL PhD student Carl Vondrick, who is first author on a related paper that he will present this week at the International Conference on Computer Vision and Pattern Recognition (CVPR). “We wanted to show that just by watching large amounts of video, computers can gain enough knowledge to consistently make predictions about their surroundings.”

Me? I always want hugs, but only from robots.

[ MIT News ]

Airobotics provides an end-to-end, fully automatic solution for collecting aerial data and gaining invaluable insights. The industrial grade platform is available on-site and on-demand, providing industrial facilities with premium aerial data collection, processing and analysis in a faster, safer, more efficient way.

A doghouse for your drone is a very cool idea in theory, as long as it can work as advertised in practice.

[ AIRobotics ] via [ Engadget ]

Welcome to Menlo Park, Calif., where elementary schools are full of Peppers and NAOs and even a couple of humans, if you look closely:

[ RobotsLab ]

The man himself, James Dyson, talks about why they didn’t sell a robotic vacuum three years ago:

Admirable restraint, sir.

[ Dyson ]

SRI does a lot of cool stuff, but they don’t really sell anything: they spin off companies and technology to do that. So, hearing from them about low-cost robotics provides a little bit of a hint about where they see future commercialization opportunities.

[ SRI Robotics ]

Microsoft Research has been uploading a bajillion videos of lectures and panels over the last week or so, and a couple on AI seemed especially interesting, since they feature people like Andrew Ng, Yann LeCun, Fei-Fei Li, Eric Horvitz, Oren Etzioni, and many other AI stars.

[ Microsoft Research ]

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