Video Friday: Murata Cheerleaders, Soft Robotics, and ROSCon

We'll get you all caught up on robot videos from the last few weeks

3 min read
Video Friday: Murata Cheerleaders, Soft Robotics, and ROSCon
Image: Murata

Once again, we managed to survive IROS. And you know what that means... Time to start preparing for ICRA 2015 in May in Seattle—w00t! But having a few months off is not the worst thing ever, since by "off" we only mean catching up with everything else going on in the wide wide world of robotics. Let's get to it.

Despite the fact that Murata has a pair of very sophisticated little humanoid(ish) robots, they're not really in the business of making robots at all. Rather, they make things (like robots) in order to show off their skills at making component-y things. Not that we care, really, because whenever they introduce something new, it's almost always guaranteed to be fun. Like these robotic cheerleaders!

According to the FAQ on the Murata website, the cheerleaders are "elementary school students full of energy and curiosity" and can move at about 30 cm/s, "probably the fastest of any robot ever!" Or not!

[ Murata ]

Harvard doesn't have to work very hard to sell us on why soft robots are so cool. Instead, they're working hard to make soft robotics more accessible to people, by putting together an open source toolkit that'll help you put a soft robot together for yourself:

[ Soft Robotics Toolkit ]

This Adept Quattro is not only fast in handling the fish but it is also measuring their electrical resistance to detect the presence of caviar:

[ Adept ]

The Human Exploration Telerobotics project, managed by NASA's Ames Research Center in Moffett Field, Calif., is developing and testing robots to improve the way humans live and work in space. Some of the project's robots have human-like "hands" and "legs" while others have wheels or are small, free-flying satellites. All have the potential to help astronauts reduce the amount of time they spend on routine maintenance tasks; to safely and quickly make repairs outside the spacecraft; or to remotely explore and work on a planet or asteroid's surface.

[ NASA HET ]

How ridiculous can delivery drones get? This. This ridiculous.

Flite Test ]

This is not the first mobile 3D printing robot on the scene, but it is a simple and elegant implementation, as long as you're primarily interested in simple structures:

[ LIFE ] via [ Gizmodo ]

Inspired by UC Berkeley's STAR robot, Billy, the blue beetle is a hexapod robot that can be mostly entirely (mostly) entirely 3D printed, mostly.

Just don't teach that robot 3D printer how to do this. That would cause some real trouble.

[ SMILE ]

Later this month, Singapore will host AUVSI Foundation's Maritime RobotX Challenge for autonomous surface vessels:

[ Maritime RobotX Challenge ]

Northrop Grumman's MQ-4C Triton unmanned surveillance platform made its first cross country trip earlier this month. The video is a bit of a non-event, except that it gives you a good sense of how enormous these aircraft are; with a wingspan of 130 feet, they're substantially bigger than their Global Hawk precursors.

[ Triton ]

Coming at you direct from a fresh drill hole at the base of Mt. Sharp, it's the latest Curiosity Rover Report:

[ MSL ]

If you weren't at ROSCon last week, shame on you, but the organizers were kind enough to record everything and then throw the lot up online for your enjoyment. We won't post it all here (the link below will take you to the complete set of talks), just these five special selections:

Brian Gerkey: Opening Remarks

Lightning Talks 1

Allison Thackston: ROS in Space

Lightning Talks 2

Ryan Gariepy: Closing remarks

[ OSRF Vimeo ]

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