Close

Video Friday: Robot Cube, Drone Fight Club, and the Rest of 2013

2014 is here, but we still have a little bit of catching up to do from last year

3 min read
Video Friday: Robot Cube, Drone Fight Club, and the Rest of 2013

Well, as you may have noticed, we took a little bit of a break over the last week or two. Hopefully you can agree (at least a little bit) that we earned it; after all, it takes time to recover from the massive sunburn and millions of mosquito bites that we suffered at the DRC

So now that we're back, and now that it's Friday, we've got a post full of videos to get you all caught up on the end of 2013.

We've been following Cubli for ages, and somehow Gajan Mohanarajah managed to secretly finish building a working version that's able to stand itself up without exploding:

"For us, it is just a cool little cube that can jump up, balance, and walk." Just, they say.

You can read lots more technical detail about how Cubli works on Robohub.

[ ETH ]

 

 

Another project that we've been following for ages is TU Delft's DelFly micro aerial vehicle. A new minuscule stereo vision system and lightweight onboard processing allows the flapping wing robot to keep itself entertained for about 10 minutes without crashing into anything, no external computers (or humans) necessary:

[ DelFly ]

 

 

 

We're going to have much more for you on the DRC over the next month or so, but in the meantime, our friends over a Clearpath Robotics have a couple recap vids with some interesting team interviews:

 

[ Clearpath ]

 

 

You remember Budgee, right? We met it at RoboBusiness forever ago. And by forever ago, I mean October. It's now on Kickstarter, and you can preorder one for $1,300:

[ Kickstarter ]

 

 

These two videos are student projects from MIT's "Biomimetics, Biomechanics, and Bio-Inspired Design" class, taught by Sangbae Kim, who definitely knows a thing or two about biorobotics.

Team RoboBlade (Tian Gan, Fang-Yu Liu, and Matthew Gilbertson)

 

Kanga (Spencer Boone, Otto Briner, Saya Date, and David Wise)

 

These were just a few of our favorites; you can see more at the MIT Biomimetics YouTube channel.

[ YouTube ]

 

 

A Drone Fight Club, you say?

As long as these drones truly are as indestructible as the video claims, this looks like it could be a lot of fun.

[ Game of Drones ] via [ Robots Dreams ]

 

 

3D Robotics put on a slightly less destructive UAV demonstration on board the USS Hornet aircraft carrier in Oakland:

[ 3D Robotics ]

 

 

And for some totally non-destructive UAVs, this is a swarm of them that can actively avoid running into a human:

Note that there's a Vicon motion capture system in use here.

[ Illinios ]

 

 

That crazy gymnastics robot is rapidly approaching (or maybe even surpassed) the point at which humans are comfortable competing:

[ YouTube ]

 

 

Here is a robot that lifts things if you ask it nicely. Rather a lot of things, in fact:

[ YouTube ]

 

 

At UPenn, taking a class called "Design of Mechatronic Systems" is really just a thinly veiled excuse to play with hockey robots for a semester:

Throughout the school year, members of the class, led by Jonathan Fiene, director of laboratory programs for the Department of Mechanical Engineering and Applied Mechanics, design pint-sized robotic hockey teams that face off in an annual competition known as The Robockey Cup. Each team produces three robots that skate on wheels, shoot with pistons, and see the puck, the goals, and each other using a variety of sensors.

[ UPenn ]

 

 

ABB is trying to teach robots to cut things out of stone, and it looks like they're doing a halfway decent job at it:

 

 

It's Team Blacksheep's 2013 retrospective. Come for the music and the visuals, stay for the occasional buzzing of law enforcement and farm animals:

[ Team Blacksheep ]

 

 

Let's wrap with a video from the National Science Foundation and NBC, who got access to Google's autonomous car program:

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