We know. We skipped Video Friday last week. We're sorry. But cool stuff happened that we wanted to bring you right away. We're going to make up for it this week, though, with an extra helping of robot vids, so let's get right to it.
There were some Twitter rumors this week about a new ASIMO, but it turned out that it was all just a promo for the North American TV debut of the current version of ASIMO that was introduced back in 2011. It's worth watching anyway (if you can handle daytime TV), because it's still impressive, except for the voice recognition, which is terrible to the extent that it may be nonexistent.
[ ASIMO ]
Here's a robot that is new: it's a version of SenseFly's eBee drone designed specifically for agriculture, featuring a choice of infrared or multispectral cameras to provide you with easy to acquire, timely data about your crops.
[ eBee Ag ]
I think of this thing as more of an externally actuated mannequin than an actual robot, but the rest of the Internet seems to be calling it a robot, so here ya go: it's Porton Man, an infantry suit tester (like Petman) from the U.K.:
[ BBC ]
Zenta took his MorpHex MKII outside and let it freakily roll around:
[ Zenta ]
Why do I never get tired of watching Team Blacksheep's drone videos? They're SO PRETTY!
[ Team Blacksheep ]
One of the selling points of Rethink Robotics' Baxter is that end users will get software upgrades that will significantly improve the capabilities and performance of their robots. This video shows the substantial improvement in speed that Baxter got in just the last year through software upgrades alone:
[ Rethink Robotics ]
Turns out, it's really freakin' hard to shoot down a moving drone, even if you've got a whole bunch of people with machine guns:
Via [ PopSci ]
Crabster's manipulation mode involves unfolding arms out of its two front legs. Note that the forward arm motion is 4x speed.
[ KIOST ]
When roboticists want an excuse to try and screw their robot up somehow, they call it "robustness testing."
[ AMBER Lab ]
I'm not sure that you can really play an effective game of beer pong with a drone, but what's so great about this video is seeing how you can smash these drones into things over and over again and it just doesn't matter:
[ Game of Drones ]
Double backflip, with a twist:
[ Hinametitu ]
We're not the happiest with Kuka after their ping pong fiasco, but they do make some cool giant robots, like their omniMove platform:
[ Kuka omniMove ]
In the mood for some destruction? Check out the 2014 Central Illinois Bot Brawl's greatest hits compilation:
[ CIRC ]
SparkFun's 2014 Autonomous Vehicle Competition kicks off June 21st, and here's a preview of this year's course:
[ SparkFun AVC ]
This concept for on-demand drones is fun to think about, even though its near-term realism is sketchy at best for many of the same reasons why we're not buying into Amazon's urban drone delivery.
[ Gofor Drones ]
From ETH Zurich:
In this video we demonstrate the capabilities of our monocular pose tracking system. It consists of infrared LEDs on the quadrotor and an infrared camera on the arm of a ground robot. Since we know the positions of the LEDs on the quadrotor, we can precisely estimate its position and orientation. We are able to stabilize a quadrotor under illumination changes up to complete darkness. Our algorithm is robust to false detections. This with an additional infrared LED, which we move closely to the other LEDs. To estimate the pose of the quadrotor, we need at least four LEDs. However, five are currently mounted. Our system can handle the occlusion of an LED and is still precise enough to stabilize the quadrotor. Since we track the quadrotor relative to the camera, the quadrotor stays with the ground robot, even if it is moving. Our system works also outdoors.
[ Paper ]
This is a Dash robot in a box. It is perhaps the best thing I have ever seen.
[ Dash Robotics ]
Let's wrap the week with three think pieces, in no particular order:
RI Seminar: Bilge Mutlu : Human-Centered Methods for Designing Robotic Products
TEDx Fulbright: Max Versace of Neurala on the Future of Robots