Video Friday: A Humanoid in the Kitchen, Transparent Gel Robots, and NFL's Ball-Dropping Drone

Your weekly selection of awesome robot videos

6 min read

Erico Guizzo is IEEE Spectrum's Digital Innovation Director.

ARMAR-III humanoid robot preparing dinner
Image: Karlsruhe Institute of Technology via YouTube

Video Friday is your weekly selection of awesome robotics videos, collected by your 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!):

Robotics Alley – February 28-1, 2017 – Minneapolis, Minn., USA
HRI 2017 – March 6-9, 2017 – Vienna, Austria
IEEE ARSO – March 8-10, 2017 – Austin, Texas, USA
IEEE SSRR – March 10-13, 2017 – Shanghai, China
NYC Drone Film Festival – March 17-19, 2017 – NYC, NY, USA
European Robotics Forum – March 22-24, 2017 – Edinburgh, Scotland
Automate – April 3-3, 2017 – Chicago, Ill., USA
U.S. National Robotics Week – April 8-16, 2017 – USA
NASA Swarmathon – April 18-20, 2017 – NASA KSC, Florida, USA
RoboBusiness Europe – April 20-21, 2017 – Delft, Netherlands
ICARSC – April 26-30, 2017 – Coimbra, Portugal

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

Need help preparing a romantic dinner for two? ARMAR will give you a hand. On the menu: lettuce.

The EU project Xperience presents the results of the project, in which the humanoid robot ARMAR-III sets the table and prepares dinner in collaboration with a human. In the example task of preparing a salad and setting a table together with a human, the robot ARMAR-III uses its knowledge gained from previous experience to plan and execute the necessary actions towards its goal. The demonstration highlights the aspects of the realization of integrated complete robot systems, and emphasizes the concept of structural bootstrapping on the levels of human-robot communication and physical interaction, sensorimotor learning, learning of object affordances, and planning in robotics. This research is a collaboration between KIT, IIT, SDU, JSI, UIBK, UEDIN and UGOE.

[ Xperience Project ]

Thanks Mirko!

Engineers at MIT have fabricated transparent gel robots that can perform a number of fast, forceful tasks, including kicking a ball underwater, and grabbing and releasing a live fish.

As far as we know, no fish were harmed during the course of this research, but a whole bunch of fish were probably very confused.

[ MIT ]

It’s a little bit trippy to think about, but from a certain perspective, if robots are communicating to each other through the cloud all the time, at some point, are you just talking to one robot brain with multiple bodies??

From the HRI Laboratory at Tufts University, submitted to HRI 2017.

[ Tufts ]

RoboCup’s mid-size league is one of my favorite robot soccer events, and Tech United Eindhoven is looking good for 2017:

Yep, on track to defeat human players by 2050.

[ Tech United ]

Hanson Robotics is well-known for making expressive robotic heads out of a flexible skin-like material called “frubber,” and then packing those heads with some conversational AI. We haven’t heard much from them for the last couple years, but they now have this Einstein robotic toy on Kickstarter which is slightly less expensive than their last Einstein robotic toy.

Now, calling this toy “your personal genius” who will “be your friend”—that isn’t overselling it, right? Hrm.

[ Kickstarter ] via [ Hansen Robotics ]

When they’re not crashing into things, drones can take some absolutely amazing video, as the NYC Drone Film Festival highlights:

March 17-19 in, you guessed it, NYC.

[ NYCDFF ]

Drone video and chill with Team BlackSheep in Austria.

[ TBS ]

At a recent HackDay event here at Clearpath, a team from the Research division transformed a RC car into a 1/5th scale autonomous driving development platform. They outfitted a Losi RC car with a Velodyne laser scanner, Novatel GPS and Point Grey Flea3 camera, all of which integrated with onboard battery and computer running ROS. The team took it out to a local go cart race track to test the handling and performance.

I was cringing so hard for that Velodyne in some of those corners.

[ Clearpath ]

My buddy Andrew at Gizmodo nailed it with his headline about this video: “Watch Football Stars Get Bombed by Ball-Dropping Drones.”

And now back to football being boring again.

[ Robotics Trends ] via [ Gizmodo ]

NASA’s SPHERES robots may be most impressive at 30x speed:

ESA astronaut Thomas Pesquet and Roscosmos cosmonaut Andrei Borisenko setting up the SPHERES droids for a test run in preparation of a live educational activity – at 30 times increased speed.

[ NASA SPHERES ]

Why would you need six TurtleBot 3s? To deliver six cookies, of course!

[ ROBOTIS ]

You know what nobody, anywhere, ever wants to do? Inspect container ship ballast tanks. Thanks, Flyability!

[ Flyability ]

We did our best to cover the DARPA Robotics Challenge Finals for you, but we didn’t have the bandwidth to spend a whole lot of time with every team. MIT has put together its own little mini documentary on the challenge, which gives a unique behind the scenes perspective, including how a first-place win slipped through their fingers when their robot failed at the wall task.

[ MIT DRC ]

If you missed WAFR (Workshop on the Algorithmic Foundations of Robotics) back in December, they’ve done an absolutely incredible job of making all of the content of the workshop accessible to everyone. Videos, speakers, supplemental materials, and even 29 pages (!) of notes from the question and answer sessions. We’re posting the three plenary talks, but you’ll for sure want to look through the rest of the technical program.

Erik Demaine: “Replicators, Transformers, and Robot Swarms: Science Fiction through Geometric Algorithms”

Science fiction is a great inspiration for science. How can we build reconfigurable robots like Transformers or Terminator 2? How can we build Star Trek-style replicators that duplicate or mass-produce a given shape at the nano scale? How can we orchestrate the motion of a large swarm of robots? Recently we’ve been exploring possible answers to these questions through computational geometry, in the settings of reconfigurable robots (both modular and folding robots that can become any possible shape), robot swarms (which may be so small and simple that they have no identity), and self-assembly (building computers and replicators out of DNA tiles).

John Canny: “A Guided Tour of Computer Vision, Robotics, Algebra, and HCI”

This talk will be a fast, firmly-shepherded tour of work on vision, robotics, algebra and HCI. It will cover several decades of work, and draw connections between earlier work and the state-of-the-art now. Many of these problems were challenges in the definition phase - figuring out the real problem to be solved, and then finding the right methods to solve it. Several of them required digging deeply into other disciplines to discover acctionable principles. In all cases they involved trying new things from the great self-service counter of ideas. Some highlights include mapping high-dimensional sets, moving sets of objects by shaking, flying robots, 3D video and language-learning games. I’ll close with recent work on scalable machine learning and deep learning. Much of the work to date in ML and DL is framed as an optimization problem. In ongoing work, we are exploring an alternative framing as Monte-Carlo simulation.

Dan Halperin: “From Piano Movers to Piano Printers: Computing and Using Minkowski Sums”

The Minkowski sum of two sets P and Q in Euclidean space is the result of adding every point in P to every point in Q. Minkowski sums constitute a fundamental tool in geometric computing, used in a large variety of domains including motion planning, solid modeling, assembly planning, 3d printing and many more. At the same time they are an inexhaustible source of intriguing mathematical and computational problems. We survey results on the structure, complexity, algorithms, and implementation of Minkowski sums in two and three dimensions. We also describe how Minkowski sums are used to solve problems in an array of applications, and primarily in robotics and automation.

[ WAFR 2016 ]

There are a bunch of excellent videos that just posted from the NASA Ames 2016 summer lecture series, but these two are particularly robot-y.

The allure of deep space drives humanity’s curiosity to further explore the universe, but the risks associated with spaceflight are still limiting. Technological advancements in robotics and data processing are pushing the envelope of Human planetary exploration and habitation. Dr. Terry Fong from the NASA Ames’ Intelligent Robotics Group will describe how we are reinventing the approach to explore the universe.

Nature is a major source of inspiration for robotics and aerospace engineering, giving rise to biologically inspired structures. Tensegrity robots mimic a structure similar to muscles and bones to produce a robust three-dimensional skeletal structure that is able to adapt. Vytas SunSpiral will present his work on biologically inspired robotics for advancing NASA space exploration missions.

[ NASA Ames ]

The Conversation (0)