The July 2022 issue of IEEE Spectrum is here!

Close bar

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!):

IEEE ICARM 2017 – August 27-31, 2017 – Hefei, China
IEEE RO-MAN – August 28-31, 2017 – Lisbon, Portugal
CLAWAR 2017 – September 11-13, 2017 – Porto, Portugal
FSR 2017 – September 12-15, 2017 – Zurich, Switzerland
Singularities of Mechanisms and Robotic Manipulators – September 18-22, 2017 – Johannes Kepler University, Linz, Austria
ROSCon – September 21-22, 2017 – Vancouver, B.C., Canada
IEEE IROS – September 24-28, 2017 – Vancouver, B.C., Canada
RoboBusiness – September 27-28, 2017 – Santa Clara, Calif., USA
Drone World Expo – October 2-4, 2017 – San Jose, Calif., USA
HAI 2017 – October 17-20, 2017 – Bielefeld, Germany
ICUAS 2017 – October 22-29, 2017 – Miami, Florida, USA

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

Of course designing robots is challenging, but if someone were to make it easy, how could we justify publishing all of these papers and putting on conferences and stuff? Sigh, thanks MIT.

“Designing robots usually requires expertise that only mechanical engineers and roboticists have,” says PhD student and co-lead author Adriana Schulz. “What’s exciting here is that we’ve created a tool that allows a casual user to design their own robot by giving them this expert knowledge.”

Casual roboticists? Is that a thing you can be...?

[ Paper ] via [ MIT CSAIL ]


The Korea Atomic Energy Research Institute says the combination of a drone and snake robot (that can make a cute little "C" shape when it wants to be picked up) is ideal for accident monitoring.


That nifty Voliro drone from ETH Zurich is being put to work by the team of undergrads who invented it, because apparently getting that drone to work in the first place wasn't good enough and they had to do more stuff in order to get their degrees.

[ Voliro ]

A more in-depth look at the Democratic Robot, which finished 5th in the July 2017 Weaponized Plastic event, despite limited weaponry and defenses consisting primarily of printed pictures of kittens. The Democratic Robot is unique among the entrants in that it did not have a driver controlling it, instead using an electronic voting system built with a Raspberry Pi and the Telegram app.

[ Fetch Robotics ]

For whatever it’s worth, the new world record for simultaneous robot dancing is now 1,069 instead of 1,007.

There was at least one robot getting a face full of concrete there, I guess that's probably why it's a weird number like 1,069.

[ Guiness ] via [ BB ]

Somehow, the Dyson Rapid Development Challenge was not won by the adorable little robot elevator at 1:07.

[ Dyson ]

Intel experts examine what it will take for people to trust autonomous cars. In this video, community members experience a driverless ride -- and share their reactions.

[ Intel ] via [ Engadget ]

While I dislike most drone delivery videos, this is at least one case where "we have a dumb drone that can dumbly haul stuff from one nearby place to another as long as there are no obstacles in the way" is actually useful, since there's a bunch of water in the way.

From the looks of it, though, that's a big stretch for "urban environment."

[ Flytrex ]

Brought to you by the latest "let's staple a weapon to a drone and overproduce a video about it" company:

[ Duke Robotics ]

Your autonomous car doesn't care a jot whether there's an eclipse happening, which is a good thing, I guess?

TORC's autonomous car also does quite well in the rain:

On the first day of our coast-to-coast trip from Washington, D.C., to Seattle, Washington, the team experienced a downpour while navigating through heavy traffic. “In the worst of the West Virginia downpour, the car could see better than we could,” said one of Torc’s safety drivers who participated in the trip. Our local tests included autonomous lane changes, passing, and merging on and off highways—all through rain. Torc’s multi-sensor approach used the strength of several sensors (including radar and LiDAR). The sensors have a 360°-view of the cars’ surroundings, and we utilize our proven algorithms along with real-time data to help the car “see” through low visibility.

[ TORC Robotics ]

It's not every day you see a robot crab with four legs and a humanoid robot with six (!) arms both beating up on a robot that may or may not be made of solid gold:

[ Biped Robot News ]

This video summarizes the deployment of applications on Valkyrie performed by Steven Jens Jorgensen from the U. of Texas at Austin and other researchers at NASA, IHMC, and U. Michigan. Given desired end-effector poses, a nonlinear optimization routine is used to solve the whole-body Inverse Kinematics (IK) of NASA's Valkyrie robot while satisfying balance constraints.

Maybe one day, I'll get a chance to fist bump Valkyrie like that bottle of Tide did.


Sharp edged tools and objects pose a severe problem and allow collaborative robots (Cobots), to move only with inefficient velocities. [DLR] recently introduced a Robotic Airbag, which covers these sharp edges within less than a second always before the Cobot starts moving. Pressure sensors detect the safety status of the Robotic Airbag and provide collision detection. The Robotic Airbag is pulled back again when the object has to be released or the tool is required.

Can I get one of these just, like, for fun?


We present a quadrotor system capable of autonomously landing on a moving platform using only onboard sensing and computing. We rely on state-of-the-art computer vision algorithms, multi-sensor fusion for localization of the robot, detection and motion estimation of the moving platform, and path planning for fully autonomous navigation. Our system does not require any external infrastructure, such as motion-capture systems. No prior information about the location of the moving landing target is needed. We validate our system in both synthetic and real-world experiments using low-cost and lightweight consumer hardware. To the best of our knowledge, this is the first demonstration of a fully autonomous quadrotor system capable of landing on a moving target, using only onboard sensing and computing, without relying on any external infrastructure.

[ Paper ] via [ UZH ]

RoboCup simulation league is a far cry from reality, but UT Austin is scarily good at it. Their virtual NAOs managed to score 171 goals in RoboCup 2017, and they were scored on zero times. Here are 10 minutes worth of highlights; some of them are pretty incredible.

If only NAOs could do that in real life, right?

[ UT Austin Villa ]

This video is a bit tedious, but it's showing something important- the first demonstration of an autonomous "crash into me instead of crashing into a human" truck.

A better way of solving this problem, I think, is to just put everyone in autonomous cars instead. Much safer.

[ Wired ]

Should your driverless car kill you if it means saving five pedestrians? In this primer on the social dilemmas of driverless cars, Iyad Rahwan explores how the technology will challenge our morality and explains his work collecting data from real people on the ethical trade-offs we're willing (and not willing) to make.

[ TED ]

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

“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.

This article is part of our special report on AI, “The Great AI Reckoning.”

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