Video Friday: Snake Robot Swims, Nao Goes to School, KITT Escapes

In this edition of Video Friday, Nao at school, snake robot on vacation, and strange robot sightings in San Francisco.

4 min read
Video Friday: Snake Robot Swims, Nao Goes to School, KITT Escapes

Nao humanoid robot high school

In this edition of Video Friday, Nao goes to school, snake robot goes on vacation, and strange robot sightings are reported in San Francisco.

Last week, we got a strange email describing several robot sightings in San Francisco. YouTube videos showed KITT, the Knight Rider car, escaping from a garage, a group of Naos riding the subway, and a Mars rover taking a stroll on the Golden Gate promenade. Hmmm ... We immediately suspected it was all a viral marketing stunt. And by someone with deep pockets to stage these elaborate performances. And we were right! It's a marketing campaign by GE called "Brilliant Machines." It features some really famous robots, including Data from Star Trek, B9 from Lost in Space, and Robby the Robot from Forbidden Planet. Apparently GE has new products that will incorporate some AI capabilities and the company thought that using robots would help drive the point. Well, it got our attention, though we were hoping for a cool new robot movie (Robopocalypse was our guess), not a TV commercial. Check out the video below and this Tumblr page for more "robot sightings."


Shigeo Hirose from the Tokyo Institute of Technology is famous for his bio-inspired robotic snakes, and among his most impressive creations is the ACM-R5 snake bot. In this new video, we see the latest version, called ACM-R5H, developed in collaboration with Tokyo Tech spin-off HiBot. We have no idea why the video is called "HiBot ACM-R5 in Hollywood" (is the snake pursuing a movie career?), but who cares? It's just the coolest thing to watch this machine having some fun in the water.

[ HiBot ]


I love robots that balance on balls. There's something fascinating about robots that have no legs, no wheels, no tracks. They're on a perpetual balancing act. But granted, other than research or artistic purposes, why build a ball-balancing robot? What application could possibly require such a machine? Now University of Idaho engineers have an answer to that question. And the answer is: a marching band drum, of course! With a conventional drumset, the drummer has to use a harness to carry the instrument around. You can guess it's probably not easy nor comfortable. So the engineers created the Human-Assisted Robotic Drumset. It consists of a ball-balancing mechanism that supports the weight of the drumset and senses the movements of the drummer, helping to move the instrument in the desired direction.

[ University of Idaho


Automaton readers might remember the superfast Japanese book scanner we wrote about a couple of years ago. Created by University of Tokyo researchers, the machine users a 1000-frame-per-second camera system—the same system that allows robot hands to catch eggs in mid-air among other high-speed feats—to photograph a book as its pages flip. Special software detects the curvature of the scanned pages and flattens the images. With the device you could in theory scan an entire book in seconds! But flipping a book manually has its problems: you might skip pages or the quality of the scans might not be good enough. So now the researchers have engineered a device that can hold the book and flip through the pages carefully. They say the scanner can achieve 250 pages per minute.

[ Ishikawa Oku Laboratory ] via [ Dvice ]


Early this year, we saw a squad of flying robots playing the James Bond theme. Now researchers at Georgia Robotics and Intelligent Systems (GRITS) Lab at Georgia Tech have programmed a swarm of tiny mobile robots to perform Beethoven's Fur Elise on a simulated piano. Why would you want to teach a bunch of mini bots to play the piano? The researchers explain: "By solving the corresponding spatio-temporal routing problem, the smallest possible robot team is deployed in order to effectively 'play' the musical score, while minimizing the total distance travelled."

[ GRITS Lab ] via [ Gizmag ]


Automaton readers are also familiar with the Cyclocopter developed at the University of Maryland by Moble Benedict, Matthew Westerfield, Vikram Hrishikeshavan, and Prof. Inderjit Chopra. Instead of conventional helicopter blades, this flying robot uses cycloidal-rotors (cyclorotors). Its creators claim the mechanism has advantages such as higher aerodynamic efficiency and maneuverability and the ability to take-off and land vertically. The current model has a twin-cyclorotor and a horizontal tail rotor configuration, and in ther latest video the researchers demonstrate stable autonomous hover using a novel attitude control technique using differential RPM control of the rotors and thrust vectoring for rolling and yawing.

Thanks, Moble!


Nao is by far one of the coolest robots around. It can dance better than most of us, play soccer, tell stories, and perform comedy routines. It's used in research by robotics labs all over the world, and also by researchers and doctors to help kids in hospitals. But there's one place that we think Nao would have an even greater impact: schools. Several universities already use Nao in classrooms to teach robotics, AI, and computer science. The little humanoid, however, could play an important role in high school education (secondary school, as it's known in some countries). Nao could be used to make some math and physics concept more interesting to study. Some schools are already experimenting with this idea, but it would be great to see this happen on a larger scale. Imagine students equipped with tablets, prototyping electronic boards like the Arduino, 3D printers, and also robots in their classrooms! Almost makes me wish I could go back to school. Almost.

[ Aldebaran Robotics ]

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

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