Automaton iconAutomaton

German Robot Plays Pool, Throws Down Robot Pool Gauntlet

Well, it's inevitable now. RoboGames obviously needs to add a new event: robot pool. Willow Garage got their PR2 sinking balls as part of a week-long hackathon, and at ICRA, the Germans answered back with a similarly-sized dual arm robot able to pocket five balls in a row:

Thomas Nierhoff, a masters student at Technische Universität München (TUM), used a human-sized mobile robot with dual 7-DOF arms that's able to manipulate a pool cue similarly to how a human does. A camera above the table tracked the positions of the balls and helped the robot plan its shots, separating each into various difficulty thresholds to help the bot decide which it should take. It managed to nail most of the easier shots about 80% of the time, which isn't too shabby, and seems like it would probably make it competitive with the PR2.

It's a shame, then, that Germany is such a long way from California. But wait! It just so happens that there are several PR2s in Germany. And it also just so happens that one of them is right there at TUM, albeit in a different lab. Personally, I don't see how it would be possible not to set up a friendly little game, and if Rosie wants to get involved too, I'm all for that. Place your bets in the comments!

This robot was presented at ICRA in a paper entitled "Playing Pool with a Dual-Armed Robot" by Thomas Nierhoff, Omiros Kourakos, and Sandra Hirche, all with the Institute of Automatic Control Engineering at TUM.

[ TUM ]

Microdrones Film Confused African Wildlife

microdrones md4-1000 film african wildlife

It's a well known fact that animals from the Arctic to Africa have absolutely no idea what to think about robots. Taking full advantage of this phenomenon, Microdrones let one of their MD4-1000 quadrotors loose on safari in Kenya, and it set about capturing video like you've probably never seen before.

While I'm not one to spout propaganda about how robots are revolutionizing every aspect of our lives (okay, I totally am), this is an entirely new way of filming animals that's just beginning to be explored through trial and error. We're used to watching animals from afar through gigantic zoom lenses, but small flying robots offer the opportunity to get in the middle of things without causing too much of a ruckus, and this is just one of the first tentative stabs at a whole new world of footage that would do David Attenborough proud. And it's not just for animals, either: imagine flying one of these things into an erupting volcano.

It looks like these clips are part of a show that Microdrones is putting together for TBS Television Japan, but we'll make sure and let you know if it ever shows up online.

[ Microdrones ]

DARPA Concludes Nano Air Vehicle Program, We Wonder What's Next

The original concept, on left, and the final robot, on right

We've written a fair number of articles starting with the phrase "DARPA wants" followed by something that's nearly always entirely improbable and often borderline nutty. It's rare that DARPA actually gets exactly what it wants, but with their Nano Air Vehicle program, that seems to have happened.

As the above video shows, it was definitely not an easy process to make a life sized, fully controllable surveillance robot that's more or less indistinguishable for a hummingbird, but AeroVironment managed to pull it off. Of the technical goals and milestones that DARPA set out for the robot, it managed to meet all and exceed many:

  • Demonstrate precision hover flight within a virtual two-meter diameter sphere for one minute.

  • Demonstrate hover stability in a wind gust flight which required the aircraft to hover and tolerate a two-meter per second (five miles per hour) wind gust from the side, without drifting downwind more than one meter.

  • Demonstrate a continuous hover endurance of eight minutes with no external power source.

  • Fly and demonstrate controlled, transition flight from hover to 11 miles per hour fast forward flight and back to hover flight.

  • Demonstrate flying from outdoors to indoors, and back outdoors through a normal-size doorway.

  • Demonstrate flying indoors 'heads-down' where the pilot operates the aircraft only looking at the live video image stream from the aircraft, without looking at or hearing the aircraft directly.

  • Fly the aircraft in hover and fast forward flight with bird-shaped body and bird-shaped wings.

AeroVironment says that it would take a decade to make this robot ready for deployment, but DARPA doesn't just hand out piles of cash to make cool stuff for no reason. There's a future here, whether or not we hear about it immediately, so just make sure to give hummingbirds a second look from now on.

[ Nano Air Vehicle Program and AeroVironment ]

Juggling Robots Get Fancier

UPDATE: The Czech roboticists updated their video with labels and a slow motion sequence, making it easier to see how the robot juggles three, and then four, and finally five balls, and also how it drops one ball at the end.

Robots are especially good at juggling. This is not to say that juggling is a particularly easy problem to tackle, because it's not, but it's a fun excuse to design a robot to demonstrate precision control and high-speed object tracking. The robot in the video above, for example, was built by three masters students from the Department of Control Engineering at the Czech Technical University in Prague. It uses three linear motors, including one for each arm and a third for a central ball deployment system, along with two pivoting "hands" to catch and toss up to five balls at once. The feedback loop is closed using data from encoders built in the motors, and a high-speed camera helps to fine-tune the trajectories of the balls.

You don't actually need a high-speed vision system to juggle, though. We first met the "blind juggler" with it's fascinating passively adaptive single ball juggling capability back in 2009. Since then, it's gotten a fairly significant upgrade over the past year or so, which its designer, Philip Reist from ETH Zurich, presented last month at ICRA:

Remember, there's no sensing going on here. No cameras, no force sensors, no microphones, nothing at all. The robot is able to juggle without having any idea what the ball is doing, simply by virtue of the level of feedback control inherent in its design. It's really quite beautiful... You know, from a mechanical perspective. You can read about how this is possible here.

The Pendulum Juggler robot was presented in an ICRA paper unsurprisingly entitled "Design of the Pendulum Juggler," by Philipp Reist and Raffaello D’Andrea from the Institute for Dynamic Systems and Control, ETH Zurich, Switzerland.

[ Five Ball Juggler ] via [ Hack a Day ]

[ Blind Juggler ]

Gecko-Inspired Window Washing Robot is Powered Entirely by Water

gecko-inspired climbing cleaning robot

Batteries and motors are heavy and inefficient in that they expend a significant percentage of their power just moving their own mass. This is especially apparent in climbing robots, which spend most of their time hoisting themselves vertically upward. Researchers from Zhejiang University in China have developed a robot that's capable of sticking to smooth surfaces, climbing vertically, and washing windows, relying almost entirely on water pressure:

To function, the robot gets connected to a faucet with a loop (a really long loop, if necessary) of hose. As water flows through the hose, its pressure accomplishes several things. First, the water passes through fluidic vacuum generators, which use that same Bernoulli principle that those supersonic jet grippers take advantage of to turn the motion of a fluid into a vacuum. This allows the bot's feet to stick to any smooth surface.

Then, the water is routed through a solenoid valve to a piston that's attached to the "spine" of the robot. The inspiration for this design was the gecko, arguably the best wall-climber in existence, and the upshot of it is that the robot can climb relatively quickly (constrained only by the time it takes to establish a solid vacuum) and turn in either direction with just one single spinal actuator. And of course lastly, the water is squirted out at the end of the robot's arm to do the actual washing.

The robot does currently use a very small battery to power the wireless communication system and to trip the servo to control the direction of motion, but it's certainly possible that a small turbine could run all that stuff instead. The present design is able to lift twice its body weight in payload using just standard tap water pressure, and future versions might be able to conduct inspections, fight fires, paint, or even perform repairs.

This robot was presented in an ICRA paper entitled "A Gecko Inspired Fluid Driven Climbing Robot," by Jilin Liu, Zhangqian Tong, Jinyuan Fu, Donghai Wang, Qi Su, and Jun Zou of the Institute of Mechatronic Control Engineering at Zhejiang University, China.

This Is What PR2s Do for Fun

People have programmed PR2s to do all sorts of fun things, but most of these things are human-y fun, not robot fun. Georgia Tech has built what they're calling a "PR2 Playpen," which is designed to keep their PR2 busy (and entertained?) while teaching it valuable life skills at the same time.

Robots tend to have difficulty when it comes to interacting with unfamiliar objects. We've seen some clever ways to at least partially circumvent this, but to perform best, robots need to be taught how to pick things up and then practice with different algorithms to find what works. This is rather time consuming, and the PR2 Playpen is designed to help automate the task. A conveyor belt drops random objects one at a time into a workspace in front of a PR2, which studies them and attempts to pick them up. The robot can autonomously evaluate different controllers and strategies, while collecting data to improve its algorithms at the same time.

The other benefit to this system is that the robot can keep itself busy and productive without any human supervision. There's a limited amount of time that research labs can keep their PR2s hard at work, and I bet that even the busiest lab would have trouble actively using their robots more than 50 percent of the time, if that. With the PR2 Playpen, the robot can spend all night every night teaching itself to get better at grasping things, and thanks to ROS, all robots everywhere will be able to benefit from what it learns.

[ Georgia Tech Healthcare Robotics Lab ]

Little Amphibious Tumbling Robot Tackles Tough Terrain

As components get smaller, robots are getting smaller as well, but in general small robots have big problems with obstacles and rough terrain. We've seen a variety of examples of robots that have found ways around this problem (most notably robots that jump or fly), but this might be the most creative yet: it's a robot that tumbles.

By "tumble," I mean that this robot is designed to move by flipping itself end-over-end in a somersaulting motion. It's called Aquapod, and it was created by the University of Minnesota's Center for Distributed Robotics. Aquapod uses two carbon fiber arms connected to servo motors that can rotate continuously to, as the researchers put it, "induce a tumble."

The reason that it's called Aquapod, incidentally, is that it's also waterproof, with the ability to control its buoyancy, floating or sinking or even just chilling out somewhere in the water column. This enables it to operate quite happily on land as well as in water, where it can sink itself to the bottom of lakes and streams and tumble along the bottom.

Aquapod might not be the fastest robot ever, but it has no trouble tumbling over slippery surfaces, through sand, and towards skeptical ducks. The offset arms help to give it more degrees of freedom to escape from vegetation and other obstacles, trading a little bit of efficiency for increased robustness.

The general intent is for Aquapod to be used in water monitoring or aquatic sensor deployment, where bunches of them can team up to float down rivers, sinking and floating and deploying sensors and taking measurements as they go. It would even be possible to stick one underneath an iced-over lake to monitor fish populations during the winter, where the robot could move around by "inverse tumbling" on the underside of the ice while upside-down.

Next up will be to work in solar power along with autonomous control for long-duration research. Even without any of that stuff the robot is still a very promising platform, though, since it's estimated to cost only about $2,000 to build.

Aquapod was presented in an ICRA paper entitled "Aquapod: Prototype Design of an Amphibious Tumbling Robot," by Andrew Carlson and Nikos Papanikolopoulos from the Center for Distributed Robotics at the University of Minnesota.

Robot Uses Supersonic Jets of Air to Stick to Almost Anything

There are all kinds of ways to stick to a surface, but one of the simplest is to use a gripper that operates on the Bernoulli principle. All the Bernoulli principle says is that as a liquid moves faster, its pressure decreases. For the purpose of a robotic gripper, air counts as a fluid, and if you squirt air out around the edges of a circular gripper fast enough, it'll start to generate a vacuum force that's strong enough to grab things without the surface of the gripper actually needing to touch them. The major upside of this technique is that you get a non-contact vacuum grip, so it's useful for grabbing stuff that's sterile or fragile.

Image via
Image: Bosch Rexroth AG

While Bernoulli grippers are fine for picking up things, they're not generally strong enough to enable a robot to support its own weight, much less climb. A research group from the University of Canterbury in New Zealand has developed a supersonic version of the Bernoulli gripper that's five times stronger than the conventional version, which is enough to allow a robot to climb on a bunch of different surfaces. And when you're watching this video, keep in mind that unlike pretty much every other climbing robot in existence, the grippers on this robot aren't touching the wall:

The geometry of the new type of air gripper (or non-contact adhesive pad, abbreviated NCAP) that this robot uses has been carefully designed to use a tiny little gap (a mere 25 μm in size) to force the airflow to go supersonic. Or more precisely, Mach 3. This doesn't require an increase in airflow or in pressure, it's all done with the geometry of the gripper itself compressing the airflow and speeding it up:

This airflow creates a low pressure vortex inside the gripper which provides the actual adhesion force, and in testing on the robot, this supersonic gripper is able to support five times as much weight as a conventional Bernoulli gripper, all without using any additional air volume or pressure.

As for the robot itself, it may be used for industrial inspections. The supersonic non-contact grippers will be available in "some months" for "a few hundred dollars," the researchers say.

The robot was presented in an ICRA paper entitled "An Investigation into Improved Non-Contact Adhesion Mechanism Suitable for Wall Climbing Robotic Applications," authored by Matthew Journee, XiaoQi Chen, James Robertson, Mark Jermy, and Mathieu Sellier.

ICRA 2011 Expo Gallery

While most of ICRA was devoted to research presentations, there was a lively expo floor stuffed with robots that would be from all corners of the globe, if a globe had any corners. We're nowhere near finished with our coverage of the research, but for today, enjoy this gallery of pics from the expo:

Guarding the entrance to the expo hall were Yaskawa's light saber dueling robots, which as far as I can tell were battling with each other non-stop for five days straight. Obviously, they'd had lessons.

Adept is now selling the AQUA2 research robot, which is a commercial derivative of the RHex platform designed for underwater operations. 

Also from Adept was this intelligent robot kiosk, which incorporates a touchscreen display on a mobile base with autonomous navigation.

The Shadow C6M Smart Motor Hand is touted as the most advanced dextrous robot hand in the world, boasting 24 movements which allow for direct mapping from human hand motions onto the robot hand.

Willow Garage managed to ship a PR2 all the way to Shanghai in a crate, where it immediately (well, almost immediately) got busy picking up squishy turtle toys and putting them down again. 

The reason for PR2's turtle toys was all the publicity surrounding the recent debut of TurtleBot, which took part in an impromptu educational robot parade along with Kuka's youBot and Aldebaran Robotics' Nao

DARwIn-OP kept itself busy all week kicking a red ball around and forcing people to dodge out of the way of its exceptionally determined object-tracking algorithms.

Looking for a robot to do something dirty or dangerous? Shanghai's own xPartner Robotics Company has you covered.

TurtleBot may not be the fastest robot on the block, but its spacious upper deck is good for riding around on, as Nao discovered.


This is actually one of the very first production versions of the Kuka youBot. Pretty sexy, even in orange. 

Stay tuned for more ICRA coverage

PR2 Learns to Read, Can't Pronounce 'Robot' (UPDATE: Yes I Can, Says PR2)

UPDATE: Menglong Zhu, the UPenn researcher who taught their PR2 robot to read, contacted us to say that the robot, named Graspy, took issue with our headline. Graspy claims it can pronounce "robot" and sent us the audio to prove:

Teaching a robot to read out in the wild is no easy task, thanks in large part to the propensity of graphic designers (along with us normal people) to use a bewildering number of different fonts and colors to better communicate creative vision, mood, or just general boredom with Helvetica.

The University of Pennsylvania's GRASP Lab has conquered these factors, along with such things as variable lighting and distance, and has gotten their PR2 (named "Graspy") to wander around, reading things non-stop in a monotone and perhaps slightly confused voice. This newfound literacy will be available for download for both PR2s and generalized ROS platforms, which means that you can give your robot a huge brain upgrade and vastly increase its interactive capabilities with just a few simple clicks.

Two questions remain unanswered, though: can it read Wingdings, and will it, on principle, read something written in Comic Sans?

[ GRASP Lab ]


PR2 Robot Can Scan And Bag Your Groceries
Wed, May 11, 2011

Blog Post: Stanford University has their PR2 picking up items in a checkout line, scanning them, and putting them in a bag for you

How Robots Can Learn From Your Pathetic Failures
Wed, May 18, 2011

Blog Post: Getting a robot to do what you want is never an easy task, especially if you can't even do the task yourself

Lingodroid Robots Invent Their Own Spoken Language
Tue, May 17, 2011

Blog Post: These little robots make up their own words to tell each other where they are and where they want to go

Awesomely Bad Ideas: Teaching a Robot to Sword Fight
Fri, May 13, 2011

Blog Post: Georgia Tech has given a robot a sword and told it that humans are out to get it, all in the name of safety



IEEE Spectrum's award-winning robotics blog, featuring news, articles, and videos on robots, humanoids, automation, artificial intelligence, and more.
Contact us:

Erico Guizzo
New York, N.Y.
Senior Writer
Evan Ackerman
Berkeley, Calif.
Jason Falconer
Angelica Lim
Tokyo, Japan

Newsletter Sign Up

Sign up for the Automaton newsletter and get biweekly updates about robotics, automation, and AI, all delivered directly to your inbox.

Load More