Automaton iconAutomaton

Soft Actuators Go From Squishy to Stiff (and Back Again)

Soft actuators are appealing for robotics because they’re cheap (made out of plastics or polymers and air), inherent compliant and relatively safe for humans to interact with, and able to adapt themselves to grip a wide range of objects. Being soft does tend to make them by definition bad at being hard, so for those times when you need an actuator with some stiffness, well, that’s just too bad.

Or is it?

Researchers at Technische Universitat Berlin led by Professor Oliver Brock have combined soft pneumatic actuators with a jamming system that results in a variable-stiffness actuator that’s soft when you want and hard when you want.

Read More

Robots Learn to Push Heavy Objects With Their Bodies, Just Like You

The payload of a robot is a well-defined number that usually refers to how much mass its actuators or mobility system can comfortably support. The payload of a human works in a similar way, except that sometimes we can cheat, by offloading the mass of an object to the ground, and moving it purely by overcoming friction and shoving it along. For very heavy objects, doing this involves using the weight and stability of our whole bodies as well as our muscles, and robots are learning to do this, too.

Read More

Video Friday: Aerial Manipulator, Car-Removal Robot, Robotic Limbs, and More From ICRA 2015

All this week, we’ve been at ICRA in Seattle. A bunch of you are probably here too, and if you’re not, we’re sorry, because it’s awesome. The last few days we’ve bounced around as many different sessions as we can, and we have all kinds of amaaazing things to write about: what you’ve seen so far is just the start.

Try as we might, we can’t squeeze everything into its own article, so for Video Friday this week, we’re going to post a heaping stack of ICRA videos along with their accompanying abstracts. For you impatient types, we’ll return to normal Video Friday not next week (because it’ll be the first day of the DARPA Robotics Challenge Finals), but the week after, if we’re still alive by then.

If you have any questions about these videos, let us know: we have access to all of the accompanying papers, and if we can’t answer your question ourselves, just about all of the authors will be within (non-creepy) grabbing distance for most of today.

Read More

Self-Healing Actuators Make Breaking Your Robot No Big Deal

Robots tend to spend a lot of the time broken. This isn’t just because they break a lot (although they do break a lot), but also because they’re usually difficult and often expensive to fix quickly. Electronics in general is also difficult and expensive to fix, which is why we have fuses: sacrificial components that take one for the team when something goes wrong. At ICRA yesterday, we saw a similar idea intended to protect actuators from damage. This mechanical fuse takes things one step further, however, by being able to heal itself, making a broken robot just like new in a matter of hours.

Read More

Origami Robot Folds Itself Up, Does Cool Stuff, Dissolves Into Nothing

At ICRA 2015 in Seattle yesterday, researchers from MIT demonstrated an untethered miniature origami robot that self-folds, walks, swims, and degrades. That’s the title of their paper, in fact, and they delivered on all of those promises: from a flat sheet with a magnet on it, their robot folds itself up in just a few seconds, is immediately ready to zip around on land or water driven by magnetic fields, and then when you’ve run out of things to do with it, drive it into a tank of acetone and it’ll dissolve. This is the first time that a robot has been able to demonstrate a complete life cycle like this, and eventually, it’ll be doing it inside your body.

Read More

Damage Recovery Algorithm Could Make All Robots Unstoppable

For the last three years, we’ve been watching as the hexapods created by Antoine Cully and Jean-Baptiste Mouret have been getting increasingly difficult to put out of action. Using an exceptionally clever algorithm, the robots have demonstrated that they can shrug off absurd amounts of damage, adapting within minutes to recover their mobility even if you chop a third of their legs off. 

Today, this research has made the cover of Nature, which is a Very Big Deal (at least if you’re a scholar), and it brings along with it some updates and even more potential for the future.

Read More

Clearpath Puts Baxter on Wheels, Announces Ridgeback Mobile Base

As capable and adaptable as Baxter is, it’s not a robot that’s well known for its mobility. You can get some wheels for it, but you’re still stuck pushing it around when you want it to move anywhere. Sensing an opportunity in the forthcoming age of mobile manipulators, Clearpath Robotics is announcing Ridgeback, an “omnidirectional development platform” designed to give Baxter, or any other research robot, some much-needed mobility.

Read More

Robotic Cockroach Launches Robotic Bird Off of Its Back

We’ve written before about the advantages of multi-modal robots: by combining two different forms of locomotion in one platform, you can take advantage of (say) the efficiency and endurance of a ground robot with the range and versatility of a flying robot. However, designing one robot that can walk and fly tends to be both complicated and inefficient, which is why hetergeneous robot teams are often more appealing. Instead of trying to cram every capability into one robot, you just use several different robots with different specializations and find some way of getting them to work together. Like this robotic cockroach that can serve as an aircraft carrier for a robotic bird.

Read More

Video Friday: Deep-Learning Robots, DRC Practice, and Drone Pilot Competition

Apologies for the light posting this week: the entire IEEE Spectrum team (both digital and print) was closeted away in meetings working on ways to better serve you, dear reader. Did we come up with some? Sure we did, but for now, they’re secret until we get them to work.

Leading the video news for today is research from UC Berkeley focused on teaching robots to learn tasks in ways that can be adapted to new situations, using a deep learning approach based on neural nets. The upshot is that it enables robots (like Berkeley’s PR2, named BRETT) to learn new tasks in a matter of hours and perform those tasks generally independently of their environment, all with a minimal amount of sensors.

This is stupendously important in two ways: first, it means that robots get significantly easier to teach, as opposed to requiring programming. And second, it means that robots are able to do useful stuff in useful environments, like your house as opposed to a robotics lab. Watch BRETT do his thing, and all the rest of our videos, starting right now.

Read More


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