Myo Armband Provides Effortless Gesture Control of Robots, Anything Else

This gesture recognition system doesn't need any external sensors to work

3 min read
Myo Armband Provides Effortless Gesture Control of Robots, Anything Else

At ICRA last year, JPL presented a robotic control system called the BioSleeve, which is a sensor-packed bandage that wraps around your arm and lets you control robots with movements and gestures. It's essentially a gesture recognition system that works independently of any external sensors (like cameras or motion capture systems), meaning that you can use it in a variety of positions and in just about any location that you happen to be, like outside, or in space.

The problem with hardware like this is we all know that it's going to be a long long long long looong time before something that works in a lab at JPL finds its way onto our arms as consumers. But you know what? That's perfectly fine, because a Canadian startup called Thalmic Labs has its own wearable gesture sensing peripheral that's about to hit the consumer market, and we got to check it out last month at CES.

The Myo is built around eight EMG (electromyography) muscle activity sensors along with a nine-axis inertial measurement unit (that's three axes each for accelerometer, gyro, and magnetometer), meaning that you get forearm gesture sensing along with relative motion sensing (as opposed to absolute position). The EMG sensors pick up on the electrical potential generated by muscle cells, and with the Myo on your forearm, the sensors can read all of the muscles that control your fingers, letting them spy on finger position as well as grip strength.

Also somehow stuffed into the Myo armband (the final consumer version will be about half as thick as the developer version in the video) is a rechargeable lithium battery (good for "multi-day usage"), an ARM processor, Bluetooth 4.0 LE, a micro USB port for charging, and wireless compatibility with PCs, Macs, iOS, and Android. Open source APIs enable even more versatility.

For most users, getting the Myo to work will be as simple as slipping it on your arm and making gestures, a set of which will be preprogrammed into the device. To keep you from accidentally gesturing yourself into oblivion, there's a unique on/off gesture to enable or disable the armband. You'll be able to map gestures to commands on your computer just like a keyboard: in a video game context, for example, instead of using your mouse button to fire a gun, you can use your trigger finger. Or instead of hitting "R" to reload, you can raise your arm and make a physical gun reloading motion. For extra degrees of freedom, wear a second Myo on your other arm, too.

As for robotics, the big advantage of systems like Myo (or JPL's BioSleeve) is that it doesn't require external infrastructure or a controller that you have to hold onto, keep track of, and otherwise be careful with. With a wearable control system, you can keep it on all the time, and instantly activate it with a gesture. It's simple and intuitive and can be operated with a minimal amount of training, but at the same time, is versatile enough to control a wide variety of robots. But there's a trade-off: Neither the Myo or the BioSleeve might offer the extra-fine level of control that you can get with something more traditional (like a PS3 controller). As robotic autonomy increases, though, reliance on high-level commands will become the norm, and that's what things like the Myo are likely best at.

Thalmic is planning to ship consumer Myo units by the middle of this year, and you can pre-order them for $150.

[ Thalmic Labs ]

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