[Engadget] Columbia University’s low-cost robotic arm is controlled by facial muscles, we go face-on (video)~Reviews~Evaluation

Engadget post time: May 05, 2013 at 07:04AM

Columbia University's low-cost robotic arm is controlled by facial muscles, we go face-on (video)

We’ve seen Emotiv’s Epoc headset control cars and trapeze acts, but now a small posse of students at Columbia University is teaching it how to control a robotic arm. The appendage, aptly named ARM for Assistive Robotic Manipulator, was envisioned as a wheelchair attachment to help the disabled. According to the team, the goal was to keep costs in the neighborhood of $5,000 since insurance outfits Medicare and Medicaid won’t foot a bill for assistive tech that’s much more than $10,000. To keep costs low, the crew built the limb from laser cut wood, and managed to keep the final price tag at $3,200. Since picking up EEG signals and interpreting them accurately can be tricky, the group says it settled on monitoring EMG waves, which are triggered by muscle movements, for additional reliability.

Lifting your eyebrows makes the device open its grip, clenching your teeth shuts it and moving your lips to the left and right twists the claw, while other motions are currently handled by using a PlayStation 2 controller. In the lab, the contraption has seven degrees of freedom, but it was reduced to five when we took it for a spin. It was hit or miss when this editor put the headgear on, between making sure facial gestures were spot on and the equipment’s attempts to pick up clear signals.

Filed under: ,


Reference source: Engadget


Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )


Connecting to %s