Cognitive Labs

More on the theme of cognitive control of devices and objects...

Todd A. Kuiken, M.D., Ph.D. has pioneered a technique known as targeted muscle reinnervation (TMR), that allows a prosthetic arm to respond directly to the brain's signals, allowing wearers to open and close their artificial hands and bend and straighten their artificial elbows nearly as naturally as their own arms. Doctors first perform nerve transfer surgery to redirect nerves that go to the amputated arm to the patient's chest muscles. Then when the chest muscle contracts, an electromyogram picks up the electrical signal to move the prosthetic arm. So when the patient thinks 'close hand,"' the hand closes. Now the team wants to see if they can extract more information from the electrical signals produced by the nerves to provide a greater number of hand and arm movements. Theyd have been able to identify unique EMG patterns with 95% accuracy for 16 different elbow, wrist, hand, thumb, and finger movements. 'We've been able to demonstrate remarkable control of artificial limbs and it's an exciting neural machine interface that provides a lot of hope,' says Dr. Kuiken.

From

Labels: AI, control, intelligence, interface, man-machine

After you take a test, you will start to see this kind of interface...




Think of it as supply-chain optimization for your brain. Rather than nodes in a supply chain, we optimize nodes in the brain, where impedance collects.

Labels: interface, score, test

In the future, you may be able to control a robot with just your brain. Researcher Rajesh Rao demonstrated his brain-powered robot at the Brain-Computer Interface Conference in Whistler, Canada last week.

A human operator is able to control the robot by looking through two 'eyes' affixed to the front of the robot which display the robot's field of view on a computer monitor. A specially wired electrode cap is worn by the operator, who then sends commands to the robot to perform specific activities simply by thinking them.

Currently, only high-level simple commands are recognized; however, Rao believes that with deeper integration into the brain of the operator, increasingly complex commands will be possible.

Right now, the "thought commands" are limited to a few basic instructions. A person can instruct the robot to move forward, choose one of two available objects, pick it up, and bring it to one of two locations. Preliminary results show 94 percent accuracy in choosing the correct object.

Objects available to be picked up are seen by the robot's camera and conveyed to the user's computer screen. Each object lights up randomly. When the person looks at the object that he or she wants to pick up and sees it suddenly brighten, the brain registers surprise. The computer detects this characteristic surprised pattern of brain activity and conveys the choice back to the robot, which then proceeds to pick up the selected object. A similar procedure is used to determine the user's choice of a destination once the object has been picked up.

"One of the important things about this demonstration is that we're using a 'noisy' brain signal to control the robot," Rao says. "The technique for picking up brain signals is non-invasive, but that means we can only obtain brain signals indirectly from sensors on the surface of the head, and not where they are generated deep in the brain. As a result, the user can only generate high-level commands such as indicating which object to pick up or which location to go to, and the robot needs to be autonomous enough to be able to execute such commands."

Rao's team has plans to extend the research to use more complex objects and equip the robot with skills such as avoiding obstacles in a room. This will require more complicated commands from the "master's" brain and more autonomy on the part of the robot.


Press release: University of Washington

Labels: brain, interface, neuroscience, robot