They are not quite psychic yet, but the machines are better at reading your mind. Researchers have invented a new noninvasive method for recording brain activity patterns and use them to direct a robot. Scientists hope that technology will give "locked in" patients-those too disabled to communicate with the outside world ability to interact with others and even give the illusion of being physically present, or "telepresent" with friends and family.
Back brain-machine interface systems allowed people to control robots, sliders, or prostheses with conscious thought, but they often take a lot of effort and concentration, says José del R. Millán, a biomedical engineer at the Ecole Polytechnique Fédérale de Lausanne (EPFL) in Switzerland, which develops brain-machine interface systems that do not require to be implanted in the brain. the the objective of Millán is to make the control easier than driving a car on a road. a partially autonomous robot would allow a user to stop focusing on the tasks that he or she would normally unconsciously, as following a person or avoid running into walls. But if the robot encounters an unexpected event and needs to make a split second decision, the thoughts of the user can replace the artificial intelligence robot.
To test their technology, Millán and his colleagues have created a robot telepresent by modifying a commercially available bot called Robotino. The robot looks a bit like a platform on three wheels and can avoid obstacles on its own using infrared sensors. On top of the robot, the researchers placed a laptop running Skype, an audio and video Internet chat system, a wireless Internet connection. This allowed the human controller to see where the robot was going, and because the laptop also showed a video of the user, he allowed others to interact with the user as if the user was really there. The user also wore a small cap of electroencephalogram (EEG) electrodes, which measured brain activity. This system translates the EEG signals in the navigation instructions and transmits them in real time for the robot.
EEG patterns for movement and navigation are similar from person to person and group Millán has shown that after a little practice, a healthy person can share control with the robot with very little effort. But would a bedridden patient, who has not used its members for years, have the same pattern of brain waves and be able to control the robots as effectively?
The researchers recruited two patients whose lower body was paralyzed and had been bedridden for 6 or 7 years. The researchers trained the patients to control the robot for 1 hour per week for 6 weeks. With instructions transmitted via a wireless connection, patients should not leave the hospital and were able to control the robot in the laboratory at EPFL Millán, 100 kilometers. At the end of the training period, the researchers asked subjects to drive the robot to different objectives, such as furniture, people, and small objects around the lab for 12 minutes.
The disabled patients performed as well as healthy subjects, Millán and colleagues report this week at the IEEE Engineering in Medicine and Biology Conference Society in Boston. When the researchers turned off the shared control, forcing topics to focus continuously on the control of the robot, the subjects took a lot longer to navigate the maze when they shared control.
Millan said he was not terribly surprised that disabled people can control the robot, which previous research using brain scans showed that even patients who have been paralyzed since birth can imagine yet moving their limbs. But he was surprised how quickly they learned. He now hopes to involve more bedridden patients, including locked-in patients in the study. He also sees future applications for the brain-machine interface shared control, such as changes to allow a user to control a prosthesis or a wheelchair. Researchers can possibly add an arm current telepresent robot to enable it to grasp objects.
Neuroengineer Jose Carmena of the University of California, Berkeley, said the approach of Millán "a lot of novelty" in the way it integrates both natural and artificial systems. There are a few drawbacks he said, in a system that uses a hat instead of a device implanted directly in the brain, such as background signals that the cap can pick up. But for this application, he says, it is "a interesting avenue for telepresence. "
Millán said the bedridden patients were delighted to participate in the study. "This opens a new possibility for the families," he said, which could interact with their bedridden loved ones on a video connection without having to sit at a computer. But would the disabled patients families are creeped out by a follow robot in the kitchen while they make dinner? "well, that's something we're going to ask," he said.
0 Komentar