University of Essex researchers have developed a simulator in which pairs of brain-computer interface (BCI) users had to steer a craft toward the exact center of a planet by thinking about one of eight directions.
Brain signals representing the users' chosen direction, as interpreted by the machine-learning system, were merged in real time and the spacecraft followed that path. The simulation flights were 67 percent on target for a single user, but 90 percent accurate for two users.
The researchers say combining the signals removes the random noise that accompanies electroencephalography signals. "When you average signals from two people's brains, the noise cancels out a bit," says Essex's Riccardo Poli.
The method also can compensate for a lapse in attention. "When there are two users, a lapse by one will not have much effect, so you stay on target," Poli says.
He notes their research also might help lead to a time when groups of people linked to BCIs could work together to control complex robotic and telepresence systems, including those in space.
From New Scientist
View Full Article
Abstracts Copyright © 2013 Information Inc., Bethesda, Maryland, USA
No entries found