Tech
Brain-Controlled Robot Developed Could Do What Humans Are Thinking
Elaine Hannah
First Posted: Mar 08, 2017 03:00 AM EST
Scientists from Al laboratory at the Massachusetts Institute of Technology (MIT CSAIL) are now developing a robot that does not need a push button or command to perform tasks. It would just read human's mind by collecting data on brain activity and signals using the electroencephalography (EEG) monitor.
So, what if the robot read human's mind incorrectly? Using the electroencephalography (EEG), the robot can tell when it has made a mistake in an object-sorting task by detecting a change in the signals. The robot will be embarrassed and will blush when it is wrong. On the other hand, it could correct its actions when the human mentally agreeing or disagreeing with it.
CSAIL director Daniela Rus said this study indicates that they could one day control robots in much more intuitive ways. "Imagine being able to instantaneously tell a robot to do a certain action without needing to type a command, push a button or even say a word." She added that a streamed lined approach like that would improve human abilities to supervise factory robots, driverless cars and other technologies they have not even invented yet, as noted by Breaking News.
In addition, the new development could be applied to self-driving cars. If in case the robot makes an error, humans can use brain signals to automatically correct its error with the use of the so-called brain-computer interface (BCI). On the other hand, the method requires people to train with the BCI and even learn to restrain their thoughts so the robot could understand them.
The researchers added that this technology could make the communication with machines more intuitive and instantaneous. This could also be applied to supervising factory robots to controlling robotic prostheses.
Joseph DelPreto, a Ph.D. candidate at CSAIL who worked on the project, told Live Science that when humans and robots work together, a person basically has to learn the language of the robot, learn a new way to communicate with it, adapt to its interface. He further said that in this work, they were interested in seeing how a person can have the robot adapt to humans rather than the other way around.
See Now:
NASA's Juno Spacecraft's Rendezvous With Jupiter's Mammoth Cyclone
©2024 ScienceWorldReport.com All rights reserved. Do not reproduce without permission. The window to the world of science news.
More on SCIENCEwr
First Posted: Mar 08, 2017 03:00 AM EST
Scientists from Al laboratory at the Massachusetts Institute of Technology (MIT CSAIL) are now developing a robot that does not need a push button or command to perform tasks. It would just read human's mind by collecting data on brain activity and signals using the electroencephalography (EEG) monitor.
So, what if the robot read human's mind incorrectly? Using the electroencephalography (EEG), the robot can tell when it has made a mistake in an object-sorting task by detecting a change in the signals. The robot will be embarrassed and will blush when it is wrong. On the other hand, it could correct its actions when the human mentally agreeing or disagreeing with it.
CSAIL director Daniela Rus said this study indicates that they could one day control robots in much more intuitive ways. "Imagine being able to instantaneously tell a robot to do a certain action without needing to type a command, push a button or even say a word." She added that a streamed lined approach like that would improve human abilities to supervise factory robots, driverless cars and other technologies they have not even invented yet, as noted by Breaking News.
In addition, the new development could be applied to self-driving cars. If in case the robot makes an error, humans can use brain signals to automatically correct its error with the use of the so-called brain-computer interface (BCI). On the other hand, the method requires people to train with the BCI and even learn to restrain their thoughts so the robot could understand them.
The researchers added that this technology could make the communication with machines more intuitive and instantaneous. This could also be applied to supervising factory robots to controlling robotic prostheses.
Joseph DelPreto, a Ph.D. candidate at CSAIL who worked on the project, told Live Science that when humans and robots work together, a person basically has to learn the language of the robot, learn a new way to communicate with it, adapt to its interface. He further said that in this work, they were interested in seeing how a person can have the robot adapt to humans rather than the other way around.
See Now: NASA's Juno Spacecraft's Rendezvous With Jupiter's Mammoth Cyclone