The incredible work undertaken by Artificial Intelligence geniuses has been backed by private funding from Boeing and the US National Science Foundation. <\/p>\n
A team from MITs Computer Science and Artificial Intelligence Laboratory (CSAIL) and Boston University that allows people to correct robot mistakes instantly with nothing more than their brains. <\/p>\n
Using data from an electroencephalography (EEG) monitor that records brain activity, the system can detect if a person notices an error as a robot performs an object-sorting task. <\/p>\n
Jason Dorfman, MIT CSAIL <\/p>\n
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 <\/p>\n
CSAIL director Daniela Rus <\/p>\n
The teams novel machine-learning algorithms enable the system to classify brain waves in the space of 10 to 30 milliseconds. <\/p>\n
While the system currently handles relatively simple binary-choice activities, the studys senior author says that the work suggests that we could one day control robots in much more intuitive ways. <\/p>\n
CSAIL director Daniela Rus told Express.co.uk: 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. <\/p>\n
Jason Dorfman, MIT CSAIL <\/p>\n
A streamlined approach like that would improve our abilities to supervise factory robots, driverless cars and other technologies we havent even invented yet. <\/p>\n
In the current study the team used a humanoid robot named Baxter from Rethink Robotics, the company led by former CSAIL director and iRobot co-founder Rodney Brooks. <\/p>\n
The paper presenting the work was written by BU PhD candidate Andres F. Salazar-Gomez, CSAIL PhD candidate Joseph DelPreto, and CSAIL research scientist Stephanie Gil under the supervision of Rus and BU professor Frank H. Guenther. <\/p>\n
Jason Dorfman, MIT CSAIL <\/p>\n
The paper was recently accepted to the IEEE International Conference on Robotics and Automation (ICRA) taking place in Singapore this May. <\/p>\n
Past work in EEG-controlled robotics has required training humans to think in a prescribed way that computers can recognise. <\/p>\n
Rus team wanted to make the experience more natural and to do that, they focused on brain signals called error-related potentials (ErrPs), which are generated whenever our brains notice a mistake. <\/p>\n
Jason Dorfman, MIT CSAIL <\/p>\n
As the robot indicates which choice it plans to make, the system uses ErrPs to determine if the human agrees with the decision. <\/p>\n
Rus added: As you watch the robot, all you have to do is mentally agree or disagree with what it is doing. <\/p>\n
You dont have to train yourself to think in a certain way - the machine adapts to you, and not the other way around. <\/p>\n
The work in progress identified that ErrP signals are extremely faint, which means that the system has to be fine-tuned enough to both classify the signal and incorporate it into the feedback loop for the human operator. <\/p>\n
In addition to monitoring the initial ErrPs, the team also sought to detect secondary errors that occur when the system doesnt notice the humans original correction. <\/p>\n
Scientist Stephanie Gil said: If the robots not sure about its decision, it can trigger a human response to get a more accurate answer. <\/p>\n
These signals can dramatically improve accuracy, creating a continuous dialogue between human and robot in communicating their choices. <\/p>\n
While the system cannot yet recognise secondary errors in real time, Gil expects the model to be able to improve to upwards of 90 per cent accuracy once it can. <\/p>\n
In addition, since ErrP signals have been shown to be proportional to how egregious the robots mistake is, the team believes that future systems could extend to more complex multiple-choice tasks. <\/p>\n
Jason Dorfman, MIT CSAIL <\/p>\n
1 of 9 <\/p>\n
Salazar-Gomez notes that the system could even be useful for people who cant communicate verbally: a task like spelling could be accomplished via a series of several discrete binary choices, which he likens to an advanced form of the blinking that allowed stroke victim Jean-Dominique Bauby to write his memoir The Diving Bell and the Butterfly. <\/p>\n
Wolfram Burgard a professor of computer science at the University of Freiburg who was not involved in the research added: This work brings us closer to developing effective tools for brain-controlled robots and prostheses. <\/p>\n
Given how difficult it can be to translate human language into a meaningful signal for robots, work in this area could have a truly profound impact on the future of human-robot collaboration.\" <\/p>\n
<\/p>\n
Read the original:<\/p>\n
Artificial intelligence experts unveil Baxter the MIND CONTROL ... - Express.co.uk<\/a><\/p>\n","protected":false},"excerpt":{"rendered":" The incredible work undertaken by Artificial Intelligence geniuses has been backed by private funding from Boeing and the US National Science Foundation. A team from MITs Computer Science and Artificial Intelligence Laboratory (CSAIL) and Boston University that allows people to correct robot mistakes instantly with nothing more than their brains. Continue reading