This New Robot Can Self-Correct Its Mistake By Reading Human Brain

Posted: Mar 6 2017, 10:33am CST | by , in News | Latest Science News

 

This New Robot can Self-Correct its Mistake by Reading Human Brain
A new feedback system enables human operators to correct a robot's choice in real-time. Photo Credit: Jason Dorfman/MIT CSAIL
  • New Robot can Self-Correct itself Using Human Brain as an Interface
 

A new robot, developed by a team from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) and Boston University, by the name of Baxter can self-correct itself using the human brain as an interface.

Robots are modeled on human beings and their abilities. They need to understand on an information processing level what goes on within the human brain.

This may mean for now a sort of hybrid human-robot interface that allows both to meet each other halfway. This will also help in the full exploration of linguistic rules and the carrying out of tasks that are complex in nature.  

Robots that are an extension of humans are not a new idea. The concept of a cyborg has been around since the inception of the science of robotics.

Yet it is a chilling idea since we are dealing with human life here and like genetics which is a nascent science this too has many important ethical consequences which must be kept in mind.

A group of scientists from MIT managed to create a feedback loop that allows robots to correct their mistakes using human brains as an aid along the way. This is the first time such an attempt at a man-machine thinking interface has been made. 

Via an EEG monitor, the system is able to notice when a robot makes an error and thus it rectifies it at the drop of a hat. Brain waves are pigeon-holed within the time-span of 10 to 30 milliseconds and thus machine learning takes place through algorithms.

At present, binary choices are all the robot can accomplish in creating correct options via a human brain’s input. One fine day in the future, robots could actually earn the gift of intuition.

Imagine if a robot could spontaneously do something even if it is under the command of a human being. There would be no need for complex programming. Just a simple message or signal would be enough.  

A feedback system developed at MIT enables human operators to correct a robot's choice in real-time using only brain signals. Video: CSAIL

This methodology could lead to factory robots, driverless vehicles and myriad technologies that we haven’t even thought about up until now.

This novel humanoid robot has been named Baxter and its abilities are the stuff of which dreams are made of. It is almost like the coming of age of artificial intelligence.

One is reminded of Isaac Asimov’s laws of robotics. All that is needed to control this robot called Baxter is either an assent or dissent command from a human brain via an EEG.

The rectification process via which mistakes are undone is very complex yet the result is that it looks pretty simple. This is just the dawn of brain-controlled robots. We still have a long way to go in this Century of the Mind.  

This story may contain affiliate links.

Comments

The Author

<a href="/latest_stories/all/all/20" rel="author">Sumayah Aamir</a>
Sumayah Aamir (Google+) has deep experience in analyzing the latest trends.

 

 

Advertisement

comments powered by Disqus