Robots aren’t supposed to make mistakes. But if they do, a team from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) and Boston University have developed a way to correct the robot’s actions by using a person’s electroencephalography (EEG) brain signals.

The human needs to wear an EEG cap that measures their brain signals. The system looks for brain signals called “error-related potentials” (ErrPs) that are generated when the brain notices a mistake has been made. As the robot indicates which choice it plans to make, the system uses ErrPs to determine if the human agrees with the decision.

The system works in real-time, classifying brain waves in 10-30 milliseconds. The system, which is being tested on Rethink Robotics’ Baxter, even make the robot feel embarrassed when it makes a mistake. The idea is to make robots a more natural extension of humans.

Paper: Correcting Robot Mistakes in Real Time Using EEG Signals

“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,” says CSAIL director Daniela Rus, who won the 2017 Engelberger Robotics Awards for Education. “A streamlined approach like that would improve our abilities to supervise factory robots, driverless cars and other technologies we haven’t even invented yet.”

The team’s next step is to refine the system so that it can handle multiple-choice and other complex tasks besides simple binary-choice activities, which is what you see in the video atop this page.

“As you watch the robot, all you have to do is mentally agree or disagree with what it is doing,” says Rus. “You don’t have to train yourself to think in a certain way – the machine adapts to you, and not the other way around.”

In addition to monitoring ErrPs, the team also detects “secondary errors” that occur when the system doesn’t notice the human’s original correction. “If the robot’s not sure about its decision, it can trigger a human response to get a more accurate answer,” the team says. “These signals can dramatically improve accuracy, creating a continuous dialogue between human and robot in communicating their choices.”

“This work brings us closer to developing effective tools for brain-controlled robots and prostheses,” says Wolfram Burgard, a professor of computer science at the University of Freiburg who was not involved in the research. “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.”