A new feedback system developed at MIT enables human operators to correct a robot's choice in real-time using only brain signals. 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. Novel machine-learning algorithms enable the system to classify brain waves in the space of 10 to 30 milliseconds. The team focused on brain signals called "error-related potentials" (ErrPs), which are generated whenever our brains notice a mistake. As the robot indicates which choice it plans to make, the system uses ErrPs to determine if the human agrees with the decision. This system could be useful for people who can’t communicate verbally - a task like spelling could be accomplished via a series of several discrete binary choices.