EEG With Artificial Intelligence As Control Device

Abstract

Described herein is a system and method for controlling a computing system by an AI network based upon an electroencephalograph (EEG) signal from a user. The user's EEG signals are first detected as the user operates an existing controller, during which time the associated artificial intelligence (AI) system learns by correlating the EEG signals with the commands received from the controller. Once the AI system determines that there is sufficient correlation to predict the user's actions, it can take control of the computing system and initiate commands based upon the user's EEG signal in place of the user's actions with the controller. At this point, weights in the AI network may be locked so that further commands from the controller, or the lack thereof, do not reduce correlation with the EEG signals. In some embodiments, the AI network may initiate commands faster than the user would be able to do.

1 . A method of controlling a computing system that performs actions based upon input from a controller that represents actions of a user, comprising:
 receiving by an electroencephalograph (EEG) detector an EEG signal representing the brain wave activity of a user;   determining by an artificial intelligence (AI) network a likelihood that an action of the user can be predicted based upon the EEG signal;   when the likelihood that the action of the user can be predicted exceeds a predetermined threshold, initiating by the AI network an AI network input to the computing system that represents the predicted action of the user;   receiving at the computing system and the AI network an input from the controller representing the action of the user; and   updating by the AI network weights in the AI network to better correlate the received EEG signal with the input received from the controller.   
     
     
         2 . The method of  claim 1  wherein initiating by the AI network the AI network input to the computing system further comprises substituting by the AI network the AI network input for the controller input. 
     
     
         3 . The method of  claim 2  wherein initiating by the AI network the AI network input to the computing system further comprises initiating the AI network input to the computing system before the controller input would be received by the computing system. 
     
     
         4 . (canceled) 
     
     
         5 . A system for controlling a computing system that performs actions based upon input from a controller that represents actions of a user, comprising:
 an electroencephalograph (EEG) detector configured to receive an EEG signal representing the brain wave activity of a user; and   an artificial intelligence (AI) network configured to:
 determine a likelihood that an action of the user can be predicted based upon the EEG signal; 
 when the likelihood that the action of the user can be predicted exceeds a predetermined threshold, initiate an AI network input to the computing system that represents the predicted action of the user; and 
 update weights in the AI network to better correlate the received EEG signal with the input received from the controller. 
   
     
     
         6 . The system of  claim 5  wherein the AI network is further configured to initiate the AI network input to the computing system by substituting the AI network input for the controller input. 
     
     
         7 . The system of  claim 6  wherein the AI network is further configured to initiate the AI network input to the computing system before the controller input would be received by the computing system. 
     
     
         8 . (canceled) 
     
     
         9 . (canceled) 
     
     
         10 . (canceled) 
     
     
         11 . (canceled) 
     
     
         12 . (canceled)