SYSTEM AND METHOD FOR BRAIN MACHINE INTERFACE (BMI) CONTROL USING REINFORCEMENT LEARNING

摘要

A Brain Machine Interface (BMI) agent (1 10) is provided, that when operatively coupled to a subject during a mental task by the subject to control a prosthetic device (130), monitors one or more states (125) of neural activity of the subject, receives feedback associated with a behavior of the prosthetic device responsive to the control, learns a functional mapping between the mental task and the behavior in view of the feedback, and applies at least one control action (1 15) to the prosthetic device in accordance with the learning to control the prosthetic device for a targeted behavior.