The present application relates to a closed-loop
brain computer interface-based
rehabilitation training method and apparatus, a device, and a storage medium. The method comprises: assessing
fine motor skills of a hand of a subject, and setting a target training force range on the basis of an assessment result; collecting electroencephalogram signals of the subject during actual hand-grasping or
motor imagery of hand-grasping, and collecting, by means of an electromyographic
signal collection module, electromyographic signals of the hand of the subject during hand-grasping; acquiring a movement intention force of the subject as an actual force; calculating a difference between the actual force and a target training force, and generating a control instruction on the basis of the difference to control a
rehabilitation training device; and providing, to the subject by means of the
rehabilitation training device, a haptic feedback force equal to the difference such that the subject adjusts the force of
motor imagery or actual hand-grasping, and generating a
training action for
rehabilitation training. In the present application, by integrating
brain computer interface technology with 3D games, the interactivity and enjoyment are enhanced for subjects, thereby improving the enthusiasm and initiative for training.