Research on intrinsic motivation of robot based on central nervous system

According to the anthropopathic characteristics of the robot, this paper puts forward a central nervous system model based on the basal ganglia, and studies the working cooperation among cerebellum, basal ganglia, cerebral cortex and other nerve apparatus, so that the perceive model about a central nervous system is established. The perceive model mostly consists of cerebellum, basal ganglia and cerebral cortex, thereinto, the cerebellum realizes sensorimotor mapping from states to actions by supervised learning; and the basal ganglia implements probabilistic choice based on operant conditioning principle to actions using action forecast evaluation results; moreover, the cerebral cortex receives and sends useful information to the basal ganglia and cerebellum, consequently, the closed feedback loop of a central nervous system is formed. This paper describes the concrete structure, function and arithmetic about the central nervous system model based on the basal ganglia, and performs some simulation experiments on the two-wheeled robot. The results reappearance the self-learning ability and movement balance skill of the robot like human, and indicate that this model has the better perceive characters and robustness.