A study on the cognitive model of robot sensorimotor system1

Abstract

A cognitive model for sensorimotor system of self-rebalancing robot is presented based on Skinner operant conditioning principle. The model mainly consists of three parts, which are cerebellum, basal ganglia and cerebral cortex. In the model, the cerebellum realizes the mapping from sensorimotor states to actions by supervised learning mechanism, the basal ganglia decides the proper action based on the operant conditioning theory and the results of action forecast evaluation, and the cerebral cortex sends collected information to cerebellum and basal ganglia and consequently forms the closed loop feedback sensorimotor system. The structure, function and algorithm of the proposed model are presented in this paper. Simulation and experimental results on a two-wheeled robot demonstrate that this model has better cognitive characters and it enables the robot to master the skill of balance control in movement through self-learning.

Skill Learning for Intelligent Robot by Perception-Action Integration: A View from Hierarchical Temporal Memory

“…Cutsuridis and Taylor examined several neurocomputational mechanisms of visuomotor brain processes and coordinately integrated them to establish a neural framework for the visual grasping tasks [13]. A cognitive model [14] based on Skinner operant conditioning principle is designed for a robot to master the balancing skill. This model consists of cerebellum, basal ganglia, and cerebral cortex.…”