Affiliations: [a] School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing, China | [b] College of Electrical Engineering, Hebei United University, HeBei, Tangshan, China
Correspondence:
[*]
Corresponding author:Tao Shi, College of Electrical Engineering, Hebei United University, 46 Xinhua Road, Tangshan 063009, Hebei, China. Tel./Fax: +86 03152592520; E-mail: [email protected]
Note: [1] This work is supported by NSFC (61203343).
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.
