Bionic Learning Algorithm Based on Skinner's Operant Conditioning and Control of Robot

Abstract

Aiming at the problem about the movement balance control of two-wheeled self-balancing mobile robot, a learning algorithm that it is made up of BP neural network and eligibility traces based on the operant conditioning theory is put forward as a learning mechanism of the two-wheeled robot. The algorithm utilizes the characters of eligibility traces about quicker learning speed, higher reliability and ability in resolving effect about delay, so that the two-wheeled robot can obtain the movement balance skills of controlling like a human or animal by interacting, studying and training with unknown environmental, and realize the movement balance control of the two-wheeled robot by using the complex learning algorithm. Finally, a simulation experiment is done and the simulation results show that a learning mechanism of the complex learning algorithm can embodies the stronger skills of self-learning and abilities of balance control of the robot, and it also has the higher research significance in theory and the application value in project.