Self-Learning of Robot Based on Skinner's Operant Conditioning
Ren Hong-ge, Ruan Xiao-gang · 2009
Aiming at the problem about the movement balance of two-wheeled self-balancing mobile robot, a learning mechanism of the operant conditioning theory based on recurrent neural network is adopted. The critical function is approached and the most superior choice to the action is made by recurrent neural network. Thus, the two-wheeled self balancing mobile robot can obtain the movement balance skills of controlling like a human or animal by forming, developing and improving gradually in terms of self-organization, and solve the control problem about the movement balance in the free-model external environment through learning and training. Finally, a simulation experiment is designed and compared in two states of disturbance and non-disturbance. The simulation results show that the Skinnerpsilas operation conditioning has a stronger ability of self-balance control and self-learning, and the robustness is good, and it also has the higher research significance in theory and the application value in project.