Position Control of a Four-Legged Walking Robot with Neural Network

In this paper, the use of a proposed recurrent neural network control system to control a four-legged walking robot is investigated. The control system consists of a neural controller, standard PD controller and the walking robot. The robot is a planar four-legged walking robot. The proposed Neural Network (NN) is employed as an inverse controller of the robot. The NN has three layers, which are input, hybrid hidden and output layers. The results show that the neural-network controller can, after sufficient training epochs, efficiently control prescribed positions of the stance and swing legs during double stance phase of gait cycle. The goal of the use of this proposed neural network is to increase the robustness of the control of the dynamic walking gait of this robot in the case of external disturbances. Also, PD controller alone and Computed torque method (CTM) control system are used to control walking robot’s position for comparison.