A Study on the Design of Error-Based Adaptive Robust RBF Neural Network Back-Stepping Controller for 2-DOF Snake Robot’s Head

Abstract

In this paper, we will propose the controller of a 2-DOF head in a snake robot for effective image data reading when the snake robot is driving, and present an error-based adaptive robust radial base function neural network back-stepping controller. The snake robot head system is a nonlinear system, and there are unmeasurable disturbances that occur while driving. To solve this problem, we use back-stepping controller and radial basis function neural network to compensate for unmeasurable disturbances to improve the steady state. In order to further compensate for the network approximation error that occurs during training or large signal changes, we use adaptive coefficients and error functions to approximate the network approximation error and design adaptive robust terms. Compared to the previous controller, the proposed controller can actively compensate for large signal changes and has the advantage of not generating residual input in a steady state. The proposed controller is based on Lyapunov function candidate to design an adaptive law and prove the system stability. The stability of the control system is proven through Lyapunov analysis and bounded. The proposed controller compared and verified the controller performance for two inputs through simulation and presented the efficiency of the controller.