Adaptive Neural Network Control of Robot Based on a Unified Objective Bound

Abstract

In the conventional adaptive neural network control of robotic manipulator, the desired position of robot end effector is specified as a point or trajectory. In addition, it is usually difficult to guarantee the transient performance of adaptive neural network control system due to the initialization error of the weight of neural network. In this paper, a new control formulation is proposed for the adaptive neural network control of robotic manipulator, which unifies existing neural network control tasks such as setpoint control, trajectory tracking control, and trajectory tracking control with prescribed performance bound. The proposed method also includes a new adaptive neural network control scheme where the objective for the robot end effector can be specified as a dynamic region, instead of the desired position or trajectory. The stability of the closed-loop system is analyzed using Lyapunov-like analysis. Experimental results are presented to illustrate the performance of the proposed approach and the energy-saving property of the proposed neural network controller with dynamic region.