Control of uncertain constrained nonholonomic mobile manipulator based on recurrent neural network

In this paper, an adaptive recurrent neural network controller is proposed to control a class of constrained mobile manipulators with unknown dynamics. The system is subject to both holonomic and nonholonomic constraints. Recurrent Neural Network is considered to approximate the unknown dynamics. The proposed control strategy guarantees that the system motion asymptotically converges to the desired manifold while the constraint force remains bounded.