Adaptive neural network control for uncertain MIMO robotic systems with time-varying delay and unknown backlash-like hysteresis

This paper proposes an adaptive neural network control scheme for uncertain nonlinearly multi-input-multi-output (MIMO) robotic systems with time-varying delay and unknown backlash-like hysteresis. The radial basis function neural network (RBFNN) is used to approximate the unknown nolinear function term of the uncertain MIMO robotic systems and the unknown backlash-like hysteresis nonlinearity. To compensate the time-varying delays and unknown backlash-like hysteresis, a new version of high dimensional integral Lyapunov function is presented to construct a Lyapunov-based adaptive control structure. By combining the high dimensional integral-type Lyapunov function and RBFNN, the global stability of the considered systems is ensured and the tracking errors converge to the origin. Simulation studies on 2-DOF robotic manipulators demonstrate the proposed method is effective.