Sliding mode position/force control for constrained reconfigurable manipulator based on adaptive neural network

This paper presents a novel position/force control approach for a constrained reconfigurable manipulators. First, the reduced-order dynamic model of the constrained reconfigurable manipulator system is formulated. Second, a sliding mode control method with adaptive neural network is proposed with guaranteed control performance. The neural network system is used to estimate the nonlinear parts that including the friction item and the constraint force of each joint. The stability of the close-loop system is proved by using the Lyapunov theory. Finally, the simulations are performed with two different configurations of reconfigurable manipulators to illustrate the advantage of the designed method.