Search

A position/force control strategy is proposed for flexible-joint manipulator(FJRM) with uncertainties and disturbances. The radial basis function neural network(RBFNN) is used to estimate and compensate the unknown parts of the robot model. According to backstepping technology, a position/force control scheme is proposed to reduce the effect of unknown parts and system disturbances, and to improve the force tracking accuracy while ensuring the position control accuracy. The uniformly bounded of all signals of the closed-loop system is proved by Lyapunov stability theorem. In the end, the proposed controller is applied to the two-rigid-link FJRM, and the simulation results show the effectiveness and feasibility of the proposed control scheme.