Abstract: The manipulator system is a multi-input and multi-output system with highly coupled，nonlinear dynamic characteristics and many unpredictable factors in its structure and parameters in practical work. A fuzzy neural network controller is designed for this system，and the parameters of FNNC are optimized by combining particle swarm optimization algorithm and BP algorithm. The simulation results show that the scheme has strong adaptability，stability， and anti-interference performance to the control system，and effectively solves the trajectory tracking problem of the manipulator.

Key words: manipulator, fuzzy neural network, particle swarm optimization algorithm