This paper aims to improve the grasping precision of the packaging manipulator through a positioning method of the packaging manipulator based on fuzzy neural network. By combining laser rangefinder with industrial camera, the initial positioning of the target point and the attitude deviation could be achieved. A fuzzy neural network controller was designed to improve the accuracy of error compensation by adjusting the key parameters of PID control. Furthermore, fruit fly optimization algorithm was used to optimize the initial value of neural network controller, which could improve the performance of the control system. Finally, experimental research was carried out. The experimental results showed that the maximum absolute error could be reduced from 7.704 9 mm to 1.424 2 mm. The average absolute positioning error was reduced by about 82.5%. The execution efficiency of the manipulator was similar to that of the control group. The positioning method can greatly improve the positioning accuracy of robots and meet the requirements of packaging, chemical, food and other related industries.