Abstract: The lunar surface sampling and encapsulation mission of Chang’e 5 probe requires the use of a sampling manipulator and its terminal actuator to grip the lunar surface soil sample container. In order to overcome the adverse effects of the unstructured lunar surface environment on manipulator control and to solve the control problem of precise gripping sample container, a gripping decision system of sample container based on visual servo is proposed and designed. The system adopts the fixed position camera and the “eye in hand” camera to obtain the characteristics of the actuator at the end of the manipulator and the sample container, and the extended Kalman filter (EKF) algorithm is used to estimate the control parameters of the manipulator terminal actuator’s position and attitude, so as to eliminate the trajectory jitter of the control, and realize the accurate clamping of the sample container. Finally, through analyzing the on orbit data and images, the results show that the proposed visual servo control method is correct and effective.

Key words: Chang ’e 5 probe, Visual servo, Gripping control, Extended Kalman filter (EKF), Sampling &, encapsulation, Lunar surface soil sample container