Objective:Solve the problems of poor positioning accuracy and low grasping success rate of the Delta robot in food sorting, and improve the robot's flexible grasping ability.Methods:Based on the existing binocular vision and delta robot technology, a flexible grasping method of delta robot based on binocular vision was proposed. Zhang Zhengyou calibration method was used to calibrate the camera, the target was identified and located by Hough transform at the chord midpoint, and the delta robot was controlled to grasp the dynamic target according to PID tracking and grasping. The feasibility of this method was verified by analyzing the performance of single target sorting and multi-target sorting.Results:This method can accurately, quickly and stably grab the target dynamically (success rate was above 94.0%).Conclusion:The combination of binocular vision and delta robot can effectively improve the positioning accuracy of the robot and the success rate of sorting and grasping.