Grasping and Positioning Control of Production Line Handling Manipulator under Visual Proofreading Constraints
In order to improve the low grasping and positioning control accuracy of production line handling manipulator caused by random vibration,noise and other confounding existing in intelligent production line environment,which affects the sensor accuracy of manipulator,a research on grasping and positioning control method of the production line handling manipulator with intelligent visual constraints is proposed.The movement process of the production line handling manipulator is analyzed and the problems that the manipulator needs to determine the position of the target object during grasping operations are comprehended.With the improved YOLOv2 model,the position of the object ready for transportation is identified and its size is estimated.The improved K-means clustering algorithm is applied to estimate the relative distance between the object to be moved and the robotic arm through the clustering process to remedy the drawbacks of sole reliance on sensors.A PLC controller is designed to achieve positioning control of the robotic arm,and with the introduction of cerebellar model neural network,the motion control ability of the human cerebellum is simulated and the PID control algorithm is optimized,which enable the robotic arm to be more stable and accurate in grasping and positioning control.The experimental results show that the proposed method has strong anti-interference ability,high accuracy and good grasping and positioning control efficiency for the production line handling robot arm.
production line handling manipulatorPLC controllerPID control algorithmcerebellar model neural networkgrab positioning control
万方数据
维普
