A tracking control method, device and medium for a redundant robotic arm

Abstract

The invention discloses a tracking control method, device and medium of a redundant manipulator. The method includes: initializing the joint angle of the manipulator, the first CMAC network model and the second CMAC network model; obtaining the first joint angle and obtaining the target displacement ;According to the first joint angle and the target displacement, the first adjustment angle is obtained through the first CMAC network model; according to the first adjustment angle, the second joint angle is determined, and the movement of the mechanical arm is controlled according to the second joint angle; the third joint angle is obtained , and determine the target Jacobian matrix through the second CMAC network model according to the third joint angle; obtain the first position and the second position; update the first CMAC network model and the second CMAC network model according to the difference between the first position and the second position , take the third joint angle as the first joint angle, and then return to the step of obtaining the target displacement until the tracking control of the manipulator is completed. The technical scheme of the invention can deal with the interference brought by various uncertain factors to the model parameters.

Description

technical field [0001] The invention relates to the technical field of manipulator control, in particular to a tracking control method, device and medium of a redundant manipulator. Background technique [0002] When the number of driving degrees of freedom of the manipulator, such as joint angles, is more than that required to complete the task, the manipulator can be called a redundant manipulator. The extra degree of freedom makes the redundant manipulator have higher flexibility and safety, so this kind of manipulator has broad potential application prospects in various fields. [0003] The existing technology defines a CMAC cerebellum model connection control network. The input of the neural network includes the error between the target position at the next moment and the actual position of the end of the mechanical arm at the current moment, and the joint angle at the current moment. The output of the CMAC neural network is the joint angle adjustment. Quantitatively d...

AI Technical Summary

Problems solved by technology

However, the disadvantage of the existing technology is that it is necessary to know the accurate model information of the manipulator (such as the length of the connecting rod) to calculate the Jacobian matrix, and the existence of various uncertain factors will affect the accuracy of the model information, thereby affecting the control Accuracy of the program

Images