Redundant mechanical arm repeating movement plan-oriented final-state network optimization method

Abstract

The invention relates to a redundant mechanical arm repeating movement plan-oriented final-state network optimization method which comprises the following steps of (1) determining an expected target trajectory r*(t) and an expected closed joint angle theta * (0) of a redundant mechanical arm end effector; (2) designing a final-state attraction optimization index, and forming a mechanical arm repeating movement planning scheme, wherein the initial joint angle during the actual movement of a redundant mechanical arm can be assigned at will, and the end effector is not required to be located on the expected trajectory; presetting the initial joint angle theta (0) during the actual movement of the redundant mechanical arm, adopting the theta (0) as a movement initial point, and forming a repeating movement planning scheme with a final-state attraction optimization characteristic; (3) building a final-state network model of a limited value activation function, and using a final-state network for solving a time-varying matrix equation; and (4) using a result obtained through solving for controlling each joint motor so as to drive the mechanical arm to execute the task. The invention provides the redundant mechanical arm repeating movement method with high accuracy and finite time convergence.

Description

technical field [0001] The present invention relates to repetitive motion planning and control technology of redundant mechanical arms, in particular, to a final state attraction optimization performance index, inverse movement of redundant mechanical arms under the condition that the initial position of each joint angle of the mechanical arm deviates from the expected trajectory Learn how to solve. Background technique [0002] Manipulators have always been a research hotspot in the field of robotics. A robotic arm refers to a mechanical device with an active end. Its end tasks include handling, welding, painting, and assembly. It has been widely used in industrial manufacturing, medical treatment, entertainment services, fire protection, military, and space exploration. According to the degree of freedom (Degrees-of-Freedom, DOF), the manipulator can be divided into a redundant manipulator and a non-redundant manipulator. A redundant manipulator is one that has more DOF ...

AI Technical Summary

Problems solved by technology

[0012] In order to overcome the shortcomings of the existing final state network optimization methods that do not have finite time convergence, slow convergence speed, and low convergence accuracy, in the present invention, a recursive neural network with finite time convergence performance is used to solve time-varying problems

Images