Final state network optimizing method for double-arm mechanical hand synchronous repeated motion planning

Abstract

A final state network optimizing method for double-arm mechanical hand synchronous repeated motion planning comprises the following steps that firstly, the expected target tracks r*L (t) and r*R (t) of a left end effector and a right end effector of a double-arm mechanical hand and the expected drawing angles theta * L (0) and theta * R (0) of a left joint angle and a right joint angle of the double-arm mechanical hand are determined; secondly, final state attraction optimization indexes are designed, and the double-arm mechanical hand synchronous repeated motion planning scheme is formed; thirdly, a final state network model of a limited value activation function is constructed, and the final state network is used for solving a time-varying matrix equation; and fourthly, the solved resultis used for controlling various joint motors, and mechanical arms are driven to execute tasks. A double-arm mechanical hand repeated motion method high in precision and capable of achieving finite time convergence is provided, and when the initial positions of the left joint angle and the right joint angle of the mechanical hand are set at will, it is guaranteed that the double-arm mechanical hand can still effectively finish the work task, and whether various joint angles are in the expected task tracks or not does not need to be considered.

Description

technical field [0001] The present invention relates to the synchronous repetitive motion planning and control technology of a dual-arm multi-link manipulator, in particular, to a limited-time convergence performance index and a manipulator inversion method under the condition that the initial positions of the joint angles of the left and right arms of the manipulator deviate from the expected trajectory. Kinematic solution method. Background technique [0002] Robot technology is widely used in various fields and plays a huge role in production and research. The manipulator of the robot, that is, the multi-link robotic arm, can move the end effector to a specified position in space and complete the corresponding trajectory task. According to the degree of freedom (Degrees-of-Freedom, DOF), the manipulator can be divided into a redundant manipulator and a non-redundant manipulator. Redundant manipulators possess more degrees of freedom than DOF required to accomplish a giv...

AI Technical Summary

Problems solved by technology

Due to the complexity of the calculation process, singular points in the solution process, and the limit of the physical joint angle of the manipulator, the most widely used pseudo-inverse formula cannot usually be applied to solve periodic repetitive motions, making it difficult to predict the trajectory of the dual-arm manipulator.

Images