A redundant manipulator repetitive motion planning method based on Euler discrete periodic rhythm neural network

Abstract

The invention relates to a redundant manipulator repetitive motion planning method based on an Euler-type discrete periodic rhythm neural network, comprising the following steps: 1) adopting a quadratic optimization to analyze the inverse kinematics of the manipulator on an angular acceleration layer, and designing an angular acceleration Jacobian equation; 2) the angular velocity norm being equivalent to the angular acceleration norm, and a standard quadratic program scheme being established; 3) discretizing the periodic rhythm neural network by the Euler forward differential method to obtainan Euler-type discrete periodic rhythm neural network solver and use the solver to solve a standard quadratic programming scheme; 4) driving each joint motor through the controller to make the manipulator carry out repetitive motion planning from the initial position. The invention realizes the repetitive motion planning of the control redundant manipulator by using the Euler-type discrete periodic rhythm neural network, and the Euler-type discrete periodic rhythm neural network is easier to realize the suppression of periodic noise in hardware.

Description

technical field [0001] The invention relates to the field of redundant manipulator control, in particular to a redundant manipulator repetitive motion planning method based on Euler type discrete periodic rhythmic neural network. Background technique [0002] The redundant manipulator is a terminal active mechanical device with a degree of freedom greater than the minimum degree of freedom required by the task space. Its motion tasks include welding, painting, assembly, excavation, and drawing, etc. It is widely used in equipment manufacturing, product processing, and machine operations. and other national economic production activities. The inverse kinematics problem of the redundant manipulator refers to the problem of determining the joint angle of the manipulator given the end pose of the manipulator. When the task at the end of the redundant manipulator is a closed curve, each joint may not be able to return to the initial position. This phenomenon is called the joint ...

AI Technical Summary

Problems solved by technology

The redundant manipulator is also disturbed by periodic noise, which may cause the repeated motion planning of the redundant manipulator to fail

At the same time, continuous periodic rhythmic neural networks are not easy to implement in hardware

Images