A Design Method of Variable-parameter Neural Solver for Motion Planning of Redundant Manipulators

A motion planning and design method technology, applied in the direction of manipulators, program control manipulators, instruments, etc., can solve unreasonable and unsatisfactory problems

Active Publication Date: 2020-04-28
SOUTH CHINA UNIV OF TECH
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

When the neural network is applied in the actual system, such a requirement is often difficult to meet
In addition, in the actual system, the reciprocal of the inductance parameter value and the capacitance parameter value is usually time-varying, especially in large-scale power electronic systems, AC motor control systems, power network systems, etc., the system parameters are set to fixed values is unreasonable

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A Design Method of Variable-parameter Neural Solver for Motion Planning of Redundant Manipulators
  • A Design Method of Variable-parameter Neural Solver for Motion Planning of Redundant Manipulators
  • A Design Method of Variable-parameter Neural Solver for Motion Planning of Redundant Manipulators

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0073] figure 1 Shown is the flowchart of the variable parameter neural solver design method of the example of the present invention; A kind of variable parameter neural solver design method for redundant manipulator motion planning comprises the steps:

[0074] 1) According to the task to be solved, the performance index and constraint conditions of the redundant manipulator are formalized, that is, the parameter index of the actual redundant manipulator is modeled, and the physical system model is established;

[0075] 2) converting the physical system model in step 1) into the time-varying quadratic programming standard form of the system;

[0076] 3) according to Lagrangian multiplier method, the quadratic programming model in step 2) is carried out optimal value optimization;

[0077] 4) converting the optimization information in step 3) into a standard time-varying matrix form;

[0078] 5) based on the matrix design deviation function equation in step 4);

[0079] 6) ...

Embodiment 2

[0127] In order to demonstrate the actual system design process, a 6-degree-of-freedom manipulator example is used to illustrate the problem: the MATLAB simulation experiment of this example is based on Kinova-JACO 2 Based on the lightweight bionic robotic arm. The total weight of this type of robotic arm is 4.4kg, and the maximum control distance is 77cm.

[0128] This type of redundant manipulator contains 6 degrees of freedom in total, that is, θ(t) contains 6 elements; the space dimension at the end of the manipulator is 3, including three directions of X axis, Y axis and Z axis; Its Jacobian matrix is The initial joint angle of the redundant manipulator is set as θ(0)=[1.675,2.843,-3.216,4.187,-1.710,-2.650]; the task execution cycle t is set to 8s; the parameter γ is set to Set at 50. In this example, in order to demonstrate the superiority of the variable parameter neural solver proposed by the present invention for redundant manipulator motion planning, the Kinova-...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a design method for a variable parameter neural solver for motion planning of a redundancy mechanical arm. The method comprises the following steps that the solved task is converted into a performance index and a constraint condition of the redundancy mechanical arm; the performance index and the constraint condition is converted into a time-varying quadratic programming standard form of a to-be-solved system; according to a lagrangian multiplier method, the optimal value in the time-varying quadratic programming standard form is optimized; optimized information is converted into a standard time-varying matrix equation form; a deviation function is designed according to the standard time-varying matrix equation form; according to the deviation function and a power type variable parameter recursion neural dynamics method, the variable parameter neural solver used for the motion planning of the redundancy mechanical arm on a real number field is designed; and a network state solution obtained through the variable parameter neural solver is the optimal solution for the motion planning of the redundancy mechanical arm system. The method has the advantages of being high in calculation speed, high in precision, fast in convergence, high in instantaneity, and good in robustness.

Description

technical field [0001] The patent of the invention belongs to the robot motion planning method, in particular to a design method of a variable parameter neural solver for redundant mechanical arm motion planning. Background technique [0002] Redundant manipulator refers to the degree of freedom (Degrees of Freedom, or DOF) of the manipulator is greater than the degree of freedom necessary to complete the task. With more degrees of freedom, the redundant manipulator can also complete additional tasks such as obstacle avoidance, joint angle limit constraints, and the singular state of the manipulator while completing various tasks of the end effector. The traditional method for solving the inverse kinematics problem of redundant manipulators is based on the pseudo-inverse method. This method has a large amount of calculation and cannot solve the inequality problem, which is greatly restricted in the actual application and operation of the manipulator. In recent years, a sol...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): B25J9/16
CPCB25J9/1664G05B2219/40511
Inventor 张智军孔令东
Owner SOUTH CHINA UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap