Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Nonlinear constrained primal-dual neural network robot action planning method

A nonlinear constraint, neural network technology, applied in the field of original-dual neural network robot motion planning, to overcome the problem of error accumulation and eliminate the problem of initial error.

Active Publication Date: 2018-05-11
SOUTH CHINA UNIV OF TECH
View PDF4 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Many recurrent neural networks have been applied to robot redundancy solving problems, but these neural network methods are mainly for robot motion planning problems with convex set constraints

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
  • Nonlinear constrained primal-dual neural network robot action planning method
  • Nonlinear constrained primal-dual neural network robot action planning method
  • Nonlinear constrained primal-dual neural network robot action planning method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0048] A primal-dual neural network robot action planning method under nonlinear equality constraints, comprising the following steps:

[0049] S1. Based on the expected task, the current state of the robot is obtained through the sensor and the inverse kinematics analysis of the robot trajectory is performed on the velocity layer using the quadratic optimization scheme. The performance index of the quadratic optimization scheme is the minimum speed two-norm and has A nonlinear equality constraint and a feasible set of robot joint angle constraints;

[0050] S2, converting the quadratic optimization scheme of the robot based on nonlinear constraints designed in step S1 into a standard form of a quadratic programming problem;

[0051] S3. Solving a standard quadratic programming optimal solution problem in step S2 is equivalent to solving a linear variational inequality problem;

[0052] S4, converting the linear variational inequality problem in step S3 into a solution to a p...

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 nonlinear constrained primal-dual neural network robot action planning method, which comprises the steps of acquiring a current state of a robot, and adopting a quadratic optimization scheme for carrying out inverse kinematics analysis on a robot track on a speed layer; converting the quadratic optimization scheme to a standard form of a quadratic planning problem; enabling a quadratic planning optimization problem to be equivalent to a linear variational inequality problem; converting the linear variational inequality problem to a solution of a piecewise linearity projection equation based on nonlinear equality constraint; utilizing a nonlinear constrained primal-dual neural network solver for solving the piecewise linearity projection equation; and transferringa solved instruction to a robot instruction input port, and driving a robot to carry out path follow. According to the nonlinear constrained primal-dual neural network robot action planning method provided by the invention, convex set constraint and non-convex set constraint can be compatible, a preliminary test error problem occurred in robot control is eliminated, and an error accumulation problem during a robot control process is solved.

Description

technical field [0001] The invention relates to the technical field of robot motion planning and control, in particular to a primal-dual neural network robot motion planning method with nonlinear constraints. Background technique [0002] In recent years, industrial robots and robotic arms have attracted more and more attention. In industrial manufacturing, medical rehabilitation, entertainment, military research and space exploration, robots have unique significance. In order to endow robots with more changing and flexible functions, the research on robot motion planning and control methods in practical applications plays a unique role. [0003] Robots are usually divided into non-redundant robots and redundant robots. A redundant robot is one that has more degrees of freedom than the minimum required to complete a task. With more degrees of freedom, redundant robots can perform additional secondary tasks. This also allows redundant robots to have greater flexibility an...

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 Applications(China)
IPC IPC(8): B25J9/16
CPCB25J9/16B25J9/1664
Inventor 张智军陈思远
Owner SOUTH CHINA UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com