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

Full-state constraint rigid mechanical arm safe and reliable control method based on defining learning

A control method and a technology to determine learning, applied to manipulators, program-controlled manipulators, manufacturing tools, etc.

Active Publication Date: 2017-09-15
SOUTH CHINA UNIV OF TECH
View PDF4 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

On this basis, the present invention adopts the command filter and successfully solves the loop construction problem of the full-state limited rigid manipulator controller that may be generated by the traditional push-back design through the method of designing the compensation signal

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
  • Full-state constraint rigid mechanical arm safe and reliable control method based on defining learning
  • Full-state constraint rigid mechanical arm safe and reliable control method based on defining learning
  • Full-state constraint rigid mechanical arm safe and reliable control method based on defining learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0077] This embodiment provides a safe and reliable control method for a full-state limited rigid manipulator based on deterministic learning. The schematic diagram of the full-state limited rigid manipulator system is as follows figure 1 As shown, the overall control block diagram is as follows figure 2 As shown, its detailed implementation process includes:

[0078] Step 1. Establish the dynamic model and expected periodic trajectory of the full-state constrained rigid manipulator:

[0079]

[0080] where x 1 =[x 1,1 ,x 1,2 ] T is the angular position of the manipulator joint, x 2 =[x 2,1 ,x 2,2 ] T is the angular velocity of the manipulator joint, k 1 =[ k 11 , k 12 ] T , k 2 =[ k 21 , k 22 ] T , is a definite normal constant vector, M(x 1 ) is the inertia matrix of the manipulator system, V m (x 1,x 2 ) is the centripetal force matrix, G(x 1 ) is the gravitational vector, F(x 2 ) is the friction vector, τ is the control torque, M(x 1 ...

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 full-state constraint rigid mechanical arm safe and reliable control method based on defining learning. The method includes the following steps that a kinetic model and an expected period track of a full-state constraint rigid mechanical arm are established; a state converter is established; a non-affine model is configured into an affine model; the track error of the angle position of the converted mechanical arm is defined; a compensation track error signal is designed; a neural network controller based on defining learning is designed; and a static neural network controller based on experiential knowledge is established. By means of the method, it can be ensured that the track error is finally converged into a small neighborhood of zero, the mechanical arm can also be limited to run in a given safe work zone, a defining learning theory is adopted, uncertain closed-loop dynamic learning of the rigid mechanical arm is achieved, the converged neural network weight is stored, redundancy training is avoided due to the stored experience knowledge, the responding speed of a system is increased, and the tracking performance on the transient state process of the rigid mechanical arm is improved.

Description

technical field [0001] The invention relates to the field of full-state limited control of rigid manipulators, in particular to a safe and reliable control method for full-state limited rigid manipulators based on deterministic learning. Background technique [0002] At present, the robotic arm is the most widely used automatic mechanical device in the field of robotics. In addition to being mainly used in industrial manufacturing, its application devices can be found in commercial agriculture, medical rescue, entertainment services, military security, and even space exploration. . With the increase of application scenarios and the increase of task complexity, people have higher and higher requirements for the work efficiency and work quality of the robotic arm. At present, there are relatively few studies on the safety control of robotic arms. When the robotic arm interacts with people, its high rigidity is likely to cause harm to surrounding personnel. Therefore, it is n...

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
IPC IPC(8): B25J9/16
CPCB25J9/161B25J9/163B25J9/1651
Inventor 王敏邹永涛陈志广张燕雯
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