Mechanical arm control method based on RBF neural network

A neural network and control method technology, applied in the field of robotic arm control, can solve the problem that parameters cannot be accurately predicted, and achieve the effect of being suitable for application and reducing workload

Inactive Publication Date: 2019-01-18
JILIN UNIV
View PDF6 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In actual engineering, the payload of the manipulator will change, and many parameters cannot be accurately predicted during the movement. The adaptive control method of the RBF network has the advantage of not requiring p

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
  • Mechanical arm control method based on RBF neural network
  • Mechanical arm control method based on RBF neural network
  • Mechanical arm control method based on RBF neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] see Figure 1 to Figure 12 Shown:

[0029] The mechanical arm control method based on RBF neural network provided by the present invention, its method is as follows:

[0030] Step 1. According to the working principle of each module of the human brain cognitive system and the mechanism of operating conditioning, a cognitive learning model mechanism of the manipulator is provided.

[0031] According to the working mechanism of each part of the human brain, a cognitive learning model with the cerebellum-basal ganglia operating conditioned reflex as the main learning mechanism is proposed, so that the agent system can continuously learn through the behavior network, the evaluation network and the role of the supervisor .

[0032] Such as figure 1 As shown, the behavioral network is jointly realized by the cerebellum module and the basal ganglia module, and it is a behavior of exploring the outside world, which is realized through probabilistic behavior selection. The c...

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 mechanical arm control method based on an RBF neural network. The method includes the steps of firstly, providing a cognition learning model mechanism of a mechanical arm; secondly, putting forward a behavior cognition model based on cerebellum-basal ganglion and a hybrid learning algorithm; thirdly, establishing a mathematical model for the mechanical arm to autonomouslylearn through the artificial neural network and a reinforcement learning method; fourthly, establishing a mechanical arm imitation experimental model in a Matlab; fifthly, verifying the mechanical arm control method based on the RBF neural network. The method has the advantages that the method is not only suitable for the mechanical arm, but also can be applied to other mechanical fields; the method can be applied to other control fields; the method is more suitable for application, and the workloads of programmers can be greatly reduced; the mechanical arm with the autonomous learning capacity has higher competitiveness in future.

Description

technical field [0001] The invention relates to a method for controlling a manipulator, in particular to a method for controlling a manipulator based on an RBF neural network. Background technique [0002] At present, the basis for the development of robots is intelligence. In the robot control system, the most critical thing is the learning mechanism and ability. Simulating the learning mechanism of intelligent agents, so that robots can automatically acquire new knowledge and skills through continuous training and learning like living organisms, and realize self-improvement, is a hot issue in the field of robot control. [0003] In actual engineering, the payload of the manipulator will change, and many parameters cannot be accurately predicted during the movement. The adaptive control method of the RBF network has the advantage of not requiring prior knowledge of unknown parameters, such as the quality of the load. , the position of the terminal of the manipulator and th...

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
CPCB25J9/1605B25J9/163
Inventor 曲兴田田农王鑫杜雨欣张昆李金来刘博文王学旭
Owner JILIN UNIV
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