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

Robot behavior verification and recognition method based on GA-BP network

A technology of GA-BP and recognition method, which is applied in the direction of neural learning method, character and pattern recognition, biological neural network model, etc., can solve the problem of falling into local optimum, and achieve the effect of improving the efficiency of imitation learning

Active Publication Date: 2020-07-10
JINLING INST OF TECH
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In view of the above problems, the present invention proposes a robot behavior verification and recognition method based on the GA-BP network, and optimizes the BP network by utilizing the optimal characteristic of the global search of the genetic algorithm, so as to prevent the BP algorithm from falling into a local optimum during learning. Disadvantages, so that the model has good convergence and adaptability, and the network has a good recognition effect

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
  • Robot behavior verification and recognition method based on GA-BP network
  • Robot behavior verification and recognition method based on GA-BP network
  • Robot behavior verification and recognition method based on GA-BP network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] Below in conjunction with accompanying drawing and specific embodiment the present invention is described in further detail:

[0046] The invention provides a robot behavior verification and recognition method based on the GA-BP network, realizes precise behavior recognition, and can improve the efficiency of robot motion imitation.

[0047] As an embodiment of the present invention, the present invention provides a robot behavior verification and recognition method based on the GA-BP network. The framework diagram of the robot behavior verification and recognition method based on the GA-BP network is as follows figure 1 As mentioned above, the schematic diagram of the GA-BP network training method is as follows figure 2 As shown, the schematic diagram of the joint points of Kinect is as follows image 3 As mentioned, the specific steps are as follows;

[0048] Step1: collect data;

[0049] For the actions {action_1, action_2, ..., action_N} stored in the robot action...

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 proposes a robot behavior verification and recognition method based on a GA-BP network. A BP network is optimized by utilizing the global search optimal characteristic of a genetic algorithm, the defect that the BP algorithm is caught in local optimum in learning is avoided, the model has good convergence and adaptability, and the network has a good recognition effect. According to the method provided by the invention, the behavior verification problem of robot imitation learning is solved, the accurate identification is completed when a human body makes an action: if the actionis contained in the matching library, the action is called to complete subsequent execution steps, and if not, learning is carried out, so the action imitation efficiency of the robot can be improved.

Description

technical field [0001] The invention relates to the field of robot behavior verification and recognition, in particular to a robot behavior verification and recognition method based on a GA-BP network. Background technique [0002] The action imitation learning of the robot mainly includes four steps: imitation, learning, copying and reproduction of intelligence. Through the learning method, the robot can save the actions required for imitation to the robot action library. When using it, the robot calls the internal action library to complete the corresponding action. action. At present, the widely used robot action imitation learning application is based on the Kinect method, which uses the Kinect platform to collect human body data and transmit the data to the robot for learning. However, in the process of robot imitation learning, it is impossible for a specific action every The joint angles of the second learning are exactly the same. Through the recognition of the acti...

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): G06N3/04G06N3/08G06N3/12G06K9/00G06K9/40
CPCG06N3/084G06N3/126G06V40/20G06V10/30G06N3/045
Inventor 司海飞胡兴柳史震方挺
Owner JINLING INST 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