Epidemic prevention robot knowledge learning and migration method and system

A knowledge learning and robotics technology, applied in the field of knowledge learning and transfer of epidemic prevention robots, can solve problems such as difficult application, insufficient training samples, and high training overhead, and achieve the effect of online knowledge transfer

Active Publication Date: 2021-01-15
UNIV OF SCI & TECH OF CHINA
View PDF5 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For the anti-epidemic robot, its ability to learn and update continuously through autonomous learning is very necessary, but the traditional convolutional neural network has insufficient training samples, high training

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
  • Epidemic prevention robot knowledge learning and migration method and system
  • Epidemic prevention robot knowledge learning and migration method and system
  • Epidemic prevention robot knowledge learning and migration method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0075]Such asfigure 1 As shown, this implementation discloses a knowledge learning and migration method for epidemic prevention robots, which includes the following steps S1 to S6:

[0076]S1. On the basis of constructing the knowledge base of epidemic prevention robots, according to the overall task planning, the independent task unit after subtask decomposition, the construction of multi-task sub-networks; the use of independent sub-task joint actions, indoor environment, robot movement The data set of the path, the sub-network model of each sub-task is trained; the sub-neural network containing multiple learnable parameters is defined, the input sub-task data set is iterated, and the input environment and movement are processed through the multi-layer sub-network structure The data is forwarded, and the difference between the output value and the target value is calculated at the same time, the gradient is propagated back to the parameters of the sub-neural network, and finally the ...

Embodiment 2

[0092]The knowledge learning and migration method of the epidemic prevention robot provided according to the present invention includes:

[0093]1. Epidemic prevention robots build knowledge base and knowledge learning knowledge transfer process design

[0094]Such asfigure 1 As shown, the task learning and knowledge accumulation and online knowledge transfer of epidemic prevention robots include task decomposition, offline knowledge base construction, task network construction and knowledge transfer learning, construction of online knowledge reasoning engine, construction of knowledge graph, task intelligence understanding and robot knowledge migrate. The functions of each part are as follows:

[0095](1) Perform task decomposition

[0096]Describe the data model of the robot task description and its expression method, decompose the tasks of the robot, establish a model of the robot's change to the task state, and describe the target state of each task and the new target state based on the mod...

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 provides an epidemic prevention robot knowledge learning and migration method and system, and the method comprises the steps: 1, building a subtask offline knowledge base based on manualand priori knowledge according to an epidemic prevention scene of a robot application; 2, constructing a subtask network model based on multiple tasks according to the offline knowledge base, and carrying out task migration learning training; 3, constructing a knowledge reasoning engine based on the sub-task network model and task transfer learning training; 4, constructing a knowledge graph according to a knowledge reasoning engine; 5, performing task environment-based mode training according to the knowledge graph; and 6, performing knowledge migration according to the mode training resultbased on the task environment. The robot can be widely used in epidemic prevention and control, so that manpower is liberated, the risk that workers are infected in epidemic prevention and control isreduced, and the method and system can play an important role in epidemic prevention and control.

Description

Technical field[0001]The invention relates to the technical field of epidemic prevention robots, in particular to a method and system for learning and migrating knowledge of epidemic prevention robots.Background technique[0002]With the sudden outbreak of the novel coronavirus COVID-19, the work and lives of people all over the world have been severely affected. With the development of the epidemic, the pressure on medical resources and public health resources has become more and more serious, and the problem of insufficient manpower and the high risk of infection of staff have become more and more serious. There is an urgent need for a measure to replace manpower.[0003]Robots are often used to perform dangerous and repetitive tasks to free up manpower. It happens to meet the requirements for epidemic prevention. Therefore, more and more places are considering the use of epidemic prevention robots for epidemic prevention and control. For epidemic prevention robots, its ability to lea...

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): G06F16/36G06N3/04G06N3/08G16H50/70G16H50/80
CPCG06F16/367G06N3/084G16H50/70G16H50/80G06N3/045
Inventor 高洪波郝正源李智军
Owner UNIV OF SCI & TECH OF CHINA
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