Unlock instant, AI-driven research and patent intelligence for your innovation.

Method for reasoning robot behavior link based on knowledge graph

A knowledge map and robot technology, applied in the field of knowledge map, artificial intelligence robot task behavior planning, can solve problems such as the inability to directly act on the job target, the inability to directly complete the task of taking eggs, and the absence of the job target, so as to solve the problem of screening and sorting. Effect

Pending Publication Date: 2022-07-08
ZHEJIANG LAB
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] At present, robot behavior control mostly relies on rule constraints for control. When planning job tasks, you may encounter problems that the job target does not exist or cannot directly act on the job target (for example, picking eggs cannot be directly completed, but must be decomposed into opening and closing). closet and fetching eggs); unable to reason complex multi-step behavior plans based on the environment and cognition

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
  • Method for reasoning robot behavior link based on knowledge graph
  • Method for reasoning robot behavior link based on knowledge graph
  • Method for reasoning robot behavior link based on knowledge graph

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] In order to make the objectives, technical solutions and technical effects of the present invention clearer, the present invention will be described in further detail below with reference to the accompanying drawings.

[0035] like Figure 7 As shown, the present invention proposes a method for inferring a robot behavior link based on a knowledge graph, which specifically includes the following steps:

[0036] (1) Build a triple knowledge graph to represent the relationship between actions and objects:

[0037] First construct a node, the node is composed of a noun, the noun represents the name of an object or the name of a person or an animal, and contains a list of noun features, features can modify nouns as attributes of nouns; the relationship between nodes is transitive The verb node vt indicates that the source node source acts on the target target node through the action vt, for example: monkey-eat-banana; loops can occur during construction, and the maximum num...

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 method for reasoning a robot behavior link based on a knowledge graph, and relates to the field of artificial intelligence robot task behavior planning and knowledge graphs. The method comprises the following steps: firstly, constructing a triple knowledge graph, and then constructing a robot ontology knowledge graph; planning a behavior tree link according to the constructed triple knowledge graph and the robot ontology knowledge graph to obtain a complete robot behavior target; obtaining all paths according to the behavior tree link; then screening paths according to actions capable of being executed by the robot, and sorting the screened links; and finally, robot behavior link planning is completed by using the ranked links. According to the method, a robot behavior control problem is converted into a knowledge graph solving problem.

Description

technical field [0001] The invention relates to the fields of artificial intelligence robot task behavior planning and knowledge graph, in particular to a method for inferring a robot behavior link based on the knowledge graph. Background technique [0002] At present, robot behavior control mostly relies on rule constraints for control. When planning work tasks, there will be problems that the work target does not exist or cannot directly act on the work target (for example, taking eggs cannot be completed directly, but must be decomposed into open Closet and picking up eggs); inability to reason complex multi-step behavioral planning based on the environment and cognition. SUMMARY OF THE INVENTION [0003] In order to solve the above-mentioned technical problems existing in the prior art, the present invention proposes a method for inferring a robot behavior link based on a knowledge graph, and its specific technical scheme is as follows: [0004] A method for inferring...

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): G06N5/04G06F16/36
CPCG06N5/04G06F16/367
Inventor 周元海宋伟朱世强穆宗昊金天磊任杰袭向明徐泽民
Owner ZHEJIANG LAB