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

Mobile robot sonar data fusion method based on DSmT theory

A mobile robot and data fusion technology, applied in the computer field, can solve the problems of affecting the output results, the reliability of the fusion results, and the large impact of the accuracy output results, so as to achieve the effect of not affecting the reliability, reducing the amount of calculation, and effectively identifying

Active Publication Date: 2018-11-13
XIDIAN UNIV
View PDF4 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The disadvantage of this method is that the combination rule of D-S evidence theory distributes the reliability of the focal element of conflict under the fusion framework evenly to all the propositional elements, but according to the D-S combination rule, when the two data completely conflict, it cannot Combining with this rule, when the two evidences are highly conflicting, using this rule to synthesize may lead to results that are contrary to the actual common sense
The disadvantages of the method disclosed in this patent application are: the determination of neural network parameters requires the support of a large number of sample data, and the accuracy of the parameters has a great impact on the output results, and the reliability of the fusion results will also be affected
[0005] In the process of creating a map for a mobile robot, in the fusion processing of sonar data, the existing technology cannot solve the problem of fusion of conflicting data, and the calculation is too large to achieve the highest efficiency. The accuracy of the parameters also affects the output results and affects the map. Creation of reliability of results

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
  • Mobile robot sonar data fusion method based on DSmT theory
  • Mobile robot sonar data fusion method based on DSmT theory
  • Mobile robot sonar data fusion method based on DSmT theory

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0030] In sonar-based map creation, due to the strong uncertainty of sonar information, multiple sonar sensors are required to acquire information at different times and fuse multiple sonar information. At the present stage, the application of information fusion technology is mainly in the military field. Modern warfare has widely used various high-tech. Multi-sensor and multi-source information systems must be used to obtain more battlefield information. Its data processing capacity and processing capacity far exceed that of a single sensor. With the continuous increase in the types and quantities of sensors, multi-sensor information fusion technology has been widely used. In addition, information fusion technology has gradually penetrated into many fields. In the field of mobile robots, the application of information fusion technology is increasingly widespread, but there are still many problems, such as the inability to complete the processing of conflicting data, for exam...

Embodiment 2

[0044] The mobile robot sonar data fusion method based on DSmT theory is the same as embodiment 1, and the DSmT mixing and combination rule of sonar data at different times under the constraints described in step 4 refers to multiple different data sets loaded by the mobile robot body. The combined reliability of the grid state acquired by the sonar sensor in the direction under empty, obstacle and unknown conditions together form a new combined reliability, and combine the new combined reliability with the non-empty feature function Multiply to get the reliability assignment of the raster.

[0045] The classic combination rules of DSmT theory do not have any constraints, but in the process of actual evidence information fusion, most of them have constraints. The mixed combination rules of DSmT theory solve this problem. It has a set of constraints, which is more suitable for the actual fusion. need. Map information is the collection of all grid state information, assigning ...

Embodiment 3

[0047] The mobile robot sonar data fusion method based on DSmT theory is the same as embodiment 1-2, the DSmT mixing and combination rules of sonar data at different times under the constraints described in step 4, the specific reliability fusion results and each combination The calculation formulas of the rules are:

[0048]

[0049]

[0050]

[0051]

[0052] Among them, m 1 ( ) and m 2 (·) assigns the basic reliability from two different data sources, m μ (Ω)(C) represents the reliability fusion result with constraints, μ is the constraint condition E∩O=Φ, where Φ is the absolute empty set, C∈D Ω , is a non-empty characteristic function, if but The value is '0', otherwise it is '1', is the constraint condition set, Φ represents the absolute empty set, Indicates the relative empty set condition. In the above formula, S 1 (C) is the DSmT combination rule without any constraints, S 2 (C) is to assign all the combined reliability assignments of the ab...

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 a mobile robot sonar data fusion method based on the DSmT theory and solves the fusion problem of acquired sonar data under a conflict condition. The method includes: using a sonar sensor to acquire information, and building a sonar sensor measuring model; dividing a sonar detection sector area into a void area and an area which can be occupied according to the measuring model; rasterizing the two-dimensional planar environment of a mobile robot, providing the discrimination frame of the grids, and building a credibility assignment calculation model under the discrimination frame; building the DSmT mixing and combination rules of different-moment sonar data under a constraint condition, and completing the fusion of the mobile robot sonar data according to the DSmT mixing and combination rules of the different-moment sonar data. The method has the advantages that the DSmT theory is applied to the mobile robot sonar data fusion, the fusion problem of conflict datais solved, the peripheral grid state of the robot can be accurately judged, and the method is applicable to the map creation of the mobile robot in an unknown environment in actual application.

Description

technical field [0001] The invention belongs to the field of computer technology and relates to data fusion, in particular to a mobile robot sonar data fusion method based on DSmT theory, which can be used for map creation of mobile robots in unknown environments in practical applications. Background technique [0002] The use of intelligent mobile robots to detect unknown and complex environments has always been a hot and difficult topic for robotics experts at home and abroad. Map creation is a manifestation of the mobile robot's perception of the environment. In an unknown environment, the mobile robot obtains information about the surrounding environment through sensors mounted on the body, such as sonar, laser, infrared, vision, etc., and analyzes the information. Recombine and fuse, then outline or image the surrounding environment and localize the mobile robot itself. The sonar sensor is often used as an important sensor for mobile robots because of its low price, ea...

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): G01S15/93
CPCG01S15/931
Inventor 柴慧敏吕少楠方敏赵昀瑶
Owner XIDIAN UNIV
Features
  • Generate Ideas
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com