Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Improved AMCL positioning method based on semantic map with wall corner information and robot

A semantic map and positioning method technology, applied in the field of robotics, can solve problems such as convergence failure

Active Publication Date: 2021-10-08
WUHAN UNIV OF SCI & TECH
View PDF8 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002]The robot localization based on the AMCL (adaptive Monte Carlo Localization) algorithm can converge smoothly in the general case, but due to some Limitations, there will also be convergence failures, and there are still some deficiencies worth improving

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
  • Improved AMCL positioning method based on semantic map with wall corner information and robot
  • Improved AMCL positioning method based on semantic map with wall corner information and robot
  • Improved AMCL positioning method based on semantic map with wall corner information and robot

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] The present invention aims at the problem that the AMCL positioning algorithm is prone to positioning failure in some scenarios, and proposes an improved AMCL positioning method based on a semantic map with corner information, and uses a deep learning model (including but not limited to the SSD model) for object recognition and detection during the positioning process , to identify and extract the semantic information of the corner and other objects around the environment, and construct the corner information lookup table by extracting the semantic position relationship of the object during the positioning process, and use the semantic map with the corner information to realize the visual pre-positioning first, so that the robot can be in the In the case of a small amount of prior information and motion, the initial positioning can be realized more quickly, combined with the AMCL algorithm and the environment map matching, the particle weight update method is improved, an...

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 an improved AMCL positioning method based on a semantic map with wall corner information and a robot. According to the method, an established two-dimensional semantic grid map is utilized, and the semantic map is fused with a target detection method based on deep learning to extract central point positions of wall corners and other various objects in the environment in the grid map, so that a semantic information graph around the corner points is formed. And near obstacle distance value calculation is performed on the loaded grid map, and a semantic lookup table around the angular points is generated. And a proposed visual pre-positioning method is combined, so that the mobile robot can realize initial positioning more quickly under the condition of a small amount of prior information and movement. And a particle weight updating mode is improved, and an AMCL algorithm and environment map matching are synchronously combined to carry out fine positioning. Contrast experiments are carried out under different environment conditions, and it is verified that the method improves the particle convergence rate of the robot and particularly improves the positioning accuracy and robustness when the environment has certain similarity or changes to a certain extent.

Description

technical field [0001] The invention belongs to the field of robot mapping, positioning and navigation, and in particular relates to an improved AMCL positioning method based on a semantic map with wall corner information and a robot. Background technique [0002] The robot localization based on the AMCL (adaptive Monte Carlo Localization) algorithm can generally converge the particle set smoothly, but due to some limitations of the algorithm itself, there will be cases where the convergence fails, and there are still some things worth improving. inadequacies. The AMCL algorithm takes into account that particles may be updated too fast during the positioning process, which may lead to convergence errors. At the same time, it also limits the update speed of the particle filter to prevent particles from missing or degrading rapidly in order to increase the diversity of data during particle observation. adverse phenomena. Because of this, due to the lack of prior information,...

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): G01C21/00G01S17/89G01S17/86
CPCG01C21/005G01C21/3841G01S17/89G01S17/86
Inventor 蒋林左建朋聂文康金胜昔杨立
Owner WUHAN UNIV OF SCI & TECH
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
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