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

Robot relocation method based on landmark information and multi-sensor data fusion

A multi-sensor, data fusion technology, applied in two-dimensional position/channel control, instruments, motor vehicles, etc.

Inactive Publication Date: 2019-08-20
GUANGDONG UNIV OF TECH
View PDF5 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention overcomes the shortcomings and deficiencies of the existing robot positioning technology in known environments, and mainly aims at the positioning error problem in SLAM synchronous real-time mapping and positioning, and proposes a fusion of laser perception data and visual recognition information, and utilizes A method of re-correcting positioning to eliminate positioning errors based on landmark information

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 relocation method based on landmark information and multi-sensor data fusion
  • Robot relocation method based on landmark information and multi-sensor data fusion
  • Robot relocation method based on landmark information and multi-sensor data fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0064] Such as figure 1 , figure 2 , image 3 As shown, the robot relocation method based on landmark information and multi-sensor data fusion includes the following steps:

[0065] Step S1: Construct a map, and simultaneously set and determine several objects with distinctive features as landmarks in the system during the process of constructing a known map. The selection of landmark objects and the determination of the position of landmark objects in the current environment must comply with the requirements of this method The basic principle;

[0066] Step S2: Use a clustering algorithm to gather the laser points falling on the same landmark object into a laser point cluster to form laser data;

[0067] Step S3: generating visual semantic information for visually recognized objects through deep learning and image matching;

[0068] Step S4: Use calibration parameters and geometric models to fuse laser data and visual semantic information to generate semantic laser data,...

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 robot relocation method based on landmark information and multi-sensor data fusion for the problem of positioning error in synchronous instant mapping and positioning, and aims to achieve the purposes of overcoming shortcomings and defects of positioning technique of existing robots in a complex environment. The objective of the invention is to incorporate visually recognized landmark information into laser-perceived data, and correspond the landmark marked with a semantic label to an accurate position information on the map, and then reversely calculate the true position of the robot on the map, thereby correcting the positioning error of the robot, improving positioning accuracy and repositioning ability of the robot in the autonomous navigation process, and enhancing position self-correcting level of the robot.

Description

technical field [0001] The invention relates to the field of artificial intelligence, and more specifically, to a robot relocation method based on fusion of landmark information and multi-sensor data. Background technique [0002] Traditional positioning algorithms, such as those proposed by Hanten R[1] based on particle filter, use predicted values ​​and observed values ​​for scan matching to update the positioning algorithm. The information is relatively accurate, and when the characteristics of the surrounding environment objects are relatively obvious, small-scale pose corrections can be completed adaptively, but the dependence on the odometer information is too high, and the response sensitivity to changes in the surrounding environment is not enough. The fault tolerance is not high when the cumulative error is too large, the position drifts, and the human movement is unexpected, which leads to a large distortion of positioning when various situations occur. [0003] A...

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): G05D1/02
CPCG05D1/0246G05D1/0257G05D1/0223G05D1/0221G05D1/0276
Inventor 杨爽曾碧
Owner GUANGDONG UNIV 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