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

A method and device for multi-point cloud map fusion based on offline global optimization

A technology of global optimization and map fusion, which is applied to measuring devices, electromagnetic wave re-radiation, radio wave measurement systems, etc., can solve problems such as high requirements for algorithm implementation and difficult implementation, and achieve flexible and changeable implementation plans, avoid ghosting, Improved stability and reliability effects

Active Publication Date: 2022-07-01
ZHEJIANG LAB
View PDF14 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, at present, there are few related studies on multi-point cloud map fusion, and they mainly focus on online methods, which have high requirements for algorithm implementation, are not easy to carry out, and need to balance mapping performance and real-time operation

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
  • A method and device for multi-point cloud map fusion based on offline global optimization
  • A method and device for multi-point cloud map fusion based on offline global optimization
  • A method and device for multi-point cloud map fusion based on offline global optimization

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] In order to make the objectives, technical solutions and technical effects of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments of the description.

[0036] like figure 1 As shown, a multi-point cloud map fusion method based on offline global optimization of the present invention includes the following steps:

[0037] Step 1: Adapt the laser SLAM method based on GPS information initialization, and build self-constraint through the laser SLAM method: Based on the open source laser SLAM method—LIO-SAM process, initialize and adapt GPS information, and use open source laser SLAM at the same time. The key frame pose information, point cloud information and constraint information are preserved during and at the end of the method, wherein the constraint information includes: odometer factor, GPS factor and loop closure factor.

[0038] Specifically, it includes the follow...

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 and device for multi-point cloud map fusion based on offline global optimization. The method includes: step 1, adapting a laser SLAM method initialized based on GPS information; According to the online laser SLAM method described in the above S1, multiple point cloud maps are sequentially obtained; Step 3, load the information of each point cloud map offline, and sequentially construct the odometer factor, loopback factor and GPS factor of each point cloud map ; Step 4, construct mutual constraint factors between different point cloud maps; Step 5, set optimization parameters, perform global optimization, and save the final fusion point cloud and all key frame information. Compared with the method of online multi-point cloud map fusion, the method of the invention improves the stability and reliability of multi-point cloud map fusion, reduces the difficulty of algorithm implementation, and does not need to consider the balance between mapping performance and real-time operation. .

Description

technical field [0001] The invention relates to the field of positioning and mapping based on lidar sensors, in particular to a multi-point cloud map fusion method and device based on offline global optimization. Background technique [0002] Since the Simultaneous Localization and Mapping (SLAM) problem was first proposed in 1985, SLAM technology has experienced more than 30 years of development, and its theoretical system has been basically perfected; now it has entered the era of robust perception for specific applications , especially in the fields of mobile robots and unmanned driving, and a large number of SLAM methods with excellent performance continue to emerge. [0003] In the process of unmanned vehicles performing specific tasks, the prior point cloud map used for matching and positioning is an indispensable part of the entire algorithm module, and the point cloud map can be obtained by existing mature laser SLAM methods. However, for a large-scale environment, ...

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 Patents(China)
IPC IPC(8): G01C21/00G01S17/86G01S17/89
Inventor 华炜高海明张顺胡艳明马也驰邱奇波
Owner ZHEJIANG LAB
Features
  • R&D
  • 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