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

Laser SLAM method based on surface line corner feature extraction

A technology of corner feature and line feature, which is applied in the field of laser SLAM based on surface line corner feature extraction, can solve the problem of huge data volume, achieve good map building effect and increase error effect

Active Publication Date: 2020-08-25
TIANJIN UNIV
View PDF2 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The above commonly used methods often have high hardware requirements. Although the accuracy is high, the amount of data processed during front-end matching is very large.

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
  • Laser SLAM method based on surface line corner feature extraction
  • Laser SLAM method based on surface line corner feature extraction
  • Laser SLAM method based on surface line corner feature extraction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0057] The present invention will be described in further detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0058] According to the laser SLAM method based on surface line corner feature extraction described in the present invention, the specific framework of the method is as follows figure 1 shown.

[0059] The key steps are as follows:

[0060] 1. Initialize the map and various parameters, and allocate memory;

[0061] 2. Collect the point cloud collected by 3D lidar;

[0062] 3. Perform data preprocessing on the collected point cloud, and remove the point cloud points beyond the effective range of the lidar; the preprocessing of the point cloud is as follows:

[0063] (301) Traversing all the original point clouds, setting the effective distance, using a filter, removing the point cl...

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 laser SLAM method based on facial line corner feature extraction, which comprises the following steps: (1) initializing a map and various parameters, and allocating memory; (2) collecting point cloud collected by the 3D laser radar; (3) carrying out data preprocessing on the collected point cloud; (4) carrying out projection; (5) removing blocking points; (6) extracting surface, line and corner features; (7) carrying out surface normal vector estimation on the surface and line features; (8) performing front-end registration calculation on the angular point feature information; (9) removing redundant parts in the point cloud, and storing key frame information, pose information and carrier track information; (10) performing loopback detection on the key frame information and the motion trail information; (11) performing back-end optimization; (12) updating the pose, performing fusing and mapping, and publishing map information and track information; and (13) skipping to the step (2), and continuing to run until the mapping is completed or the process is closed.

Description

technical field [0001] The invention relates to the field of synchronous positioning and mapping of three-dimensional laser radar, in particular to a laser SLAM method based on surface line corner point feature extraction. Background technique [0002] In the research field of mobile robots, Simultaneous Localization and Mapping (SLAM) has always been a hot research topic. SLAM provides navigation maps and real-time positions for robots, and these are the tools for robots to perform path planning and path tracking. premise, so it occupies a very important position in mobile robot navigation. Since the SLAM problem was raised in 1986, SLAM technology has made great progress in all walks of life. Now a large number of applications of SLAM-related algorithms have emerged in the market, such as: driverless cars, service robots, drones, Unmanned underwater vehicles, virtual reality and augmented reality, etc. The environment perception sensors commonly used in SLAM mainly inclu...

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): G06T15/00G06T7/33
CPCG06T15/00G06T7/33G06T2207/10012G06T2207/10044Y02T10/40
Inventor 胡超芳张帅鹏
Owner TIANJIN UNIV
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