Loopback detection method based on two-dimensional grid map

A grid map and detection method technology, applied in image analysis, measurement device, image data processing, etc., can solve problems such as large amount of calculation, simple hardware facilities, and no calculation of search space, so as to eliminate accumulated errors and avoid poor real-time performance. , to avoid computationally expensive effects

Active Publication Date: 2020-08-14
NANJING UNIV OF SCI & TECH
View PDF5 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, the main problem of most loopback optimization calculation methods is that the current maximum probability calculation of the scan matching subgraph adopts the brute force search method, and the search space is not calculated, which makes the calculation amount large during loopback, and mobile devices often have simple hardware facilities and cannot be done. Complicated calculations, all map construction cannot guarantee real-time performance

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
  • Loopback detection method based on two-dimensional grid map
  • Loopback detection method based on two-dimensional grid map
  • Loopback detection method based on two-dimensional grid map

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0014] Such as figure 1 As shown, a kind of loop detection method based on two-dimensional grid map of the present invention comprises the following steps:

[0015] (10) Scanning and extracting feature points: LiDAR generates point cloud information for each frame, and the radar data of each frame is regarded as a scan. First, the scanning points are selected to calculate the curvature, and the feature points on the edge and plane are selected with the curvature as a constraint;

[0016] Such as figure 2 As shown, the scanning feature point extraction step includes:

[0017] (11) Curvature calculation: Assume that the initial scan is empty and expressed as Then enter the radar information to write the scan point information The 5 points on the edge of each scan do not participate in the selection of feature points, because the periphery does not meet the conditions for calculating the curvature of the five points on the left and right; for any point A, select five points...

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 loopback detection method based on a two-dimensional grid map. The method comprises the following steps: generating point cloud information for each frame of laser radar, taking radar data of each frame as one-time scanning, selecting scanning points, calculating the curvature, and selecting feature points on the edge and plane through taking the curvature as a constraintcondition; converting obtained scanning coordinates into sub-graph coordinates, forming a grid map by utilizing the probability that the scanning points occupy grids for continuous times, and optimizing according to a definition formula before the scanning points are inserted into the sub-graph; creating sub-graphs, and connecting the sub-graphs to realize mapping of a large scene; and optimizingthe poses of all the feature points and the sub-graphs to eliminate accumulative errors caused by the sub-graphs and improve the accuracy. The loopback detection method of the two-dimensional grid map is small in calculated amount and high in real-time performance.

Description

technical field [0001] The invention belongs to the field of SLAM, in particular to a loop detection method based on a two-dimensional grid map. Background technique [0002] The purpose of loop detection technology is to build a complete map, which is widely used in SLAM map construction. With the advancement of sensor technology, the number of laser points of lidar has increased and the accuracy has improved, which has provided great help for building scene maps. How to solve the loopback problem in building maps is a difficult problem for SLAM technology. The error caused by a large number of submaps in the construction map can be reduced by optimizing the poses of all scans and submaps, generally by calculating the maximum probability of the current scan in the submap. [0003] At present, the main problem of most loopback optimization calculation methods is that the current maximum probability calculation of the scan matching subgraph adopts the brute force search met...

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): G06T7/60G06T7/70G01S17/89
CPCG06T7/60G06T7/70G01S17/89
Inventor 赵壮袁夏
Owner NANJING 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
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap