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

Indoor mobile robot glass detection and map updating method based on depth image restoration

A mobile robot and depth image technology, applied in surveying and navigation, instruments, measuring devices, etc., can solve the problems that the map cannot show glass obstacles and affect the positioning and navigation planning work, and achieve safe and stable navigation functions and low system perception costs. low effect

Active Publication Date: 2022-02-25
BEIHANG UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to solve the problem existing in the prior art that glass obstacles cannot be represented in the map created by the robot, which seriously affects the subsequent positioning and navigation planning work, the present invention provides an indoor mobile robot glass detection and map update based on depth image restoration methods, including:

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
  • Indoor mobile robot glass detection and map updating method based on depth image restoration
  • Indoor mobile robot glass detection and map updating method based on depth image restoration
  • Indoor mobile robot glass detection and map updating method based on depth image restoration

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0056] Embodiment 1: The present invention provides a method for glass detection and map updating of an indoor mobile robot based on depth image restoration, the process of which is as follows figure 1 shown. The specific steps are:

[0057] S1: Process lidar information, obtain intensity data, and screen areas suspected of having glass based on the intensity data;

[0058]S2: Select the RGBD camera image based on the information of the area where glass is suspected to exist, use the convolutional neural network to identify the RGBD camera image, and judge whether there is glass in the area, define the absence of glass as the first category, and define the presence of glass as the second category Class II situation;

[0059] S3: When the result is the first type of situation, the map is updated normally without repairing;

[0060] S4: When the result is the second type of situation, judge the defect point type in the depth data acquired by the RGBD camera, center on the def...

Embodiment 2

[0089] Embodiment 2: The present invention provides a method for glass detection and map update of an indoor mobile robot based on depth image restoration. Further, the specific steps are:

[0090] S1: Process lidar information, obtain intensity data, and screen areas suspected of having glass based on the intensity data;

[0091] Further, the suspected area of ​​the glass is screened, and the received laser radar distance information is firstly screened.

[0092] According to the characteristics of the data returned when the lidar scans the glass, find the distance information with a large enough single distance change according to the time stamp, and use this as a condition to trigger the glass suspected area detection program. After the program is triggered, record the current time. Time stamp, and then continuously collect the distance information under N time stamps, and perform variance analysis on the N data. If the variance is large enough, it means that the area is su...

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 an indoor mobile robot glass detection and map updating method based on depth image restoration. The method comprises: firstly, screening a suspected glass existence area based on laser radar intensity data; then, according to the suspected region RGB image, using a convolutional neural network to determine whether glass exists truly; if yes, extracting the boundary of the glass area, judging defect points of the depth image, and repairing depth information of the defect points according to the boundary of the glass area; and finally, performing plane sampling on the depth image, supplementing and updating missing glass obstacles in the original map, and outputting a grid map for planning. The method solves the problem that the map integrity and navigation safety are affected by glass perception failure due to the existence of the characteristics of glass transmission, refraction, polarization and the like in the existing mapping algorithm and equipment, and has the advantages of low system perception cost and safe and stable navigation function.

Description

technical field [0001] The invention belongs to the field of indoor mobile robots, and in particular relates to a glass detection and map updating method for an indoor mobile robot based on depth image restoration. Background technique [0002] In the field of service robots, indoor mobile robot-related technologies are currently the hotspots of research and application. The research mainly focuses on map construction, positioning, navigation, etc., that is, to solve the problems of "where am I" and "where am I going" of mobile robots. At present, the technology of synchronous positioning and mapping of robots using lidar and odometer information in unknown environments is relatively mature. However, compared with the structured laboratory environment, the actual operating environment is often more complex and changeable. [0003] When facing indoor glass curtain walls, partitions, glass doors and other objects, due to the characteristics of glass such as transmission, ref...

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): G01S13/86G01S13/89G01C21/20
CPCG01S13/867G01S13/89G01C21/206G01C21/3841
Inventor 陶永温宇方高赫段练韩栋明
Owner BEIHANG UNIV