Map database creation method, mobile machine using the same, and computer readable storage medium

Patent metadata

Field	Value
Publication number	US-11710277-B2
Application number	US-202117482450-A
Country	US
Kind code	B2
Filing date	Sep 23, 2021
Priority date	Dec 4, 2020
Publication date	Jul 25, 2023
Grant date	Jul 25, 2023

Abstract

A map database creation method is provided. The method includes: obtaining a factor set including factors; dividing a map database into levels based on the factors, and taking each interval of the last level as one sub-database; creating an initial map based on a factor value of each factor corresponding to each sub-database, and creating the sub-database as an initial map database by storing the corresponding initial map in the sub-database; finding the initial map matching a current lighting condition from the initial map database based on the current lighting condition, and taking the found initial map as a positioning map; and performing a visual positioning based on the positioning map, creating an expanded map corresponding to the current lighting condition based on the visual positioning, and creating the sub-database corresponding to the current lighting condition as an expanded map database by storing the corresponding expanded map in the sub-database.

First claim

What is claimed is:

1. A computer-implemented map database creation method for a mobile machine, comprising:
obtaining a factor set including a plurality of factors affecting lighting conditions;
dividing a map database into a plurality of levels based on the factors such that an amount of the levels is the same as an amount of the factors, each level corresponds to a corresponding one of the factors, and each level includes a plurality of intervals, and taking each of the intervals of a last level as one sub-database;
creating an initial map for visual positioning based on a factor value of each of the factors corresponding to each sub-database, and creating the sub-database as an initial map database by storing the corresponding initial map in the sub-database;
finding the initial map matching a current lighting condition from the initial map database based on the current lighting condition, and taking the found initial map as a positioning map; and
performing a visual positioning on the mobile machine based on the positioning map, creating an expanded map corresponding to the current lighting condition based on the visual positioning, and creating the sub-database corresponding to the current lighting condition as an expanded map database by storing the corresponding expanded map in the sub-database.

2. The method of claim 1 , wherein the factor set includes a first factor and a second factor; wherein the dividing the map database into the plurality of levels based on the factors such that the amount of the levels is the same as the amount of the factors, each level corresponds to a corresponding one of the factors, and each level includes the plurality of intervals, and taking each of the intervals of the last level as the sub-database comprises:
dividing the map database into two levels according to the first factor and the second factor;
dividing due map database into a plurality of first intervals according to the factor value of the first factor;
dividing each of the first intervals into a plurality of second intervals according to the factor value of the second factor; and
taking each of the second intervals as one sub-database.

3. The method of claim 2 , wherein the first factor is weather and the second factor is time.

4. The method of claim 1 , wherein the factor set includes a weather condition factor, a time factor, and a lighting factor.

5. The method of claim 1 , wherein the creating the initial map for visual positioning based on a factor value of each of the factors corresponding to each sub-database, and creating the sub-database as the initial map database by storing the corresponding initial map in the sub-database comprises:
creating the initial map based on the factor value of each of the factors corresponding to each sub-database using ORB-SLAM2, wherein the initial map corresponding to each sub-database is created from a. same spatial pose.

6. The method of claim 1 wherein the mobile machine has a camera, and the performing the visual positioning on the mobile machine based on the positioning map, creating the expanded map corresponding to the current lighting condition based on the visual positioning comprises:
obtaining an absolute pose of the camera based on the positioning map using a tracking module of ORB-SLAM2, obtaining a relative pose of the camera by performing a relative positioning on an image captured by the camera using a visual odometer module of ORB-SLAM2, and obtaining the optimized absolute pose of the camera by performing an optimizing fusion on the absolute pose and the relative pose using an optimization module of ORB-SLAM2; and
creating a new expanded map based on the optimized absolute pose of the camera using a mapping module of ORB-SLAM2, wherein the new expanded map has a same coordinate system with the positioning map.

7. The method of claim 6 , wherein the obtaining the optimized absolute pose of the camera by performing the optimizing fusion on the absolute pose and the relative pose using the optimization module of ORB-SLAM2 comprises:
obtaining a relative pose constraint corresponding to the relative pose, and calculating an initial absolute pose based on the relative pose and the relative pose constraint; and
obtaining an absolute pose constraint, and obtaining a target absolute pose by optimizing the initial absolute pose based on the absolute pose constraint.

8. A mobile machine, comprising;
a processor;
a memory coupled to the processor; and
one or more computer programs stored in the memory and executable on the processor;
wherein, the one or more computer programs comprise:
instructions for obtaining a factor set including a plurality of factors affecting lighting conditions;
instructions for dividing a map database into a plurality of levels based on the factors such that an amount of the levels is the same as an amount of the factors, each level corresponds to a corresponding one of the factors, and each level includes a plurality of intervals, and taking each of the intervals of a last level as one sub-database;
instructions for creating an initial map for visual positioning based on a factor value of each of the factors corresponding to each sub-database, and creating the sub-database as an initial map database by storing the corresponding initial map in the sub-database;
instructions for finding the initial map matching a current lighting condition from the initial map database based on the current lighting condition, and taking the found initial map as a position map; and
instructions for performing a visual positioning on the mobile machine based on the positioning map, creating an expanded map corresponding to the current lighting condition based on the visual positioning, and creating the sub-database corresponding to the current lighting condition as an expanded map database by storing the corresponding expanded map in the sub-database.

9. The mobile machine of claim 8 , wherein the factor set includes a first factor and second factor; wherein the instructions for dividing the map database into the plurality of levels based on the factors such that the amount of the levels is the same as the amount of the factors, each level corresponds to a corresponding one of the factors, and each level includes the plurality of internals, and taking each of the intervals of the last level as lie sub-database comprise:
instructions for dividing the map database into two levels according to the first factor and the second factor;
instructions for dividing the map database into a plurality of first intervals according to the factor value of the first factor;
instructions for dividing each of the first intervals into a plurality of second intervals according to the factor value of the second factor; and
instructions for taking each of the second intervals as one sub-database.

10. The mobile machine of claim 9 , wherein the first factor is weather and the second factor is time.

11. The mobile machine of claim 8 . wherein the factor set includes a weather condition factor, a time factor, and a lighting factor.

12. The mobile machine of claim 8 , wherein the instructions for creating the initial map for visual positioning based on a factor value of each of the factors corresponding to each sub-database, arid creating the sub-database as the initial map database by storing the corresponding initial map in the sub-database comprise:
instructions for creating the initial map based on the factor value of each of the factors corresponding to each sub-database using ORB-SLAM2, wherein the initial map corresponding to each sub-database is created from a same spatial pose.

13. The m

Assignees

• Ubtech Robotics Corp Ltd

Inventors

• Huang Mingqiang
• Liu Zhichao
• Lai Youfang
• Zhao Yun

Classifications

• G06T19/003 Primary

  Navigation within 3D models or images · CPC title

• G06F16/29 Primary

  Geographical information databases · CPC title

• G06T7/73

  using feature-based methods · CPC title

• G06T15/50

  Lighting effects · CPC title

• G06T19/20

  Editing of three-dimensional [3D] images, e.g. changing shapes or colours, aligning objects or positioning parts · CPC title