Pose determining method for mobile robot and apparatus and mobile robot thereof

Patent metadata

Field	Value
Publication number	US-11034028-B2
Application number	US-201916561033-A
Country	US
Kind code	B2
Filing date	Sep 5, 2019
Priority date	Jul 9, 2019
Publication date	Jun 15, 2021
Grant date	Jun 15, 2021

Abstract

The present disclosure provides a pose determining method for a mobile robot as well as an apparatus and a mobile robot thereof. The method includes: obtaining a first position of a mobile robot in each local map after building an initial local map corresponding to a current environment and rotating; determining first environmental contour points of each of the local maps and corresponding first gradient directions, and obtaining a relative position of each of the first environmental contour points and the corresponding first position; building an angle histogram in each of the local maps; determining a second position of second environmental contour points of a global map and corresponding second gradient directions; and predicting a third position in the global map of the mobile robot, counting an appearance amount of the third positions, and determining a target pose of the mobile robot in the global map.

First claim

What is claimed is:

1. A computer-implemented pose determining method for a mobile robot having one or more sensors, comprising executing on a processor of the mobile robot steps of:
obtaining environment data of a current environment of the mobile robot through the one or more sensors, and building an initial local map corresponding to the current environment based on the environment data;
rotating the initial local map according to a first preset angular interval to obtain rotated local maps, and obtaining a first position of the mobile robot in each of the rotated local maps;
determining first environmental contour points of each of the rotated local maps and a first gradient direction corresponding to each of the first environmental contour points, and obtaining a relative position of each of the first environmental contour points and the corresponding first position in each of the rotated local maps;
building an angle histogram in each of the rotated local maps corresponding to the relative position based on a second preset angular interval and the first gradient direction of each of the rotated local maps;
determining a second position corresponding to second environmental contour points of a pre-built global map and a second gradient direction each of the second environmental contour points; and
predicting a third position in the global map of the mobile robot in each of the rotated local maps based on the second gradient direction, the second position, and the angle histogram in each of the rotated local maps, counting an appearance amount of the third positions, and determining a target pose of the mobile robot in the global map based on the appearance amount.

2. The method of claim 1 , wherein the step of predicting the third position in the global map of the mobile robot in each of the rotated local maps based on the second gradient direction, the second position, and the angle histogram in each of the rotated local maps, counting the appearance amount of the third positions, and determining the target pose of the mobile robot in the global map based on the appearance amount comprises:
determining an angular interval of the second environmental contour points in each of the angle histograms based on the second gradient direction;
obtaining a target relative position in the angular interval, and predicting the third position in the global map of the mobile robot in each of the rotated local maps based on the second position and the target relative position;
counting the appearance amount of the third positions in each of the rotated local maps; and
determining the third position with the largest appearance amount as a target position of the mobile robot in the global map, and determining a first heading angle of the mobile robot in the rotated local map corresponding to the third position with the largest appearance amount as the target beading angle of the mobile robot in the global map.

3. The method of claim 2 , wherein before the step of determining the first heading angle of the mobile robot in the rotated local map corresponding to the third position with the largest appearance amount as the target heading an of the mobile robot in the global map further comprises;
obtaining an initial heading angle of the mobile robot in the initial local map before the initial local map is rotated; and
determining a rotational amount of each of the rotated local maps, and determining the first heading angle of the mobile robot in each of the rotated local maps based on the rotational amount, the first preset angular interval, and the initial heading angle.

4. The method of claim 1 , wherein the step of building the angle histogram in each of the rotated local maps corresponding to the relative position based on the second preset angular interval and the first gradient directions of each of the rotated local maps comprises:
performing a pre-processing on each of the first gradient directions according to a preset processing manner to obtain a second angle corresponding to each of the first gradient directions; and
building the angle histogram in each of the rotated local maps corresponding to the relative position based on the second preset angular interval and the second angle.

5. The method of claim 1 , wherein the step of determining the first environmental contour points of each of the rotated local maps and the first gradient direction corresponding to each of the first environmental contour points comprises:
detecting the first environmental contour points of each of the rotated local maps through a Sobel operator, and calculating the first gradient direction corresponding to each of the first environmental contour points.

6. The method of claim 5 , wherein the step of calculating the first gradient direction corresponding to each of the first environmental contour points comprises:
calculating the first gradient direction based on the following formula:

Angle
ij

=

arctan
⁡

(

G
yij

G
xij

)

;

where, Angle ij is the first gradient direction corresponding to the j-th first environmental contour point of the i-th muted local map, and G xij is a first gradient of the j-th first environmental contour point of the i-th rotated local map in the first gradient direction, G yij is first gradient of the j-th first environmental contour point of the i-th rotated local map in the second gradient direction.

7. The method of claim 1 , wherein the one or more sensors comprise a laser scanner, and the step of obtaining the environment data of the current environment of the mobile robot through the one or more sensors comprises:
obtaining the environment data of the current environment of the mobile robot through the laser scanner.

8. A pose determining apparatus for a mobile robot having one or more sensors, comprising:
a local map building module configured to obtain environment data of a current environment of the mobile robot through the one or more sensors, and build local maps corresponding to the current environment based on the environment data;
a first position obtaining module configured to rotate the local maps according to a first preset angular interval, and obtain a first position of the mobile robot in each of the local maps;
a relative position obtaining module configured to determine first environmental contour points of each of the local maps and a first gradient direction corresponding to each of the first environmental contour points, and obtain a relative position of each of the first environmental contour points and the corresponding first position in each of the local maps;
an angle histogram building module configured to build an angle histogram in each of the local maps corresponding to the relative position based on a second present angular interval anal the first gradient direction of each of the local maps;
a second gradient direction determining module configured to determine a second position corresponding to second environmental contour points of a pre-built global map in the mobile robot and a second gradient direction of each of the second environmental contour points; and
a target pos

Assignees

• Ubtech Robotics Corp Ltd

Inventors

• Hu Xu
• Nie Peng
• Fang Wei
• Hu Jiawen
• Xiong Youjun

Classifications

• G05D1/024 Primary

  in combination with a laser (lasers per se H01S) · CPC title

• G06V10/46

  Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features (colour feature extraction G06V10/56) · CPC title

• G06V20/10

  Terrestrial scenes (scenes under surveillance with static cameras G06V20/52; scenes perceived from the exterior of a vehicle G06V20/56; scenes perceived from the interior of a vehicle G06V20/59) · CPC title

• B25J13/089 Primary

  Determining the position of the robot with reference to its environment · CPC title

• G06T7/73 Primary

  using feature-based methods · CPC title