Method for determining pose of robot, robot and computer-readable storage medium

Patent metadata

Field	Value
Publication number	US-12589495-B2
Application number	US-202318395309-A
Country	US
Kind code	B2
Filing date	Dec 22, 2023
Priority date	Jun 25, 2021
Publication date	Mar 31, 2026
Grant date	Mar 31, 2026

Abstract

A method for determining a pose of a robot having a lidar including: obtaining a first pose of the robot in a map coordinate system; determining first positions of laser points corresponding to the lidar in the map coordinate system according to the first pose when the lidar performs laser scanning; determining matching scores between the first positions and grids where the first positions are located according to the first positions and mean values of the grids where the first positions are located, wherein the grids are grids in a probability map corresponding to the map coordinate system; determining a first confidence level for the first pose based on the matching scores; and determining a target pose according to the first confidence level.

First claim

What is claimed is:

1 . A computer-implemented method for determining a pose of a robot comprising a lidar, comprising:
obtaining a first pose of the robot in a map coordinate system; determining first positions of laser points corresponding to the lidar in the map coordinate system according to the first pose when the lidar performs laser scanning; determining matching scores between the first positions and grids where the first positions are located, according to coordinates of the first positions and mean values of the grids where the first positions are located, wherein the grids are grids in a probability map corresponding to the map coordinate system; determining a first confidence level for the first pose based on the matching scores; and determining a target pose according to the first confidence level; wherein determining the target pose according to the first confidence level comprises:
adjusting the first pose within an adjustment range to obtain second poses;
determining a second confidence level for each of the second poses; and
determining the target pose based on one of the second poses with a largest one of the second confidence levels.

2 . The method of claim 1 , wherein a number of the laser points is at least two and a number of the matching scores is at least two; determining the first confidence level for the first pose based on the matching scores comprises:
using an average of the at least two matching scores as the first confidence level for the first pose.

3 . The method of claim 1 , wherein determining the target pose based on one of the second poses with the largest one of the second confidence levels comprises:
optimizing the one of the second poses with the largest one of the second confidence levels using a preset algorithm to obtain optimized third poses; determining a third confidence level for each of the third poses; and determining one of the third poses with a largest one of the third confidence levels as the target pose.

4 . The method of claim 1 , further comprising, before adjusting the first pose within the adjustment range to obtain the second poses,
determining the adjustment range based on the first confidence level.

5 . The method of claim 4 , wherein determining the adjustment range based on the first confidence level comprises:
when the first confidence level is less than a preset value, using a first range as the adjustment range; and when the first confidence level is greater than the preset value, using a second range as the adjustment range, wherein the second range is smaller than the first range.

6 . The method of claim 1 , wherein determining the target pose according to the first confidence level comprises:
obtaining an updated first pose if the first confidence level is less than a preset value; and determining the target pose based on the updated first pose.

7 . The method of claim 1 , wherein each grid in the probability map corresponds to the mean value and a variance, and the mean value and the variance of each grid are determined based on a number of laser points present within the corresponding grid and positions of the laser points present within the corresponding grid during a laser scanning process.

8 . The method of claim 7 , wherein the coordinate of the first position is a two-dimensional vector comprising an x-axis coordinate and a y-axis coordinate of the first position, and the mean value of the grid where the first position is located is a two-dimensional vector formed by coordinates corresponding to the grid where the first position is located; or
wherein the coordinate of the first position is a three-dimensional vector comprising the x-axis coordinate, the y-axis coordinate, and a z-axis coordinate corresponding to the first position, and the mean value of the grid where the first position is located is a three-dimensional vector formed by coordinates corresponding to the grid where the first position is located.

9 . The method of claim 8 , wherein the matching scores between the first positions and the grids where the first positions are located are calculated according to the following equation:

score
i

=

exp
(

-

(

X
i

-

q
i

)

T

⁢

∑

i

-
1

(

X
i

-

q
i

)

2

)

,

where X i represents the first positions, q i represents the mean values of the grids where the first positions are located, score; represents the matching scores, and the matching scores range from 0 to 1, T represents transpose operation,

∑

-
1

 denotes covariance operation, and exp stands for exponential operation.

10 . The method of claim 8 , wherein determining the matching scores between the first positions and the grids where the first positions are located comprises:
calculating and using differences between the coordinates of the first positions and the mean values of the grids where the first positions are located as the matching scores.

11 . A robot comprising:
one or more processors; one or more lidars electrically coupled to the one or more processors; and a memory coupled to the one or more processors, the memory storing programs that, when executed by the one or more processors, cause performance of operations comprising: obtaining a first pose of the robot in a map coordinate system; determining first positions of laser points corresponding to the one or more lidars in the map coordinate system according to the first pose when the one or more lidars performs

Assignees

• Ubtech Robotics Corp Ltd

Inventors

• Gu Yulong
• Xiong Youjun
• Zhang Simin
• Zhao Yun

Classifications

• B25J19/022 Primary

  using lasers · CPC title

• B25J9/1653

  parameters identification, estimation, stiffness, accuracy, error analysis · CPC title

• B25J9/161

  Hardware, e.g. neural networks, fuzzy logic, interfaces, processor · CPC title

• B25J9/1661 Primary

  characterised by task planning, object-oriented languages · CPC title