Robot control method and apparatus and robot using the same

Patent metadata

Field	Value
Publication number	US-11331806-B2
Application number	US-202016843921-A
Country	US
Kind code	B2
Filing date	Apr 9, 2020
Priority date	Dec 26, 2019
Publication date	May 17, 2022
Grant date	May 17, 2022

Abstract

The present disclosure discloses a robot control method as well as an apparatus, and a robot using the same. The method includes: obtaining a human pose image; obtaining pixel information of key points in the human pose image; obtaining three-dimensional positional information of key points of a human arm according to the pixel information of the preset key points; obtaining a robotic arm kinematics model of a robot; obtaining an angle of each joint in the robotic arm kinematics model according to the three-dimensional positional information of the key points of the human arm and the robotic arm kinematics model; and controlling an arm of the robot to perform a corresponding action according to the angle of each joint. The control method does not require a three-dimensional stereo camera to collect three-dimensional coordinates of a human body, which reduces the cost to a certain extent.

First claim

What is claimed is:

1. A computer-implemented control method for a robot, comprising executing on a processor steps of:
obtaining a human pose image;
obtaining pixel information of a plurality of preset key points in the human pose image;
obtaining three-dimensional positional information of key points of a human arm according to the pixel information of the plurality of preset key points, wherein the key points of the human arm are preset key points of an area at which the human arm in the human pose image is located;
obtaining a robotic arm kinematics model of a robot:
obtaining an angle of each joint in the robotic arm kinematics model according to the three-dimensional positional information of the key points of the human arm and the robotic arm kinematics model; and
controlling an arm of the robot to perform a corresponding action according to the angle of each joint;
wherein the arm of the robot comprises a first joint, a second joint, and a third joint, a fourth joint and a wrist portion sequentially connected through a connecting rod, the key points of the human arm comprise a shoulder point, an elbow point, and a wrist point; wherein the step of obtaining the angle of each joint in the robotic arm kinematics model according to the three-dimensional positional information of the key points of the human arm and the robotic arm kinematics model comprises:
obtaining a vector from the shoulder point to the elbow point, a vector from the elbow point to the wrist point, and a vector from the shoulder point to the wrist point according to the three-dimensional positional information of the key points of the human arm;
obtaining an angle q 1 =a tan 2({right arrow over (r)} SE (0), {right arrow over (r)} SE (1)) of the first joint and an angle

q

2
¯

=

tan

-
1

⁡

(

r
->

SE

⁡

(
2
)

/

r
->

SE

⁡

(
0
)

2

+

r
->

SE

⁡

(
1
)

2

)

of the second joint according to the vector from the shoulder point to the elbow point, wherein {right arrow over (r)} SE (0) represents a component of {right arrow over (r)} SE in a vertical direction of a human body, {right arrow over (r)} SE (1) represents a component of {right arrow over (r)} SE in a perpendicular direction of the human body, {right arrow over (r)} SE (2) represents a component of {right arrow over (r)} SE in a horizontal direction of the human body, and {right arrow over (r)} SE represents a vector from the shoulder point to the elbow point:
obtaining an angle

q
4

=

cos

-
1

⁡

(



r
→

S
⁢
E



2

+



r
->

EW



2

-

|

r
->

SW

⁢

|
2

⁢

/
2

⁢



r
→

S
⁢
E



|

r
->

EW

|

)

of the fourth joint according to the vector from the shoulder point to the elbow point, the vector from the elbow point to the wrist point, and the vector from the shoulder point to the wrist point, wherein {right arrow over (r)} EW represents the vector from the elbow point to the wrist point and {right arrow over (r)} SW represents the vector from the shoulder point to the wrist point;
obtaining a first coordinate system transformation matrix of a coordinate system of the first joint with respect to a coordinate system of a shoulder portion of the arm of the robot;
obtaining a second coordinate system transformation matrix of a coordinate sy

Assignees

• Ubtech Robotics Corp Ltd

Inventors

• Lin Zecai
• Guo Miaochen
• Liu Yizhang
• Xiong Youjun
• Pang Jianxin

Classifications

• B25J9/1607

  Calculation of inertia, jacobian matrixes and inverses · CPC title

• B25J9/1664 Primary

  characterised by motion, path, trajectory planning · CPC title

• B25J9/12

  electric · CPC title

• B25J9/161

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

• B25J13/00

  Controls for manipulators (programme controls B25J9/16) · CPC title