IP Library › Granted Patent US 12,397,416
Granted Patent B2
US 12,397,416 · App. 17/565,889 · Granted Aug 26, 2025

Robot control method, storage medium and electronic device

Inventors: Xiao-Qing William Huang (Shanghai, CN); ZhanChao Zhang (Shanghai, CN); Shikui Ma (Shanghai, CN); Bin Wang (Shanghai, CN); Guanghua Yang (Shanghai, CN)
Assignee: CloudMinds Robotics Co., Ltd.
B25J9/163
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,397,416
App. No.
17/565,889
Granted
Aug 26, 2025
Kind
B2
Abstract

A robot control method includes: the first control instruction of the robot is obtained; the behavior blueprint corresponding to the first control instruction is determined, the behavior blueprint including the plurality of blueprint nodes connected according to the target sequence; and the preset functions corresponding to the blueprint nodes are executed according to the target sequence. The preset functions corresponding to the blueprint nodes may include the atomic API ability, the meta skill and the task skill. The atomic API ability is used for characterizing a specific function executed by the robot through a component, the meta skill is used for characterizing a function of an execution unit of the robot, the task skill is used for characterizing a function of user-oriented execution of a target task by the robot, the robot includes one or a plurality of execution units, and each execution unit includes one or more components.

Claims (65)

1. A robot control method, wherein the method comprises:

obtaining a first control instruction of a robot;

determining a behavior blueprint corresponding to the first control instruction, wherein the behavior blueprint comprises a plurality of blueprint nodes connected according to a target sequence; and

executing preset functions corresponding to the blueprint nodes according to the target sequence; wherein

the preset functions corresponding to the blueprint nodes comprise an atomic API ability, a meta skill and a task skill, wherein the atomic API ability is used for characterizing a specific function executed by the robot through a component, the meta skill is used for characterizing a function of an execution unit of the robot, the task skill is used for characterizing a function of user-oriented execution of a target task by the robot, the robot comprises one or a plurality of execution units, and each execution unit comprises one or a plurality of components;

wherein the task skill comprises a behavior skill; the behavior skill comprises one or a plurality of action skills; each action skill comprises one or a plurality of the meta skills; and each meta skill comprises one or a plurality of the atomic API abilities;

wherein there are a plurality of the behavior blueprints, and the method further comprises: performing nested calls of the plurality of the behavior blueprints.

2. The method according to claim 1 , wherein the behavior blueprint comprises a first blueprint node and one or a plurality of first candidate blueprint nodes connected after the first blueprint node according to the target sequence; and the executing the preset functions corresponding to the blueprint nodes according to the target sequence comprises:

executing, if there is one first candidate blueprint node, a preset function corresponding to the first candidate blueprint node after executing a preset function corresponding to the first blueprint node.

3. The method according to claim 2 , wherein the behavior blueprint further comprises a target execution condition corresponding to each first candidate blueprint node, and the executing the preset functions corresponding to the blueprint nodes according to the target sequence comprises:

determining, if there are a plurality of the first candidate blueprint nodes, a first candidate blueprint node corresponding to satisfying the target execution condition according to an execution result of the first blueprint node and/or a current state of the robot after executing the preset function corresponding to the first blueprint node, and determining the first candidate blueprint node as a second blueprint node; and

executing a preset function corresponding to the second blueprint node.

4. The method according to claim 1 , wherein the method further comprises:

obtaining, if receiving a node control instruction input by a user specific to the robot, a target blueprint node indicated by the node control instruction in a case of executing a preset function corresponding to a current blueprint node;

continuing to execute a preset function corresponding to the target blueprint node after executing the preset function corresponding to the current blueprint node; and

continuing to execute a preset function corresponding to a blueprint node located after the target blueprint node in the behavior blueprint according to the sequence.

5. The method according to claim 1 , wherein the behavior blueprint is generated in advance in the following manner:

obtaining a blueprint constructing instruction input by a user;

generating the plurality of blueprint nodes according to a node function correspondence relation in the blueprint constructing instruction, wherein the node function correspondence relation comprises correspondence relations between the blueprint nodes and the preset functions;

generating the target sequence for connecting the plurality of blueprint nodes according to a node connection relation in the blueprint constructing instruction; and

connecting the plurality of blueprint nodes according to the target sequence to generate the behavior blueprint.

6. A non-transitory computer readable storage medium, storing a computer program thereupon, when the computer program in the non-transitory computer readable storage medium is executed by a processor, the processor is caused to:

obtain a first control instruction of a robot;

determine a behavior blueprint corresponding to the first control instruction, wherein the behavior blueprint comprises a plurality of blueprint nodes connected according to a target sequence; and

execute preset functions corresponding to the blueprint nodes according to the target sequence; wherein

the preset functions corresponding to the blueprint nodes comprise an atomic API ability, a meta skill and a task skill, wherein the atomic API ability is used for characterizing a specific function executed by the robot through a component, the meta skill is used for characterizing a function of an execution unit of the robot, the task skill is used for characterizing a function of user-oriented execution of a target task by the robot, the robot comprises one or a plurality of execution units, and each execution unit comprises one or a plurality of components;

wherein the task skill comprises a behavior skill; the behavior skill comprises one or a plurality of action skills; each action skill comprises one or a plurality of the meta skills; and each meta skill comprises one or a plurality of the atomic API abilities;

wherein there are a plurality of the behavior blueprints, and the processor is further configured to perform nested calls of the plurality of the behavior blueprints.

7. The non-transitory computer readable storage medium according to claim 6 , wherein the behavior blueprint comprises a first blueprint node and one or a plurality of first candidate blueprint nodes connected after the first blueprint node according to the target sequence; and when the computer program in the non-transitory computer readable storage medium is executed by the processor, the processor is further caused to:

execute, if there is one first candidate blueprint node, a preset function corresponding to the first candidate blueprint node after executing a preset function corresponding to the first blueprint node.

8. The non-transitory computer readable storage medium according to claim 7 , wherein the behavior blueprint comprises a target execution condition corresponding to each first candidate blueprint node; and when the computer program in the non-transitory computer readable storage medium is executed by the processor, the processor is further caused to:

determine, if there are a plurality of the first candidate blueprint nodes, a first candidate blueprint node corresponding to satisfying the target execution condition according to an execution result of the first blueprint node and/or a current state of the robot after executing the preset function corresponding to the first blueprint node, and determining the first candidate blueprint node as a second blueprint node; and

execute a preset function corresponding to the second blueprint node.

9. The non-transitory computer readable storage medium according to claim 6 , when the computer program in the non-transitory computer readable storage medium is executed by the processor, the processor is further caused to:

obtain, if receiving a node control instruction input by a user specific to the robot, a target blueprint node indicated by the node control instruction in a case of executing a preset function corresponding to a current blueprint node;

continue to execute a preset function corresponding to the target blueprint node after executing the preset function corresponding to the current blueprint node; and

continue to execute a preset function corresponding to a blueprint node located after the target blueprint node in the behavior blueprint according to the sequence.

10. The non-transitory computer readable storage medium according to claim 6 , when the computer program in the non-transitory computer readable storage medium is executed by the processor, the processor is further caused to:

obtain a blueprint constructing instruction input by a user;

generate the plurality of blueprint nodes according to a node function correspondence relation in the blueprint constructing instruction, wherein the node function correspondence relation comprises correspondence relations between the blueprint nodes and the preset functions;

generate the target sequence for connecting the plurality of blueprint nodes according to a node connection relation in the blueprint constructing instruction; and

connect the plurality of blueprint nodes according to the target sequence to generate the behavior blueprint.

11. An electronic device, comprising:

a memory, storing a computer program thereupon; and

a processor, configured to execute the computer program in the memory so as to:

obtain a first control instruction of a robot;

determine a behavior blueprint corresponding to the first control instruction, wherein the behavior blueprint comprises a plurality of blueprint nodes connected according to a target sequence; and

execute preset functions corresponding to the blueprint nodes according to the target sequence; wherein

the preset functions corresponding to the blueprint nodes comprise an atomic API ability, a meta skill and a task skill, wherein the atomic API ability is used for characterizing a specific function executed by the robot through a component, the meta skill is used for characterizing a function of an execution unit of the robot, the task skill is used for characterizing a function of user-oriented execution of a target task by the robot, the robot comprises one or a plurality of execution units, and each execution unit comprises one or a plurality of components;

wherein the task skill comprises a behavior skill; the behavior skill comprises one or a plurality of action skills; each action skill comprises one or a plurality of the meta skills; and each meta skill comprises one or a plurality of the atomic API abilities;

wherein there are a plurality of the behavior blueprints, and the processor is further configured to perform nested calls of the plurality of the behavior blueprints.

12. The electronic device according to claim 11 , wherein the behavior blueprint comprises a first blueprint node and one or a plurality of first candidate blueprint nodes connected after the first blueprint node according to the target sequence; and the processor is further configured to:

execute, if there is one first candidate blueprint node, a preset function corresponding to the first candidate blueprint node after executing a preset function corresponding to the first blueprint node.

13. The electronic device according to claim 12 , wherein the behavior blueprint further comprises a target execution condition corresponding to each first candidate blueprint node; and the processor is further configured to:

determine, if there are a plurality of the first candidate blueprint nodes, a first candidate blueprint node corresponding to satisfying the target execution condition according to an execution result of the first blueprint node and/or a current state of the robot after executing the preset function corresponding to the first blueprint node, and determining the first candidate blueprint node as a second blueprint node; and

execute a preset function corresponding to the second blueprint node.

14. The electronic device according to claim 11 , wherein the processor is further configured to:

obtain, if receiving a node control instruction input by a user specific to the robot, a target blueprint node indicated by the node control instruction in a case of executing a preset function corresponding to a current blueprint node;

continue to execute a preset function corresponding to the target blueprint node after executing the preset function corresponding to the current blueprint node; and

continue to execute a preset function corresponding to a blueprint node located after the target blueprint node in the behavior blueprint according to the sequence.

15. The electronic device according to claim 11 , wherein the processor is further configured to:

obtain a blueprint constructing instruction input by a user;

generate the plurality of blueprint nodes according to a node function correspondence relation in the blueprint constructing instruction, wherein the node function correspondence relation comprises correspondence relations between the blueprint nodes and the preset functions;

generate the target sequence for connecting the plurality of blueprint nodes according to a node connection relation in the blueprint constructing instruction; and

connect the plurality of blueprint nodes according to the target sequence to generate the behavior blueprint.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 23, 2026
From: CLOUDMINDS ROBOTICS CO., LTD.
To: CHONGQING XINGJIE SHUXING TECHNOLOGY PARTNERSHIP ENTERPRISE (LIMITED PARTNERSHIP)
Reel/Frame 074153/0492 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 30, 2021
From: HUANG, XIAO-QING WILLIAM; ZHANG, ZHANCHAO; MA, SHIKUI; WANG, BIN; YANG, GUANGHUA
To: CLOUDMINDS ROBOTICS CO., LTD.
Reel/Frame 058601/0093 →
Priority Claims (1)
CN 202110401397.5 · Apr 14, 2021 · national
Continuity (2)
Continuation PCTCN2021103292 · Jun 29, 2021
Related Publication 20220331953A1 · Oct 20, 2022
References Cited (17)
US 20120136481A1 · Maisonnier · 2012 [cited by examiner]
US 20160059412A1 · Oleynik · 2016 [cited by examiner]
US 20190291277A1 · Oleynik · 2019 [cited by examiner]
US 20200230817A1 · Han · 2020 [cited by examiner]
US 20210237266A1 · Kalashnikov · 2021 [cited by examiner]
CN 110147986A · 2019 [cited by applicant]
CN 110297697A · 2019 [cited by applicant]
CN 110825121A · 2020 [cited by applicant]
CN 110825368A · 2020 [cited by applicant]
CN 111267086A · 2020 [cited by applicant]
CN 111452042A · 2020 [cited by applicant]
CN 111552238A · 2020 [cited by applicant]
KR 20180063391A · 2018 [cited by applicant]
WO 2020075419A1 · 2020 [cited by applicant]
Notice of Reasons for Refusal issued by the Japan Patent Office for Japanese Patent Application No. JP2021-578155, dated Jul. 4, 2023, with an English translation. [cited by applicant]
First Office Action issued by China National Intellectual Property Administration for corresponding Chinese application No. 202110401397.5 dated Mar. 9, 2022, with full English translation. [cited by applicant]
International Search Report of the International Searching Authority issued by China National Intellectual Property Administration for corresponding International Patent Application No. PCT/CN2021/103292, mailed on Jan.… [cited by applicant]