CN-116476063-B - Robot operation task instantiation method and related device

CN116476063BCN 116476063 BCN116476063 BCN 116476063BCN-116476063-B

Abstract

The invention relates to the technical field of robots, in particular to a robot operation task instantiation method and a related device. The invention firstly uses all possible operation tasks, all types of entities required for completing all possible operation tasks and preset knowledge of the type of robot to create the body, namely the body is a static unchanged database, and the entity information and the robot information required for completing any one possible operation task are reserved. Then, the invention screens the corresponding preset knowledge from the body based on the specific operation task, and adds the corresponding attribute value, the association relation and the time sequence information to the screened preset knowledge in combination with the specific operation task so as to form an example which can be identified by the robot. The embodiment of the invention is derived from the body, and the preset knowledge in the body is combined according to the requirements of the operation tasks, so that the embodiment of any operation task can be obtained, and the flexibility of the embodiment is enhanced.

Inventors

WANG NA
Miao Shengyi
ZHONG DAMING
WEN ZHENKUN
HUANG HAIMING
LI ZHICHAO

Assignees

深圳大学

Dates

Publication Date: 20260505
Application Date: 20230423

Claims (7)

1. A method for instantiating a robotic task, comprising: creating an ontology for storing all preset knowledge, wherein the preset knowledge is used for representing a robot, an entity operated by the robot and an operation task completed by the robot through an operation entity; Screening the preset knowledge corresponding to the operation task from the body, and recording the preset knowledge as target knowledge; Determining a hierarchical relation among the target knowledge and attribute values of the target knowledge according to the operation task, wherein the hierarchical relation is used for representing relevance and time sequence information among the target knowledge; According to the hierarchical relation among the target knowledge and the attribute value of each target knowledge, constructing an instance for expressing the semantics of the operation task; The creating an ontology for storing all preset knowledge, wherein the preset knowledge is used for characterizing a robot, an entity operated by the robot and an operation task completed by the robot through an operation entity, and comprises the following steps: determining scene information of the entity, attribute information of the entity and component information of the robot in the preset knowledge; Constructing a preset task; decomposing the preset tasks to obtain each preset subtask; creating preset actions corresponding to the preset subtasks, wherein the preset actions are actions corresponding to the components of the robot; creating a body according to the scene information, the attribute information of the entity, the component information of the robot, each preset subtask and the preset action corresponding to each preset subtask; The step of screening the preset knowledge corresponding to the operation task from the body, and recording the preset knowledge as target knowledge, comprises the following steps: screening tasks matched with the operation tasks from the preset tasks, and marking the tasks as matched tasks; Screening the preset actions in the target knowledge corresponding to each subtask of the matching task from each preset action; screening the component information in the target knowledge corresponding to the matching task from the component information according to the screened preset actions; Determining the robots in the target knowledge corresponding to the screened component information; screening entities in the target knowledge corresponding to the matching task from the entities in the ontology; According to the screened entities, the scene information of the entity is screened from the scene information; Determining a hierarchical relationship between the target knowledge and an attribute value of the target knowledge according to the operation task, wherein the hierarchical relationship is used for representing relevance and time sequence information between the target knowledge, and the method comprises the following steps: determining the time sequence information corresponding to each screened preset action; Determining time sequence information corresponding to each subtask of the screened matching task; determining the relevance between the screened entity and the screened component information; And determining the relevance between the screened preset action and the screened entity and the screened scene information.
2. The robot operation task instantiation method according to claim 1, wherein said creating an ontology for storing all preset knowledge for characterizing a robot and an entity operated by the robot and an operation task the robot completes by operating the entity, comprises: determining scene information of the entity, attribute information of the entity and component information of the robot in the preset knowledge; and creating an ontology according to the scene information, the attribute information of the entity and the component information of the robot, wherein the ontology does not contain the hierarchical relationship among the scene information, the attribute information of the entity and the component information of the robot.
3. The method for instantiating the task of the robot operation according to claim 1, wherein constructing the instance expressing the semantics of the task of the operation according to the hierarchical relationship between the respective target knowledge and the attribute value of the respective target knowledge comprises: Respectively representing time sequence information corresponding to each screened preset action, time sequence information corresponding to each subtask of the screened matching task, relevance between the screened entity and the screened component information, relevance between the screened preset action and the screened entity and relevance between the screened entity and the screened scene information by using the pointing direction of an arrow to obtain a template of the operation task; Determining the number of the scene area in the attribute value, the model of the entity and the execution parameter value of the preset action; And constructing an instance for expressing the semantics of the operation task according to the template of the operation task, the serial number of the scene area, the model of the entity and the execution parameter value of the preset action.
4. The method for instantiating the operation task of the robot according to claim 3, wherein constructing the instance for expressing the semantics of the operation task according to the template of the operation task, the number of the scene area, the model of the entity, and the execution parameter value of the preset action comprises: and placing the number of the scene area at the position of the scene area on the template, placing the model of the entity at the position of the entity on the template, and placing the execution parameter value at the position of the preset action on the template to obtain an instance for expressing the semantics of the operation task.
5. A robot-operated task instantiation device, the device comprising: The system comprises a body creation module, a body creation module and a storage module, wherein the body creation module is used for creating a body for storing all preset knowledge, and the preset knowledge is used for representing a robot, an entity operated by the robot and an operation task completed by the robot through an operation entity; the knowledge screening module is used for screening the preset knowledge corresponding to the operation task from the body and recording the preset knowledge as target knowledge; The hierarchical attribute construction module is used for determining the hierarchical relation among the target knowledge and the attribute value of each target knowledge according to the operation task, wherein the hierarchical relation is used for representing the relevance and time sequence information among the target knowledge; The instance construction module is used for constructing an instance for expressing the semantics of the operation task according to the hierarchical relationship among the target knowledge and the attribute value of the target knowledge; The creating an ontology for storing all preset knowledge, wherein the preset knowledge is used for characterizing a robot, an entity operated by the robot and an operation task completed by the robot through an operation entity, and comprises the following steps: determining scene information of the entity, attribute information of the entity and component information of the robot in the preset knowledge; Constructing a preset task; decomposing the preset tasks to obtain each preset subtask; creating preset actions corresponding to the preset subtasks, wherein the preset actions are actions corresponding to the components of the robot; creating a body according to the scene information, the attribute information of the entity, the component information of the robot, each preset subtask and the preset action corresponding to each preset subtask; The step of screening the preset knowledge corresponding to the operation task from the body, and recording the preset knowledge as target knowledge, comprises the following steps: screening tasks matched with the operation tasks from the preset tasks, and marking the tasks as matched tasks; Screening the preset actions in the target knowledge corresponding to each subtask of the matching task from each preset action; screening the component information in the target knowledge corresponding to the matching task from the component information according to the screened preset actions; Determining the robots in the target knowledge corresponding to the screened component information; screening entities in the target knowledge corresponding to the matching task from the entities in the ontology; According to the screened entities, the scene information of the entity is screened from the scene information; Determining a hierarchical relationship between the target knowledge and an attribute value of the target knowledge according to the operation task, wherein the hierarchical relationship is used for representing relevance and time sequence information between the target knowledge, and the method comprises the following steps: determining the time sequence information corresponding to each screened preset action; Determining time sequence information corresponding to each subtask of the screened matching task; determining the relevance between the screened entity and the screened component information; And determining the relevance between the screened preset action and the screened entity and the screened scene information.
6. A terminal device, characterized in that it comprises a memory, a processor and a robot operation task instantiation program stored in the memory and executable on the processor, the processor implementing the steps of the robot operation task instantiation method according to any one of claims 1-4 when executing the robot operation task instantiation program.
7. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a robot-operation task instantiation program, which, when executed by a processor, implements the steps of the robot-operation task instantiation method according to any one of claims 1-4.

Description

Robot operation task instantiation method and related device Technical Field The invention relates to the technical field of robots, in particular to a robot operation task instantiation method and a related device. Background When the robot works in a strange scene, an instance for guiding the robot to work needs to be constructed in advance, and then the robot works according to semantic information covered in the instance. In the prior art, a specific example is set only according to a specific scene, so that the execution efficiency of the robot for carrying out work according to the example is reduced, namely, the execution efficiency of the robot is reduced due to lack of flexibility only according to the example set by the specific scene. In summary, the prior art reduces the flexibility of building instances. Accordingly, there is a need for improvement and advancement in the art. Disclosure of Invention In order to solve the technical problems, the invention provides a robot operation task instantiation method and a related device, which solve the problem that the flexibility of building an instance is reduced in the prior art. In order to achieve the above purpose, the present invention adopts the following technical scheme: In a first aspect, the present invention provides a method for instantiating a robot operation task, including: creating an ontology for storing all preset knowledge, wherein the preset knowledge is used for representing a robot, an entity operated by the robot and an operation task completed by the robot through an operation entity; Screening the preset knowledge corresponding to the operation task from the body, and recording the preset knowledge as target knowledge; Determining a hierarchical relation among the target knowledge and attribute values of the target knowledge according to the operation task, wherein the hierarchical relation is used for representing relevance and time sequence information among the target knowledge; and constructing an instance for expressing the semantics of the operation task according to the hierarchical relationship among the target knowledge and the attribute value of the target knowledge. In one implementation, the creating an ontology for storing all preset knowledge, where the preset knowledge is used to characterize a robot and an entity operated by the robot, and an operation task completed by the robot through the operation entity, includes: determining scene information of the entity, attribute information of the entity and component information of the robot in the preset knowledge; and creating an ontology according to the scene information, the attribute information of the entity and the component information of the robot, wherein the ontology does not contain the hierarchical relationship among the scene information, the attribute information of the entity and the component information of the robot. In one implementation, the creating an ontology for storing all preset knowledge, where the preset knowledge is used to characterize a robot and an entity operated by the robot, and an operation task completed by the robot through the operation entity, includes: determining scene information of the entity, attribute information of the entity and component information of the robot in the preset knowledge; Constructing a preset task; decomposing the preset tasks to obtain each preset subtask; creating preset actions corresponding to the preset subtasks, wherein the preset actions are actions corresponding to the components of the robot; and creating an ontology according to the scene information, the attribute information of the entity, the component information of the robot, each preset subtask and the preset action corresponding to each preset subtask. In one implementation manner, the screening the preset knowledge corresponding to the operation task from the body, and marking the preset knowledge as target knowledge includes: screening tasks matched with the operation tasks from the preset tasks, and marking the tasks as matched tasks; Screening the preset actions in the target knowledge corresponding to each subtask of the matching task from each preset action; screening the component information in the target knowledge corresponding to the matching task from the component information according to the screened preset actions; Determining the robots in the target knowledge corresponding to the screened component information; screening entities in the target knowledge corresponding to the matching task from the entities in the ontology; And according to the screened entities, screening the scene information of the entity from each scene information. In one implementation manner, the determining, according to the operation task, a hierarchical relationship between the target knowledge and an attribute value of the target knowledge, where the hierarchical relationship is used to characterize relevance and timing information between the