CN114185281B - Robot simulation platform control method, terminal and medium based on knowledge base - Google Patents
Robot simulation platform control method, terminal and medium based on knowledge base Download PDFInfo
- Publication number
- CN114185281B CN114185281B CN202111529268.0A CN202111529268A CN114185281B CN 114185281 B CN114185281 B CN 114185281B CN 202111529268 A CN202111529268 A CN 202111529268A CN 114185281 B CN114185281 B CN 114185281B
- Authority
- CN
- China
- Prior art keywords
- knowledge base
- robot
- task
- simulation platform
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000004088 simulation Methods 0.000 title claims abstract description 128
- 238000000034 method Methods 0.000 title claims abstract description 78
- 230000009471 action Effects 0.000 claims abstract description 30
- 230000008569 process Effects 0.000 claims description 30
- 238000004458 analytical method Methods 0.000 claims description 16
- 238000000354 decomposition reaction Methods 0.000 claims description 4
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 230000008901 benefit Effects 0.000 abstract description 10
- 238000012549 training Methods 0.000 abstract description 8
- 238000007726 management method Methods 0.000 description 8
- 238000004590 computer program Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 230000003993 interaction Effects 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B17/00—Systems involving the use of models or simulators of said systems
- G05B17/02—Systems involving the use of models or simulators of said systems electric
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Abstract
The invention discloses a robot simulation platform control method, a terminal and a medium based on a knowledge base, wherein the method comprises the following steps: acquiring a knowledge base of the robot, and determining a target task of the robot in a current scene according to the knowledge base; analyzing the target task to obtain an operation sequence of the target task, and displaying the operation sequence in a simulation platform interface; acquiring an operation instruction input by a target object in a simulation platform interface, and updating an operation sequence according to the operation instruction; and acquiring corresponding knowledge base data according to the updated operation sequence, and controlling the robot to execute corresponding skills and action primitives according to the knowledge base data. According to the robot simulation platform control method based on the knowledge base, the operation sequence of the robot is verified through the simulation platform, the execution efficiency and the safety of the robot for completing the task target can be continuously trained and improved, and training times in an actual scene can be reduced, so that the economic benefit of the robot in a strange scene is improved.
Description
Technical Field
The invention relates to the field of robots, in particular to a robot simulation platform control method, a terminal and a medium based on a knowledge base.
Background
At present, robots are widely used in the fields of industry, agriculture, medical treatment, military and the like. Skill manipulation and motion planning with respect to robots is an important research direction in the field of robots. With the continuous development of society, the environment and scene faced by robots are more and more complex, and the progress of science and technology puts more strict demands on the execution efficiency of robots.
The simulation platform is applied to the operation of the robot by research work, but only the task is decomposed into an operation sequence on a macroscopic level, and the operation sequence is not defined from a fundamental microscopic level; therefore, aiming at unfamiliar scenes and complex task demands, training in actual scenes is required to be enhanced, so that the simulation platform cannot improve the execution efficiency and safety of the robot and the economic benefit of the robot in unfamiliar scenes.
Accordingly, there is a need in the art for improvement.
Disclosure of Invention
The invention aims to solve the technical problems of low execution efficiency and safety of a robot based on a simulation platform in the prior art.
The technical scheme adopted for solving the technical problems is as follows:
in a first aspect, the present invention provides a method for controlling a robotic simulation platform based on a knowledge base, the method for controlling a robotic simulation platform based on the knowledge base comprising the steps of:
acquiring a knowledge base of a robot, and determining a target task of the robot in a current scene according to the knowledge base;
analyzing the target task to obtain an operation sequence of the target task, and displaying the operation sequence in a simulation platform interface;
acquiring an operation instruction input by a target object in the simulation platform interface, and updating the operation sequence according to the operation instruction;
and acquiring corresponding knowledge base data according to the updated operation sequence, and controlling the robot to execute corresponding skills and action primitives according to the knowledge base data.
In one implementation, the acquiring a knowledge base of the robot, and determining, according to the knowledge base, a target task of the robot in a current scene, previously includes:
setting the knowledge base in the robot based on the form of parameter expression;
setting a plurality of scene layers, task layers, skill layers and action layers in the knowledge base, and storing corresponding knowledge base data in the set layers.
In one implementation, the obtaining a knowledge base of a robot, and determining, according to the knowledge base, a target task of the robot in a current scene includes:
acquiring a knowledge base of the robot;
acquiring scene information of the robot, and searching a corresponding scene layer and a task layer in the knowledge base according to the scene information;
and determining a target task of the robot in the current scene according to the scene layer and the task layer.
In one implementation manner, the analyzing the target task to obtain an operation sequence of the target task, and displaying the operation sequence in a simulation platform interface includes:
analyzing the target task according to the authority of the target object to obtain an operation sequence containing a target, a scene and skills;
and previewing the process of executing the target task by the robot in the simulation platform interface according to the operation sequence and the corresponding knowledge base data.
In one implementation manner, the analyzing the target task according to the authority of the target object to obtain an operation sequence including a target, a scene and a skill includes:
acquiring authority information of the target object, and judging whether the authority information is appointed authority information or not;
if the authority information is the appointed authority information, a task analysis interface is called through a preset instruction;
and decomposing the target task into the target, the scene and the skills through the task analysis interface, and forming the operation sequence through the decomposed target, scene and skills in a sequencing mode.
In one implementation, obtaining an operation instruction input by a target object in the simulation platform interface, and updating the operation sequence according to the operation instruction includes:
acquiring an operation instruction input by the target object in the simulation platform interface;
determining a target, a scene and a skill selected by the target object according to the operation instruction;
and updating the operation sequence according to the selected targets, scenes and skills.
In one implementation, the acquiring corresponding knowledge base data according to the updated operation sequence, and controlling the robot to execute corresponding skills and action primitives according to the knowledge base data includes:
acquiring corresponding knowledge base data according to the updated operation sequence;
determining corresponding execution parameters according to the acquired knowledge base data, and outputting the knowledge base data and the execution parameters to a simulation system;
and controlling the robot to execute skills and action primitives in the updated operation sequence through the simulation system.
In one implementation manner, the robot simulation platform control method based on the knowledge base further comprises the following steps:
and demonstrating the skill operation process of the robot for executing the target task in real time in the simulation platform interface.
In a second aspect, the present invention provides a terminal comprising: the system comprises a processor and a memory, wherein the memory stores a robot simulation platform control program based on a knowledge base, and the robot simulation platform control program based on the knowledge base is used for realizing the robot simulation platform control method based on the knowledge base according to the first aspect when being executed by the processor.
In a third aspect, the present invention provides a medium, which is a computer readable storage medium storing a knowledge base based robotic simulation platform control program, which when executed by a processor is configured to implement the knowledge base based robotic simulation platform control method according to the first aspect.
The technical scheme adopted by the invention has the following effects:
according to the method for controlling the robot simulation platform based on the knowledge base, the target task of the robot in the current scene is determined through the knowledge base, and the operation sequence of the target task can be obtained by analyzing the target task, so that the operation sequence of the robot is verified by using the simulation platform, and the execution efficiency and the safety of the robot for completing the task target are improved under the condition that the simulation platform is continuously trained; in addition, the training times in the actual scene can be reduced by the control mode of the simulation platform, so that the economic benefit of the robot in the unfamiliar scene is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to the structures shown in these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for controlling a robotic simulation platform based on a knowledge base in one implementation of the invention.
FIG. 2 is a flow chart of a planning of a robotic simulation platform in one implementation of the invention.
FIG. 3 is a flow chart of the execution of a simulation task by a robot in one implementation of the invention.
Fig. 4 is a functional schematic of a terminal in one implementation of the invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more clear and clear, the present invention will be further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Exemplary method
Aiming at unfamiliar scenes and complex task demands, the training intensity of the robot in the actual scenes needs to be enhanced, however, the existing robot simulation platform only analyzes the tasks macroscopically and cannot refine the tasks in the bottom layer application, so that the execution efficiency and the safety of the robot cannot be improved, and the economic benefit of the robot in the unfamiliar scenes cannot be improved.
In view of the fact that the adaptability of robots in unfamiliar situations is still to be enhanced and the efficiency of performing complex tasks is also in need of improvement. The inventor proposes a robot simulation platform control method based on knowledge base, this method analyzes the skill operation of the robot first, and decompose into the multi-level operation layer; then splitting the task requirements into different skill sequences, action sequences and related executable parameters; finally, the operation sequence of the robot is verified through the simulation platform, so that the execution efficiency and the safety of the robot for completing the task target can be continuously trained and improved, and training in an actual scene can be reduced, so that the economic benefit is improved.
As shown in fig. 1, an embodiment of the present invention provides a method for controlling a robotic simulation platform based on a knowledge base, where the method for controlling a robotic simulation platform based on a knowledge base includes the following steps:
step S100, a knowledge base of the robot is obtained, and a target task of the robot in the current scene is determined according to the knowledge base.
In this embodiment, the robot simulation platform control method based on the knowledge base is applied to a terminal, where the terminal includes but is not limited to: the terminal equipment used for controlling the robot, such as a robot, or a smart television, a mobile phone, a tablet personal computer and the like.
In this embodiment, in the control method of the simulation platform of the robot based on the knowledge base, a complex task may be subjected to planning decomposition to obtain a series of operation sequences, so as to facilitate verification of the operation sequences and execution of the operation sequences by the simulation platform of the robot; according to the method, the operation skills of the robot are expressed in a knowledge mode according to target tasks to be completed by the robot, and the operation skills of the robot are controlled and managed through a simulation platform.
Specifically, as shown in fig. 2, the simulation system of the robot includes: module 100, module 200, module 300, and module 400; the module 100 is a knowledge base of a robot, and can be used for storing data sets of various targets and scenes, operation skills and execution parameters for realizing tasks of the robot; the module 200 is a simulation platform, is a visual man-machine interaction platform with a simulated reality execution effect, and can integrate and sequence knowledge base data into executable data; the module 300 is a dialogue management module, and can be used for judging the use authority of an operator, and if the authority passes, preprocessing a specific task instruction and converting the specific task instruction into internal data identifiable by a knowledge base; the module 400 is an instruction hub module, and can issue specific task operation instructions to the simulation system.
In order to provide the targets and scenes, the operating skills and the execution parameters required by the robot system under different tasks; before implementing the simulation platform control method, the embodiment also needs to set a knowledge base in a simulation system of the robot, and set a layered scene layer, a task layer, a skill layer and an action layer in the knowledge base.
Specifically, when setting up the knowledge base, the method may include the following steps:
firstly, setting the knowledge base in the robot based on the form of parameter expression;
secondly, setting a plurality of scene layers according to different scenes under the catalog of the knowledge base, wherein each scene layer corresponds to one operation scene of the robot, for example: the method comprises the following steps of mobile phone assembly, flat plate assembly, camera assembly and other scenes;
again, several task layers are set under each scene layer directory, where each task layer corresponds to a task under the scene, for example: in the camera-assembled scenario, task 1 is included: plug-in cord a (R1001), task 2: plug-in cord B (R1002), task 3: task information such as the plug-in cord C (R1003).
Finally, setting a plurality of skill layers under each task layer catalog, wherein the skill layers express the operation skills required by each task in a serialized form; for example: performing skill sequence 1 may complete task 1, skill sequence 1 including skill 1: j101, skills 2: j102, … skills N.
In addition, a plurality of action layers are arranged under each skill layer catalog, wherein each action layer corresponds to one action primitive under the skill.
It should be noted that, when the knowledge base is set, for all the levels in the knowledge base, the corresponding knowledge base data can be stored in the level; the knowledge base data may be existing scene data, task data, skill data and action primitive data, or may be newly added scene data, task data, skill data and action primitive data by means of on-site editing and/or importing.
The knowledge base is set in a parameter expression and layering mode, so that the robot can quickly acquire required operation skills and action primitives according to the current scene and task during simulation operation, and the efficiency of acquiring knowledge base data by the robot is improved.
That is, in one implementation of the present embodiment, the step S100 includes the following steps:
step S001, setting the knowledge base in the robot based on the form of parameter expression;
step S002, setting a plurality of scene layers, task layers, skill layers and action layers in the knowledge base, and storing corresponding knowledge base data in the set layers.
In this embodiment, when implementing the simulation platform control method, a preset knowledge base needs to be obtained from a storage module of the robot, where the storage module is a module 100; by acquiring the knowledge base of the robot, a data set of targets and scenes can be acquired from the knowledge base, so that corresponding target tasks are determined from the data set according to the current scene of the robot, and the task executing process of the robot is conveniently preformed in a simulation platform of the robot.
Specifically, when acquiring the target task of the robot, the current operation scene information of the robot may be acquired by means of camera shooting, or may be input by means of manual input (selection), for example: the current operation scene information of the robot is camera assembly; and then searching a corresponding scene layer in the knowledge base according to the acquired scene information, and searching a task layer associated with the scene layer according to the searched scene layer, so as to determine a target task of the robot in the current scene in the task layer.
That is, in one implementation manner of the present embodiment, the step S100 specifically includes the following steps:
step S101, acquiring a knowledge base of the robot;
step S102, scene information of the robot is obtained, and corresponding scene layers and task layers are searched in the knowledge base according to the scene information;
step S103, determining a target task of the robot in the current scene according to the scene layer and the task layer.
According to the embodiment, the knowledge base is arranged in the simulation system of the robot, and required knowledge base data can be obtained from the corresponding knowledge base layer according to the target task of the robot and the scene information where the target task is located in the process of the simulation operation of the robot, so that the thinned target task is demonstrated in a simulation interface in a serialization operation mode.
As shown in fig. 1, in an implementation manner of the embodiment of the present invention, the method for controlling a robot simulation platform based on a knowledge base further includes the following steps:
and step 200, analyzing the target task to obtain an operation sequence of the target task, and displaying the operation sequence in a simulation platform interface.
In this embodiment, after determining a target task of the robot, the target task may be parsed by a management and control module of the robot, where the management and control module is a module established based on task requirements in an operation process of the robot; the target task is decomposed into the target, the scene and the skill, and the decomposed target, scene and skill can be displayed in a sequencing mode, so that an operation sequence with a certain operation sequence is formed.
Specifically, in the process of analyzing the target task, authority information of an operator (i.e., a target object) may be acquired first, where the authority information includes authority levels of the operator using the robot and the simulation platform, and the authority levels may include no authority, a first authority level (e.g., a use authority), a second authority level (e.g., a management authority), and the like in order according to a priority principle.
Further, under the condition that the operator has the function of operating the robot and the simulation platform, the target task can be analyzed according to the authority of the operator, so that an operation sequence containing a target, a scene and skills is obtained; the process of analyzing the target task is mainly realized through the management and control module, namely, a corresponding task analysis interface is called through the management and control module, and the corresponding operation sequence can be obtained through analysis by utilizing the task analysis interface.
Further, after the operation sequence is obtained through analysis, corresponding knowledge base data can be obtained from a knowledge base according to the operation sequence, wherein the knowledge base data are data sets of operation skills and execution parameters in the knowledge base; by acquiring the corresponding knowledge base data, the acquired knowledge base data can be utilized to conduct previewing in the simulation platform interface so as to show the specific process of the robot executing the target task.
That is, in one implementation manner of the present embodiment, the step S200 specifically includes the following steps:
step S201, analyzing the target task according to the authority of the target object to obtain an operation sequence containing a target, a scene and skills;
step S202, previewing the process of executing the target task by the robot in the simulation platform interface according to the operation sequence and the corresponding knowledge base data.
In this embodiment, in the process of implementing the above step S201, after acquiring the authority information of the operator, it is determined whether the authority information is the specified authority information; the designated authority information can be authority information corresponding to the first authority level or the second authority level; the authority information of the operator is determined by the module 300 (i.e. the dialogue management module), and if the authority of the operator passes, the specific task instruction (i.e. the operation sequence) of the target task is preprocessed, so that the task instruction is converted into the internal data which can be identified by the knowledge base.
Further, if the authority information of the operator is the appointed authority information, a task analysis interface is called through a preset instruction; the preset instructions are instructions corresponding to a calling scene layer, a task layer and a skill layer; correspondingly, the task analysis interfaces are interfaces corresponding to a scene layer, a task layer and a skill layer.
Further, decomposing the target task into the target, the scene and the skill through the task parsing interface; the method comprises the steps of decomposing a scene through a scene layer interface to obtain a scene, decomposing through a task layer interface to obtain a target, and decomposing through a skill layer interface to obtain a skill; then, forming the operation sequence by the decomposed targets, scenes and skills according to a serialization form; and the target task is displayed in a serialization mode, wherein the serialization mode refers to that the operation skills in the knowledge base are combined into execution data with a certain sequence according to the specific requirements of achieving the target task, so that the robot can execute corresponding operations according to the data.
That is, in one implementation manner of the present embodiment, the step S201 specifically includes the following steps:
step S201a, obtaining the authority information of the target object, and judging whether the authority information is the appointed authority information or not;
step S201b, if the authority information is the appointed authority information, a task analysis interface is called through a preset instruction;
step S201c, decomposing the target task into the target, the scene and the skill through the task analysis interface, and forming the operation sequence from the decomposed target, scene and skill in a sequenced form.
According to the method and the device, the target task can be analyzed according to the authority of an operator, so that an operation sequence containing the target, the scene and the skills is obtained, and needed knowledge base data are obtained from a knowledge base in the form of serialization operation skills, so that the operation process of the robot for executing the target task in the actual scene is simulated with a visual effect.
As shown in fig. 1, in an implementation manner of the embodiment of the present invention, the method for controlling a robot simulation platform based on a knowledge base further includes the following steps:
step S300, an operation instruction input by the target object in the simulation platform interface is obtained, and the operation sequence is updated according to the operation instruction.
In this embodiment, when an operator uses the simulation platform of the robot, the robot may automatically decompose the target task into a specific operation sequence according to the scene information and the task information, so that a specific task instruction is converted into internal data identifiable by a knowledge base according to the operation sequence, and the operation process of the robot is previewed on the simulation platform interface by using the knowledge base data.
In addition, when the operator uses the simulation interface of the robot, the operator can also define the targets, scenes and skills according to the requirements of realizing the target tasks; specifically, the operator can input a corresponding operation instruction in the simulation interface of the robot, and the robot acquires the operation instruction input by the operator through the simulation platform interface, so that the target, the scene and the skill selected by the operator are determined according to the operation instruction, and the operation sequence is updated according to the selected target, scene and skill.
In the process of customizing targets, scenes and skills by the operator, the module 300 (i.e. the dialogue management module) of the robot simulation system can convert the task data of the human-computer defined by the operator into the internal representation data of the knowledge base, further access the skills and action knowledge graphs stored in the knowledge base through the simulation platform, analyze the input control data with the help of the knowledge graphs to obtain the output data required to be executed by the robot, and finally output the execution result to the human-computer interaction interface so as to display the updated (i.e. customized) operation sequence in the simulation platform interface.
That is, in one implementation manner of the present embodiment, the step S300 specifically includes the following steps:
step S301, an operation instruction input by the target object in the simulation platform interface is obtained;
step S302, determining a target, a scene and a skill selected by the target object according to the operation instruction;
and step S303, updating the operation sequence according to the selected targets, scenes and skills.
According to the embodiment, the simulation platform capable of being operated in a self-defined mode is arranged in the robot, so that the robot has a visual effect and can simulate the actual operation, and the robot can integrate and sequence knowledge base data into a man-machine interaction platform capable of executing data.
As shown in fig. 1, in an implementation manner of the embodiment of the present invention, the method for controlling a robot simulation platform based on a knowledge base further includes the following steps:
step S400, obtaining corresponding knowledge base data according to the updated operation sequence, and controlling the robot to execute corresponding skills and action primitives according to the knowledge base data.
In this embodiment, after updating the operation sequence according to the operation sequence defined by the operator, the robot acquires corresponding knowledge base data from the knowledge base according to the updated operation sequence, further determines corresponding execution parameters according to the acquired knowledge base data, and outputs the knowledge base data and the execution parameters to the simulation system, so as to simulate and control skills and action primitives in the operation sequence after the robot is updated by the simulation system, thereby realizing the process of simulating real operation by the simulation platform.
In the process of simulating and controlling the robot to execute operation, a specific task operation instruction (namely an instruction corresponding to an operation sequence) is issued to the simulation system through the instruction center module, the simulation system obtains the task operation instruction and converts the task operation instruction into internal representation data of the knowledge base, and then the skill and action knowledge graph stored in the knowledge base is accessed through the simulation platform, and the input control data is analyzed with the help of the knowledge graph to obtain output data required to be executed by the robot.
In order to ensure the reliability and the authenticity of the simulation system when the simulation system simulates the robot to execute the target task, the robot can verify the operation skills and the execution parameters in the operation sequence before outputting specific task operation instructions.
Specifically, it may be determined whether the operation skills in the operation sequence are a set of various actions or operations to be achieved to complete a specific task objective, and then determine whether the execution parameters are physical attribute parameters, action parameters, task necessary parameters of some columns, and the like of the entity in the scene objective; the specific determination process may be performed according to the historical operation experience of the robot or the self-learning experience of the robot, which is not described herein.
That is, in one implementation manner of the present embodiment, the step S400 specifically includes the following steps:
step S401, corresponding knowledge base data are obtained according to the updated operation sequence;
step S402, determining corresponding execution parameters according to the acquired knowledge base data, and outputting the knowledge base data and the execution parameters to a simulation system;
step S403, controlling, by the simulation system, the robot to execute the skills and the action primitives in the updated operation sequence.
In one implementation manner of the embodiment of the invention, the robot simulation platform control method based on the knowledge base further comprises the following steps:
step S500, demonstrating the skill operation process of the robot for executing the target task in real time in the simulation platform interface.
In this embodiment, in addition to the operation process of the robot being previewed in the simulation platform interface, the skill operation process of the robot for executing the target task may be demonstrated in real time in the simulation platform interface in actual operation, that is, the operation process of the robot for executing the target task in actual operation may be recorded and demonstrated in real time.
Further, to facilitate understanding of the embodiments of the present invention, reference will now be made to fig. 2 and 3, and the description will be made with the objective of "chip assembly task" and scenario:
a schematic diagram of the execution flow of the simulation task under the "chip assembly task" goal and scenario is shown in fig. 3, wherein:
the module S101 is an example: expressing a chip assembly task, which is controlled by an instruction center module;
the module S102 is a rights application: the dialogue management module is used for controlling the user and applying permission if the user is not authorized; if the operation is performed by the authority, entering the next link;
the module S103 is a task parsing flow: the method is carried out in a knowledge base module, and when the right passes, the process is transferred to, wherein the process comprises an S1030 target base interface, an S1031 skill base interface and an S1032 scene base interface, and the process outputs a serialized skill and action primitive combination;
the module S104 is an execution operation module: and the serial skill and action primitive combination which is output by the task analysis module is executed by the simulation platform and is executed in sequence to complete the simulation task given by the instruction.
Through the modules and the processes, the operation process of 'chip assembly task' can be simulated and executed in the simulation platform of the robot, and an operator can optimize and adjust the skill operation process of the robot according to the operation effect displayed in the simulation platform of the robot, so that the execution efficiency and the safety of completing the task target in the actual operation process are improved, the economic benefit in unfamiliar scenes is improved, and excessive actual combat training processes in unfamiliar scenes are avoided.
According to the method for controlling the robot simulation platform based on the knowledge base, the target task of the robot in the current scene is determined through the knowledge base, and the operation sequence of the target task can be obtained by analyzing the target task, so that the operation sequence of the robot is verified by using the simulation platform, and the execution efficiency and the safety of the robot for completing the task target are improved under the condition that the simulation platform is continuously trained; in addition, the training times in the actual scene can be reduced by the control mode of the simulation platform, so that the economic benefit of the robot in the unfamiliar scene is improved.
Exemplary apparatus
Based on the above embodiment, the present invention also provides a terminal, and a functional block diagram thereof may be shown in fig. 4.
The terminal comprises: the system comprises a processor, a memory, an interface, a display screen and a communication module which are connected through a system bus; wherein the processor of the terminal is configured to provide computing and control capabilities; the memory of the terminal comprises a medium and an internal memory; the medium stores an operating system and a computer program; the internal memory provides an environment for the operation of the operating system and computer programs in the medium; the interface is used for connecting an external terminal device, for example: a mobile terminal, a computer and other devices; the display screen is used for displaying corresponding robot simulation platform control information based on the knowledge base; the communication module is used for communicating with a cloud server or a mobile terminal.
The computer program, when executed by the processor, is configured to implement a knowledge base-based control method for a robotic simulation platform.
It will be appreciated by those skilled in the art that the functional block diagram shown in fig. 4 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the terminal to which the present inventive arrangements may be applied, and that a particular terminal may include more or less components than those shown, or may combine some of the components, or have a different arrangement of components.
In one embodiment, a terminal is provided, including: the system comprises a processor and a memory, wherein the memory stores a robot simulation platform control program based on a knowledge base, and the robot simulation platform control program based on the knowledge base is used for realizing the robot simulation platform control method based on the knowledge base when being executed by the processor.
In one embodiment, a medium is provided, wherein the medium is a computer readable storage medium and the medium stores a knowledge base based robotic simulation platform control program for implementing the knowledge base based robotic simulation platform control method as above when executed by a processor.
Those skilled in the art will appreciate that implementing all or part of the above-described methods may be accomplished by way of a computer program comprising instructions for the relevant hardware, the computer program being stored on a non-volatile medium, the computer program when executed comprising the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include non-volatile and/or volatile memory.
In summary, the invention provides a robot simulation platform control method, a terminal and a medium based on a knowledge base, wherein the method comprises the following steps: acquiring a knowledge base of the robot, and determining a target task of the robot in a current scene according to the knowledge base; analyzing the target task to obtain an operation sequence of the target task, and displaying the operation sequence in a simulation platform interface; acquiring an operation instruction input by a target object in a simulation platform interface, and updating an operation sequence according to the operation instruction; and acquiring corresponding knowledge base data according to the updated operation sequence, and controlling the robot to execute corresponding skills and action primitives according to the knowledge base data. According to the robot simulation platform control method based on the knowledge base, the operation sequence of the robot is verified through the simulation platform, the execution efficiency and the safety of the robot for completing the task target can be continuously trained and improved, and training times in an actual scene can be reduced, so that the economic benefit of the robot in a strange scene is improved.
It is to be understood that the invention is not limited in its application to the examples described above, but is capable of modification and variation in light of the above teachings by those skilled in the art, and that all such modifications and variations are intended to be included within the scope of the appended claims.
Claims (7)
1. The robot simulation platform control method based on the knowledge base is characterized by comprising the following steps of:
setting the knowledge base in the robot based on the form of parameter expression;
setting a plurality of scene layers, task layers, skill layers and action layers in the knowledge base, and storing corresponding knowledge base data in the set layers; when the knowledge base is set, storing corresponding knowledge base data in each level for all levels in the knowledge base; the knowledge base data are existing scene data, task data, skill data and action primitive data, or are newly added scene data, task data, skill data and action primitive data in a field editing and/or importing mode;
acquiring a knowledge base of a robot, and determining a target task of the robot in a current scene according to the knowledge base;
analyzing the target task to obtain an operation sequence of the target task, and displaying the operation sequence in a simulation platform interface;
acquiring an operation instruction input by a target object in the simulation platform interface, and updating the operation sequence according to the operation instruction;
acquiring corresponding knowledge base data according to the updated operation sequence, and controlling the robot to execute corresponding skills and action primitives according to the knowledge base data;
analyzing the target task to obtain an operation sequence of the target task, and displaying the operation sequence in a simulation platform interface, wherein the analysis comprises the following steps:
analyzing the target task according to the authority of the target object to obtain an operation sequence containing a target, a scene and skills; calling a corresponding task analysis interface based on the management and control module, and analyzing to obtain a corresponding operation sequence by utilizing the task analysis interface;
according to the operation sequence and the corresponding knowledge base data, previewing the process of executing the target task by the robot in the simulation platform interface;
the analyzing the target task according to the authority of the target object to obtain an operation sequence comprising a target, a scene and skills, which comprises the following steps:
acquiring authority information of the target object, and judging whether the authority information is appointed authority information or not;
if the authority information is the appointed authority information, a task analysis interface is called through a preset instruction;
decomposing the target task into the target, the scene and the skill through the task analysis interface; the scene is obtained through the scene layer interface decomposition, the target is obtained through the task layer interface decomposition, the skill is obtained through the skill layer interface decomposition, and the decomposed target, scene and skill form the operation sequence in a sequencing mode.
2. The method for controlling a robot simulation platform based on a knowledge base according to claim 1, wherein the steps of obtaining a knowledge base of a robot and determining a target task of the robot in a current scene according to the knowledge base comprise:
acquiring a knowledge base of the robot;
acquiring scene information of the robot, and searching a corresponding scene layer and a task layer in the knowledge base according to the scene information;
and determining a target task of the robot in the current scene according to the scene layer and the task layer.
3. The knowledge base-based robotic simulation platform control method according to claim 1, wherein obtaining an operation instruction input by a target object in the simulation platform interface and updating the operation sequence according to the operation instruction comprises:
acquiring an operation instruction input by the target object in the simulation platform interface;
determining a target, a scene and a skill selected by the target object according to the operation instruction;
and updating the operation sequence according to the selected targets, scenes and skills.
4. The method for controlling a robotic simulation platform based on a knowledge base according to claim 1, wherein the obtaining corresponding knowledge base data according to the updated operation sequence and controlling the robot to execute corresponding skills and action primitives according to the knowledge base data comprises:
acquiring corresponding knowledge base data according to the updated operation sequence;
determining corresponding execution parameters according to the acquired knowledge base data, and outputting the knowledge base data and the execution parameters to a simulation system;
and controlling the robot to execute skills and action primitives in the updated operation sequence through the simulation system.
5. The knowledge base based robotic simulation platform control method of claim 1, further comprising:
and demonstrating the skill operation process of the robot for executing the target task in real time in the simulation platform interface.
6. A terminal, comprising: the system comprises a processor and a memory, wherein the memory stores a robot simulation platform control program based on a knowledge base, and the robot simulation platform control program based on the knowledge base is used for realizing the robot simulation platform control method based on the knowledge base according to any one of claims 1-5 when being executed by the processor.
7. A medium, characterized in that the medium is a computer readable storage medium, the medium storing a knowledge base based robot simulation platform control program, which when executed by a processor is adapted to implement the knowledge base based robot simulation platform control method according to any of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111529268.0A CN114185281B (en) | 2021-12-14 | 2021-12-14 | Robot simulation platform control method, terminal and medium based on knowledge base |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111529268.0A CN114185281B (en) | 2021-12-14 | 2021-12-14 | Robot simulation platform control method, terminal and medium based on knowledge base |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114185281A CN114185281A (en) | 2022-03-15 |
| CN114185281B true CN114185281B (en) | 2024-02-20 |
Family
ID=80605015
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111529268.0A Active CN114185281B (en) | 2021-12-14 | 2021-12-14 | Robot simulation platform control method, terminal and medium based on knowledge base |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114185281B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114580576B (en) * | 2022-05-05 | 2022-09-06 | 中国科学院自动化研究所 | Robot task planning method and device based on knowledge processing |
| CN116401347A (en) * | 2023-03-09 | 2023-07-07 | 北京海致星图科技有限公司 | Flexible hooking method based on knowledge capability and robot |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107180105A (en) * | 2017-06-01 | 2017-09-19 | 北京果毅科技有限公司 | A kind of update method, device and the electronic equipment of the knowledge base of intelligent assistant |
| CN108687760A (en) * | 2017-03-30 | 2018-10-23 | 株式会社安川电机 | Robot motion instructs generation method and robot motion command generating device |
| US10304455B1 (en) * | 2018-02-09 | 2019-05-28 | Wipro Limited | Method and system for performing a task based on user input |
| CN111098301A (en) * | 2019-12-20 | 2020-05-05 | 西南交通大学 | Control method of task type robot based on scene knowledge graph |
| CN111203878A (en) * | 2020-01-14 | 2020-05-29 | 北京航空航天大学 | Robot sequence task learning method based on visual simulation |
| CN111258571A (en) * | 2020-02-11 | 2020-06-09 | 达闼科技（北京）有限公司 | Robot application program development method, system, device and storage medium |
| US10792810B1 (en) * | 2017-12-14 | 2020-10-06 | Amazon Technologies, Inc. | Artificial intelligence system for learning robotic control policies |
| CN113199472A (en) * | 2021-04-14 | 2021-08-03 | 达闼机器人有限公司 | Robot control method, device, storage medium, electronic device, and robot |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11345030B2 (en) * | 2019-05-28 | 2022-05-31 | Intel Corporation | Methods and apparatus for complex assembly via autonomous robots using reinforcement learning action primitives |
-
2021
- 2021-12-14 CN CN202111529268.0A patent/CN114185281B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108687760A (en) * | 2017-03-30 | 2018-10-23 | 株式会社安川电机 | Robot motion instructs generation method and robot motion command generating device |
| CN107180105A (en) * | 2017-06-01 | 2017-09-19 | 北京果毅科技有限公司 | A kind of update method, device and the electronic equipment of the knowledge base of intelligent assistant |
| US10792810B1 (en) * | 2017-12-14 | 2020-10-06 | Amazon Technologies, Inc. | Artificial intelligence system for learning robotic control policies |
| US10304455B1 (en) * | 2018-02-09 | 2019-05-28 | Wipro Limited | Method and system for performing a task based on user input |
| CN111098301A (en) * | 2019-12-20 | 2020-05-05 | 西南交通大学 | Control method of task type robot based on scene knowledge graph |
| CN111203878A (en) * | 2020-01-14 | 2020-05-29 | 北京航空航天大学 | Robot sequence task learning method based on visual simulation |
| CN111258571A (en) * | 2020-02-11 | 2020-06-09 | 达闼科技（北京）有限公司 | Robot application program development method, system, device and storage medium |
| CN113199472A (en) * | 2021-04-14 | 2021-08-03 | 达闼机器人有限公司 | Robot control method, device, storage medium, electronic device, and robot |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114185281A (en) | 2022-03-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114185281B (en) | Robot simulation platform control method, terminal and medium based on knowledge base | |
| CN107610217B (en) | Nuclear power equipment virtual identification display system and method | |
| KR100929252B1 (en) | 3D stereoscopic content-based interactive technology education | |
| CN113362671B (en) | Marine nuclear emergency drilling simulation system and drilling method | |
| CN106502890A (en) | Method for generating test case and system | |
| CN110852695A (en) | Task approval method and device, server and storage medium | |
| Cassola et al. | A novel tool for immersive authoring of experiential learning in virtual reality | |
| Li et al. | A low-complexity method for authoring an interactive virtual maintenance training system of hydroelectric generating equipment | |
| Bruzzone et al. | Mixed reality for industrial applications: interactions in human-machine system and modelling in immersive virtual environment | |
| Perri et al. | Learning mathematics in an immersive way | |
| CN113268895B (en) | Combined simulation method, device, equipment and medium based on semantic mapping | |
| CN109359792B (en) | Dynamic modeling-based guidance control system and method | |
| Zhou et al. | H-GOMS: a model for evaluating a virtual-hand interaction system in virtual environments | |
| CN109871636A (en) | A kind of distribution of Virtual Simulative Experiment task and generation method and system | |
| CN112102454A (en) | Method, device and equipment for driving facial expressions and storage medium | |
| CN114131598B (en) | Hierarchical robot skill expression method, terminal and computer readable storage medium | |
| CN113228056A (en) | Runtime hardware simulation method, device, equipment and storage medium | |
| Kose et al. | Towards Assisting Interactive Reality: Interactive Reality for Education, Data Analysis and Industry | |
| CN112561276A (en) | Operation risk demonstration method and device, storage medium and electronic device | |
| KR101965732B1 (en) | the method for controling motion platform using the authoring tool | |
| CN114373359B (en) | Method and device for controlling aircraft cockpit and readable medium | |
| CN116188209B (en) | Virtual reality's physical experiment emulation intelligent engine system | |
| Xie et al. | A VR-based interactive teaching and practice environment for supporting the whole process of mining engineering education | |
| Xu | Multi-logic interactive model of virtual reality based on digital media | |
| US20240135836A1 (en) | Method for rendering mathematical models of systems into interactive training simulators |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |