CN115213889A - Robot control method, device, storage medium and robot - Google Patents
Robot control method, device, storage medium and robot Download PDFInfo
- Publication number
- CN115213889A CN115213889A CN202110951159.1A CN202110951159A CN115213889A CN 115213889 A CN115213889 A CN 115213889A CN 202110951159 A CN202110951159 A CN 202110951159A CN 115213889 A CN115213889 A CN 115213889A
- Authority
- CN
- China
- Prior art keywords
- target
- process controller
- task
- control information
- implementer
- 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.)
- Granted
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1602—Programme controls characterised by the control system, structure, architecture
-
- 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]
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Manipulator (AREA)
Abstract
The disclosure relates to a robot control method, a device, a storage medium and a robot, wherein the method comprises the following steps: when the target process controller is called, processing manual control information which is manually input and aims at the target process controller and artificial intelligence control information which is generated by an artificial intelligence subsystem and aims at the target process controller to obtain comprehensive control information; and controlling a target task realizing device corresponding to the target process controller based on the comprehensive control information. The method disclosed by the invention can improve the efficiency of executing the robot task.
Description
Technical Field
The present disclosure relates to the field of robot technology, and in particular, to a robot control method, apparatus, storage medium, and robot.
Background
With the development of the robot technology, the artificial intelligent robot is more and more appeared in daily life and work. The artificial intelligence robot is one of the robot branches, when the artificial intelligence robot works, action decision can be carried out through artificial intelligence control, in addition, action decision can also be carried out through artificial control, however, when the action decision is carried out through artificial control, an artificial intelligence system is off line, and the whole action of the robot is manually operated, so that the task execution efficiency of the robot is low.
Disclosure of Invention
The invention aims to provide a robot control method, a robot control device, a storage medium and a robot, and solves the problem that when action decision is made through manual control, the robot has low task execution efficiency.
In order to achieve the above object, in a first aspect, the present disclosure provides a robot control method applied to a target process controller in at least one process controller included in a robot control system, where the robot control system further includes an artificial intelligence subsystem and at least one task implementer, and each process controller is connected with a subordinate task implementer and/or a subordinate process controller, the method including:
when the target process controller is called, processing manual control information which is manually input and aims at the target process controller and artificial intelligence control information which is generated by an artificial intelligence subsystem and aims at the target process controller to obtain comprehensive control information;
and controlling a target task realizing device corresponding to the target process controller based on the comprehensive control information.
Optionally, the controlling the target task implementer corresponding to the target process controller based on the comprehensive control information includes:
when the task execution strategy of the target process controller is a first strategy, sequentially controlling each target task implementer based on the comprehensive control information until each target task implementer is controlled; or
When the task execution strategy of the target process controller is a second strategy, sequentially controlling each target task implementer based on the comprehensive control information until the target task implementer which successfully executes the task under the control is determined; or
And when the task execution strategy of the target process controller is a third strategy, simultaneously controlling each target task implementer based on the comprehensive control information.
Optionally, the method further comprises:
determining a subordinate task implementer connected with the target process controller as the target task implementer, and determining a task implementer indirectly connected with the target process controller through the subordinate process controller as the target task implementer.
Optionally, the process controllers and task implementers in the robot control system are distributed in a tree structure, and the determining of the subordinate task implementer connected to the target process controller as the target task implementer and the determining of the task implementer indirectly connected to the target process controller through the subordinate task controller as the target task implementer includes:
when the target process controller is searched as a father node, the leaf task realizators on the corresponding leaf nodes are searched, and the father node comprises at least one stage of leaf nodes;
determining the leaf task implementer as the target task implementer.
Optionally, the controlling the target task implementer corresponding to the target process controller based on the comprehensive control information includes:
and outputting a first calling instruction based on the comprehensive control information, wherein the first calling instruction is used for calling a subordinate flow controller connected with the target flow controller so as to realize the control of the target task implementer through the subordinate flow controller.
Optionally, the controlling the target task implementer corresponding to the target process controller based on the comprehensive control information includes:
and outputting a second calling instruction based on the comprehensive control information, wherein the second calling instruction is used for calling the target task implementer to execute a preset task.
Optionally, the artificial intelligence control information includes first control information that satisfies a preset condition, and the method further includes:
and under the condition that the artificial intelligence control information comprises the first control information, calling a target task realizing device corresponding to a target process controller to enable the target task realizing device to output prompt information, wherein the prompt information is used for guiding manual input of artificial control information for replacing the first control information.
In a second aspect, the present disclosure further provides a robot control apparatus applied to a target process controller in at least one process controller included in a robot control system, the robot control system further includes an artificial intelligence subsystem and at least one task implementer, each process controller is connected with a lower level task implementer and/or a lower level process controller, the apparatus includes:
the control information processing module is used for processing manual control information which is manually input and aims at the target process controller and artificial intelligence control information which is generated by an artificial intelligence subsystem and aims at the target process controller to obtain comprehensive control information when the target process controller is called;
and the control module is used for controlling the target task realizator corresponding to the target process controller based on the comprehensive control information.
In a third aspect, the present disclosure also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method of the first aspect.
In a fourth aspect, the present disclosure also provides a robot control device, including:
a memory having a computer program stored thereon;
a processor for executing the computer program in the memory to perform the steps of the method of the first aspect.
In a fifth aspect, the present disclosure further provides a robot, including a process controller, a task implementer, and an artificial intelligence subsystem, where the process controller includes a target process controller;
the target process controller is to: when the target process controller is called, processing manual control information which is manually input and aims at the target process controller and artificial intelligence control information which is generated by an artificial intelligence subsystem and aims at the target process controller to obtain comprehensive control information; and controlling a target task realizing device corresponding to the target process controller based on the comprehensive control information.
According to the technical scheme, when the target process controller is called, the artificial control information which is manually input and aims at the target process controller and the artificial intelligence control information which is generated by the artificial intelligence subsystem and aims at the target process controller are processed to obtain the comprehensive control information, and then the target task realizing device corresponding to the target process controller is controlled based on the comprehensive control information. Because in the control process of the robot, the comprehensive control information is generated by the artificial control information and the artificial intelligence control information together, after the robot is controlled manually, the whole action of the robot is not required to be completely operated manually, and the artificial intelligence subsystem still plays a role, so that the difficulty of manual operation is reduced, the efficiency of manual control and manual take-over is improved, and the task execution efficiency of the robot is also improved. In addition, because the manual work only participates in the control of the partial target task implementer of the robot, the control system does not need to be switched additionally, and therefore, after the manual control is finished, the robot can quickly return to the state controlled by the artificial intelligence system.
Additional features and advantages of the disclosure will be set forth in the detailed description which follows.
Drawings
The accompanying drawings, which are included to provide a further understanding of the disclosure and are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the description serve to explain the disclosure without limiting the disclosure. In the drawings:
fig. 1 is a schematic diagram of a connection relationship between a process controller and a task implementer according to an embodiment of the present disclosure.
Fig. 2 is a schematic flowchart of a robot control method according to an embodiment of the disclosure.
Fig. 3 is a schematic structural diagram of a robot control device according to an embodiment of the present disclosure.
Fig. 4 is a schematic structural diagram of another robot control device according to an embodiment of the present disclosure.
Detailed Description
The following detailed description of specific embodiments of the present disclosure is provided in connection with the accompanying drawings. It should be understood that the detailed description and specific examples, while indicating the present disclosure, are given by way of illustration and explanation only, not limitation.
Before the embodiments of the present disclosure are explained in detail, a possible connection relationship between the process controller and the task implementer related to the embodiments of the present disclosure is exemplarily shown.
Referring to fig. 1, fig. 1 is a schematic diagram illustrating a connection relationship between a process controller and a task implementer according to an exemplary embodiment of the present disclosure.
As shown in fig. 1, the system comprises four levels from top to bottom, wherein the first level comprises a flow controller 11, the second level comprises a flow controller 21, a flow controller 22 and a flow controller 23 connected with the flow controller 11, the third level comprises a task implementer 31, a flow controller 32 and a task implementer 33 simultaneously connected with the flow controller 21 and the flow controller 22, the third level further comprises a task implementer 34 and a task implementer 35 connected with the flow controller 23, and the fourth level comprises a task implementer 41 connected with the flow controller 32.
Wherein, the connected ends are all task realizators.
The process controller 21, the process controller 22, and the process controller 23 are all lower-level process controllers connected to the process controller 11, the task implementer 31 and the task implementer 33 are all lower-level task implementers connected to the process controller 21, the process controller 32 is a lower-level process controller connected to the process controller 21, and so on.
Referring to fig. 2, fig. 2 is a flowchart illustrating a robot control method according to an exemplary embodiment of the present disclosure, the method is applied to a target process controller in at least one process controller included in a robot control system, the robot control system further includes an artificial intelligence subsystem and at least one task implementer, each process controller is connected with a lower level task implementer and/or a lower level process controller, and as shown in fig. 2, the robot control method includes steps S210 to S220. Specifically, the method comprises the following steps:
s210, when the target process controller is called, processing the artificial control information which is manually input and aims at the target process controller and the artificial intelligence control information which is generated by the artificial intelligence subsystem and aims at the target process controller to obtain comprehensive control information.
The process controller can be understood as a module for making a robot action decision based on the acquired control information, and can process the acquired control information to generate comprehensive control information.
The acquired control information may include two types, namely, artificial control information and artificial intelligence control information.
The manual control information is manually input control information, and may be input by, for example, text, clicking a touch button, or voice.
The artificial intelligence control information refers to control information generated by the artificial intelligence subsystem.
The artificial intelligence subsystem is used for providing artificial intelligence decision-making for the robot, and the artificial intelligence subsystem can carry out artificial intelligence processing based on the collected environmental information and output artificial intelligence control information corresponding to each process controller. For example, in the task of picking an apple, the picked image is recognized, the position information of the apple is output, so that the robot is controlled to move to the vicinity of the apple, the image of the apple is continuously picked after the apple is moved to the vicinity of the apple, whether the apple is ripe or not is further recognized, and the picking information is output after the apple is recognized to be ripe, so that the robot is controlled to pick the ripe apple.
The integrated control information may be understood as control information corresponding to a target task implementer corresponding to the target process control, and when there are a plurality of target task implementers, the integrated control information may include control information corresponding to each target task implementer.
A task implementer may be understood as an actuator for the robot to perform various actions.
A target process controller may be understood as a process controller that, when in operation, is capable of processing based on both artificial control information and artificial intelligence control information.
In some cases, all of the flow controllers in a robotic control system may be configured to be manually intervened in control, and thus, in some embodiments, the target flow controller may be any of all of the flow controllers.
It will be appreciated that a task performed by a robot may be subdivided into a plurality of actions. For example, the task of picking apples can be divided into the actions of identifying apples, moving to the vicinity of the apples, lifting arms, picking, putting into a basket and the like, and the actions have a sequential execution sequence, for example, the sequence of automatically identifying the apples, then moving to the vicinity of the apples, then lifting arms, picking, and then putting into the basket.
Wherein a certain action may be manually intervened, e.g. a manual intervention controls the arm raising action. And in the arm lifting action, the control factors such as the initial position of the arm lifting, the arm lifting direction, the end position of the arm lifting, the arm lifting speed and the like can be included, if the arm lifting speed is required to be increased or decreased manually, manual control information for controlling the arm lifting speed can be input manually, and the manual intelligent control information is continuously input by the manual intelligent subsystem because the initial position of the arm lifting, the arm lifting direction, the end position of the arm lifting and the like are not changed. Thus, the process controller controlling the arm raising action may be configured as a target process controller. Then, in the process of completing the task of picking apples, when the moment of arm lifting action is executed, the target process controller corresponding to the arm lifting action can be called, and at the moment, the target process controller can acquire artificial control information for controlling the arm lifting speed and artificial intelligent control information for controlling the initial position, the arm lifting direction, the end position and the like of the arm lifting, process the control information and obtain comprehensive control information for controlling the arm lifting action.
And S220, controlling the target task realizator corresponding to the target process controller based on the comprehensive control information.
In the embodiment of the disclosure, after the comprehensive control information is obtained, the target task implementer corresponding to the target process controller can be controlled. Continuing with the foregoing example, the task implementer corresponding to the arm raising action may be controlled to complete the arm raising action.
By adopting the technical scheme, when the target process controller is called, the artificial control information aiming at the target process controller and the artificial intelligence control information aiming at the target process controller, which are manually input, are processed to obtain the comprehensive control information, and then the target task realizing device corresponding to the target process controller is controlled based on the comprehensive control information. Because the control process of the robot is the comprehensive control information generated by the artificial control information and the artificial intelligence control information together, after the control of the robot is intervened by the human, the whole action of the robot is not required to be operated completely by the human, and the artificial intelligence subsystem still plays a role, thereby reducing the difficulty of manual operation and control, improving the efficiency of manual control and manual takeover, and also improving the task execution efficiency of the robot. In addition, because the manual work only participates in the control of the partial target task implementer of the robot, the control system does not need to be switched additionally, and therefore, after the manual control is finished, the robot can quickly return to the state controlled by the artificial intelligence system.
In some cases, the number of the target task implementers may be multiple, and with the foregoing example, for the arm raising motion, the task implementer corresponding to the joint positioning, the task implementer corresponding to the joint rotation direction, the task implementer corresponding to the joint rotation speed, and the like may be used, and under different task requirements, the target process controller may have different task execution strategies, in which case, the target task implementer corresponding to the target process controller is controlled based on the comprehensive control information, and the method includes the following steps:
when the task execution strategy of the target process controller is a first strategy, sequentially controlling each target task implementer based on the comprehensive control information until each target task implementer is controlled; or
When the task execution strategy of the target process controller is a second strategy, sequentially controlling each target task implementer based on the comprehensive control information until the target task implementer which successfully executes the task under the control is determined; or
And when the task execution strategy of the target process controller is a third strategy, controlling each target task implementer based on the comprehensive control information.
In the embodiment of the disclosure, the task execution policy of the target process controller may include a first policy, a second policy, and a third policy.
The first policy may be understood as a policy for controlling each target task implementer one by one, that is, when the task execution policy of the target process controller is the first policy, the target process controller may control each target task implementer in sequence according to a preset control sequence of the target task implementer based on the comprehensive control information until each target task implementer is controlled. Regardless of whether task execution failed or succeeded when each target task implementer was controlled.
The second policy may be understood as a policy that, after controlling the first target task implementer that successfully executes, the subsequent task implementers are not continuously controlled any more, that is, when the task execution policy of the target process controller is the second policy, the target process controller may, based on the comprehensive control information, sequentially control the target task implementers according to a preset control sequence of the target task implementers until the target task implementer that successfully executes the task under control is determined. For example, if the first target task implementer is controlled to determine that the task is successfully executed, the subsequent target task implementers are not called.
The third policy may be understood as a policy for invoking all target task implementers, that is, when the task execution policy of the target process controller is the third policy, the target process controller may control each target task implementer simultaneously based on the integrated control information. Regardless of whether task execution failed or succeeded when each target task implementer was controlled.
By adopting the technical scheme, the robot can meet actual requirements by setting various different task execution strategies, select the adaptive task execution strategy, adapt to different task conditions and improve the applicability of the robot.
As can be seen from the foregoing, the target process controller may be connected to a lower task implementer and/or a lower process controller, in which case, the robot control method according to the embodiment of the present disclosure may further include: and determining the lower-level task implementer connected with the target process controller as the target task implementer, and determining the task implementer indirectly connected with the target process controller through the lower-level process controller as the target task implementer.
The target task implementer corresponding to the target process controller in the embodiments of the present disclosure may have various situations.
When the target process controller is connected to only the lower task implementer, the lower task implementer connected to the target process controller may be determined to be the target task implementer.
When the target process controller is connected with the subordinate task implementer and the subordinate process controller at the same time, the subordinate task implementer connected with the target process controller can be determined as the target task implementer, and meanwhile, the task implementer indirectly connected with the target process controller through the subordinate process controller can be determined as the target task implementer.
It can be understood that the more the called target process controller is located at the upper layer, the more tasks of the robot can be controlled.
By adopting the multiple target task realizators, the more detailed division of the actions executed by the robot is realized, so that the robot is more finely controlled, and meanwhile, the input manual control information is conveniently utilized to control partial actions of the robot.
Further, in some embodiments, the flow controllers and the task implementers in the robot control system are distributed in a tree structure, in which case, a subordinate task implementer connected to the target flow controller is determined as the target task implementer, and a task implementer indirectly connected to the target flow controller through the subordinate task controller is determined as the target task implementer, including the steps of:
when the target process controller is searched as a father node, the leaf task implementer on the corresponding leaf node, wherein the father node comprises at least one level of leaf node;
and determining the leaf task implementer as a target task implementer.
With continued reference to fig. 1, fig. 1 may be understood as a tree structure diagram, wherein a flow controller at a first level may be regarded as a root node, a level above may be regarded as a parent node at a level below, and a level below the parent node may be regarded as a leaf node of the level of the parent node. A leaf task implementer may be understood as a task implementer on a leaf node.
In this case, when a certain target process controller is called, when the target process controller can be searched as a parent node, the leaf task implementer on the corresponding leaf node is determined, and the leaf task implementer is determined as the target task implementer.
For example, assuming that the target flow controller to be called currently is the flow controller 21, when the flow controller 21 is taken as a parent node, the corresponding leaf nodes are the three nodes 31, 32, and 33 of the third hierarchy and the node 41 of the fourth hierarchy. The target task implementers determined at this time are the task implementer 31, the task implementer 33, and the task implementer 41.
By adopting the method, the flow controllers and the task implementers are distributed in a tree structure, so that the target task implementers corresponding to the target flow controllers can be determined quickly, and the logic for determining the target task implementers in the target flow controllers is simplified.
In combination with the foregoing, in some embodiments, the target task implementer may be a task implementer indirectly connected to the target process controller through a lower-level process controller, in which case, based on the integrated control information, controlling the target task implementer corresponding to the target process controller may include the steps of:
and outputting a first calling instruction based on the comprehensive control information, wherein the first calling instruction is used for calling a lower flow controller connected with the target flow controller so as to realize the control of the target task realization device through the lower flow controller.
It can be understood that, when the target task implementer is a task implementer indirectly connected to the target process controller through a lower process controller, the target process controller cannot directly control the indirectly connected target task implementer but needs to control through an upper process controller directly connected to the target task implementer, and thus, the target process controller may output a first call instruction based on the integrated control information to call the lower process controller connected to the target process controller to implement control of the target task implementer through the lower process controller.
In some embodiments, the integrated control information may include control information of a lower level flow controller corresponding to the call target flow controller.
It should be noted that the control of the target task implementer by the lower-level flow controller may be based on artificial intelligence control information and/or artificial control information, and is determined according to the actual task and the configuration situation.
In other embodiments, the target task implementer may be a lower task implementer directly connected to the target process controller, in which case, controlling the target task implementer corresponding to the target process controller based on the integrated control information may include:
outputting a second calling instruction based on the comprehensive control information, wherein the second calling instruction is used for calling the target task implementer to execute the preset task
It is to be understood that, when the target task implementer is a subordinate task implementer connected to the target process controller, the target process controller may directly control the directly connected target task implementer, and thus, the target process controller may output a second call instruction to call the subordinate target task implementer connected to the target process controller based on the integrated control information.
The integrated control information may include control information corresponding to the target task implementer, and the control information may indicate that the target task implementer successfully executes the preset task or fails to execute the preset task, and when the control information indicates that the target task implementer fails to execute the preset task, the second call instruction may not be issued, and when the control information indicates that the target task implementer successfully executes the preset task, the second call instruction may be issued to call a lower-level target task implementer connected to the target process controller to execute the preset task.
Illustratively, with continued reference to fig. 1, the target process controller 21 corresponds to three target task implementers, in this case, the integrated control information generated by the target process controller may include 3 pieces of control information, and the three pieces of control information respectively correspond to one target task implementer, that is, the control information 1 corresponds to the target task implementer 31, the control information 2 corresponds to the target task implementer 41, and the control information 3 corresponds to the target task implementer 33, in this case, the target process controller may issue a corresponding call instruction based on the control information indicating that the target task implementer successfully executes the preset task.
As can be seen from the foregoing, for the target task implementer 41, since it is indirectly connected to the target process controller, in this case, if the control information 2 indicates that the target task implementer 41 successfully executes the preset task, the target process controller issues a first call instruction for calling the lower process controller 32 connected to the target process controller, so as to implement control over the target task implementer 41 through the lower process controller 32.
Further, in some embodiments, the artificial intelligence control information includes first control information that satisfies a preset condition, in which case the robot control method of the embodiments of the present disclosure may further include: and under the condition that the artificial intelligence control information comprises the first control information, calling a target task implementer corresponding to the target process controller to enable the target task implementer to output prompt information, wherein the prompt information is used for guiding manual input of artificial control information for replacing the first control information.
The preset condition may be that the confidence of the artificial intelligence control information output by the artificial intelligence subsystem is lower than a preset confidence threshold. That is, in the case where there is first control information whose confidence is lower than the confidence threshold among the artificial intelligence control information output by the artificial intelligence subsystem, artificial control information for guiding the artificial input for replacing the first control information may be output.
Considering that when the artificial intelligence subsystem outputs artificial intelligence control information, it may output artificial intelligence control information whose confidence is lower than a preset confidence threshold, that is, first control information, indicating that the artificial intelligence subsystem cannot determine the accuracy of the control information, and if the first control information is used, an erroneous task execution result may be caused, in this case, the target process controller may call a target task implementer corresponding to the target process controller to output prompt information to guide manual input of artificial control information for replacing the first control information. That is, when the manual control information for the target process controller is manually input, the corresponding first control information may be replaced with the manual control information, and then the subsequent steps of processing the manually input manual control information for the target process controller and the artificial intelligence control information generated by the artificial intelligence subsystem for the target process controller are performed to obtain the integrated control information.
In addition, it is understood that the first control information may be all information in the artificial intelligence control information, or may be partial information in the artificial intelligence control information, such as one or more pieces of information. In this case, the step of processing the manually input artificial control information for the target process controller and the artificial intelligence control information generated by the artificial intelligence subsystem for the target process controller in the robot control method according to the embodiment of the present disclosure to obtain the integrated control information may include: and processing the manually input manual control information aiming at the target process controller and the second control information aiming at the target process controller generated by the artificial intelligence subsystem to obtain the comprehensive control information.
When the first control information is part of the artificial intelligence control information and the target process controller is called, the artificial control information which is manually input and aims at the target process controller and the second control information which is generated by the artificial intelligence subsystem and aims at the target process controller can be processed to obtain the comprehensive control information.
Optionally, the target task implementer for outputting the prompt message at this time may be a display screen, a speaker, or the like.
Therefore, by adopting the mode, when the artificial intelligence subsystem can not determine the accuracy of the control information, the target task implementer corresponding to the target process controller can be called to output the prompt information, and the artificial control information for replacing the first control information is guided to be manually input, so that the artificial help decision is made, and the success rate of task execution is improved.
In addition, in some embodiments, after acquiring the artificial control information, the artificial intelligence system may use the acquired artificial control information as a sample for supervised learning, so as to train the corresponding artificial intelligence model, thereby improving the decision-making capability of the artificial intelligence model in the subsequent artificial intelligence subsystem in making a decision.
It should be noted that the artificial control information and the artificial intelligence control information in the embodiments of the present disclosure may be stored in a database, and when a certain target process controller is called, the target process controller may obtain the corresponding artificial control information and the corresponding artificial intelligence control information from the database.
In addition, the robot control method according to the embodiment of the present disclosure is a one-cycle execution method, and can be repeatedly executed in a cycle.
Referring to fig. 3, an exemplary embodiment of the present disclosure further provides a robot control apparatus 300, which is applied to a target process controller of at least one process controller included in a robot control system, the robot control system further includes an artificial intelligence subsystem and at least one task implementer, each process controller is connected to a lower task implementer and/or a lower process controller, and the apparatus 300 includes:
the control information processing module 310 is configured to, when the target process controller is called, process artificial control information that is manually input and is directed to the target process controller, and artificial intelligence control information that is generated by the artificial intelligence subsystem and is directed to the target process controller, so as to obtain integrated control information;
and a control module 320, configured to control the target task implementer corresponding to the target process controller based on the integrated control information.
In some embodiments, the target task implementer is multiple, and the control module 320 includes:
the first control sub-module is used for sequentially controlling each target task implementer based on the comprehensive control information when the task execution strategy of the target process controller is a first strategy until each target task implementer is controlled;
the second control sub-module is used for sequentially controlling each target task implementer based on the comprehensive control information when the task execution strategy of the target process controller is a second strategy until the target task implementer which successfully executes the task under the control is determined;
and the third control sub-module is used for controlling each target task implementer simultaneously based on the comprehensive control information when the task execution strategy of the target process controller is a third strategy.
In some embodiments, the apparatus 300 further comprises:
and the target task implementer determining module is used for determining a subordinate task implementer connected with the target process controller as the target task implementer and determining a task implementer indirectly connected with the target process controller through the subordinate process controller as the target task implementer.
In some embodiments, the process controllers and the task implementers in the robot control system are distributed in a tree structure, and the target task implementer determination module is further configured to search for a leaf task implementer on a corresponding leaf node when the target process controller is used as a parent node, where the parent node includes at least one level of leaf nodes; and determining the leaf task implementer as a target task implementer.
In some embodiments, the target task implementer is a task implementer indirectly connected to the target process controller through a subordinate process controller, and the control module 320 is further configured to output a first call instruction based on the integrated control information, the first call instruction being used to call the subordinate process controller connected to the target process controller to implement control of the target task implementer through the subordinate process controller.
In some embodiments, the control module 320 is further configured to output a second call instruction based on the integrated control information, where the second call instruction is used to call the target task implementer to execute the preset task.
In some embodiments, the artificial intelligence control information includes first control information satisfying a preset condition, and the apparatus 300 further includes a calling module, configured to, if it is determined that the first control information is included in the artificial intelligence control information, call a target task implementer corresponding to the target process controller, so that the target task implementer outputs prompt information, where the prompt information is used to guide a human to input artificial control information for replacing the first control information.
With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
Fig. 4 is a block diagram illustrating a robot control device 400 according to an exemplary embodiment, the robot control device 400 may be, for example, a portion of a robot. As shown in fig. 4, the robot controller 400 may include: a processor 401 and a memory 402. The robotic control device 400 may also include one or more of a multimedia component 403, an input/output (I/O) interface 404, and a communication component 405.
The processor 401 is configured to control the overall operation of the robot control device 400, so as to complete all or part of the steps in the robot control method. The memory 402 is used to store various types of data to support operation at the robotic control device 400, which may include, for example, instructions for any application or method operating on the robotic control device 400, as well as application-related data, such as contact data, messaging, pictures, audio, video, and so forth. The Memory 402 may be implemented by any type of volatile or non-volatile Memory device or combination thereof, such as Static Random Access Memory (SRAM), electrically Erasable Programmable Read-Only Memory (EEPROM), erasable Programmable Read-Only Memory (EPROM), programmable Read-Only Memory (PROM), read-Only Memory (ROM), magnetic Memory, flash Memory, magnetic disk or optical disk. The multimedia components 403 may include screen and audio components. Wherein the screen may be, for example, a touch screen and the audio component is used for outputting and/or inputting audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may further be stored in the memory 402 or transmitted through the communication component 405. The audio assembly also includes at least one speaker for outputting audio signals. The I/O interface 404 provides an interface between the processor 401 and other interface modules, such as a keyboard, mouse, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 405 is used for wired or wireless communication between the robot controller 400 and other devices. Wireless Communication, such as Wi-Fi, bluetooth, near Field Communication (NFC), 2G, 3G, 4G, NB-IOT, eMTC, or other 5G, etc., or one or a combination thereof, which is not limited herein. The corresponding communication component 405 may therefore include: wi-Fi modules, bluetooth modules, NFC modules, and the like.
In an exemplary embodiment, the robot controller 400 may be implemented by one or more Application Specific Integrated Circuits (ASICs), digital Signal Processors (DSPs), digital Signal Processing Devices (DSPDs), programmable Logic Devices (PLDs), field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components for performing the above-described robot control method.
In another exemplary embodiment, a computer readable storage medium comprising program instructions which, when executed by a processor, implement the steps of the robot control method described above is also provided. For example, the computer readable storage medium may be the above-described memory 402 comprising program instructions executable by the processor 401 of the robot control device 400 to perform the above-described robot control method.
In another exemplary embodiment, a computer program product is also provided, which comprises a computer program executable by a programmable apparatus, the computer program having code portions for performing the robot control method described above when executed by the programmable apparatus.
In another exemplary embodiment, there is also provided a robot, including a process controller, a task implementer, and an artificial intelligence subsystem, the process controller including a target process controller; the target process controller is to: when the target process controller is called, processing manual control information which is manually input and aims at the target process controller and artificial intelligence control information which is generated by an artificial intelligence subsystem and aims at the target process controller to obtain comprehensive control information; and controlling a target task realization device corresponding to the target process controller based on the comprehensive control information.
The preferred embodiments of the present disclosure are described in detail with reference to the accompanying drawings, however, the present disclosure is not limited to the specific details of the above embodiments, and various simple modifications may be made to the technical solution of the present disclosure within the technical idea of the present disclosure, and these simple modifications all belong to the protection scope of the present disclosure.
It should be noted that the various features described in the above embodiments may be combined in any suitable manner without departing from the scope of the invention. To avoid unnecessary repetition, the disclosure does not separately describe various possible combinations.
In addition, any combination of various embodiments of the present disclosure may be made, and the same should be considered as the disclosure of the present disclosure, as long as it does not depart from the spirit of the present disclosure.
Claims (11)
1. A robot control method is characterized in that the robot control method is applied to a target process controller in at least one process controller included in a robot control system, the robot control system further comprises an artificial intelligence subsystem and at least one task implementer, each process controller is connected with a lower-level task implementer and/or a lower-level process controller, and the method comprises the following steps:
when the target process controller is called, processing manual control information which is manually input and aims at the target process controller and artificial intelligence control information which is generated by an artificial intelligence subsystem and aims at the target process controller to obtain comprehensive control information;
and controlling a target task realizing device corresponding to the target process controller based on the comprehensive control information.
2. The robot control method according to claim 1, wherein the plurality of target task implementers are provided, and the controlling of the target task implementer corresponding to the target process controller based on the integrated control information includes:
when the task execution strategy of the target process controller is a first strategy, sequentially controlling each target task implementer based on the comprehensive control information until each target task implementer is controlled; or
When the task execution strategy of the target process controller is a second strategy, sequentially controlling each target task implementer based on the comprehensive control information until the target task implementer which successfully executes the task under the control is determined; or
And when the task execution strategy of the target process controller is a third strategy, simultaneously controlling each target task implementer based on the comprehensive control information.
3. The robot control method of claim 1, further comprising:
determining a subordinate task implementer connected with the target process controller as the target task implementer, and determining a task implementer indirectly connected with the target process controller through the subordinate process controller as the target task implementer.
4. The robot control method according to claim 3, wherein the flow controllers and the task implementers in the robot control system are distributed in a tree structure, and the determining of the lower task implementer connected to the target flow controller as the target task implementer and the determining of the task implementer indirectly connected to the target flow controller through the lower flow controller as the target task implementer comprise:
when the target process controller is searched as a father node, the leaf task realizators on the corresponding leaf nodes are searched, and the father node comprises at least one stage of leaf nodes;
determining the leaf task implementer as the target task implementer.
5. The robot control method according to any one of claims 1 to 4, wherein the target task implementer is a task implementer that is indirectly connected to the target process controller via a subordinate process controller, and the controlling of the target task implementer corresponding to the target process controller based on the integrated control information includes:
and outputting a first calling instruction based on the comprehensive control information, wherein the first calling instruction is used for calling a lower flow controller connected with the target flow controller so as to realize the control of the target task realizing device through the lower flow controller.
6. The robot control method according to any one of claims 1 to 4, wherein the target task implementer is a subordinate task implementer directly connected to the target process controller, and the controlling of the target task implementer corresponding to the target process controller based on the integrated control information includes:
and outputting a second calling instruction based on the comprehensive control information, wherein the second calling instruction is used for calling the target task implementer to execute a preset task.
7. A robot control method according to any of claims 1-4, characterized in that the artificial intelligence control information comprises first control information satisfying a preset condition, the method further comprising:
and under the condition that the artificial intelligence control information comprises the first control information, calling a target task implementer corresponding to a target process controller to enable the target task implementer to output prompt information, wherein the prompt information is used for guiding manual input of artificial control information for replacing the first control information.
8. A robot control device, characterized in that, applied to a target process controller in at least one process controller included in a robot control system, the robot control system further includes an artificial intelligence subsystem and at least one task implementer, each process controller is connected with a subordinate task implementer and/or a subordinate process controller, the device includes:
the control information processing module is used for processing manual control information which is manually input and aims at the target process controller and artificial intelligence control information which is generated by an artificial intelligence subsystem and aims at the target process controller to obtain comprehensive control information when the target process controller is called;
and the control module is used for controlling a target task realization device corresponding to the target process controller based on the comprehensive control information.
9. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.
10. A robot control apparatus, comprising:
a memory having a computer program stored thereon;
a processor for executing the computer program in the memory to carry out the steps of the method of any one of claims 1 to 7.
11. A robot is characterized by comprising a process controller, a task implementer and an artificial intelligence subsystem, wherein the process controller comprises a target process controller;
the target process controller is to:
when the target process controller is called, processing manual control information which is manually input and aims at the target process controller and artificial intelligence control information which is generated by an artificial intelligence subsystem and aims at the target process controller to obtain comprehensive control information;
and controlling a target task realizing device corresponding to the target process controller based on the comprehensive control information.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110951159.1A CN115213889B (en) | 2021-08-18 | 2021-08-18 | Robot control method, device, storage medium and robot |
| PCT/CN2022/082338 WO2023019941A1 (en) | 2021-08-18 | 2022-03-22 | Robot control method and apparatus, storage medium, and robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110951159.1A CN115213889B (en) | 2021-08-18 | 2021-08-18 | Robot control method, device, storage medium and robot |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115213889A true CN115213889A (en) | 2022-10-21 |
| CN115213889B CN115213889B (en) | 2023-01-13 |
Family
ID=83606140
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110951159.1A Active CN115213889B (en) | 2021-08-18 | 2021-08-18 | Robot control method, device, storage medium and robot |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN115213889B (en) |
| WO (1) | WO2023019941A1 (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100153317A1 (en) * | 2008-12-11 | 2010-06-17 | Samsung Electronics Co., Ltd | Intelligent robot and control method thereof |
| CN108436918A (en) * | 2018-06-12 | 2018-08-24 | 芜湖乐创电子科技有限公司 | A kind of real-time operation robot based on automatic writing system identification |
| CN109074502A (en) * | 2018-07-26 | 2018-12-21 | 深圳前海达闼云端智能科技有限公司 | Method, apparatus, storage medium and the robot of training artificial intelligence model |
| JP2019212053A (en) * | 2018-06-05 | 2019-12-12 | 学校法人慶應義塾 | Information processing device, information processing method and program |
| US20210069905A1 (en) * | 2018-03-21 | 2021-03-11 | Beijing Orion Star Technology Co., Ltd. | Method and apparatus for generating action sequence of robot and storage medium |
| CN112809676A (en) * | 2021-01-11 | 2021-05-18 | 达闼机器人有限公司 | Joint actuator, robot, storage medium, and electronic device |
| CN112925802A (en) * | 2020-12-19 | 2021-06-08 | 添可智能科技有限公司 | Structured data generation method, device and storage medium |
| CN113051019A (en) * | 2021-03-31 | 2021-06-29 | 北京和信融慧信息科技有限公司 | Flow task execution control method, device and equipment |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9792546B2 (en) * | 2013-06-14 | 2017-10-17 | Brain Corporation | Hierarchical robotic controller apparatus and methods |
| US9050723B1 (en) * | 2014-07-11 | 2015-06-09 | inVia Robotics, LLC | Human and robotic distributed operating system (HaRD-OS) |
| CN111496774A (en) * | 2019-01-31 | 2020-08-07 | 大族激光科技产业集团股份有限公司 | Robot distributed control system and method thereof |
| CN109807903B (en) * | 2019-04-10 | 2021-04-02 | 博众精工科技股份有限公司 | Robot control method, device, equipment and medium |
| CN112549029B (en) * | 2020-12-03 | 2022-05-27 | 天津(滨海)人工智能军民融合创新中心 | Robot behavior control method and device based on behavior tree |
| CN112936267B (en) * | 2021-01-29 | 2022-05-27 | 华中科技大学 | Man-machine cooperation intelligent manufacturing method and system |
-
2021
- 2021-08-18 CN CN202110951159.1A patent/CN115213889B/en active Active
-
2022
- 2022-03-22 WO PCT/CN2022/082338 patent/WO2023019941A1/en unknown
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100153317A1 (en) * | 2008-12-11 | 2010-06-17 | Samsung Electronics Co., Ltd | Intelligent robot and control method thereof |
| US20210069905A1 (en) * | 2018-03-21 | 2021-03-11 | Beijing Orion Star Technology Co., Ltd. | Method and apparatus for generating action sequence of robot and storage medium |
| JP2019212053A (en) * | 2018-06-05 | 2019-12-12 | 学校法人慶應義塾 | Information processing device, information processing method and program |
| CN108436918A (en) * | 2018-06-12 | 2018-08-24 | 芜湖乐创电子科技有限公司 | A kind of real-time operation robot based on automatic writing system identification |
| CN109074502A (en) * | 2018-07-26 | 2018-12-21 | 深圳前海达闼云端智能科技有限公司 | Method, apparatus, storage medium and the robot of training artificial intelligence model |
| CN112925802A (en) * | 2020-12-19 | 2021-06-08 | 添可智能科技有限公司 | Structured data generation method, device and storage medium |
| CN112809676A (en) * | 2021-01-11 | 2021-05-18 | 达闼机器人有限公司 | Joint actuator, robot, storage medium, and electronic device |
| CN113051019A (en) * | 2021-03-31 | 2021-06-29 | 北京和信融慧信息科技有限公司 | Flow task execution control method, device and equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2023019941A1 (en) | 2023-02-23 |
| CN115213889B (en) | 2023-01-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3425849B1 (en) | State control method and device | |
| CN111523596B (en) | Target recognition model training method, device, equipment and storage medium | |
| US11055583B1 (en) | Machine learning for computing enabled systems and/or devices | |
| US11961509B2 (en) | Training a user-system dialog in a task-oriented dialog system | |
| CN106023994B (en) | Voice processing method, device and system | |
| US11654552B2 (en) | Backup control based continuous training of robots | |
| US11069356B2 (en) | Computer system and method for controlling user-machine dialogues | |
| CN111680517B (en) | Method, apparatus, device and storage medium for training model | |
| US11982999B2 (en) | Defect detection task processing method, device, apparatus and storage medium | |
| CN112114832B (en) | Vehicle upgrade control method, terminal device, vehicle, and computer storage medium | |
| CN112149741B (en) | Training method and device for image recognition model, electronic equipment and storage medium | |
| CN109271223A (en) | Windows switching method, device, terminal and computer readable storage medium | |
| CN115213889B (en) | Robot control method, device, storage medium and robot | |
| CN114047745B (en) | Robot motion control method, robot, computer device, and storage medium | |
| KR102212352B1 (en) | Method and apparatus for controlling robots | |
| CN112529162B (en) | Neural network model updating method, device, equipment and storage medium | |
| CN111680599B (en) | Face recognition model processing method, device, equipment and storage medium | |
| CN110569973A (en) | Network structure searching method and device and electronic equipment | |
| US20180169862A1 (en) | Motion control method and robot using same | |
| CN109960489B (en) | Method, device, equipment, medium and question-answering system for generating intelligent question-answering system | |
| JP2020042787A (en) | Automatic driving support method, driving device, support device, and computer-readable storage medium | |
| CN111133397A (en) | Information processing apparatus, information processing method, and program | |
| CN114475578A (en) | Method and device for generating vehicle parking strategy | |
| CN113448653A (en) | Service processing method, system, electronic equipment and computer readable medium | |
| JP7480670B2 (en) | MOTION PLANNING APPARATUS, MOTION PLANNING METHOD, AND MOTION PLANNING PROGRAM |
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 |