TW202232394A - Dynamic configuration method based on role assignation, electronic device, and medium - Google Patents

Abstract

The invention provides a dynamic configuration method based on role assignation, electronic device, and medium. The method includes defining a set of tasks as an organized sequence of behaviors based on a target plan, each task comprises a specific role and its behaviors execution; activating a plurality of roles based on the set of tasks, and each of the plurality of roles comprises a plurality of required capabilities; selecting at least one candidate robot for each activated role based on the plurality of required capabilities; assigning the activated roles to the at least one candidate robot; and controlling the assigned candidate robot to execute the behaviors corresponding to each activated role. The invention can adapt to changes in production requirements at any time and improve production capacity.

Description

Dynamic configuration method, electronic device and media based on role assignment

The present invention relates to the field of manufacturing, in particular to a dynamic configuration method, electronic equipment and media based on role assignment.

To meet changing markets, manufacturing companies should be able to adapt to flexible manufacturing requirements. With changing production requirements, manufacturing companies must adjust their factory operations. However, reconfiguring factory operations requires performing tasks to comply with production schedules, and autonomous mobile robots need to be redesigned accordingly. But autonomous mobile robots cannot easily adapt to changes in said production requirements, and their reconfiguration is time-consuming.

In view of the above problems, the present invention proposes a dynamic configuration method, electronic device and media based on role assignment, which can make the autonomous mobile robot adapt to the change of generation requirements at any time and improve the production capacity.

The present invention provides a dynamic configuration method based on role assignment, which is applied to an electronic device. The electronic device is communicatively connected with a plurality of robots. The method includes: defining a task set as an organized behavior sequence according to a target plan, Each task includes a specific role and its execution behavior; activate a plurality of roles based on the set of tasks, wherein each of the roles includes necessary capabilities; select at least one candidate robot for each active role based on the necessary capabilities; assign the active character to the at least one candidate robot; and controlling the candidate robot to perform a behavior corresponding to each active character.

In some embodiments of the present invention, the method further includes: if feedback information of the candidate robot completing the task is received, determining whether all tasks in the task set of the target plan have been completed; if the task set exists At least one task is not completed, continue to start multiple roles based on the unfinished task; repeat the selection of at least one candidate robot for each active role based on the necessary ability to control the candidate robot to perform a task corresponding to each active role. Corresponding behavior until all tasks in said task set are completed.

In some embodiments of the present invention, the method further includes: establishing a correspondence between the roles and tasks, and the tasks include a specific role and its execution content.

In some embodiments of the present invention, the method further includes: acquiring capabilities of each robot, wherein the capabilities of the robot at least include physical capabilities, operational capabilities, and perception capabilities.

In some embodiments of the present invention, each of the characters further includes a preferred ability, and the method further includes: scoring the candidate robot based on the preferred ability of the character and the ability of the robot, and obtaining a score result; assigning The scoring result is sent to the candidate robot.

In some embodiments of the present invention, the assigning the active character to the at least one candidate robot includes: traversing a plurality of the active characters; if the first target character of the plurality of active characters selects a plurality of first target characters When there is one candidate robot, determine the first target candidate robot with the highest first score result of the plurality of first candidate robots; continue to traverse the remaining roles in the plurality of active roles; if the second one of the remaining roles The target character selects a plurality of second candidate robots, and determines the second target candidate robot with the highest second score result of the plurality of second candidate robots; if the first target candidate robot and the second target candidate robot are The same robot, and the first highest score result is greater than the second highest score result, assign the first target role to the first target candidate robot; if the first target candidate robot and the second target candidate robot are the same robot, and the first highest score result is smaller than the second highest score result, assign the second target character to the second target candidate robot.

In some embodiments of the present invention, the assigning the active role to the at least one candidate robot further includes: if the first target candidate robot and the second target candidate robot are the same robot, and the first target candidate robot is the same robot The highest scoring result is equal to the second highest scoring result, assigning the first target character to the first target candidate robot; or assigning the first target character to the second target candidate robot; or assigning the first target character two target characters to the first target candidate robot; or assign the second target character to the second target candidate robot.

In some embodiments of the present invention, the assigning the active role to the at least one candidate robot further includes: if the first target candidate robot and the second target candidate robot are different robots, assigning the first target candidate robot A target character is assigned to the first target candidate robot, and the second target character is assigned to the second target candidate robot.

In some embodiments of the present invention, the method further includes: establishing a correspondence between the roles, the behaviors to be performed with an organizational sequence, the required capabilities, and the preferred capabilities.

In some embodiments of the present invention, the completion of the execution of the behavior sequence means the completion of the task associated with the assigned role.

The present invention also provides an electronic device, the electronic device includes a processor; and a memory, the memory stores a plurality of program instructions, the plurality of program instructions are loaded by the processor and executed as described above dynamic configuration method based on role assignment.

The present invention provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the aforementioned dynamic configuration method based on role assignment is implemented.

The role assignment-based dynamic configuration method, electronic device and media provided by the present invention can accurately model production requirements and dynamically assign tasks to each robot according to its functions. And many types of robots can work efficiently in highly dynamic manufacturing environments. The invention can adapt to the change of the generation requirements at any time, improves the utilization rate of the robot, and improves the production capacity.

In order to understand the objects, features and advantages of the present invention more clearly, the present invention will be described in detail below with reference to the drawings and specific embodiments. It should be noted that the embodiments of the present invention and the features in the embodiments may be combined with each other under the condition of no conflict. In the following description, many specific details are set forth in order to facilitate a full understanding of the present invention, and the described embodiments are only some, but not all, embodiments of the present invention.

Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terms used herein in the description of the present invention are for the purpose of describing specific embodiments only, and are not intended to limit the present invention.

Please refer to FIG. 1 , which is a schematic diagram of an application environment of the dynamic configuration method based on role assignment. In the present invention, the dynamic configuration method based on role assignment is applied in a multi-agent system (Multi-Agent System, MAS) 1 , and the multi-agent system 1 includes an electronic device 10 and a plurality of robots 20 . The electronic device 10 is connected to a plurality of robots 20 in communication. In one embodiment, the electronic device 10 may be a robot control server (Robot Control Server, RCS), and the robot 20 may be an autonomous mobile robot (Autonomous Mobile Robot, AMR). It should be noted that, the electronic device of the multi-agent system 1 may not be limited to one.

Please refer to FIG. 2 , which is a schematic diagram of the electronic device according to an embodiment of the present invention. In the present invention, the electronic device 10 includes, but is not limited to, a communication module 111 , a memory 112 , at least one processor 113 , and at least one communication bus 114 . The communication module 111 , the memory 112 and the processor 113 are electrically connected through the communication bus bar 114 .

In this embodiment, the communication module 111 is used to provide the electronic device 10 with a network communication function through wired or wireless network transmission. Therefore, the electronic device 10 is connected to a plurality of robots 20 through network communication. The wired network can be any type of traditional wired communication, such as the Internet, a local area network. The wireless network may be radio, Wireless Fidelity (WIFI), cellular, satellite, broadcast, Global System for Mobile Communications (GSM), General Packet Radio Service (GPRS) , Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (W-CDMA), CDMA2000, IMT Single Carrier (IMT Single Carrier), Enhanced Data Rates for GSM Evolution (Enhanced Data Rates for GSM Evolution, EDGE), long-term evolution technology (Long-Term Evolution, LTE), advanced long-term evolution technology, time-division long-term evolution technology (Time-Division LTE, TD-LTE), fifth generation mobile communication technology (5G) and other wireless communication technologies.

In this embodiment, the memory 112 is used to store the computer program 130 installed in the electronic device 10 , such as a program based on dynamic configuration of role assignment. In this embodiment, the memory 112 may be an internal storage unit of the electronic device 10 , such as a hard disk or a memory of the electronic device 10 . In other embodiments, the memory 112 can also be an external storage device of the electronic device 10 , such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital ( Secure Digital, SD) card, flash memory card (Flash Card), etc.

In this embodiment, the processor 113 may be a central processing unit (Central Processing Unit, CPU), or other microprocessors or other data processing chips capable of performing control functions. The processor 113 is used for executing software code or computing data and the like. For example, when the processor 113 executes the computer program 130, it implements the steps in the embodiment of the dynamic configuration method based on role assignment as described in FIG. 7 below. Exemplarily, the computer program 130 may be divided into one or more modules/units, and the one or more modules/units are stored in the memory 112 and processed by the at least one processor. 113 is executed to complete the present invention. The one or more modules/units may be a series of computer-readable instruction segments capable of accomplishing specific functions, and the computer-readable instruction segments are used to describe the execution process of the computer program 130 in the electronic device 10 .

Please refer to FIG. 3 , which is a schematic diagram of the robot according to an embodiment of the present invention. In this embodiment, the robot 20 may be one or more. The robot 20 includes, but is not limited to, a battery 210 , a motion mechanism 211 , a communication module 212 , a sensor 213 , a controller 214 and an actuator 215 . The battery 210 , the motion mechanism 211 , the communication module 212 , the sensor 213 , the controller 214 and the actuator 215 are electrically connected.

In this embodiment, the battery 210 is used to supply power to the motion mechanism 211 , the communication module 212 , the sensor 213 , the controller 214 and the actuator 215 . The motion mechanism 211 is used to control the movement of the robot. The motion mechanism 211 may be a wheeled, tracked or legged mechanism or any other mechanical structure. The communication module 212 is used to provide a network connection between the robot 20 and the electronic device 10 . The controller 214 is configured to receive role and task information assigned by the electronic device 10, and the controller 214 can also control the robot 20 to perform tasks according to the role and task information. The sensor 213 is used for sensing environmental information. For example, the sensor 213 may be a camera, a distance sensor, a laser scanner, or the like. The actuator 215 is configured to perform operations in the environment. For example, the actuator 215 may be a robotic arm, a lever, a conveyor belt, or the like.

In this embodiment, the robot 20 may further include a charging unit (not shown in the figure), and the charging unit is used to provide power for the battery 210 .

The present invention provides a dynamic configuration method based on role assignment, which can accurately model the target plan in production requirements, obtain multiple tasks, and dynamically assign the tasks to each robot according to its function (for example, AMR). The role assignment-based dynamic configuration method includes an agent operation process and a plan execution process.

Please refer to FIG. 4 , which is a schematic diagram of a proxy operation process in an embodiment of the present invention.

The agent operation process includes defining the capabilities of each agent and assigning roles 30 to each agent 20a. The character 30 is an abstract description. The roles describe a set of actions that the agent 20a must perform. Each agent 20a must assume a unique role 30 at a time. Each agent 20a needs to be assigned a role 30 to perform an action. As shown in FIG. 4 , the role 30 includes a required capability (Required Capabilities) 310 , a preferred capability 320 and a Behavior Set (Behavior Set) 330 .

Agents are generally considered to have autonomy, communicability, interactivity, reasoning ability and planning ability, adaptability and so on. In the present invention, the agent 20a is represented by any type of robot 20 performing a task operation. In the field of manufacturing, the agent 20a is represented by each type of robot 20 available. The capabilities 40 of the agent 20a describe the operational capabilities and limitations of a particular agent 20a. For example, the capabilities of agent 20a include physical capabilities 410, operational capabilities 420, and perception capabilities 430. The physical capabilities 410 describe the extent to which the agent 20a can manage physical tasks. For example, payload, displacement velocity, actuator, etc. The operational capabilities 420 describe a number of tasks that the agent 20a may perform, eg, shifting, patrolling, picking items, placing items, synchronizing, and the like. The perception capability 430 describes the capability of the agent 20a to perceive environmental information. For example, object recognition, the ability to respond with QR readers and RFID readers, etc.

Specifically, the agent operation process is described by assigning roles in the role library (Roles Library) to different agents, and the agent 20a performs the said agent 20a according to the provided capabilities (Provided Capabilities) of the agent 20a. The behavior corresponding to the role. The capabilities provided by the agent 20a may constitute a capability library (Capabilities Library). Therefore, when assigning roles, it is necessary to consider whether the required capabilities of the roles match the capabilities that the agent 20a can provide.

Please refer to FIG. 5 , which is a schematic diagram of a project execution process in an embodiment of the present invention. In this embodiment, the project 50 includes a set of tasks 60 , each of which may include a plurality of required roles 610 and project contributions 620 . Each task 60 has a corresponding priority order. For example, in a manufacturing environment, the plan 50 includes a prioritized set of operational requirements. The desired roles are established 610 based on manufacturing goals. The tasks define commands that meet specific requirements, the successful execution of which is defined as a project contribution 620 .

In this embodiment, the behavior of the character 30 describes the action to be performed by the agent 20a. Behavior 70 is designed as an operational command to perform a task. If the agent 20a belongs to the same role, the agent 20a can perform multiple actions 70 simultaneously.

Please refer to FIG. 6 , which is the execution flow of the dynamic configuration method based on role assignment. In this embodiment, the execution flow is executed from the first layer to the second layer, and then from the second layer to the third layer. The first layer includes a dynamic plan 50 , the second layer includes a series of tasks 60 of the dynamic plan 50 , and the third layer includes a plurality of behaviors 70 corresponding to the series of tasks. In one embodiment, the dynamic plan 50 adjusts operational requirements. Tasks 60 are scheduled according to operational requirements and contribution requests. The active character 30a is selected by matching actions 70 that can satisfy the requested contribution. The active role 30a is assigned to the agent 20a according to the best fit of its capabilities 40. The execution process ensures that project changes will automatically realign contribution requests and increase flexibility. The execution flow further ensures that only roles 30 that can contribute to the project 50 are considered, thereby reducing complexity. The execution flow further ensures that the agents 20a will distribute the task load according to their ability to contribute to the project 50, thereby increasing optimization.

Please refer to FIG. 7. FIG. 7 is a schematic flowchart of a dynamic configuration method based on role assignment provided by an embodiment of the present invention. The role-assignment-based dynamic configuration method is applied in the electronic device 10 , and the role-assignment-based dynamic configuration method may be performed using the configurations shown in FIGS. 1 to 6 . According to different requirements, the order of the steps in the flowchart can be changed, and some steps can be omitted. For the convenience of description, only the parts related to the embodiments of the present invention are shown. The dynamic configuration method based on role assignment includes the following steps.

Step S01, the electronic device 10 activates a plurality of roles based on the task list of the target plan, wherein each of the roles includes a necessary ability and a preferred ability.

In this embodiment, the target plan is a plan in the manufacturing process. For example, the target plan is to execute a predefined sequence of tasks, and the execution time needs to be minimized. The goal plan includes a list of tasks that need to be performed, and the task list includes multiple tasks. It should be noted that each task in the goal plan needs to be given a priority order, and the priority order is initially set as part of the target program. For example, as shown in Table 1, the task list includes task 0 (Task0), task 1 (Task1), task 2 (Task2), and task 3 (Task3). The priority of task 0 is higher than that of task 1, task 2 and task 3. As shown in FIG. 3 , the priority of task 1 is higher than that of task 2 and task 3 , and the priority of task 2 is higher than that of task 3 . Then, when executing the target plan, it is necessary to execute task 0 first, then execute task 1, then execute task 2, and finally execute task 3. Table 1 Target Plan Objective Execution time needs to be minimized (general sequence of operational tasks) Prioritized task list Task0 (T1) → Task1 (T3) → Task2 (T2) → Task3 (T2)

In this embodiment, the multiple tasks in the task list may be tasks of different types. For example, as shown in Table 2, the types of tasks include T1, T2, and T3. Each of the different types of missions requires a character. For example, as shown in Table 2, the required role for type T1 is R1, the required role for type T2 is R2, and the required role for type T3 is R3. Table 2 Tasks _ Type T1 T2 T3 Parameters P1 P2 P3 Required Role R1 R2 R3

In this embodiment, the type of the role is the type of role required by the task in the task list. For example, the types of roles include R1, R2, and R3.

Step S02 , the electronic device 10 activates a plurality of roles 30 based on the task set, and each role includes a necessary capability 310 and a preferred capability 320 .

In this embodiment, the roles include desired preferred abilities. The type of role corresponds to the required ability. For example, as shown in Table 3, the required capabilities of type R1 include a physical capability "PhysicalC1" with a value greater than or equal to "x", an operational capability "OperationC1", and a perception capability "PerceptionC1". Mandatory abilities of type R2 include one of the physical abilities "PhysicalC1" with a value greater than or equal to "y", another physical ability "PhysicalC2" with a value greater than or equal to "v", an operational ability "OperationC1" and a perception ability "PerceptionC1" ". Mandatory capabilities of type R3 include a physical capability "PhysicalC1" whose value is greater than or equal to "y", an operational capability "OperationC1", another operational capability "OperationC2", and a perception capability "PerceptionC1". Among them, the value corresponding to "x" is greater than the value corresponding to "y", and the value corresponding to "w" is greater than the value corresponding to "v".

In this embodiment, the role further includes a preferred ability. For example, the preferred capability includes a physical capability "PhysicalC2". It should be noted that the preferred capability is not limited to a single capability, and may also be other capabilities. For example, the sensing range, sensing accuracy and interaction speed of the sensor 213, and the like.

In this embodiment, the roles also include merit or scoring mechanisms. Robots corresponding to different roles can be scored through a scoring mechanism. The scoring mechanism includes a scoring function. The scoring function may be the value of the robot's "PhysicalC2" divided by the value of the preferred capability "PhysicalC2". The scoring function may also vary depending on the preferred abilities of the character. The preferred capabilities and metrics of the scoring function can be defined according to the desired usage. table 3 Roles _ Type R1 R2 R3 Required Capabilities PhysicalC1 ≥x OperationC1 PerceptionC1 PhysicalC1≥ y PhysicalC2 ＞= v OperationC1 PerceptionC1 PhysicCap1 ≥y OperationC1 OperationC2 PerceptionC1 Preferred Capabilities PhysicalC2 = v PhysicalC2 = w PhysicalC2 = v Score function PhysicalC2 PhysicalC2 PhysicC2

In this embodiment, the electronic device 10 establishes a corresponding relationship among roles, behaviors to be performed with an organizational sequence, and necessary capabilities and preferred capabilities.

In this embodiment, the agent 20a is defined by its capabilities and must assume roles accordingly. The capabilities of the agent 20a include multiple physical capabilities, multiple operational capabilities, and multiple sensory capabilities. One of the agents 20a corresponds to one robot 20, and certain actions are required to be performed by the robot 20. In this embodiment, the robot 20 is an AMR. For example, as shown in Table 4 below, the types of the agent 20a include AMRs of type A, AMRs of type B, and AMRs of type C. For an AMR of type A, it includes a physical ability "PhysicalC1" with a value equal to "x", a physical ability "PhysicalC2" with a value equal to "v", an operational ability "OperationC1" and a perception ability "PerceptionC1" . For AMRs of type B, the included capabilities are one physical capability with a value equal to "y", another physical capability "PhysicalC2" with a value equal to "w", an operational capability "OperationC1", another operational capability "OperationC2" and A perception ability "PerceptionC1". For AMRs of type C, the included abilities are a physical ability "PhysicalC1" with a value equal to "y", a physical ability "PhysicalC2" with a value equal to "u", an operational ability "OperationC1" and a perception ability "PerceptionC1" . Among them, the value corresponding to "x" is greater than the value corresponding to "y", the value corresponding to "w" is greater than the value corresponding to "v", and the value corresponding to "v" is greater than the value corresponding to "u". Table 4 Agents & Capabilities type AMR type A AMR type B AMR type C physical ability PhysicalC1 = x PhysicalC2 = v PhysicalC1 = y PhysicalC2 = w PhysicalC1 = y PhysicalC2 = u Operational ability OperationC1 OperationC1 OperationC2 OperationC1 Perception PerceptionC1 PerceptionC1 PerceptionC1

In one embodiment, before the electronic device 10 activates a plurality of roles based on the task set, the method further includes establishing a correspondence between the roles 30 and the tasks 60 . The task 60 includes a specific role and what the specific role needs to perform. The content of the execution includes all the parameters required to execute the role. For example, given a task that needs to transfer a role, the content to be executed may be the start point and the end point of the task of the transfer role. The role 30 corresponds to the task 60 , and according to the role 30 it is the agent 20a that must be able to perform the behavior 70 associated with the task 60 .

In one embodiment, the method further includes acquiring the capabilities 40 of each robot 20 before the electronic device 10 activates the plurality of characters based on the task set. The capability 40 of the robot 20 includes at least a physical capability 410 , an operation capability 420 and a perception capability 430 . It should be noted that, in this embodiment, one robot 20 is one agent 20a.

Step S03 , the electronic device 10 selects at least one candidate robot 20 for each active character 30 . In one embodiment, there may be one or more robots 20 having abilities 40 that match the prerequisite abilities 310 of one or more characters 30 . That is, multiple candidate robots 20 may be suitable for one character 30 , or one candidate robot 20 may perform multiple roles 30 , or only one candidate robot 20 may be suitable for one candidate robot 20 .

In one embodiment, the task 60 is related to the character 30 , which is related to the robot 20 . Therefore, the priority order of the tasks 60 will not directly affect the selection of the robot 20 , but will have an indirect effect by triggering the assignment of the roles 30 . If only one robot 20 is available, the electronic device 10 will only activate a single character 30 and assign the active character 30 to that robot 20 (even if the other characters are still active). The character 30 that will be activated depends on the priority of the tasks 60, and the activated character 30 will be assigned to an available robot 20. Even if the available bots 20 are well suited for both characters 30, only the higher priority tasks 60 to which the characters 30 are associated will be requested for assignment. Each task 60 may be assigned the same priority order if it is not necessary to utilize the priority order of tasks 60 in special circumstances.

In one embodiment, the method further includes assigning each candidate robot 20 a grade or score result. The steps to assign a score to each candidate robot include:

(1) Score each robot 20 based on the preferred capability 320 and the capability 40 of each robot 20, and obtain a scoring result. For example, the preferred capability 320 of the character 30 may be a displacement speed of 1 m/s, and the capability 40 of the candidate robot 20 may be a movement speed of 1 m/s. The score is obtained by dividing the movement speed of the candidate robot 20 by the displacement speed of the character 30 . That is, in this case, the score result is 1 point.

(2) Assign the scoring result to each candidate robot 20 . It should be noted that each robot 20 does not need to know its own score, but only needs to know its character 30 .

Step S04 , the electronic device 10 assigns the plurality of roles to the at least one candidate robot 20 .

In one embodiment, the electronic device 10 assigning the active character 30a to at least one candidate robot 20 includes: the electronic device 10 traverses a plurality of the active characters and determines a first target character among the plurality of active characters Whether a first candidate robot is selected; if the electronic device 10 determines that the first target character has selected the first candidate robot, assign the first target character to the first candidate robot. If the electronic device 10 determines that the first target character has selected multiple first candidate robots, it determines the first target candidate robot with the highest first score result of the multiple first candidate robots. The electronic device 10 continues to traverse the remaining characters among the multiple active characters, and determines whether the second target character among the remaining active characters has selected multiple second candidate robots. If the electronic device 10 determines that the second partial character needs to select multiple second candidate robots, it determines the second target candidate robot with the highest second score result of the multiple second candidate robots. The electronic device 10 determines whether the first target candidate robot 20 and the second target candidate robot 20 are the same robot and the first highest scoring result is smaller than the second highest scoring result. If the electronic device 10 determines that the first target candidate robot and the second target candidate robot are the same robot, and the first highest score result is greater than the second highest score result, assign the first target role to the first target candidate robot; if the electronic device 10 determines that the first target candidate robot and the second target candidate robot are the same robot, and the first highest score result is less than the second highest score As a result, the second target character is assigned to the second target candidate robot.

In one embodiment, the electronic device 10 assigning the active character 30 a to the at least one candidate robot 20 further includes the electronic device 10 determining whether all active characters 30 a are assigned to the robot 20 . If the electronic device 10 determines that there are still active roles unassigned, it repeats the process of traversing a plurality of the active roles until if the first target candidate robot and the second target candidate robot are the same robot, and the first score If the result is less than the second scoring result, the second target character is assigned to the second target candidate robot until all the active characters 30a have been assigned.

In one embodiment, if the electronic device 10 determines that the first and second target candidate robots are the same robot, and the first highest score result is equal to the second highest score, the electronic device 10 randomly assigns the first target character or the second target character Assigned to the first or second target candidate robot. For example, the electronic device 10 assigns the first target character to the first target candidate robot 20, or assigns the first target character to the second target candidate robot. Alternatively, the second target character may be assigned to the first target candidate robot, or the second target character may be assigned to the second target candidate robot 20 .

In one embodiment, if the electronic device 10 determines that the first target candidate robot and the second target candidate robot are different robots, assign the first target role to the first target candidate robot, and assign all from the second target character to the second target candidate robot.

In one embodiment, if there are multiple candidate robots with the same score among the multiple second candidate robots selected by the second target character, the electronic device 10 randomly assigns the second target character to any of the multiple candidates. A bot with a common score. For example, if the first target candidate robot and the second target candidate robot are the same robot, and the first highest scoring result is equal to the second highest scoring result. The electronic device 10 randomly assigns the first target character or the second target character to the first target candidate robot or the second target candidate robot. For example, the electronic device 10 assigns the first target character to the first target candidate robot; or assigns the first target character to the second target candidate robot; or assigns the second target character to all the first target candidate robot; or assign the second target character to the second target candidate robot.

In one embodiment, if the robot 20 completes its assigned task, the robot will request a new character 30. The electronic device 10 will then assign the task-completed robot the highest priority task that the robot can perform according to its capabilities. In the case of the same priority order of tasks, the robot that completes the task will perform the most suitable task according to its preferred capabilities.

Step S05, the electronic device 10 controls the candidate robot to perform the action corresponding to each active character.

In one embodiment, after determining the task corresponding to the candidate robot, the electronic device 10 sends the task to the corresponding robot, and sends the robot a command instruction for performing the behavior of the task. For example, the electronic device 10 sends Task0 (T1) to AMR A1, and sends a command instruction for executing Task0 (T1) to AMR A1, and executes the behavior of Task0 (T1).

Step S06, the electronic device 10 receives feedback information of the candidate robot completing the task.

Step S07, the electronic device 10 determines whether all tasks in the task set of the target plan are completed. If all the tasks in the task set of the target plan are completed, the process ends; if there are still uncompleted tasks in the task set of the goal plan, the process proceeds to step S08.

Step S08, the electronic device 10 continues to activate a plurality of roles based on the unfinished task, and then the flow proceeds to step S03.

In one embodiment, if the employed robot has completed the task, the robot sends feedback information to the electronic device 10, and the electronic device 10 continues to activate multiple roles based on the unfinished task, and then the process returns to step S03 for repeated execution Task. At least one candidate robot is selected based on the prerequisite abilities 310 of each active character 30a, and the one or more candidate robots are instructed to perform the behavior 70 corresponding to the assigned character until all tasks in the task list are completed. It should be noted that the robot means the execution of the contained behavior, and the completion of the execution of the behavior sequence means the completion of the task related to the assigned role.

In order to further illustrate the present invention, the following describes the dynamic configuration method based on role assignment provided by the present invention in detail with reference to the embodiments.

Example 1

Given the following team of robots that includes a robot of type A, and the robot is designated as AMR A1; a robot of type B, designated as AMR B1; and a robot of type C, And naming the robot as AMR C1, the execution sequence will proceed as follows:

(a) As shown in Table 5 below, the electronic device 10 activates a plurality of roles according to the task set of the target plan. The active roles include one role R1, two roles R2 and one role R3. table 5 Prioritized Task list Task0 (T1) → Task1 (T3) → Task2 (T2) → Task3 (T2) Active role 1 x R1 – 2 x R2 – 1 x R3

(b) The electronic device 10 selects a suitable candidate robot for each active character 30a. In Embodiment 1, the electronic device 10 selects a candidate robot according to the "required ability" 310 of the active character 30a, and assigns a score based on the "preferred ability" 320 of the active character 30a. As shown in Table 6, role R1 is suitable for AMR A1, role R2 is suitable for AMR A1 or AMR B1, and role R3 is suitable for AMR B1 or AMR C1. According to Table 3 and Table 4, the score of AMR A1 with role R1 is v/v points, the score of AMR A1 with role R2 is v/w points, and the score of AMR B1 with role R2 is w/w points, AMR B1 with role R3 has a score of w/v points, and AMR C1 with role R3 has a score of u/v points. where w is greater than v, and v is greater than u. Table 6 R1 A1 (v/v) R2 A1 (v/w) – B1 (w/w) R3 B1(w/v) – C1(u/v)

(c) The electronic device 10 assigns an active role 30a to each candidate robot. In at least one embodiment, the assigning an active role to each candidate robot comprises:

(c1) If the active character matches only one suitable candidate robot, directly assign the active character to the robot. For example, in Table 6, role R1 has only one candidate robot AMR A1, so Task0 (T1) of Table 5 is assigned to AMR A1.

(c2) Each remaining role will be assigned to an AMR with a higher score. For example, the active role corresponding to Task1 (T3) is R3, and the highest score is w/v score (AMR B1). The active role corresponding to Task2 (T2) is R2, and the highest score is w/w points (AMR B1). Therefore, Task2 (T2) of Table 5 is assigned to AMR B1.

(c3) Repeat the previous steps (c1) and (c2) until all tasks are assigned. For example, the multi-agent plan execution device 10 assigns Task1 (T3) in Table 5 to AMR C1, and the assignment result is shown in Table 7 below. Table 7 AMR Assigned Role and Task A1 Task0 (T1) B1 Task2 (T2) C1 Task1 (T3)

(d) The electronic device 10 determines that Task3 (T2) of the task list has not been completed. Therefore, the electronic device 10 continues to activate an R2 role based on the remaining tasks (Task3 (T2)). As shown in Table 8 below, the flow then returns to step (b). Repeat steps (b) to (d) described above. Table 8 Prioritized Task list Task3 (T2) Active roles 1x R2

In this embodiment, role R2 is suitable for AMR A1 or AMR B1. Character R2's AMR A1 has a score of v/w, and character R2's AMR B1 has a score of w/w. Therefore, Task3 (T2) of Table 8 is assigned to AMR B1. Then, all the tasks in Table 5 are completed, and the final execution sequence of the plan is shown in Table 9 below. Table 9 Plan Execution Sequence Round 1 assignment: A1:Task0 + B1:Task2 + C1: Task1 Round 2 assignment: B1:Task3

Example 2

Suppose there is another candidate robot that is identical to A1, called A2. Therefore, the robotics team consists of one type A robot (called AMR A1) and one type A robot (called AMR A2), one type B robot (called AMR B1) and one type C robot (called AMR B1) AMR C1). AMR A2 is capable of performing role R1. The plan of Example 2 is the same as that of Example 1, so the tasks are the same as Table 5.

In Embodiment 2, the electronic device 10 selects a candidate robot according to the "required ability" 310 of the active character 30a, and assigns a score based on the "preferred ability" 320 of the active character to generate the following table 10. Character R1 is suitable for AMR A1 or AMR A2, Character R2 is suitable for AMR A1, AMR A2 or AMR B1, and Character R3 is suitable for AMR B1 or AMR C1. According to Table 3 and Table 4, the score of AMR A1 with role R1 is v/v points, the score of AMR A2 with role R1 is also v/v points, the score of AMR A1 with role R2 is v/w points, AMR A2 with role R2 gets a score of v/w points, AMR B1 with role R2 gets a score of w/w points, and AMR B1 with role R3 gets a score of w/v points. AMR C1 with role R3 has a score of u/v points. where w is greater than v, and v is greater than u. Table 10 R1 A1 (v/v) – A2 (v/v) R2 A1 (v/w) – A2 (v/w) – B1 (w/w) R3 B1(w/v) – C1 (u/v)

Repeat operation 1:

(1): No role corresponds to only one candidate robot.

(2): Each role will be assigned to the higher scoring AMR. For example, the active role corresponding to Task0 (T1) is R1, and the highest score is v/v score (AMR A1 & AMRA2). The active role corresponding to Task1 (T3) is R3, and the highest score is w/v score (AMR B1). Task2 (T2) corresponds to the corresponding active role as R2, and the highest score is w/w score (AMR B1). The active role corresponding to Task3 (T2) is R2, and the highest score is w/w points (AMR B1). Since the priority order of Task2 (T2) is higher than that of Task3 (T2), Task2 (T2) of Table 5 is assigned to AMR B1.

Repeat operation 2:

(1): No role corresponds to only one candidate robot.

(2): Each role will be assigned to the higher scoring AMR. For example, the active role corresponding to Task0 (T1) is R1, and the highest score is v/v points (AMR A1 and AMR A2). The active role corresponding to Task1 (T3) is R3, and the highest score is u/v score. The active role corresponding to Task3 (T2) is R2, and the highest score is v/w points (AMR A1 & AMR A2). Assign Task0 (T1) in Table 5 to AMR A2. Since both AMR A1 and AMR A2 are equally suitable for executing Task0 (T1), they will be assigned randomly. Then assign Task3 (T2) in Table 5 to AMR A1.

Repeat operation 3:

(1) Role R3 has only one candidate robot AMR A1, so assign Task1 (T3) in Table 5 to AMR C1. From this, the assignment results shown in Table 11 below were obtained. Table 11 AMR Assigned Role and Task A1 Task3 (T2) A2 Task0 (T1) B1 Task2 (T2) C1 Task1 (T3)

Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be Modifications or equivalent substitutions can be made without departing from the spirit and scope of the technical solutions of the present invention.

1: Multi-agent system 10: Electronics 20: Robots 111, 212: Communication module 112: Memory 113: Processor 114: Communication bus 130: Computer programming 210: Battery 211: Movement Mechanisms 213: Sensor 214: Controller 215: Actuator 20a: Agency 30: Characters 30a: Active role 310: Essential Ability 320: Optimal Ability 330: Behavior Set 40: Ability 410: Physical Ability 420: Operational Capability 430: Perception 50: Plan 60: Mission 610: Required roles 620: Project Contribution 70: Behavior S01~S08: Steps

FIG. 1 is a schematic diagram of an application environment of a dynamic configuration method based on role assignment provided by an embodiment of the present invention.

FIG. 2 is a schematic structural diagram of an electronic device applied in the role assignment-based dynamic configuration method provided by an embodiment of the present invention.

FIG. 3 is a schematic structural diagram of a robot applied in the dynamic configuration method based on role assignment provided by an embodiment of the present invention.

FIG. 4 is a schematic diagram of a proxy operation process in a role assignment-based dynamic configuration method according to an embodiment of the present invention.

FIG. 5 is a schematic diagram of a plan execution process in the dynamic configuration method based on role assignment provided by an embodiment of the present invention.

FIG. 6 is a schematic diagram of an execution flow of a dynamic configuration method based on role assignment provided by an embodiment of the present invention.

FIG. 7 is a flowchart of a dynamic configuration method based on role assignment provided by an embodiment of the present invention.

S01~S08: Steps

Claims (12)

A dynamic configuration method based on role assignment, applied in electronic equipment, the electronic equipment is connected with multiple robots in communication, and the method comprises: Define a task set as an organized sequence of actions according to the goal plan, each task includes a specific role and its execution behavior; Activating a plurality of roles based on the set of tasks, wherein each of the roles includes prerequisite abilities; selecting at least one candidate robot for each active character based on the prerequisite abilities; assigning the active role to the at least one candidate robot; and The assigned candidate robots are controlled to perform actions corresponding to each active character. The dynamic configuration method based on role assignment as described in claim 1, further comprising: If receiving feedback information that the candidate robot has completed the task, determine whether all tasks in the task set of the target plan have been completed; If there is at least one uncompleted task in the task set, continue to activate multiple roles based on the uncompleted task; The selection of at least one candidate robot for each active character based on the requisite ability is repeatedly performed to controlling the candidate robot to perform a behavior corresponding to each active character until all tasks in the task set are completed. The dynamic configuration method based on role assignment as described in claim 2, further comprising: A corresponding relationship between the roles and tasks is established, and the tasks include specific roles and their execution content. The dynamic configuration method based on role assignment as described in claim 1, further comprising: The capabilities of each robot are acquired, wherein the capabilities of the robot at least include physical capabilities, operational capabilities and perception capabilities. The dynamic configuration method based on role assignment as described in claim 1, wherein each of the roles further includes preferred capabilities, and the method further includes: Score the candidate robot based on the character's preferred ability and the robot's ability, and obtain a scoring result; assigning the scoring result to the at least one candidate robot. According to the dynamic configuration method based on role assignment according to claim 5, the assigning the active role to the at least one candidate robot comprises: traverse a plurality of said active roles; If the first target character among the plurality of active characters selects a plurality of first candidate robots, determining the first target candidate robot with the highest first score result of the plurality of first candidate robots; Continue to traverse the remaining roles in the multiple active roles; If the second target character in the remaining characters has selected multiple second candidate robots, determining the second target candidate robot with the highest second score result of the multiple second candidate robots; If the first target candidate robot and the second target candidate robot are the same robot, and the first highest score result is greater than the second highest score result, assign the first target character to the first target candidate robot; If the first target candidate robot and the second target candidate robot are the same robot, and the first highest score result is less than the second highest score result, assign the second target character to the second target candidate robot. According to the dynamic configuration method based on role assignment according to claim 6, the assigning the active role to the at least one candidate robot further comprises: If the first target candidate robot and the second target candidate robot are the same robot, and the first highest score result is equal to the second highest score result, assign the first target character to the first target candidate robot; or assigning the first target character to the second target candidate robot; or assigning the second target character to the first target candidate robot; or assigning the second target character to the second target candidate robot. According to the dynamic configuration method based on role assignment according to claim 6, the assigning the active role to the at least one candidate robot further comprises: If the first target candidate robot and the second target candidate robot are different robots, assign the first target character to the first target candidate robot, and assign the second target character to the second target character Target candidate robot. The dynamic configuration method based on role assignment as described in claim 5, further comprising: A correspondence is established between the roles, the behaviors to be performed with an organizational sequence, the required capabilities, and the preferred capabilities. According to the role assignment-based dynamic configuration method described in claim 1, the completion of the execution of the behavior sequence means the completion of the task related to the assigned role. An electronic device is connected to a plurality of robots in communication, and the electronic device includes: processor; and A memory, the memory stores a plurality of program instructions, the plurality of program instructions are loaded by the processor and execute the role-assignment-based dynamic as described in any one of claim 1 to claim 10 A configuration method assigns tasks to the plurality of robots. A computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, implements the role-assignment-based dynamic configuration method described in any one of claim 1 to claim 10.

Images