KR102203015B1 - Operation device for plurality of robots and operation method thereof - Google Patents

Abstract

Provided are an operation device for a plurality of robots and an operation method thereof, wherein the operation device for a plurality of robots includes: a communication part communicating with at least one of the plurality of robots and communicating with the other operation device for the plurality of robots; and a control part connected to the communication part. Therefore, the operation device for a plurality of robots can have higher expandability.

Description

Operation device for a plurality of robots and its operation method {OPERATION DEVICE FOR PLURALITY OF ROBOTS AND OPERATION METHOD THEREOF}

The present disclosure relates to an operating device for a plurality of robots and a method of operating the same.

Recently, tactics using swarm drones or robots are attracting much attention as a technology that will significantly change the aspect of the future battlefield. Typically, weapon systems have been developed to maximize the performance of a single weapon with a long development cycle. On the other hand, projects with a long development cycle to achieve high performance have a risk that the existing technology is easily destroyed due to the problem of enormous cost expenditure and disruptive technology that emerged after completion of development.

Leading the way in the development of such a military weapon system is the US, Low-Cost UAV Swarming Technology (LOCUST), Collaborative Operations in Denied Environment (CODE), Close-in Covert Autonomous Disposable Aircraft (CICADA), Autonomous Mobility Applique System (AMAS), Projects are being promoted in all areas of the land/sea/air, such as AAV (Autonomous Amphibious Vehicles). Looking at their technology trends, it is not a system in which all entities are controlled and supervised by a central control station, but is composed of a decentralized system in which each entity autonomously judges, plans, and performs, enhancing autonomy and intelligence. Attempts to try are continuing. Based on this structure, a unique characteristic of a cluster called self-organization is expressed. In other words, each autonomous unmanned system performs its mission adaptively in accordance with the environment, even if the operator does not instruct it. This not only increases the operational success rate, but also increases the robustness of the mission.

Meanwhile, the US Defense Advanced Research Projects Agency (DARPA) proposed the concept of Mosaic Warfare. This makes it possible to perform combat missions by quickly combining/reorganizing each cluster object even if part of its power is lost due to enemy threats. In order to operate such a decentralized, hyper-connected swarm weapon system, a swarm operation control structure different from the existing one is required.

The disclosed embodiments are intended to disclose an operating device and a method of operating the same. The technical problem to be achieved by the present embodiment is not limited to the technical problems as described above, and other technical problems may be inferred from the following embodiments.

According to the first embodiment, as an operation device for a plurality of robots that can cooperate with each other for a target task, communication with at least one of the plurality of robots is possible, and other operation devices for the plurality of robots and A communication unit capable of communication; And a control unit connected to the communication unit, wherein the control unit acquires mission-related information from the other operating device through the communication unit, confirms a target mission based on the mission-related information, and receives a plurality of information on the target mission through the communication unit. It can be transmitted to at least one of the robots.

According to a second embodiment, there is provided a method of operating an operation device for a plurality of robots capable of cooperating with each other for a target task, the method comprising: acquiring task-related information from another operating device; Identifying a target mission based on the mission-related information; And transmitting information on the target mission to at least one of the plurality of robots.

According to the third embodiment, a computer-readable recording medium includes a non-transitory recording medium on which a program for executing the above-described operation method in a computer is recorded.

Details of other embodiments are included in the detailed description and drawings.

According to the present disclosure, a control structure including a concept in which a plurality of operating devices operate a robot cluster is proposed. Through this control structure, a large number of operators can operate a large-scale unmanned robot cluster system, and it is expected that it can be utilized in a more advanced form compared to the existing proposed cluster operation structure.

In addition, each of the modules of the operating device and the robot according to the present disclosure can be implemented as plug-and-play that can be quickly grafted and used when a new technology is developed. It provides an operating device and a robot having.

The effects of the invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description of the claims.

1 shows an operating system according to an embodiment.
2 shows an embodiment of a hierarchical control structure of an operating system.
3 shows a specific embodiment of an operating system.
4 shows a first embodiment in which the operating system operates.
5 shows a first embodiment of an operation scenario of an operating system.
6 shows a second embodiment in which the operating system operates.
7 shows a second embodiment of an operation scenario of an operating system.
8 shows a third embodiment in which the operating system operates.
9 shows an embodiment of an allocation and planning module.
10 shows a third embodiment of an operation scenario of an operating system.
11 shows a fourth embodiment in which the operating system operates.
12 shows a fourth embodiment of an operation scenario of an operating system.
13 shows an operating device according to an embodiment.
14 illustrates a method of operating an operating device according to an embodiment.

The terms used in the embodiments have selected general terms that are currently widely used as possible while considering functions in the present disclosure, but this may vary according to the intention or precedent of a technician working in the art, the emergence of new technologies, and the like. In addition, in certain cases, there are terms arbitrarily selected by the applicant, and in this case, the meaning will be described in detail in the corresponding description. Therefore, the terms used in the present disclosure should be defined based on the meaning of the term and the contents of the present disclosure, not the name of a simple term.

When a part of the specification is said to "include" a certain component, it means that other components may be further included rather than excluding other components unless otherwise stated. In addition, terms such as ".. unit" and ".. module" described in the specification mean a unit that processes at least one function or operation, which may be implemented as hardware or software or a combination of hardware and software. have.

The expression of "at least one of a, b, and c" described throughout the specification is'a alone','b alone','c alone','a and b','a and c','b and c' ', or'a, b, c all' may be included.

Hereinafter, exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings so that those of ordinary skill in the art may easily implement the exemplary embodiments. However, the present disclosure may be implemented in various different forms and is not limited to the exemplary embodiments described herein.

Hereinafter, exemplary embodiments of the present disclosure will be described in detail with reference to the drawings.

1 shows an operating system according to an embodiment.

The operating system 10 may include a plurality of operating devices 110 and 120 and a plurality of robots 210 and 220. In FIG. 1, for convenience, a plurality of operation devices 110 and 120 are illustrated as two operation devices, but the plurality of operation devices 110 and 120 may be composed of three or more operation devices, and a plurality of robots 210 and 220 Although shown as these two robots, a plurality of robots 210 and 220 may be composed of three or more robots.

Each of the plurality of operation devices 110 and 120 may be an operation device for a plurality of robots 210 and 220 capable of cooperating with each other for a target mission.

Each of the plurality of operating devices 110 and 120 may communicate with at least one of the plurality of robots 210 and 220, and communication between the plurality of operating devices 110 and 120 may be possible.

The first operation device 110 may obtain mission-related information from the second operation device 120, confirm a target mission based on the mission-related information, and transmit information on the target mission to a plurality of robots 210,220. ) Can be transmitted to at least one of. The mission-related information may include information on a target mission and information on operational authority.

The first operating device 110 may obtain information on the operating authority from the second operating device 120. Specifically, the first operating device 110 may be delegated from the second operating device 120 the authority to operate the first robot 210 among the plurality of robots 210 and 220. For example, when communication with the first robot 210 is unstable, the second operating device 120 may transmit the authority to operate the first robot 210 to the first operating device 110. Accordingly, the first operating device 110 may transmit information on the target task to the first robot 210 according to the information on the operating authority.

The first operating device 110 may share mission-related information with the second operating device 120 to determine a first target task, and transmit information on the first target task to at least one of the plurality of robots 210 and 220. Can be transmitted. In addition, the second operating device 110 may share mission-related information with the first operating device 110 to determine a second target task, and transmit information on the second target task to at least one of the plurality of robots 210 and 220. Can be transferred to one. Since the mission-related information of the first operating device 110 and the mission-related information of the second operating device 120 may be asymmetric, the first operating device 110 and the second operating device 120 are related to each other. By sharing information, you can determine your target mission. For example, the first operation device 110 and the second operation device 120 can negotiate a force arrangement regarding a plurality of robots 210, 220, and the first operation device 110 It is possible to control the deployment of some of the plurality of robots 210 and 220 according to the target mission, and the second operation device 120 may arrange the troops of some of the plurality of robots 210 and 220 according to the second target mission. Can be controlled.

According to an embodiment, the first operating device 110 may recognize the first robot 210 of the plurality of robots 210 and 220 as an operating device, and transmit mission-related information to the first robot 210. have. Subsequently, as an operating device, the first robot 210 may check the target task based on the task-related information, and transmit information on the target task to at least one other robot. According to another embodiment, the first operation device 110 may transmit mission-related information to the plurality of robots 210 and 220, and the plurality of robots 210 and 220 operate the first robot 210 under mutual agreement. Can be determined by For example, the plurality of robots 210 and 220 may determine the first robot 210 including the most information on the surrounding environment as the operating device. Subsequently, as an operating device, the first robot 210 may check the target task based on the task-related information, and transmit information on the target task to at least one other robot.

At least one of the plurality of operating devices 110 and 120 and the plurality of robots 210 and 220 may be an artificial intelligence-based device or a robot. For example, the operating device 110 may be a device capable of receiving a command from an operator, and the operating device 120 may be an artificial intelligence-based device. For example, at least one of the plurality of robots 210 and 220 may be a drone.

The first operating device 110 acquires information about a specific situation from the first robot 210, selects at least one of optimization and deep reinforcement learning based on the information about the specific situation, and selects the selected method. You can check the target mission accordingly. Specifically, in solving a specific situation, the first operation device 110 may select deep reinforcement learning when the computational complexity is greater than or equal to a predetermined criterion, and select an optimization method when the computational complexity is less than a predetermined criterion. For example, the first operation device 110 may set a target task as an optimization problem solving method when formulating is possible in solving a specific situation, and deep reinforcement learning when formulating is impossible in solving a specific situation The target mission can be set using the algorithm. According to an example, when there is a need to modify the reconnaissance movement line of the first robot 210 due to the appearance of an obstacle, the first operation device 110 modifies the target mission as an optimization problem solving method to perform the modified target mission first. It can be transmitted to the robot 210. According to another example, the first operation device 110 may set a target mission using an algorithm that has been in-depth reinforcement learning in order to prepare a response plan due to the unexpected appearance of an enemy robot, and the set target mission 210).

Therefore, through the operation system 10, a control structure including a concept (Many-to-Many) in which a plurality of operation devices operate a robot cluster can be implemented, so that a plurality of operators can be used in various forms (human-human, human- AI, AI-AI, etc.) can operate a large-scale unmanned robot cluster system.

2 shows an embodiment of a hierarchical control structure of an operating system.

Referring to FIG. 2, a plurality of operating devices 110 and 120 may check a mission and transmit information on a mission to at least one of the plurality of robots 210 and 220. At least one of the plurality of robots 210 and 220 may sequentially select a task, a task, and a behavior based on the information on the task. In addition, among the plurality of robots 210 and 220, an action according to a behavior may be performed.

3 shows a specific embodiment of an operating system.

The operating system 30 may include an operating device 300 and a robot 350. Since the operating system 10 may correspond to the operating system 10 of FIG. 1, a description of overlapping contents will be omitted.

The operating device 300 may include a communication module 310 and a global situational awareness module 320.

The communication module 310 may include a first communication module 312, a second communication module 314, and a security module 316.

The first communication module 312 may be a module for communication between operating devices. In other words, communication between the plurality of operating devices may be performed through the first communication module of each of the plurality of operating devices. The second communication module 314 may be a module for communication with the robot 350. In other words, communication between the plurality of operating devices and the plurality of robots may be performed through the second communication module. According to an embodiment, in FIG. 2, the first communication module 312 and the second communication module 314 are shown to be separated from each other, but according to another embodiment, the first communication module 312 and the second communication module 314 ) May be an integrated communication module.

The security module 316 may perform a security function of determining whether data received from each of the first communication module 312 and the second communication module 314 is normal. Accordingly, the operating device 300 can secure high reliability security in communication through the security module 316.

The global context recognition module 320 may perform a function for grasping the overall situation related to the mission. For example, the global context recognition module 320 can analyze the mission status data received through observation, and display the mission performance status like a global map through monitoring. have.

The robot 350 may include a communication module 360, a local context recognition module 370, a task layer 380, a work layer 390, and a control layer 395.

The communication module 360 may include a first communication module 362, a second communication module 364, and a security module 366. The first communication module 362 may be a module for communication with the operating device 300. The second communication module 364 may be a module for communication with another robot. The security module 366 may perform a security function of determining whether data received from each of the first communication module 362 and the second communication module 364 is normal.

The local situation recognition module 370 may perform a function of localizing the surrounding situation. For example, a robot performing a mission on the battlefield can acquire local information. For example, the local context recognition module 370 can analyze the mission status data received through observation and generate a local map for context recognition, such as a local map.

The robot 350 must perform a task according to the information on the task transmitted from the operating device 300, set the task, select tasks and actions according to the task, and action-based control to perform the selected task Can be performed sequentially. This process may be modularized into a task layer 380, a work layer 390, and a control layer 395 in the robot 350. For example, each of the task layer 380, the work layer 390, and the control layer 395 may be a module that performs each operation in the robot 350.

The task layer 380 may select a task from the task database, convert the new task into a database when a new task is determined, and use it for a future task. In addition, the task layer 380 may calculate a global path point (ie, a global path) for performing the task.

The task layer 390 may select actions such as path point tracking and collision avoidance from the action database, and when a new task is identified, it can be converted into a database and used for future tasks. In addition, the work layer 390 may calculate a local path point (ie, a local path) to be actually performed calculated through action selection.

The control layer 395 may perform Guidance/Navigation/Control (GNC) for control from a planned route point. Also, the control layer 395 may control an action of the robot 350 from a control input calculated through an actuator and a sensor, and obtain sensor data.

Each of the modules of the operating device 300 and the robot 350 may be implemented as plug-and-play that can be quickly grafted and used when a new technology is developed.

4 shows a first embodiment in which the operating system operates.

The operating device 300 may receive a mission situation. According to an embodiment, the operating device 300 may receive a mission situation from an operator, and according to another embodiment, the operating device 300 may receive a mission situation from another operating device. The operating device 300 may receive information about the task and task DB 402. Specifically, the operating device 300 may receive information on the task and work DB 402 together with information on the mission situation from another operating device.

The operation device 300 may receive the operation authority of the robot through a concept such as hand-over during a mission.

5 shows a first embodiment of an operation scenario of an operating system.

The operating device 300 may receive information on a mission to prevent an attack of the attacking drone cluster 520 using the defense drone cluster 510 which is robots. In FIG. 5, for convenience of explanation, a defensive drone cluster 510 of 10 robots and an attack drone cluster 520 of 10 robots are illustrated, but the number is not limited thereto. In FIG. 5, an area marked with a fan shape represents a search area of a defense drone.

When receiving information about a task, the operating device 300 may receive information about a database of tasks and tasks together. For example, tasks may include intercept and reconnaissance, and tasks may include path point tracking and collision avoidance.

6 shows a second embodiment in which the operating system operates.

When the operation device 300 transmits information on the received task to the robot 350, the surrounding environment information may also be transmitted to the robot 350. The surrounding environment information may include information on weather forecasts and terrain information. In addition, the operating device 300 may recognize the global situation based on the surrounding environment information and may determine the mission state. The operating device 300 may review the security of the surrounding environment information and allow the normal surrounding environment information to be transmitted to the robot 350. Even if a plurality of operating devices are not connected to the web or do not have a built-in database, information can be transmitted to each other through the first communication module.

The robot 350 may acquire information about a mission and information about a surrounding environment through the first communication module 362. In addition, the robot 350 may obtain status and mission information from a surrounding robot through the second communication module 364. In addition, the robot 350 may perform a normality review on the information acquired through the security module 366. In addition, the robot 350 may execute not only functions such as a checksum, but also various normality review and security modules being developed in the field of communication and unmanned systems when reviewing the normality of the acquired information. For example, the robot 350 checks and verifies whether the mission and database received from the operation device 300 and the mission and database received from the surrounding robot match, and if they do match, the acquired information is determined to be safe and agreed ( consensus), you can perform your mission. In addition, the robot 350 may utilize an encryption code within the protocol.

7 shows a second embodiment of an operation scenario of an operating system.

The operating device 300 may transmit information on a mission and information about a surrounding environment to the first drone 712 and the second drone 714 of the defense drone cluster 510.

Criteria for defining a surrounding robot may vary, but according to an embodiment, a surrounding robot may be defined according to a physical distance and whether or not a communication connection is made. The communication assumed in FIG. 7 is a communication connection graph in which information can only be exchanged with drones on both sides of the self, and communication is possible only between drones connected by a solid line. A connected graph means that a node is connected from an arbitrary node to another neighboring node. That is, even if the mission is transmitted only to the first drone 712 and the second drone 714 in FIG. 7, all drones can acquire the mission if the mission is transmitted to neighboring drones several times. For example, through a communication connection graph, all drones can check whether they are communicating through a normality review and take pre-promised actions, such as homing to an emergency situation.

8 shows a third embodiment in which the operating system operates.

The robot 350 may perform an assignment and planner procedure by extracting a specific task from the task database. Specifically, the task layer 380 may select a task using a built-in task assignment algorithm, and calculate a global path by calculating a path point required to perform the task. In this process, when it is identified that a new task is required, the task layer 380 may convert the databaseized information to the operating device 300 through the first communication module 362 by performing database conversion. For example, since the operating device 300 may have a better function of hardware or software than the robot 350, the operating device 300 may apply a more effective task selection algorithm based on database information. As another embodiment, the task layer 380 may not only perform database creation when a task that is not synchronized in advance occurs, but also the task layer 380 may perform allocation and planning for tasks that have been generated by itself. Through this, it is possible to build an operating system that can respond well to the environment that changes in real time.

9 shows an embodiment of an allocation and planning module.

The robot 350 may include an allocation and planning module 910. The allocation and planning module 910 is plug-and-play, so that new algorithms can be quickly applied. For example, the allocation and planning module 910 may select any one of an optimization method (Optimization), deep reinforcement learning, Bayesian reinforcement learning, and a heuristic approach. . For example, the optimization method may include a Consensus Based Bundle Algorithm (CBBA). For example, the allocation and planning module 910 may determine a task by applying any one of an optimization method, deep reinforcement learning, Bayesian reinforcement learning, and a heuristic method in consideration of computational complexity for a specific situation.

10 shows a third embodiment of an operation scenario of an operating system.

The task database can be set up as tasks for interception and reconnaissance. The detection range of sensors in defense drones can be set by distance and angle of view. Interception can mean an intercept in which the defensive drone hits the attacking drone directly, and when the defensive drone detects the attacking drone within a certain distance, the defensive drone can shoot down the attacking drone with a preset probability. Defensive drones can use a consensus-based allocation algorithm (e.g., CBBA) to select tasks for each vehicle to select defensive drones to perform intercept tasks for attacking drones that come within the detection range, and reconnaissance drones. You can do your job.

Referring to FIG. 10, attack drones A1, A2, A3 and defense drones D1, D2, D3, and D4 may exist. At this time, the defense drone (D1) can detect the attack drone (A1), the defense drone (D2) can detect the attack drone (A1), and the defense drone (D3) can detect the attack drone (A2, A3). Can be detected, and the defense drone (D4) may not be able to detect the attacking drone. Defensive drones (D1, D2, D3, D4) can communicate only with neighboring drones, so the defensive drones (D1, D2, D3, D4) are Consensus can be reached through a bidding sheet. As a result, assignments are made like D1-A1, D3-A2, and D4-A3, so that the intercept task can be performed, and D2 who is not assigned the task can continue to perform the reconnaissance task. Defensive drones (D1, D2, D3, D4) can select each task to be performed through an algorithm that allocates the task, and calculates the required waypoint to perform the task and calculates the global path. ), you can perform the calculation and task selection process.

11 shows a fourth embodiment in which the operating system operates.

The robot 350 may select an action to be performed by the robot 350 from the calculated global path. Specifically, assuming that there are two types of path point tracking and collision avoidance as a database of input tasks, the task layer 390 is a task that attempts to follow the global path calculated in the previous task selection step, and an obstacle that unexpectedly appears. -up & unknown obstacle), it is possible to determine the action by creating a local path in consideration of the work to avoid the action, and to perform an appropriate action according to the determined action. For example, the control layer 395 can derive the most appropriate set of actions.

When a new job is identified, the job layer 390 may perform databaseization on the new job, and may transmit the database to the operating device 300. Specifically, a database for a task and a database for a task may be transmitted to the operating device 300 together. The control layer 395 may control the robot 350 by performing Guidance, Navigation, Control (GNC) according to a local path. Such control information may be transmitted to the local context recognition module 370, and the local context recognition module 370 may transmit the local context recognition result to the operating device 300 through the first communication module 362. The control layer 395 may sense the surrounding environment through a sensor.

12 shows a fourth embodiment of an operation scenario of an operating system.

Referring to FIG. 12, the defense drone D4 may perform control by selecting an action to be performed from the calculated global path. The database (DB) of the input task is route point tracking and collision avoidance, and the defense drone (D4) considers the task to follow the global route calculated in the previous task selection step and the task to avoid unknown objects. Paths can be created, actions can be determined, and appropriate actions can be performed.

13 shows an operating device according to an embodiment.

The operating device 1300 may include a communication device 1310 and a controller 1320. In the operating device 1300 illustrated in FIG. 13, only components related to the present embodiment are shown. Accordingly, it can be understood by those of ordinary skill in the art related to the present embodiment that other general-purpose components may be further included in addition to the components shown in FIG. 13. Since the operating device 1300 may include contents related to the operating devices 110 and 300, descriptions of overlapping contents will be omitted.

The communication unit 1310 is a device for performing wireless communication and may communicate with an external electronic device. In addition, communication technologies used by the communication unit 1310 include Global System for Mobile communication (GSM), Code Division Multi Access (CDMA), Long Term Evolution (LTE), 5G, Wireless LAN (WLAN), and Wireless-Fidelity (Wi-Fi). ), Bluetooth™, Radio Frequency Identification (RFID), Infrared Data Association (IrDA), ZigBee, Near Field Communication (NFC), and the like.

The controller 1320 may control the overall operation of the operating device 1300 and process data and signals. The control unit 1320 may be configured with at least one hardware unit. In addition, the controller 1320 may operate by one or more software modules generated by executing program codes stored in the memory. The controller 1320 may include a processor and a memory, and the processor may control the overall operation of the operating device 1300 and process data and signals by executing program codes stored in the memory.

The control unit 1320 can obtain mission-related information from other operating devices through the communication unit 1310, can check the target mission based on the mission-related information, and multiple information on the target mission through the communication unit 1310 It can be transmitted to at least one of the robots.

The mission-related information may include information on the authority to operate the first robot among a plurality of robots, and the control unit 1320 transmits information on the target mission to the first robot through the communication unit 1310. I can.

The controller 1320 may share mission-related information with other operating devices through the communication unit 1310 to identify a first target task, and transmit information on the first target task to some of the plurality of robots. In addition, the other operating device may share mission-related information with the controller 1320 to confirm the second target task and transmit information on the second target task to another part of the plurality of robots.

The control unit 1320 may recognize the first robot among the plurality of robots as another operating device, and may transmit first mission-related information to the first robot. The first robot may check the first target mission based on the first mission related information and transmit information on the first target mission to at least one robot.

The control unit 1320 obtains information on a specific situation from a first robot among a plurality of robots through the communication unit 1310, and based on the information on the specific situation, optimization and deep reinforcement learning ), it is possible to select at least one method and check the target mission according to the selected method. In solving a specific situation, the controller 1320 may select deep reinforcement learning when the computational complexity is greater than or equal to a predetermined criterion, and select an optimization method when the computational complexity is less than a predetermined criterion.

The communication unit 1310 may include a security module that determines whether information obtained from at least one of the plurality of robots or information obtained from the other operating device is normal.

The control unit 1320 may receive databased information on a task or task from at least one of a plurality of robots through the communication unit 1310, and perform a target task based on the databased information. I can confirm.

14 illustrates a method of operating an operating device according to an embodiment.

Since each step of the operation method of FIG. 14 may be performed by the operating device 1300 of FIG. 13, descriptions of contents overlapping with those of FIG. 13 will be omitted.

In step S1410, the operating device 1300 may acquire mission-related information from another operating device.

In step S1420, the operating device 1300 may check the target mission based on the mission-related information.

In step S1430, the operating device 1300 may transmit information on the target task to at least one of the plurality of robots.

The operating device or robot according to the above-described embodiments includes a processor, a memory for storing and executing program data, a permanent storage such as a disk drive, a communication port for communicating with an external device, a touch panel, and a key. ), a user interface device such as a button, and the like. Methods implemented as software modules or algorithms may be stored on a computer-readable recording medium as computer-readable codes or program instructions executable on the processor. Here, the computer-readable recording medium is a magnetic storage medium (e.g., read-only memory (ROM), random-access memory (RAM), floppy disk, hard disk, etc.) and optical reading medium (e.g., CD-ROM ) And DVD (Digital Versatile Disc). The computer-readable recording medium is distributed over network-connected computer systems, so that computer-readable codes can be stored and executed in a distributed manner. The medium is readable by a computer, stored in memory, and executed on a processor.

This embodiment may be represented by functional block configurations and various processing steps. These functional blocks may be implemented with various numbers of hardware or/and software configurations that perform specific functions. For example, the embodiment is an integrated circuit configuration such as memory, processing, logic, a look-up table, etc., capable of executing various functions by controlling one or more microprocessors or other control devices Can be hired. Similar to how components can be implemented with software programming or software elements, this embodiment includes various algorithms implemented with a combination of data structures, processes, routines or other programming components, including C, C++, Java ( Java), an assembler, etc. may be implemented in a programming or scripting language. Functional aspects can be implemented with an algorithm running on one or more processors. In addition, the present embodiment may employ a conventional technique for electronic environment setting, signal processing, and/or data processing. Terms such as “mechanism”, “element”, “means”, and “composition” can be used widely, and are not limited to mechanical and physical configurations. The term may include a meaning of a series of routines of software in connection with a processor or the like.

The above-described embodiments are only examples, and other embodiments may be implemented within the scope of the claims to be described later.

Claims (10)

As an operation device for a plurality of robots that can cooperate with each other for a target mission,
A communication unit capable of communicating with at least one of the plurality of robots and capable of communicating with other operating devices for the plurality of robots; And
It includes a control unit connected to the communication unit,
The control unit,
Obtaining mission-related information from the other operating device through the communication unit,
Check the target mission based on the mission-related information,
Transmitting information on the target mission to at least one of the plurality of robots through the communication unit,
The control unit,
Obtaining information about a specific situation from the first robot among the plurality of robots through the communication unit,
Selecting at least one method of optimization and deep reinforcement learning, based on the information on the specific situation,
Identify the target mission according to the selected method,
The control unit,
In the case of solving the specific situation, when the computational complexity is greater than or equal to a predetermined criterion, deep reinforcement learning is selected, and when the computational complexity is less than a predetermined criterion, an optimization method is selected. The method of claim 1,
The above mission related information,
Including information on the authority to operate a second robot among the plurality of robots,
The control unit,
An operating device that transmits information on the target task to the second robot through the communication unit. The method of claim 1,
The control unit,
By sharing the mission-related information with the other operating device through the communication unit, confirming the first target mission,
Transmit information on the first target mission to some of the plurality of robots,
The other operating device shares the task-related information with the operating device, confirms a second target task, and transmits information on the second target task to another part of the plurality of robots. The method of claim 1,
The control unit,
Recognizing the second robot among the plurality of robots as another operating device,
Transmits the first mission-related information to the second robot,
The second robot,
An operating device for confirming a first target task based on the first task-related information, and transmitting information about the first target task to at least one robot. delete delete The method of claim 1,
The communication unit,
And a security module that determines whether information obtained from at least one of the plurality of robots or information obtained from the other operating device is normal. The method of claim 1,
The control unit,
An operating device that can receive databaseized information on a task or task from at least one of the plurality of robots through the communication unit, and confirms a target task based on the databased information . As a method of operating an operation device (operation device) for a plurality of robots that can cooperate with each other for a target mission,
Obtaining mission-related information from another operating device;
Identifying the target mission based on the mission-related information; And
Transmitting information on the target mission to at least one of the plurality of robots,
The step of confirming the target mission,
Obtaining information on a specific situation from a first robot among the plurality of robots;
Selecting at least one of optimization and deep reinforcement learning based on the information on the specific situation; And
Confirming the target mission according to the selected method,
Selecting the at least one method,
And selecting deep reinforcement learning when the computational complexity is greater than or equal to a predetermined criterion in solving the specific situation, and selecting an optimization method when the computational complexity is less than a predetermined criterion. As a non-transitory recording medium that can be read by a computer, a program for executing an operation method of an operation device for a plurality of robots that can cooperate with each other for a target mission is recorded on a computer,
The operation method,
Obtaining mission-related information from another operating device;
Identifying the target mission based on the mission-related information; And
Transmitting information on the target mission to at least one of the plurality of robots,
The step of confirming the target mission,
Obtaining information on a specific situation from a first robot among the plurality of robots;
Selecting at least one of optimization and deep reinforcement learning based on the information on the specific situation; And
Confirming the target mission according to the selected method,
Selecting the at least one method,
And selecting deep reinforcement learning when the computational complexity is greater than or equal to a predetermined criterion in solving the specific situation, and selecting an optimization method when the computational complexity is less than a predetermined criterion.

Images