KR20130068603A - Method for assigning roles to multi robot - Google Patents

Method for assigning roles to multi robot Download PDF

Info

Publication number
KR20130068603A
KR20130068603A KR1020110135893A KR20110135893A KR20130068603A KR 20130068603 A KR20130068603 A KR 20130068603A KR 1020110135893 A KR1020110135893 A KR 1020110135893A KR 20110135893 A KR20110135893 A KR 20110135893A KR 20130068603 A KR20130068603 A KR 20130068603A
Authority
KR
South Korea
Prior art keywords
robot
role
intruder
information
robots
Prior art date
Application number
KR1020110135893A
Other languages
Korean (ko)
Inventor
전서현
조영조
장민수
이대하
김재홍
손주찬
Original Assignee
한국전자통신연구원
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 한국전자통신연구원 filed Critical 한국전자통신연구원
Priority to KR1020110135893A priority Critical patent/KR20130068603A/en
Publication of KR20130068603A publication Critical patent/KR20130068603A/en

Links

Images

Classifications

    • BPERFORMING OPERATIONS; TRANSPORTING
    • B25HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25JMANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J9/00Programme-controlled manipulators
    • B25J9/16Programme controls
    • B25J9/1656Programme controls characterised by programming, planning systems for manipulators
    • B25J9/1669Programme controls characterised by programming, planning systems for manipulators characterised by special application, e.g. multi-arm co-operation, assembly, grasping
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B25HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25JMANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J9/00Programme-controlled manipulators
    • B25J9/16Programme controls
    • B25J9/1679Programme controls characterised by the tasks executed
    • B25J9/1682Dual arm manipulator; Coordination of several manipulators
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02PCLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/02Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]

Landscapes

  • Engineering & Computer Science (AREA)
  • Robotics (AREA)
  • Mechanical Engineering (AREA)
  • Manipulator (AREA)

Abstract

According to an aspect of the present invention, there is provided a method for assigning a role of a cluster robot, the method comprising: performing a specific role by a first robot, which is at least one of the robots constituting the cluster robot, or attempting to perform a specific role by the first robot; If it is determined that the first robot cannot perform the role, allocating the second robot to at least one of the robots forming the cluster robot; And performing the role by the second robot.

Description

Method for assigning roles to multi robot}

The present invention relates to a multi robot technology, and more particularly, to a method for assigning a role to a group robot.

In order for robots to work smoothly in complex environments, they must have the same intelligence and autonomy as humans. In order to give these autonomous powers to robots, large scale processing power is required along with sophisticated sensors and precise controllers, and robots are expensive. In addition, when the work needs to be performed in a large area, the work efficiency of the robot is inevitably reduced.

It is well known that using a robot consisting of several robots to make up for this weakness is much more efficient and stable. In particular, construction, defense security, etc. are representative fields that can increase work efficiency by using cluster robots.

When a plurality of robots are initially set to perform only a role inputted, an abnormal situation may occur and one or more robots may not play a specific role. In such a case, the robot will perform the mission without the role of the robot and the overall mission completion will be reduced.

1 shows an example of such a situation, in which the situation occurs while the cluster robot is performing a surveillance boundary task in a space. If an intruder is found in the example of FIG. 1, the cluster robot must surround the intruder. To do this, a robot that first discovers an intruder or recognizes an intruder correctly conveys the location of the intruder to other robots, commands the siege to surround the intruder, and keeps track of the intruder. Referring to FIG. 1A, the robot A recognizes an intruder and issues a siege command. The rest of the robots do not capture the front of the intruder, or they are not aware of the intruder precisely due to the effects of lighting. Referring to FIG. 1B, the robots B, C, D, and E receive an intruder position information or an invader envelopment command from the robot A, and in response, surround the intruder. Robot A continues to track intruders and update location information or siege commands. However, when the intruder obscures the view of the robot A or disappears from the view of the robot A as shown in FIG. 1 (c), the robot A can no longer perform its role, and other robots that cannot confirm the position of the intruder are more. The intruder can no longer be properly surrounded. Thus, as shown in Figure 1 (d), the cluster robot misses the intruder.

The technical problem to be achieved by the present invention, if any one of a number of robots constituting the cluster robot can not play a role, other robots can perform the role to improve the task completion of the cluster robot, cluster robot To provide a way to assign roles.

In order to solve the above technical problem, in the method of assigning a role of a cluster robot according to the present invention, at least one of the robots constituting the cluster robot performs a specific role or the first robot attempts to perform a specific role. Doing; If it is determined that the first robot cannot perform the role, allocating the second robot to at least one of the robots forming the cluster robot; And performing the role by the second robot.

The assigning may include: transmitting, by the first robot, information indicating that the role of the cluster robot is impossible to perform, and information about the role; And determining, by the robots receiving the information from the first robots, at least one robot to perform the role.

The assigning may include transmitting information indicating that the first robot cannot perform the role and information about the role to a server; Determining, by the server receiving the information, at least one robot that performs the role among the robots forming the cluster robot; And transmitting, by the server, information about the role to the determined robot.

The role may include at least one of tracking a target, transmitting a position of the target, or transmitting an enclosing command of the target.

The assigning may include: transmitting, by the first robot, information about the role including information indicating that the role of the cluster robot is impossible to perform, and location information of the target; And determining, by the robots receiving the information from the first robots, at least one robot to play the role, wherein the second robot performing the role is based on the position information. It can play the role.

The assigning may include: transmitting, to the server, information about the role including information indicating that the first robot cannot perform the role and location information of the target; Determining, by the server receiving the information, at least one robot that performs the role among the robots forming the cluster robot; And transmitting, by the server, information about the role to the determined robot, and the second robot performing the role may perform the role based on the location information.

According to the present invention described above, when any one of the plurality of robots constituting the cluster robot can not play a role, the other robot can perform the role to improve the task completion of the cluster robot.

FIG. 1 illustrates a situation in which a robot cannot perform a specific role while a cluster robot performs a surveillance boundary task in a space.
2 is a flowchart illustrating a role assignment method of a cluster robot according to an embodiment of the present invention.
3 is a detailed flowchart of step 240 according to an embodiment of the present invention.
4 is a detailed flowchart of step 240 according to another embodiment of the present invention.
5 is a flowchart illustrating a role assignment method of a cluster robot according to another embodiment of the present invention.
FIG. 6 is a reference diagram to help explain the exemplary embodiment of the present invention illustrated in FIG. 5.
7 is a flowchart illustrating a role assignment method of a cluster robot according to another embodiment of the present invention.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the drawings. In the following description and the accompanying drawings, substantially the same components are denoted by the same reference numerals, and redundant description will be omitted. In the following description of the present invention, a detailed description of known functions and configurations incorporated herein will be omitted when it may make the subject matter of the present invention rather unclear.

2 is a flowchart illustrating a role assignment method of a cluster robot according to an embodiment of the present invention.

The first robot, which is one of the robots constituting the cluster robot, performs a specific role or attempts to perform a specific role (step 210). However, there may be one or more robots performing or attempting a role.

If it is possible for the first robot to play a role, it continues to play a role (step 230). However, if it is determined that it is impossible for the first robot to perform a role, the performance of the role is allocated to a second robot, which is one of the robots forming the cluster robot, in operation 240. However, there may be one or more other robots to which role performance is assigned.

In operation 240, the second robot assigned to perform the role performs the corresponding role (250).

3 is a detailed flowchart of step 240 according to an embodiment of the present invention. This embodiment corresponds to the case where the cluster robot itself performs the function of assigning a role to the cluster robot.

If it is determined that the first robot cannot perform the role, the first robot transmits information indicating that the role cannot be performed to other robots and information on the corresponding role (step 310). Here, the information on the role may include information indicating what the role is and information obtained as a result of performing the role to date.

Receiving information from the first robot, the robot determines a robot to perform a corresponding role among them (step 320). Here, the determination of the robot to play a role may be determined in various ways depending on the role. For example, if any robot may play a role, any robot among the robots that receive the information may be determined as the robot to play the role. If a specific function is required to perform the role, any robot among the robots having the function may be determined as the robot to play the role. In addition, among the robots receiving the information, the robot may be determined to be the most suitable robot to perform the corresponding role according to a predetermined standard. The robots that receive the information can communicate with each other for this determination and negotiate according to a predetermined algorithm.

Referring back to FIG. 2, in step 250, a second robot assigned to perform a role performs a corresponding role by referring to information received from the first robot.

4 is a detailed flowchart of step 240 according to another embodiment of the present invention. This embodiment corresponds to a case where a separate server (not shown) in charge of controlling the cluster robot performs a function of assigning a role to the cluster robot.

If it is determined that the first robot cannot perform the role, the first robot transmits information indicating that the role cannot be performed and information on the corresponding role (step 410). Here, the information on the role may include information indicating what the role is and information obtained as a result of performing the role to date.

The server receiving the information from the first robot determines a robot to perform a corresponding role among the robots constituting the cluster robot (step 420). In this embodiment, the robots continuously communicate with the server, and the server has information about the location, role, function, etc. of each robot. The determination of the robot to play a role may be determined in various ways depending on the role. For example, if any robot may play a role, any robot except the first robot among the robots constituting the cluster robot may be determined as a robot to play a role. If a specific function is required to perform the role, any robot among the robots having the function may be determined as the robot to play the role. In addition, among the robots constituting the cluster robot, it may be determined to be the most suitable robot to perform the corresponding role according to a predetermined standard.

When the robot to play the role is determined, the server transmits the information about the role received from the first robot to the determined robot (step 430).

Referring back to FIG. 2, in step 250, the second robot that has received the information about the role from the server performs the corresponding role by referring to the information received from the server.

5 is a flowchart illustrating a role assignment method of a cluster robot according to another embodiment of the present invention. This embodiment corresponds to the case where the mission of the cluster robot is a surveillance boundary mission in a certain space, and also when the cluster robot itself performs a function of assigning a role to the cluster robot. Hereinafter, a description will be given with reference to FIG. 6 to help explain the present embodiment.

First, a first robot, which is one of the robots constituting the cluster robot, recognizes a specific target in a given space (step 510). In this embodiment, the target is assumed to be an intruder. Here, since the first robot recognizes the intruder, the role of the first robot may be an intruder surrounding command transmission, intruder location information transmission, intruder tracking, etc. to other robots. Of course, the first robot may play only some of these roles.

Recognizing the intruder, the first robot transmits the invader siege command to other robots and transmits the location information of the intruder (step 520). Referring to FIG. 6A, the robot A transmits an intruder siege command to the robots B, C, D, and E, and transmits the intruder's position information (x0, y0). As a result, as shown in FIG. 6 (b), robot A and robots B, C, D, and E surround the intruder. Robot A now keeps track of intruders, updates robot location information, and delivers it to other robots.

If it is possible for the first robot to perform intruder tracking, the first robot continues to play a role (step 540). However, the intruder may obscure the robot's field of view, move quickly elsewhere to circumvent the robot's tracking, or it may become impossible to play a role due to a fault inside the robot. If it is determined that the first robot cannot perform the intruder tracking as described above, the first robot transmits information indicating that the role cannot be performed to other robots and information on the corresponding role (step 550). The information on the role includes information indicating that the role to be performed is the tracking and transmission of location information of the intruder, and the location information of the intruder most recently obtained. Referring to FIG. 6C, when the intruder obstructs the field of view of the robot A with a black cloth, the robot A can no longer perform a role of tracking the intruder and updating location information. Therefore, as shown in (d) of FIG. 6, the robot A transmits information indicating that intruder tracking is impossible and role information including the most recently obtained intruder position information (x0 ', y0') to other robots.

In operation 550, the robots, which have received role inability information and role information from the first robot, determine a robot to perform a role of tracking an intruder and transmitting location information (step 560). Here, any robot except the first robot among the robots constituting the cluster robot may be determined as a robot to play a role. Alternatively, the robot in the position closest to the position of the intruder may be determined as a robot to play a role, with reference to the position information of the intruder obtained from the first robot. Alternatively, when there is another robot that recognizes an intruder besides the first robot, the robot may be determined as a robot to play a role. If there is more than one robot that recognizes the intruder, a robot that recognizes the intruder more accurately or a robot closer to the intruder may be determined as a robot to play a role.

When the robot to play the role is determined, the robot performs the role of tracking and transmitting location information of the intruder by referring to the information received from the first robot (step 570). Here, if the robot to play a role correctly recognizes the intruder, the intruder can be tracked based on the recognition result. If the robot to play the role does not recognize the intruder correctly and only acquires the past location information of the intruder from the first robot, the location of the intruder is based on the acquired location information and the image obtained through the camera. You can then estimate the intruder.

Referring to FIG. 6E, the robots B, C, D, and E receive role impossible information and role information from the robot A, and determine B as a robot to perform the role that the robot A performed. The robot B then tracks the intruder based on the information received from the robot A, and obtains the intruder's position information (x1, y1). Robot B sends the intruder's location information (x1, y1) to other robots and instructs him to surround the intruder again. Referring to FIG. 6F, the robots C, D, and E, which have received the intruder's position information from the robot B and the robot B, move based on the intruder's position information and surround the intruder again.

7 is a flowchart illustrating a role assignment method for a cluster robot according to another embodiment of the present invention. This embodiment corresponds to a case where the mission of a cluster robot is a surveillance boundary mission in a space, and when a separate server (not shown) in charge of controlling the cluster robot performs a function of assigning a role to the cluster robot. Corresponding.

First, a first robot, which is one of the robots constituting the cluster robot, recognizes a specific target in a given space (step 710). In this embodiment, the target is assumed to be an intruder. Here, since the first robot recognizes the intruder, the role of the first robot may be an intruder surrounding command transmission, intruder location information transmission, intruder tracking, etc. to other robots. Of course, the first robot may play only some of these roles.

Recognizing the intruder, the first robot transmits the invader siege command to other robots and transmits the location information of the intruder (step 720).

If it is possible for the first robot to perform intruder tracking, the robot continues to play a role (step 740). However, the intruder may obscure the robot's field of view, move quickly elsewhere to circumvent the robot's tracking, or it may become impossible to play a role due to a fault inside the robot. If it is determined that the first robot cannot perform the intruder tracking as described above, the first robot transmits information indicating that the role cannot be performed and information on the role (step 750). The information on the role includes information indicating that the role to be performed is the tracking and transmission of location information of the intruder, and the location information of the intruder most recently obtained.

In operation 750, the server, which has received the role impossible information and the role information from the first robot, determines the robot to perform the role of tracking the intruder and transmitting location information (step 760). Here, any robot except the first robot among the robots constituting the cluster robot may be determined as a robot to play a role. Alternatively, the robot in the position closest to the position of the intruder may be determined as a robot to play a role, with reference to the position information of the intruder obtained from the first robot. Alternatively, based on the information obtained through communication with the cluster robot, if there is another robot that recognizes the intruder besides the first robot, the robot may be determined as a robot to play a role. If there is more than one robot that recognizes the intruder, a robot that recognizes the intruder more accurately or a robot closer to the intruder may be determined as a robot to play a role.

When the robot to play the role is determined, the server transmits information about the role to the robot (step 770). The robot receiving the information from the server refers to this information and performs the role of tracking the intruder and transmitting location information (step 780). Here, if the robot to play a role correctly recognizes the intruder, the intruder can be tracked based on the recognition result. If the robot to play the role does not recognize the intruder correctly and only acquires the past location information of the intruder from the first robot, the location of the intruder is based on the acquired location information and the image obtained through the camera. You can then estimate the intruder.

The above-described embodiments of the present invention can be embodied in a general-purpose digital computer that can be embodied as a program that can be executed by a computer and operates the program using a computer-readable recording medium. The computer-readable recording medium includes a storage medium such as a magnetic storage medium (e.g., ROM, floppy disk, hard disk, etc.), optical reading medium (e.g., CD ROM,

So far I looked at the center of the preferred embodiment for the present invention. It will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims. Therefore, the disclosed embodiments should be considered in an illustrative rather than a restrictive sense. The scope of the present invention is defined by the appended claims rather than by the foregoing description, and all differences within the scope of equivalents thereof should be construed as being included in the present invention.

Claims (1)

In the role assignment method of the cluster robot,
A first robot, which is at least one of the robots constituting the cluster robot, plays a specific role or the first robot attempts to play a specific role;
If it is determined that the role of the first robot is impossible, allocating the specific role to a second robot, which is at least one of the robots forming the cluster robot; And
And a role of the second robot to perform the role.
KR1020110135893A 2011-12-15 2011-12-15 Method for assigning roles to multi robot KR20130068603A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1020110135893A KR20130068603A (en) 2011-12-15 2011-12-15 Method for assigning roles to multi robot

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1020110135893A KR20130068603A (en) 2011-12-15 2011-12-15 Method for assigning roles to multi robot

Publications (1)

Publication Number Publication Date
KR20130068603A true KR20130068603A (en) 2013-06-26

Family

ID=48864195

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1020110135893A KR20130068603A (en) 2011-12-15 2011-12-15 Method for assigning roles to multi robot

Country Status (1)

Country Link
KR (1) KR20130068603A (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20160082627A (en) 2014-12-26 2016-07-08 서울대학교산학협력단 Market-based decentralized task assignment method for UAV and recording medium recorded program to perform the method
KR101668078B1 (en) * 2015-04-23 2016-10-19 국방과학연구소 Autonomous robot collaborative system and method
KR20180076854A (en) * 2016-12-28 2018-07-06 한국생산기술연구원 Pick Up Robot System and Control Method thereof
WO2020141635A1 (en) * 2019-01-03 2020-07-09 엘지전자 주식회사 Control method for robot system
CN112247987A (en) * 2020-09-29 2021-01-22 深圳优地科技有限公司 Robot scheduling method and device, robot and storage medium
WO2023008598A1 (en) * 2021-07-27 2023-02-02 주식회사 럭스로보 Smart ai kit control system capable of mission delivery

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20160082627A (en) 2014-12-26 2016-07-08 서울대학교산학협력단 Market-based decentralized task assignment method for UAV and recording medium recorded program to perform the method
KR101668078B1 (en) * 2015-04-23 2016-10-19 국방과학연구소 Autonomous robot collaborative system and method
KR20180076854A (en) * 2016-12-28 2018-07-06 한국생산기술연구원 Pick Up Robot System and Control Method thereof
WO2020141635A1 (en) * 2019-01-03 2020-07-09 엘지전자 주식회사 Control method for robot system
US11500393B2 (en) 2019-01-03 2022-11-15 Lg Electronics Inc. Control method of robot system
CN112247987A (en) * 2020-09-29 2021-01-22 深圳优地科技有限公司 Robot scheduling method and device, robot and storage medium
WO2023008598A1 (en) * 2021-07-27 2023-02-02 주식회사 럭스로보 Smart ai kit control system capable of mission delivery

Similar Documents

Publication Publication Date Title
KR20130068603A (en) Method for assigning roles to multi robot
CN109917818B (en) Collaborative search containment method based on ground robot
US8279283B2 (en) Methods and systems for operating a video surveillance system
TWI629150B (en) Computer-implemented methods and systems of using object observations of mobile robots
Piciarelli et al. Dynamic reconfiguration in camera networks: A short survey
US10788316B1 (en) Multi-sensor real-time alignment and calibration
Yao et al. Can you see me now? Sensor positioning for automated and persistent surveillance
US20170213077A1 (en) Event signal processing method and apparatus
Wang et al. Visibility-aware trajectory optimization with application to aerial tracking
CN110533694A (en) Image processing method, device, terminal and storage medium
Johnson et al. Artificial intelligence—an enabler of naval tactical decision superiority
CN108364369B (en) Unmanned aerial vehicle inspection point determining method, unmanned aerial vehicle inspection point determining device, unmanned aerial vehicle inspection point determining medium, unmanned aerial vehicle inspection point determining equipment and unmanned aerial vehicle inspection point determining system
JP2013077088A (en) Information acquisition device, information acquisition method, information acquisition program, and information acquisition system
Sharma et al. Robust hybrid visual servoing using reinforcement learning and finite-time adaptive FOSMC
Al-Muteb et al. An autonomous stereovision-based navigation system (ASNS) for mobile robots
KR102681341B1 (en) Method and apparatus for learning variable CNN based on non-correcting wide-angle image
US8854461B2 (en) Method of controlling camera
Hirt et al. Geometry extraction for ad hoc redirected walking using a slam device
WO2019093297A1 (en) Information processing device, control method, and program
EP3745332A1 (en) Systems, device and method of managing a building automation environment
TW201435656A (en) Information technology device input systems and associated methods
Davani et al. An autonomous system for efficient control of ptz cameras
Liang et al. Real‐time visual tracking design for an unmanned aerial vehicle in cluttered environments
RU2772407C1 (en) Method and system for optical-inertial tracking of a moving object
Ishikawa et al. FindView: Precise Target View Localization Task for Look Around Agents

Legal Events

Date Code Title Description
WITN Withdrawal due to no request for examination