WO2021104412A1 - 集群机器人调度方法、装置、系统、设备及计算机可读存储介质 - Google Patents

集群机器人调度方法、装置、系统、设备及计算机可读存储介质 Download PDF

Info

Publication number
WO2021104412A1
WO2021104412A1 PCT/CN2020/132025 CN2020132025W WO2021104412A1 WO 2021104412 A1 WO2021104412 A1 WO 2021104412A1 CN 2020132025 W CN2020132025 W CN 2020132025W WO 2021104412 A1 WO2021104412 A1 WO 2021104412A1
Authority
WO
WIPO (PCT)
Prior art keywords
robot
task
attributes
ability
server
Prior art date
Application number
PCT/CN2020/132025
Other languages
English (en)
French (fr)
Inventor
郑晓琨
王翔宇
Original Assignee
炬星科技（深圳）有限公司
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 炬星科技（深圳）有限公司 filed Critical 炬星科技（深圳）有限公司
Publication of WO2021104412A1 publication Critical patent/WO2021104412A1/zh

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J11/00—Manipulators not otherwise provided for
    • B25J11/008—Manipulators for service tasks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
    • G06Q10/087—Inventory or stock management, e.g. order filling, procurement or balancing against orders

Definitions

  • the present invention relates to the technical field of robots, in particular to a cluster robot scheduling method, device, system, equipment and computer readable storage medium.
  • AMR Automatic Mobile Robot
  • the present invention proposes a cluster robot scheduling method, device, system, equipment and computer-readable storage medium, which have solved the unreasonable task allocation in the prior art, and the increase in the invalid driving distance of the robot brings lower execution efficiency and lower operating costs. High technical issues.
  • a cluster robot scheduling method provided by the present invention includes:
  • Each robot obtains its own static attributes and dynamic attributes, and inputs the static attributes, the dynamic attributes, and the execution requirements to its own evaluation model to obtain an evaluation score for the ability of each robot to perform the task.
  • the present invention also provides a cluster robot scheduling device, which includes:
  • the task decomposition unit is used to receive and decompose the tasks issued by the server to obtain the execution requirements.
  • the task scoring unit is used to obtain the static attributes and dynamic attributes of each robot itself, and input the static attributes, the dynamic attributes, and the execution requirements into the evaluation model of the robot itself, and obtain the status of each robot performing the task Ability assessment score.
  • the task receiving unit is configured to upload the ability evaluation score to the server, and receive a task allocation instruction generated by the server according to the ability evaluation score.
  • the present invention also proposes a cluster robot scheduling system, which includes:
  • the robot is used to receive and decompose the tasks issued by the server, obtain the execution requirements, and obtain its own static attributes and dynamic attributes, and input the static attributes, the dynamic attributes, and the Perform requirements and obtain evaluation scores for their own ability to perform the task.
  • the robot central control server is configured to receive the ability evaluation score uploaded by the robot, and generate and issue task allocation instructions according to the ability evaluation score.
  • the present invention also provides a cluster robot scheduling device, which includes a memory, a processor, and a computer program that is stored on the memory and can run on the processor.
  • a cluster robot scheduling device which includes a memory, a processor, and a computer program that is stored on the memory and can run on the processor.
  • Each robot obtains its own static attributes and dynamic attributes, and inputs the static attributes, the dynamic attributes, and the execution requirements to its own evaluation model to obtain an evaluation score for the ability of each robot to perform the task.
  • the present invention also provides a computer-readable storage medium having a cluster robot scheduling program stored on the computer-readable storage medium, and the cluster robot scheduling program is executed by a processor to realize the steps of the cluster robot scheduling method described above.
  • the beneficial effect of the present invention is that by receiving and decomposing the tasks issued by the server, the execution requirements are obtained; then, each robot obtains its own static attributes and dynamic attributes, and inputs the static attributes and all the attributes to its own evaluation model. According to the dynamic attributes and the execution requirements, the ability evaluation scores of the robots to perform the tasks are obtained; the ability evaluation scores are uploaded to the server, and the tasks generated by the server according to the ability evaluation scores Assign instructions.
  • a high-efficiency and accurate cluster robot scheduling scheme is realized, which makes task scheduling more reasonable, saves task execution time, and improves the overall health of the robot.
  • Fig. 1 is a first flowchart of a cluster robot scheduling method provided by an embodiment of the present invention.
  • Fig. 2 is a second flowchart of a cluster robot scheduling method provided by an embodiment of the present invention.
  • Fig. 3 is a schematic diagram of scheduling of a cluster robot scheduling method provided by an embodiment of the present invention.
  • Fig. 4 is a structural block diagram of a cluster robot scheduling device provided by an embodiment of the present invention.
  • Fig. 5 is an architecture diagram of a cluster robot scheduling system provided by an embodiment of the present invention.
  • module means, “part” or “unit” used to denote elements is only used to facilitate the description of the present invention, and has no specific meaning in itself. Therefore, “module”, “part” or “unit” can be used in a mixed manner.
  • FIG. 1 is the first flowchart of the cluster robot scheduling method provided by the embodiment of the present invention.
  • This embodiment proposes a cluster robot scheduling method, which includes:
  • Each robot obtains its own static attributes and dynamic attributes, and inputs the static attributes, the dynamic attributes, and the execution requirements to its own evaluation model, to obtain an evaluation score of the ability of each robot to perform the task .
  • the server includes the central control system of the robot, or a server with task scheduling.
  • each robot receives a task issued by the server, its own control system decomposes the received task to obtain the execution requirement corresponding to the task.
  • the execution requirement refers to the task when the task is delivered to the robot for execution. , The demand for the required capabilities of the robot.
  • each robot when each robot decomposes the task and obtains the execution requirements, each robot will obtain its own static and dynamic attributes.
  • the static properties of the robot refer to the current software and hardware configuration properties of the robot, that is, the inherent properties of the robot in a period of time
  • the dynamic properties of the robot refer to the current state information properties of the robot, that is, to obtain the current time.
  • the robot's own control system generates an evaluation model, which is used to score itself according to the received task.
  • the reference factors for the score include the robot's own static attributes, dynamic attributes, and decomposed execution requirements. Therefore, according to the evaluation model, the evaluation scores of each robot's ability to perform the above tasks are obtained.
  • each robot After each robot obtains its own ability evaluation score according to the evaluation model, it uploads the above-mentioned ability evaluation score to the server, and then the server sorts according to the above-mentioned ability evaluation score, and at the same time, combines the current delivery Task attributes, generate and issue task execution instructions to robots with a certain score value, where the task attributes include information including the number of robots delivered for execution.
  • Fig. 2 is a second flowchart of the cluster robot scheduling method provided by the embodiment of the present invention. Based on the above implementation steps, the method also includes:
  • S02. Decompose the task set to obtain the ability attribute of each task.
  • the static attributes of each robot in the cluster robot are acquired, where the static attributes include hardware components, sensor components, and software versions of each robot.
  • the hardware components include the mechanical equipment and display equipment of each robot, for example, whether the robot body has a movable device, whether the robot body has a manipulator, whether the robot body has a lighting fixture, and whether the robot body has a system interface display device, so as to facilitate Show tasks, etc.
  • the sensor components include sensors related to each robot function, for example, whether the robot body has a vision module sensor, whether the robot body has a lidar sensor, and so on.
  • the software version includes the software version of each robot control system, the software version of each functional component, and the functional categories supported by the aforementioned hardware components and sensor components.
  • the task set is decomposed to obtain the ability attributes of each task.
  • the task set is decomposed to obtain the task type, task area, hardware type, sensor type, and software version type.
  • a set is a collection of statistically significant tasks issued by the server at the current moment or within a period of time. By decomposing a larger-scale task set, the ability attribute of each task is obtained, so that the coverage of the ability attribute is more For comprehensive.
  • the task set is a collection of tasks accumulated by each robot in the process of task execution.
  • the task types include pickup and handling tasks, sorting and handling tasks, cleaning tasks, formation tasks, self-inspection tasks, inspection tasks, etc.
  • the task area includes the current location of the robot, the location of the execution target, and the scope of the task execution area. , The security range of task execution, etc.
  • the hardware types include whether the above-mentioned robot bodies have movable devices, whether the robot bodies have mechanical arms, whether the robot bodies have lighting fixtures, and whether the robot bodies have system interface display devices, etc.
  • the sensor types include the above Whether the robot body has a vision module sensor, whether the robot body has a lidar sensor, etc.
  • the software version type includes the software version of the above-mentioned robot control system, the software version of each functional component, and the functional categories supported by the above-mentioned hardware components and sensor components, etc. .
  • the evaluation value is obtained according to the judgment result, and the evaluation model related to each robot itself is generated within the scope of the task set according to the evaluation value.
  • the robot's own control system is used to train according to the task set in its task execution cycle to obtain its own evaluation model, and at the same time, continuously evaluate the model based on newly received and executed tasks Training is performed to make the evaluation model more accurate; optionally, in this embodiment, the robot receives the initial version of the evaluation model issued by the server, and then the robot’s own control system is used to execute the cycle according to its task The task set within is trained to obtain its own evaluation model. At the same time, the evaluation model is continuously trained according to the newly received and executed tasks, so that the accuracy of the evaluation model is higher.
  • the received tasks are decomposed to obtain the current task type, current task area, hardware requirements, sensor requirements, and software version requirements.
  • the task types include pickup and handling tasks, sorting and handling tasks, cleaning tasks, formation tasks, self-inspection tasks, inspection tasks, etc.
  • the task area includes the current location of the robot, the location of the execution target, and the scope of the task execution area. , The security range of task execution, etc.
  • the hardware types include whether the above-mentioned robot bodies have movable devices, whether the robot bodies have mechanical arms, whether the robot bodies have lighting fixtures, and whether the robot bodies have system interface display devices, etc.
  • the sensor types include the above Whether the robot body has a vision module sensor, whether the robot body has a lidar sensor, etc.
  • the software version type includes the software version of the above-mentioned robot control system, the software version of each functional component, and the functional categories supported by the above-mentioned hardware components and sensor components, etc. .
  • each robot after decomposing the received task, each robot obtains its own dynamic attributes, where the dynamic attributes include current position, current power, and current mileage; then, input to its own evaluation model
  • the above-mentioned static attributes, dynamic attributes, and execution requirements obtain the evaluation scores of each robot's ability to perform the task.
  • the ability evaluation score is uploaded to the server, and then the server determines the above-mentioned number according to the number of robots required in the task execution process.
  • the qualified value of the ability evaluation score and at the same time, send task execution instructions to robots that meet this qualified value.
  • FIG. 3 is a schematic diagram of scheduling of a cluster robot scheduling method provided by an embodiment of the present invention. Based on the above implementation steps, in this scheduling diagram, a server and the robot 1, robot 2, robot 3...robot n (n>10) that maintain a communication connection with the server constitute a task scheduling system.
  • robot 1, robot 2, robot 3...Robot n all have their own control system, which is used to obtain the evaluation score of the ability to perform each task in combination with the evaluation model.
  • the server determines that task A is currently to be executed, and then delivers this task A to robot 1, robot 2, robot 3...Robot n; optionally, according to certain initial conditions, Among the n robots, send task A to robot 1, robot 2, robot 3...Robot n-3, where the initial condition can be the judgment condition generated by the robot feedback information of the previous task execution cycle to avoid waiting
  • the executed task is sent to all robots to avoid imposing processing burden on robots that are not suitable to perform the task; optionally, the task is excluded from the robot 1, robot 2, robot 3...Robot n to be issued robot.
  • robot 1, robot 2, robot 3...robot n-3 receives task A to be executed, robot 1, robot 2, robot 3...robot n-3 respectively obtain their own static and dynamic attributes, and send them to The evaluation model of its own inputs the static attributes, dynamic attributes, and the execution requirements of task A, thereby obtaining the evaluation scores P1, P2, P3...P of robot 1, robot 2, robot 3...Robot n-3 for the ability to perform task A (N-3); Then, robot 1, robot 2, robot 3...Robot n-3 respectively upload the ability evaluation scores P1, P2, P3...P(n-3) to the server.
  • the server receives the ability evaluation scores P1, P2, P3...P(n-3) uploaded by robot 1, robot 2, robot 3...robot n-3, first, determine the task attributes of the task A to be executed,
  • the task attribute includes the number of robots required during the execution of the task. When the number of robots required is greater than 1, the task attribute also includes conditional relations such as the cooperation mode and execution order of the task execution.
  • the ability is determined according to the task attribute Evaluate the score threshold and determine the robot above this threshold as the performer of this task A; optionally, when the number of robots above this threshold is greater than 1, combine the above conditional relationship to determine the task A in the multi-robot execution process
  • the cooperation mode and execution order in the system, and the task execution instruction of task A is generated from this, and the task instruction is issued to the robots above this threshold. Therefore, the multi-robots above this threshold will cooperate according to the preset The method and order of execution jointly execute this task A.
  • the beneficial effect of this embodiment is that the execution requirements are obtained by receiving and decomposing the tasks issued by the server; then, each robot obtains its own static attributes and dynamic attributes, and inputs the static attributes, The dynamic attributes and the execution requirements obtain the ability evaluation scores of the robots to perform the tasks; upload the ability evaluation scores to the server, and receive the ability evaluation scores generated by the server according to the ability evaluation scores Task assignment instructions.
  • a high-efficiency and accurate cluster robot scheduling scheme is realized, which makes task scheduling more reasonable, saves task execution time, and improves the overall health of the robot.
  • Fig. 4 shows a structural block diagram of a cluster robot scheduling device provided by an embodiment of the present invention.
  • the present invention also provides a cluster robot scheduling device, which includes:
  • the task decomposition unit 10 is used to receive and decompose tasks issued by the server to obtain execution requirements.
  • the task scoring unit 20 is used to obtain the static attributes and dynamic attributes of each robot itself, and input the static attributes, the dynamic attributes, and the execution requirements into its own evaluation model, and obtain that each robot executes the task The ability assessment score.
  • the task receiving unit 30 is configured to upload the ability evaluation score to the server, and receive a task allocation instruction generated by the server according to the ability evaluation score.
  • the beneficial effect of this embodiment is that the execution requirements are obtained by receiving and decomposing the tasks issued by the server; then, each robot obtains its own static attributes and dynamic attributes, and inputs the static attributes, The dynamic attributes and the execution requirements obtain the ability evaluation scores of the robots to perform the tasks; upload the ability evaluation scores to the server, and receive the ability evaluation scores generated by the server according to the ability evaluation scores Task assignment instructions.
  • a high-efficiency and accurate cluster robot scheduling scheme is realized, which makes task scheduling more reasonable, saves task execution time, and improves the overall health of the robot.
  • Fig. 5 shows an architecture diagram of a cluster robot scheduling system provided by an embodiment of the present invention.
  • the present invention also proposes a cluster robot scheduling system, which includes:
  • the robot 40 is used to receive and decompose the tasks issued by the robot central control server 50, obtain the execution requirements, and obtain its own static and dynamic attributes, and input the static and dynamic attributes into its own evaluation model.
  • the attributes and the execution requirements obtain the evaluation score of the ability to perform the task.
  • the robot central control server 50 is configured to receive the ability evaluation score uploaded by the robot 40, and generate and issue task allocation instructions according to the ability evaluation score.
  • the beneficial effect of this embodiment is that by receiving and decomposing the tasks issued by the robot central control server, the execution requirements are obtained; then, each robot obtains its own static attributes and dynamic attributes, and inputs the said tasks into its own evaluation model.
  • the static attributes, the dynamic attributes, and the execution requirements are obtained to obtain the evaluation scores of the capabilities of the robots to perform the tasks; the capability evaluation scores are uploaded to the server, and received by the robot central control server according to the The task assignment instructions generated by the ability assessment scores.
  • a high-efficiency and accurate cluster robot scheduling scheme is realized, which makes task scheduling more reasonable, saves task execution time, and improves the overall health of the robot.
  • the present invention also provides a cluster robot scheduling device, which includes a memory, a processor, and a computer program that is stored on the memory and can run on the processor.
  • a cluster robot scheduling device which includes a memory, a processor, and a computer program that is stored on the memory and can run on the processor.
  • Each robot obtains its own static attributes and dynamic attributes, and inputs the static attributes, the dynamic attributes, and the execution requirements to its own evaluation model to obtain an evaluation score for the ability of each robot to perform the task.
  • the beneficial effect of this embodiment is that the execution requirements are obtained by receiving and decomposing the tasks issued by the server; then, each robot obtains its own static attributes and dynamic attributes, and inputs the static attributes, The dynamic attributes and the execution requirements obtain the ability evaluation scores of the robots to perform the tasks; upload the ability evaluation scores to the server, and receive the ability evaluation scores generated by the server according to the ability evaluation scores Task assignment instructions.
  • a high-efficiency and accurate cluster robot scheduling scheme is realized, which makes task scheduling more reasonable, saves task execution time, and improves the overall health of the robot.
  • the present invention also provides a computer-readable storage medium having a cluster robot scheduling program stored on the computer-readable storage medium, and the cluster robot scheduling program is executed by a processor to realize the steps of the cluster robot scheduling method described above.
  • the technical solution of the present invention essentially or the part that contributes to the existing technology can be embodied in the form of a software product, and the computer software product is stored in a storage medium (such as ROM/RAM, magnetic disk, The optical disc) includes several instructions to make a terminal (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) execute the method described in each embodiment of the present invention.
  • a terminal which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.
  • the execution requirements are obtained by receiving and decomposing the tasks issued by the server; then, each robot obtains its own static attributes and dynamic attributes, and inputs the static attributes and the dynamic attributes to its own evaluation model. , And the execution requirements, obtain the ability evaluation score of each robot to perform the task; upload the ability evaluation score to the server, and receive a task allocation instruction generated by the server according to the ability evaluation score.
  • a high-efficiency and accurate cluster robot scheduling scheme is realized, which makes task scheduling more reasonable, saves task execution time, and improves the overall health of the robot. Therefore, it has industrial applicability.

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • General Physics & Mathematics (AREA)
  • Development Economics (AREA)
  • Theoretical Computer Science (AREA)
  • General Business, Economics & Management (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Physics & Mathematics (AREA)
  • Game Theory and Decision Science (AREA)
  • Robotics (AREA)
  • Mechanical Engineering (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Educational Administration (AREA)
  • Manipulator (AREA)

Abstract

一种集群机器人调度方法、装置、系统、设备及计算机可读存储介质，其中，该方法包括：接收并分解由服务器下发的任务，得到执行需求(S1)；由各机器人获取其自身的静态属性和动态属性，并向自身的评估模型输入所述静态属性、所述动态属性、以及所述执行需求，得到所述各机器人执行所述任务的能力评估分数(S2)；将所述能力评估分数上传至所述服务器，接收由所述服务器根据所述能力评估分数生成的任务分配指令(S3)。实现了一种高时效性和准确性的集群机器人调度方案，使得任务调度更合理，节省了任务执行时间，提高了机器人的整体健康程度。

Description

集群机器人调度方法、装置、系统、设备及计算机可读存储介质 技术领域
本发明涉及机器人技术领域，尤其涉及一种集群机器人调度方法、装置、系统、设备及计算机可读存储介质。
 背景技术
现有技术中，随着电商业务不断发展，各厂商对于仓库拣货的时效性和准确性要求越来越高。为了进一步提高仓库拣货的时效性和准确性，很多厂商开始提供AMR（Automatic Mobile Robot，自主移动机器人）进行辅助。AMR可以接收WMS（Warehouse Management System，仓储管理系统）的拣货任务，然后自主移动到拣货储位前，显示任务信息，拣货人员根据界面提示进行相应的操作，从而完成任务。当机器人完成任务后，会自主移动到下一个位置继续执行任务，这样大大减少了拣货员的行走里程，提升了拣货效率。
但是，随着仓库内的单量越来越大，需要的机器人也越来越多，如何将订单“均匀地”分配给机器人成为一个难题，由于执行任务的点散落在仓库各个区域内，而机器人也散布在仓库内的不同区域内，同时，每一台机器人的状况还不一样，因此，怎样将所有任务合理分配给每一台机器人成为一个亟待解决的问题。
目前比较常见的方式是按照当前空闲的机器人顺序分配，对机器人的其它状态考虑地较少，这样可能会导致任务分配不合理，增加机器人无效行驶距离，从而影响任务的执行效率，同时，可能存在部分机器人的行驶距离远大于其它机器人的情况，从而可能带来硬件损坏、运营成本增加等不良影响。
 技术问题
本发明提出一种集群机器人调度方法、装置、系统、设备及计算机可读存储介质，已解决现有技术中的任务分配不合理，增加机器人无效行驶距离带来的执行效率较低，运营成本较高的技术问题。
 技术解决方案
为了解决上述技术问题，本发明提供的一种集群机器人调度方法包括：
接收并分解由服务器下发的任务，得到执行需求。
各机器人获取其自身的静态属性和动态属性，并向自身的评估模型输入所述静态属性、所述动态属性、以及所述执行需求，得到所述各机器人执行所述任务的能力评估分数。
将所述能力评估分数上传至所述服务器，接收由所述服务器根据所述能力评估分数生成的任务分配指令。
本发明还提出了一种集群机器人调度装置，该装置包括：
任务分解单元，用于接收并分解由服务器下发的任务，得到执行需求。
任务评分单元，用于获取各机器人自身的静态属性和动态属性，并向自身的评估模型输入所述静态属性、所述动态属性、以及所述执行需求，得到所述各机器人执行所述任务的能力评估分数。
任务接收单元，用于将所述能力评估分数上传至所述服务器，接收由所述服务器根据所述能力评估分数生成的任务分配指令。
本发明还提出了一种集群机器人调度系统，该系统包括：
机器人，用于接收并分解由服务器下发的任务，得到执行需求，以及，获取其自身的静态属性和动态属性，并向自身的评估模型输入所述静态属性、所述动态属性、以及所述执行需求，得到自身执行所述任务的能力评估分数。
机器人中央控制服务器，用于接收由所述机器人上传的所述能力评估分数，根据所述能力评估分数生成并下发任务分配指令。
本发明还提出了一种集群机器人调度设备，该设备包括存储器、处理器及存储在所述存储器上并可在所述处理器上运行的计算机程序，所述计算机程序被所述处理器执行时实现：
接收并分解由服务器下发的任务，得到执行需求。
各机器人获取其自身的静态属性和动态属性，并向自身的评估模型输入所述静态属性、所述动态属性、以及所述执行需求，得到所述各机器人执行所述任务的能力评估分数。
将所述能力评估分数上传至所述服务器，接收由所述服务器根据所述能力评估分数生成的任务分配指令。
本发明还提出了一种计算机可读存储介质，该计算机可读存储介质上存储有集群机器人调度程序，所述集群机器人调度程序被处理器执行时实现如上所述的集群机器人调度方法的步骤。
 有益效果
本发明的有益效果在于，通过接收并分解由服务器下发的任务，得到执行需求；然后，由各机器人获取其自身的静态属性和动态属性，并向自身的评估模型输入所述静态属性、所述动态属性、以及所述执行需求，得到所述各机器人执行所述任务的能力评估分数；将所述能力评估分数上传至所述服务器，接收由所述服务器根据所述能力评估分数生成的任务分配指令。实现了一种高时效性和准确性的集群机器人调度方案，使得任务调度更合理，节省了任务执行时间，提高了机器人的整体健康程度。
 附图说明
下面将结合附图及实施例对本发明作进一步说明，附图中：
图1是本发明实施例提供的集群机器人调度方法的第一流程图。
图2是本发明实施例提供的集群机器人调度方法的第二流程图。
图3是本发明实施例提供的集群机器人调度方法的调度示意图。
图4是本发明实施例提供的集群机器人调度装置的结构框图。
图5是本发明实施例提供的集群机器人调度系统的架构图。
 本发明的实施方式
应当理解，此处所描述的具体实施例仅用以解释本发明，并不用于限定本发明。
在后续的描述中，使用用于表示元件的诸如“模块”、“部件”或“单元”的后缀仅为了有利于本发明的说明，其本身没有特定的意义。因此，“模块”、“部件”或“单元”可以混合地使用。
实施例一
如图1所示是本发明实施例提供的集群机器人调度方法的第一流程图。本实施例提出了一种集群机器人调度方法，该方法包括：
S1、接收并分解由服务器下发的任务，得到执行需求。
S2、各机器人获取其自身的静态属性和动态属性，并向自身的评估模型输入所述静态属性、所述动态属性、以及所述执行需求，得到所述各机器人执行所述任务的能力评估分数。
S3、将所述能力评估分数上传至所述服务器，接收由所述服务器根据所述能力评估分数生成的任务分配指令。
在本实施例中，首先，接收并分解由服务器下发的任务，得到执行需求。其中，服务器包括机器人的中央控制系统、或者具备任务调度的服务器。当各个机器人接收到由服务器下发的任务时，由其自身的控制系统对接收到的任务进行分解，从而得到该任务对应的执行需求，其中，该执行需求是指该任务在交付机器人执行时，对该机器人所需具备能力的需求。
在本实施例中，当各机器人分解任务，得到执行需求后，各机器人将获取其自身的静态属性和动态属性。其中，机器人的静态属性是指机器人当前的软、硬件配置属性，也即，在一段时间内该机器人的固有属性，而机器人的动态属性是指机器人当前的状态信息属性，也即，获取当前时刻、或者统计一段时间内的机器人的动态信息，并由此得到该动态属性。当各机器人将获取其自身的静态属性和动态属性后，各机器人向自身的评估模型输入所述静态属性、所述动态属性、以及所述执行需求，得到所述各机器人执行所述任务的能力评估分数。其中，由机器人自身的控制系统生成一个评估模型，该评估模型用于根据接收到的任务，进行自身评分，评分的参考因子包括机器人自身的静态属性、动态属性、以及分解得到的执行需求，由此，根据该评估模型分别得到各机器人执行上述任务的能力评估分数。
在本实施例中，当各机器人根据该评估模型得到其自身的能力评估分数后，将上述能力评估分数上传至服务器，然后，由服务器根据上述能力评估分数进行排序，同时，结合当前的下发任务属性，向具备一定分数值的机器人生成并下发任务执行指令，其中，该任务属性包括包括交付执行的机器人数量等信息。
如图2所示是本发明实施例提供的集群机器人调度方法的第二流程图。基于上述实施步骤，该方法之前还包括：
S01、获取所述集群机器人中各个机器人的静态属性。
S02、对任务集进行分解，得到每个任务的能力属性。
S03、对所述各个机器人的静态属性和所述每个任务的能力属性进行匹配，生成所述评估模型。
在本实施例中，获取所述集群机器人中各个机器人的静态属性，其中，该静态属性包括各机器人的硬件组件、传感器组件以及软件版本。具体的，硬件组件包括各机器人的机械设备和显示设备，例如，机器人本体是否具备可移动装置、机器人本体是否具备机械臂，机器人本体是否具备照明灯具，机器人本体是否具备系统界面显示设备，从而便于展示任务等。具体的，传感器组件包括各机器人功能相关的传感器，例如，机器人本体是否具备视觉模组传感器，机器人本体是否具备激光雷达传感器等。具体的，软件版本包括各机器人控制系统的软件版本、各功能组件的软件版本以及上述硬件组件、传感器组件所支持的功能类别等。
在本实施例中，对任务集进行分解，得到每个任务的能力属性，具体的，分解上述任务集，得到任务类型、任务区域、硬件类型、传感器类型、以及软件版本类型，其中，该任务集是由服务器在当前时刻、或者一段时间内下发的具备统计意义的任务合集，通过对较大规模的任务集进行分解，得到每个任务的能力属性，从而使得该能力属性的覆盖范围更为全面。或者，该任务集是各机器人在进行任务执行的过程中，由其自身不断积累的任务合集。具体的，任务类型包括取件搬运任务、整理搬运任务、清理任务、编队任务、自检任务、查视任务等，任务区域包括机器人当前所在的位置、执行标的所在的位置、任务执行的区域范围、任务执行的安全范围等，硬件类型包括上述各机器人本体是否具备可移动装置、机器人本体是否具备机械臂，机器人本体是否具备照明灯具，机器人本体是否具备系统界面显示设备等，传感器类型包括上述各机器人本体是否具备视觉模组传感器，机器人本体是否具备激光雷达传感器等，软件版本类型包括上述各机器人控制系统的软件版本、各功能组件的软件版本以及上述硬件组件、传感器组件所支持的功能类别等。
在本实施例中，逐一判断上述静态属性是否满足上述能力属性，根据判断结果得到评估值，并根据评估值在任务集的范围内生成与各机器人自身相关的评估模型。可选的，在本实施例中，机器人自身的控制系统用于根据其任务执行周期内的任务集进行训练，得到自身的评估模型，同时，根据新接收并执行的任务不断地对该评估模型进行训练，从而使得该评估模型的准确性更高；可选的，在本实施例中，机器人接收由服务器下发的评估模型初始版本，然后，机器人自身的控制系统用于根据其任务执行周期内的任务集进行训练，得到自身的评估模型，同时，根据新接收并执行的任务不断地对该评估模型进行训练，从而使得该评估模型的准确性更高。
在本实施例中，当确定当前所采用的评估模型后，分解接收到的任务，得到当前任务类型、当前任务区域、硬件需求、传感器需求以及软件版本需求。具体的，任务类型包括取件搬运任务、整理搬运任务、清理任务、编队任务、自检任务、查视任务等，任务区域包括机器人当前所在的位置、执行标的所在的位置、任务执行的区域范围、任务执行的安全范围等，硬件类型包括上述各机器人本体是否具备可移动装置、机器人本体是否具备机械臂，机器人本体是否具备照明灯具，机器人本体是否具备系统界面显示设备等，传感器类型包括上述各机器人本体是否具备视觉模组传感器，机器人本体是否具备激光雷达传感器等，软件版本类型包括上述各机器人控制系统的软件版本、各功能组件的软件版本以及上述硬件组件、传感器组件所支持的功能类别等。
在本实施例中，当对接收到的任务进行分解后，由各机器人获取其自身的动态属性，其中，该动态属性包括当前位置、当前电量以及当前行驶里程；然后，向自身的评估模型输入上述静态属性、动态属性、以及执行需求，得到各机器人执行该任务的能力评估分数。
在本实施例中，当接收到任务的各机器人得到其自身执行该任务的能力评估分数后，将此能力评估分数上传至服务器，然后，服务器根据该任务执行过程中所需的机器人数量确定上述能力评估分数的合格值，同时，向满足此合格值的机器人发送任务执行指令。
图3所示是本发明实施例提供的集群机器人调度方法的调度示意图。基于上述实施步骤，在此调度示意图中，由一个服务器以及与该服务器保持通讯连接的机器人1、机器人2、机器人3…机器人n（n>10）构成一个任务调度体系。
需要说明的是，机器人1、机器人2、机器人3…机器人n均具备自身的控制系统，该控制系统用于结合评估模型得到执行各个任务的能力评估分数。
具体的，例如，首先，服务器确定当前待执行的是任务A，然后，将此任务A下发至机器人1、机器人2、机器人3…机器人n；可选的，根据一定的初始条件，在上述n个机器人中，将任务A下发至机器人1、机器人2、机器人3…机器人n-3，其中，该初始条件可以是由前一个任务执行周期的机器人反馈信息生成的判定条件，避免将待执行的任务发送至所有的机器人，避免给不合适执行该任务的机器人带来处理负担；可选的，在待下发任务的机器人1、机器人2、机器人3…机器人n中排除正在执行任务的机器人。
若当机器人1、机器人2、机器人3…机器人n-3接收到待执行的任务A，则机器人1、机器人2、机器人3…机器人n-3分别获取其自身的静态属性和动态属性，并向自身的评估模型输入该静态属性、动态属性、以及任务A的执行需求，由此，得到机器人1、机器人2、机器人3…机器人n-3执行任务A的能力评估分数P1、P2、P3…P（n-3）；然后，由机器人1、机器人2、机器人3…机器人n-3分别将能力评估分数P1、P2、P3…P（n-3）上传至服务器。
当服务器接收到由机器人1、机器人2、机器人3…机器人n-3上传的能力评估分数P1、P2、P3…P（n-3）后，首先，确定该待执行的任务A的任务属性，该任务属性包括该任务执行过程中所需机器人的数量，当所需机器人数量大于1时，该任务属性还包括该任务执行的协作方式、执行次序等条件关系，然后，根据该任务属性确定能力评估分数阈值，确定在此阈值之上的机器人作为此任务A的执行者；可选的，当在此阈值之上的机器人数量大于1时，结合上述条件关系，确定任务A在多机器人执行过程中的协作方式、执行次序，并由此生成任务A的任务执行指令，将此任务指令下发至在此阈值之上的机器人，由此，在此阈值之上的多机器人按照预设的协作方式、执行次序联合执行此任务A。
本实施例的有益效果在于，通过接收并分解由服务器下发的任务，得到执行需求；然后，由各机器人获取其自身的静态属性和动态属性，并向自身的评估模型输入所述静态属性、所述动态属性、以及所述执行需求，得到所述各机器人执行所述任务的能力评估分数；将所述能力评估分数上传至所述服务器，接收由所述服务器根据所述能力评估分数生成的任务分配指令。实现了一种高时效性和准确性的集群机器人调度方案，使得任务调度更合理，节省了任务执行时间，提高了机器人的整体健康程度。
实施例二
图4示出的是本发明实施例提供的集群机器人调度装置的结构框图。本发明还提出了一种集群机器人调度装置，该装置包括：
任务分解单元10，用于接收并分解由服务器下发的任务，得到执行需求。
任务评分单元20，用于获取各机器人自身的静态属性和动态属性，并向自身的评估模型输入所述静态属性、所述动态属性、以及所述执行需求，得到所述各机器人执行所述任务的能力评估分数。
任务接收单元30，用于将所述能力评估分数上传至所述服务器，接收由所述服务器根据所述能力评估分数生成的任务分配指令。
需要说明的是，上述装置实施例与方法实施例属于同一构思，其具体实现过程详细见方法实施例，且方法实施例中的技术特征在装置实施例中均对应适用，这里不再赘述。
本实施例的有益效果在于，通过接收并分解由服务器下发的任务，得到执行需求；然后，由各机器人获取其自身的静态属性和动态属性，并向自身的评估模型输入所述静态属性、所述动态属性、以及所述执行需求，得到所述各机器人执行所述任务的能力评估分数；将所述能力评估分数上传至所述服务器，接收由所述服务器根据所述能力评估分数生成的任务分配指令。实现了一种高时效性和准确性的集群机器人调度方案，使得任务调度更合理，节省了任务执行时间，提高了机器人的整体健康程度。
实施例三
图5示出的是本发明实施例提供的集群机器人调度系统的架构图。本发明还提出了一种集群机器人调度系统，该系统包括：
机器人40，用于接收并分解由机器人中央控制服务器50下发的任务，得到执行需求，以及，获取其自身的静态属性和动态属性，并向自身的评估模型输入所述静态属性、所述动态属性、以及所述执行需求，得到自身执行所述任务的能力评估分数。
机器人中央控制服务器50，用于接收由所述机器人40上传的所述能力评估分数，根据所述能力评估分数生成并下发任务分配指令。
需要说明的是，上述系统实施例与方法实施例属于同一构思，其具体实现过程详细见方法实施例，且方法实施例中的技术特征在装置实施例中均对应适用，这里不再赘述。
本实施例的有益效果在于，通过接收并分解由机器人中央控制服务器下发的任务，得到执行需求；然后，由各机器人获取其自身的静态属性和动态属性，并向自身的评估模型输入所述静态属性、所述动态属性、以及所述执行需求，得到所述各机器人执行所述任务的能力评估分数；将所述能力评估分数上传至所述服务器，接收由所述机器人中央控制服务器根据所述能力评估分数生成的任务分配指令。实现了一种高时效性和准确性的集群机器人调度方案，使得任务调度更合理，节省了任务执行时间，提高了机器人的整体健康程度。
实施例四
本发明还提出了一种集群机器人调度设备，该设备包括存储器、处理器及存储在所述存储器上并可在所述处理器上运行的计算机程序，所述计算机程序被所述处理器执行时实现：
接收并分解由服务器下发的任务，得到执行需求。
各机器人获取其自身的静态属性和动态属性，并向自身的评估模型输入所述静态属性、所述动态属性、以及所述执行需求，得到所述各机器人执行所述任务的能力评估分数。
将所述能力评估分数上传至所述服务器，接收由所述服务器根据所述能力评估分数生成的任务分配指令。
需要说明的是，上述设备实施例与方法实施例属于同一构思，其具体实现过程详细见方法实施例，且方法实施例中的技术特征在装置实施例中均对应适用，这里不再赘述。
本实施例的有益效果在于，通过接收并分解由服务器下发的任务，得到执行需求；然后，由各机器人获取其自身的静态属性和动态属性，并向自身的评估模型输入所述静态属性、所述动态属性、以及所述执行需求，得到所述各机器人执行所述任务的能力评估分数；将所述能力评估分数上传至所述服务器，接收由所述服务器根据所述能力评估分数生成的任务分配指令。实现了一种高时效性和准确性的集群机器人调度方案，使得任务调度更合理，节省了任务执行时间，提高了机器人的整体健康程度。
实施例五
本发明还提出了一种计算机可读存储介质，该计算机可读存储介质上存储有集群机器人调度程序，所述集群机器人调度程序被处理器执行时实现如上所述的集群机器人调度方法的步骤。
需要说明的是，上述装置、系统、设备及计算机可读存储介质与上述方法实施例属于相同的技术构思，上述方法实施例的技术特征在装置、系统、设备及计算机可读存储介质均能对应适用，这里不再重述。
在本文中，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者装置不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者装置所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括该要素的过程、方法、物品或者装置中还存在另外的相同要素。
上述本发明实施例序号仅仅为了描述，不代表实施例的优劣。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件，但很多情况下前者是更佳的实施方式。基于这样的理解，本发明的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质（如ROM/RAM、磁碟、光盘）中，包括若干指令用以使得一台终端（可以是手机，计算机，服务器，空调器，或者网络设备等）执行本发明各个实施例所述的方法。
上面结合附图对本发明的实施例进行了描述，但是本发明并不局限于上述的具体实施方式，上述的具体实施方式仅仅是示意性的，而不是限制性的，本领域的普通技术人员在本发明的启示下，在不脱离本发明宗旨和权利要求所保护的范围情况下，还可做出很多形式，这些均属于本发明的保护之内。
 工业实用性
本发明实施例通过接收并分解由服务器下发的任务，得到执行需求；然后，由各机器人获取其自身的静态属性和动态属性，并向自身的评估模型输入所述静态属性、所述动态属性、以及所述执行需求，得到所述各机器人执行所述任务的能力评估分数；将所述能力评估分数上传至所述服务器，接收由所述服务器根据所述能力评估分数生成的任务分配指令。实现了一种高时效性和准确性的集群机器人调度方案，使得任务调度更合理，节省了任务执行时间，提高了机器人的整体健康程度。因此，具有工业实用性。

Claims (11)

  1. 一种集群机器人调度方法，所述方法包括：
    接收并分解由服务器下发的任务，得到执行需求；
    各机器人获取其自身的静态属性和动态属性，并向自身的评估模型输入所述静态属性、所述动态属性、以及所述执行需求，得到所述各机器人执行所述任务的能力评估分数；
    将所述能力评估分数上传至所述服务器，接收由所述服务器根据所述能力评估分数生成的任务分配指令。
  2. 根据权利要求1所述的集群机器人调度方法，其中，所述方法之前还包括：
    获取所述集群机器人中各个机器人的静态属性；
    对任务集进行分解，得到每个任务的能力属性；
    对所述各个机器人的静态属性和所述每个任务的能力属性进行匹配，生成所述评估模型。
  3. 根据权利要求2所述的集群机器人调度方法，其中，所述获取所述集群机器人中各个机器人的静态属性，包括：
    获取所述机器人的硬件组件、传感器组件以及软件版本。
  4. 根据权利要求2所述的集群机器人调度方法，其中，所述对任务集进行分解，得到每个任务的能力属性，包括：
    分解所述任务集，得到任务类型、任务区域、硬件类型、传感器类型、以及软件版本类型。
  5. 根据权利要求2所述的集群机器人调度方法，其中，所述对所述各个机器人的静态属性和所述每个任务的能力属性进行匹配，生成所述评估模型，包括：
    逐一判断所述静态属性是否满足所述能力属性；
    根据所述判断结果得到评估值，并根据所述评估值在所述任务集的范围内生成所述评估模型。
  6. 根据权利要求1所述的集群机器人调度方法，其中，所述接收并分解由服务器下发的任务，得到执行需求，包括：
    分解所述任务，得到当前任务类型、当前任务区域、硬件需求、传感器需求以及软件版本需求。
  7. 根据权利要求1所述的集群机器人调度方法，其中，所述各机器人获取其自身的静态属性和动态属性，并向自身的评估模型输入所述静态属性、所述动态属性、以及所述执行需求，得到所述各机器人执行所述任务的能力评估分数，包括：
    所述各机器人获取其自身的动态属性，其中，所述动态属性包括当前位置、当前电量以及当前行驶里程；
    向自身的评估模型输入所述静态属性、所述动态属性、以及所述执行需求，得到所述各机器人执行所述任务的能力评估分数。
  8. 一种集群机器人调度装置，所述装置包括：
    任务分解单元，用于接收并分解由服务器下发的任务，得到执行需求；
    任务评分单元，用于获取各机器人自身的静态属性和动态属性，并向自身的评估模型输入所述静态属性、所述动态属性、以及所述执行需求，得到所述各机器人执行所述任务的能力评估分数；
    任务接收单元，用于将所述能力评估分数上传至所述服务器，接收由所述服务器根据所述能力评估分数生成的任务分配指令。
  9. 一种集群机器人调度系统，所述系统包括：
    机器人，用于接收并分解由服务器下发的任务，得到执行需求，以及，获取其自身的静态属性和动态属性，并向自身的评估模型输入所述静态属性、所述动态属性、以及所述执行需求，得到自身执行所述任务的能力评估分数；
    机器人中央控制服务器，用于接收由所述机器人上传的所述能力评估分数，根据所述能力评估分数生成并下发任务分配指令。
  10. 一种集群机器人调度设备，所述设备包括存储器、处理器及存储在所述存储器上并可在所述处理器上运行的计算机程序，所述计算机程序被所述处理器执行时实现：
    接收并分解由服务器下发的任务，得到执行需求；
    各机器人获取其自身的静态属性和动态属性，并向自身的评估模型输入所述静态属性、所述动态属性、以及所述执行需求，得到所述各机器人执行所述任务的能力评估分数；
    将所述能力评估分数上传至所述服务器，接收由所述服务器根据所述能力评估分数生成的任务分配指令。
  11. 一种计算机可读存储介质，所述计算机可读存储介质上存储有集群机器人调度程序，所述集群机器人调度程序被处理器执行时实现如权利要求1至7中任一项所述的集群机器人调度方法的步骤。
PCT/CN2020/132025 2019-11-29 2020-11-27 集群机器人调度方法、装置、系统、设备及计算机可读存储介质 WO2021104412A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201911202154.8A CN111079990B (zh) 2019-11-29 2019-11-29 集群机器人调度方法、装置、系统、设备及计算机可读存储介质
CN201911202154.8 2019-11-29

Publications (1)

Publication Number Publication Date
WO2021104412A1 true WO2021104412A1 (zh) 2021-06-03

Family

ID=70312121

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/132025 WO2021104412A1 (zh) 2019-11-29 2020-11-27 集群机器人调度方法、装置、系统、设备及计算机可读存储介质

Country Status (2)

Country Link
CN (1) CN111079990B (zh)
WO (1) WO2021104412A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116862208A (zh) * 2023-09-05 2023-10-10 中煤科工机器人科技有限公司 一种煤矿机器人集群管理系统

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111079990B (zh) * 2019-11-29 2022-11-25 炬星科技（深圳）有限公司 集群机器人调度方法、装置、系统、设备及计算机可读存储介质
WO2022032443A1 (zh) * 2020-08-10 2022-02-17 深圳技术大学 多智能主体编队搬运方法、系统和计算机可读存储介质
CN112077849A (zh) * 2020-09-11 2020-12-15 济南浪潮高新科技投资发展有限公司 基于云端管控的医疗配送机器人
CN112633741A (zh) * 2020-12-30 2021-04-09 北京云迹科技有限公司 一种任务分配的方法、设备和计算机可读存储介质
CN115344009A (zh) * 2021-05-13 2022-11-15 灵动科技（北京）有限公司 用于机器人的调度系统和方法、机器人以及定制方法
CN113771033A (zh) * 2021-09-13 2021-12-10 中冶赛迪技术研究中心有限公司 多机器人站点集成控制系统、方法、设备和介质

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070011035A1 (en) * 2003-08-25 2007-01-11 Ofir Yaffe System and method for optimizing transportations assignments and mainetenance activities
CN107831685A (zh) * 2017-10-13 2018-03-23 南方科技大学 一种群体机器人的控制方法和系统
CN108490975A (zh) * 2018-04-28 2018-09-04 广州亿航智能技术有限公司 一种无人机集群的调度方法及计算机存储介质
CN110264062A (zh) * 2019-08-12 2019-09-20 南京邮电大学 分布式多agv动态任务分配及其路径规划方法与系统
CN110405756A (zh) * 2019-06-28 2019-11-05 炬星科技（深圳）有限公司 一种任务调度方法、装置、系统、电子设备及存储介质
US20190351542A1 (en) * 2018-05-15 2019-11-21 Robert Bosch Gmbh Method for operating a robot in a multi-agent system, robot and multi-agent system
CN111079990A (zh) * 2019-11-29 2020-04-28 炬星科技（深圳）有限公司 集群机器人调度方法、装置、系统、设备及计算机可读存储介质

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
AU2014277738B2 (en) * 2013-12-19 2020-04-30 The Raymond Corporation Integrated touch screen display with multi-mode functionality
CN107679239B (zh) * 2017-10-27 2020-12-29 天津理工大学 一种基于用户行为的个性化社区推荐方法

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070011035A1 (en) * 2003-08-25 2007-01-11 Ofir Yaffe System and method for optimizing transportations assignments and mainetenance activities
CN107831685A (zh) * 2017-10-13 2018-03-23 南方科技大学 一种群体机器人的控制方法和系统
CN108490975A (zh) * 2018-04-28 2018-09-04 广州亿航智能技术有限公司 一种无人机集群的调度方法及计算机存储介质
US20190351542A1 (en) * 2018-05-15 2019-11-21 Robert Bosch Gmbh Method for operating a robot in a multi-agent system, robot and multi-agent system
CN110405756A (zh) * 2019-06-28 2019-11-05 炬星科技（深圳）有限公司 一种任务调度方法、装置、系统、电子设备及存储介质
CN110264062A (zh) * 2019-08-12 2019-09-20 南京邮电大学 分布式多agv动态任务分配及其路径规划方法与系统
CN111079990A (zh) * 2019-11-29 2020-04-28 炬星科技（深圳）有限公司 集群机器人调度方法、装置、系统、设备及计算机可读存储介质

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116862208A (zh) * 2023-09-05 2023-10-10 中煤科工机器人科技有限公司 一种煤矿机器人集群管理系统

Also Published As

Publication number Publication date
CN111079990A (zh) 2020-04-28
CN111079990B (zh) 2022-11-25

Similar Documents

Publication Publication Date Title
WO2021104412A1 (zh) 集群机器人调度方法、装置、系统、设备及计算机可读存储介质
WO2023151523A1 (zh) 基于数字孪生DaaS平台的深度学习编程方法及系统
CN109885452A (zh) 性能监控方法、装置及终端设备
CN106131158A (zh) 一种云数据中心环境下基于云租户信用度的资源调度装置
CN110569312B (zh) 一种基于gpu的大数据快速检索系统及其使用方法
CN113791906A (zh) 基于gpu资源在人工智能与工程领域调度系统及优化算法
CN110281243B (zh) 一种采摘机器人作业序列规划方法
CN109709985A (zh) 一种无人机任务优化方法、装置及系统
CN112068455A (zh) 任务仿真方法、系统、装置、电子设备及可读存储介质
CN105150209A (zh) 搬运桁架机械手精确控制系统及方法
CN112884164B (zh) 面向智能移动终端实现的联邦机器学习迁移方法与系统
CN112633850A (zh) 通过管理调用及监控rpa机器人实现业务流程自动化的方法
CN106599116B (zh) 云平台数据集成管理系统和方法
CN106078747A (zh) 一种基于虚拟现实的延时工业操作控制系统
CN116126501A (zh) 任务分配方法、装置、智能设备和存储介质
CN113282123B (zh) 一种智能化建筑室内环境监控系统
CN114819339A (zh) 一种基于仿真粒子群算法的agv配置优化方法
CN110784545B (zh) 实时数据分发系统
CN107886274A (zh) 一种多工种间物料流转管理方法及管理系统
CN114217540A (zh) 一种非标设备的控制方法、装置、设备及存储介质
CN109547557A (zh) 工业互联网智能决策方法、可读存储介质和终端
TWI663557B (zh) 製造排程變異最小化系統
CN117497469B (zh) 多尺寸的晶圆传输装置、方法及电子设备
CN112000786A (zh) 结合rpa和ai的对话机器人问题处理方法、装置和设备
CN110737775A (zh) 一种基于知识图谱和目标本体的综合评测系统

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20891998

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20891998

Country of ref document: EP

Kind code of ref document: A1