CN114193447A - Multi-robot control method, electronic device, and storage medium - Google Patents
Multi-robot control method, electronic device, and storage medium Download PDFInfo
- Publication number
- CN114193447A CN114193447A CN202111392307.7A CN202111392307A CN114193447A CN 114193447 A CN114193447 A CN 114193447A CN 202111392307 A CN202111392307 A CN 202111392307A CN 114193447 A CN114193447 A CN 114193447A
- Authority
- CN
- China
- Prior art keywords
- robot
- data
- subtask
- action path
- task
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1679—Programme controls characterised by the tasks executed
- B25J9/1682—Dual arm manipulator; Coordination of several manipulators
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1602—Programme controls characterised by the control system, structure, architecture
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1656—Programme controls characterised by programming, planning systems for manipulators
- B25J9/1664—Programme controls characterised by programming, planning systems for manipulators characterised by motion, path, trajectory planning
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Automation & Control Theory (AREA)
- Manipulator (AREA)
Abstract
The embodiment of the invention relates to the field of robots, and discloses a multi-robot control method, electronic equipment and a storage medium. The method comprises the steps of splitting a work task to be executed into a plurality of subtasks, and generating task allocation data of each subtask based on attribute information of available robots, wherein the task allocation data comprises the following steps: subtask content and a first robot that performs the subtask; generating action path planning data of each first robot based on the task allocation data and the environment three-dimensional semantic map; performing simulation evaluation on the action path planning data of each first robot; when the simulation result meets the preset requirement, sending the action path execution data generated according to the action path planning data to a corresponding first robot so as to control the first robot to execute a corresponding subtask; and monitoring state data in the sub-task executing process of the first robot, and maintaining or adjusting the action path execution data of the first robot according to the state data, so that the multi-robot cooperatively completes complex work tasks.
Description
Technical Field
The embodiment of the invention relates to the technical field of robots, in particular to a multi-robot control method, electronic equipment and a storage medium.
Background
With the continuous development and progress of the robot technology, a single mobile robot is difficult to complete complex and tedious work tasks and work indexes of production practice. Compared with a single robot, the system formed by the cooperation of a plurality of robots has certain advantages, such as: the method has the advantages of strong adaptability to the environment, strong task bearing capacity, high robustness and the like.
However, since there are many control targets involved in the cooperation of a plurality of robots, and problems such as task assignment to robots, task cooperation, and conflict resolution need to be dealt with properly, the complexity of the control logic required is higher. Therefore, how to control a plurality of robots to efficiently and accurately cooperate to complete a work task becomes a hot spot concerned by the industry.
Disclosure of Invention
An object of embodiments of the present invention is to provide a multi-robot control method, an electronic device, and a storage medium, which can control a plurality of robots to efficiently and accurately cooperate to complete a work task.
In order to solve the above technical problem, an embodiment of the present invention provides a multi-robot control method, including:
splitting a work task to be executed into a plurality of subtasks, and generating task allocation data of each subtask based on attribute information of an available robot, wherein the task allocation data comprises: subtask content and a first robot that performs the subtask;
generating action path planning data of each first robot based on the task allocation data and a pre-acquired environment three-dimensional semantic map of a scene where the work task is located;
performing simulation evaluation on the action path planning data of each first robot in the environmental three-dimensional semantic map;
when the simulation result meets a preset requirement, sending action path execution data generated according to the action path planning data to a corresponding first robot so as to control the first robot to execute a corresponding subtask;
and monitoring state data of the first robot in the sub-task executing process, and maintaining or adjusting the action path executing data of the first robot according to the state data.
An embodiment of the present invention also provides an electronic device, including:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the multi-robot control method as described above.
Embodiments of the present invention also provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the multi-robot control method as described above.
Compared with the prior art, the embodiment of the invention divides the work task to be executed into a plurality of subtasks, and generates the task allocation data of each subtask based on the attribute information of the available robot, and the method comprises the following steps: subtask content and a first robot that performs the subtask; generating action path planning data of each first robot based on task allocation data and a pre-acquired environment three-dimensional semantic map of a scene where a work task is located; performing simulation evaluation on the action path planning data of each first robot in an environmental three-dimensional semantic map; when the simulation result meets the preset requirement, sending the action path execution data generated according to the action path planning data to a corresponding first robot so as to control the first robot to execute a corresponding subtask; and monitoring state data in the sub-task executing process of the first robot, and maintaining or adjusting the action path execution data of the first robot according to the state data, so that the multi-robot cooperatively completes complex work tasks. The scheme has the following advantages:
(1) the work task is divided into a plurality of subtasks and distributed to a plurality of robots by adopting a centralized control mode, so that the cooperative distribution of the subtasks among the plurality of robots can be realized, and the problem of task conflict is solved more easily;
(2) before the robots actually execute tasks, simulation evaluation (trial and error) is carried out on the action path planning data of each robot, so that the global optimal solution during subtask distribution is easier to realize; based on lower cost and faster trial-and-error verification, a subtask allocation scheme which can achieve the target work task can be directly verified and output through an allocation strategy without the need of online verification of an entity robot;
(3) the state data of the robot in the actual subtask executing process is monitored, and the action path executing data of the robot is maintained or adjusted, so that an end-to-end complete mechanism for optimizing the target subtask allocation in a continuous closed-loop manner is realized, and the multi-robot cooperation for completing the complex task has strong fault-tolerant capability and robustness.
Drawings
One or more embodiments are illustrated by way of example in the accompanying drawings, which correspond to the figures in which like reference numerals refer to similar elements and which are not to scale unless otherwise specified.
Fig. 1 is a detailed flowchart of a multi-robot control method according to a first embodiment of the present invention;
fig. 2 is a detailed flowchart of a multi-robot control method according to a second embodiment of the present invention;
fig. 3 is a detailed flowchart of a multi-robot control method according to a third embodiment of the present invention;
fig. 4 is a detailed flowchart of a multi-robot control method according to a fourth embodiment of the present invention;
fig. 5 is a flowchart showing a multi-robot control method according to a fifth embodiment of the present invention;
fig. 6 is a detailed flowchart ii of a multi-robot control method according to a fifth embodiment of the present invention;
fig. 7 is a schematic structural diagram of an electronic device according to a sixth embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, embodiments of the present invention will be described in detail below with reference to the accompanying drawings. However, it will be appreciated by those of ordinary skill in the art that numerous technical details are set forth in order to provide a better understanding of the present application in various embodiments of the present invention. However, the technical solution claimed in the present application can be implemented without these technical details and various changes and modifications based on the following embodiments.
The first embodiment of the invention relates to a multi-robot control method, which is suitable for an application scene that a plurality of isomorphic robots or heterogeneous robots cooperate together to complete a complex task. The execution subject of the method can be a server which is communicated with the robot and is located at the cloud end to cooperatively control the robot.
In this embodiment, each robot includes at least a robot body (mainly including one or more robot joints), a robot control unit (for running an end-side operation engine and a digital twin copy of the robot) located on the robot body, various sensors (including but not limited to one or more three-dimensional stereo cameras, lidar, ultrasonic radar, millimeter radar, 2D camera) located on the robot body, and a perception preprocessing module (for perception processing of external events). In this embodiment, the server located in the cloud includes virtual digital twins (physical simulation models, such as digital twins a, digital twins B, digital twins C, … …, digital twins N), a digital twins world (generated based on an environmental three-dimensional semantic map), and a cloud control unit of each robot. The cloud control unit is used for splitting a work task to be executed by multiple robots into multiple subtasks on line and distributing the subtasks to the robots, achieving constraint check on the subtasks of the robots, comprehensively arbitrating path planning and conflict when the subtasks are executed by the robots, simulating and simulating path planning data, and operating an operation engine (used for loading an environment three-dimensional semantic map and operating a digital twin body) of the cloud.
As shown in fig. 1, the multi-robot control method includes the following steps.
Step 101: splitting a work task to be executed into a plurality of subtasks, and generating task allocation data of each subtask based on attribute information of the available robot, wherein the task allocation data comprises: subtask content and a first robot that performs the subtask.
Specifically, the server receives an externally given work task and splits the work task into a plurality of subtasks executable by the current robot according to the content of the work task. For example, in an indoor cleaning service scenario, a given work task may be indoor cleaning of a specified environment. Based on the indoor cleaning task, the server can split the cleaning task into a plurality of sub-tasks which can be executed by the current robot according to the contained specific task content based on the specific content of the cleaning task, such as cleaning the floor, glass, tables and chairs and the like. The server plans each subtask to distribute each available robot according to attribute information of the current available robot (idle robot), such as information of functions (sweeping floor, wiping glass, wiping table and chair, and the like), efficiency (speed and effect of executing the task) and power consumption (power consumption of executing the task) of the robot, so as to generate task distribution data of each subtask, wherein the task distribution data comprises: subtask content and the first robot to perform the subtask (the robot to which the subtask is assigned). For example, the format of the task allocation data may be: floor cleaning subtask-robot a, table cleaning subtask-robot B, glass cleaning subtask-robot C, … ….
Step 102: and generating action path planning data of each first robot based on the task allocation data and the pre-acquired environment three-dimensional semantic map of the scene where the work task is located.
The pre-acquired environment three-dimensional semantic map of the scene where the work task is located may be an environment semantic scene which is described through natural language and contains the scene where the target work task is located.
In one example, the process of obtaining the three-dimensional semantic map of the environment of the scene where the work task is located may include: the method comprises the following steps of scanning the environment of a scene where a work task is located in advance through any available robot to form an environment three-dimensional semantic map, wherein the environment three-dimensional semantic map comprises the following steps: semantic objects, spatial attributes and texture attributes of semantic objects.
For example, in the process of constructing the three-dimensional semantic map of the environment of the scene where the indoor cleaning task is located, one of the available robots may be selected to scan the three-dimensional environment of the scene where the indoor cleaning task is located, construct the three-dimensional semantic map, or scan the three-dimensional environment by using other scanning tools to construct the map. The constructed three-dimensional semantic map can be used for sharing a physical environment by a plurality of robots which cooperatively complete work tasks, the positioning and navigation functions of the robots are realized, and the scanning and map building precision is guaranteed to be not lower than the acquisition precision of a sensor of any robot in principle. Meanwhile, the environment three-dimensional semantic map obtained by scanning can be automatically or manually made into an environment three-dimensional semantic map capable of running in an operation engine at the cloud end or a format of a digital twin world, and task process simulation is achieved.
The constructed three-dimensional semantic map of the environment comprises the following steps: semantic objects, spatial attributes and texture attributes of semantic objects. Where a semantic object refers to a target object or object described by natural language, such as: conference rooms, floors, walls, doors, windows, tables, lights, etc.; the spatial attributes of the semantic objects refer to spatial positions and shapes of the semantic objects in a three-dimensional space and spatial affiliations among the semantic objects (the affiliations can be embodied by constructing a "knowledge graph" of the relationship among the semantic objects), and the texture attributes of the semantic objects include, but are not limited to, the attributes of the semantic objects such as size, weight, category, material, and color.
After the task allocation data and the environment three-dimensional semantic map of the scene where the work task is located are obtained, the execution process of each subtask, particularly the action path of each first robot in the environment three-dimensional semantic map, can be planned based on the task allocation data and the environment three-dimensional semantic map, so that action path planning data of each first robot is generated.
The three-dimensional environment semantics corresponding to the work area related to the subtask allocated to the first robot are the basis of path planning, and the allocation strategy of the subtask directly influences the result of the path planning. The path planning means that global path planning of the robot is achieved on the basis of global environment information, namely, under the condition that the environment information is in a known state and meets various evaluation standards such as certain time, distance or energy and the like, a collision-free optimal or suboptimal path from the current position to the final position of each first robot is found out for each first robot. On the basis of global path planning, the types of possible conflicts among the robots are predicted in the optimal or suboptimal paths selected from different starting positions to target positions of the robots, obstacle conflicts, deadlock elimination and the like are achieved, and therefore action path planning data of the first robots are formed finally.
Specifically, the server may read or load a digital twin model and related data of the first robot in the server, including but not limited to a role, a function, a current location, a current state, an executable action, a behavior blueprint, a task sequence (a task call stack, i.e., supporting multi-layer nesting between tasks), and the like; and then generating action path planning data in the environment three-dimensional semantic map when each first robot executes the corresponding subtask according to the loaded data and the environment three-dimensional semantic map of the scene where each subtask is contained in the work task. The action path refers to a moving path of the first robot at a spatial position in the three-dimensional semantic map of the environment and an operation path corresponding to the operation of the limbs of the first robot when the subtasks are executed.
Step 103: and performing simulation evaluation on the action path planning data of each first robot in the environmental three-dimensional semantic map.
Specifically, based on a pre-constructed environment three-dimensional semantic map and action path planning data corresponding to the first robot when executing the assigned subtasks, the action path planning data can be simulated and evaluated in the environment three-dimensional semantic map, and the execution condition of the cooperative execution of the work tasks by each first robot is simulated, so as to judge whether the generated action path planning data is reasonable.
In this embodiment, the simulation method and the related simulation software used in the simulation evaluation process are not limited.
Step 104: and when the simulation result meets the preset requirement, sending the action path execution data generated according to the action path planning data to the corresponding first robot so as to control the first robot to execute the corresponding subtasks.
And when the action path planning data generated by each first robot is subjected to simulation evaluation aiming at the work task and the simulation result meets the preset requirement, representing that the generated action path planning data is feasible. At this time, corresponding action path execution data can be generated according to the action path planning data and sent to corresponding first robots, so that each first robot executes the data according to the action path to cooperatively complete a given work task.
Specifically, the server may first distribute the subtask sequence, the relevant planned path, and the relevant data generated according to the action path planning data to the corresponding digital twin of the first robot; and each digital twin of the acquired subtasks forms blueprints and action data, and under the condition that the server and the entity robots keep a unified clock, the data such as the blueprints and the actions are synchronized to the digital twin copies in the control units of the entity robots. The robot control unit automatically and synchronously controls the blueprints, the action data and other related instructions and data to the physical entity robot (robot body) or intelligent equipment on the physical entity robot, and the physical entity robot or the intelligent equipment synchronously executes subtasks according to the assigned subtask sequence (time sequence).
Step 105: and monitoring state data in the subtask execution process of the first robot, and maintaining or adjusting the action path execution data of the first robot according to the state data.
Specifically, in the sub-task execution process, the physical entity robot or the intelligent device synchronously feeds back environment change, current interaction with a human and internal and external events which can affect the current robot state change to the cloud server as state data in the sub-task execution process of the first robot based on environment change information acquired by various physical sensors arranged on the physical entity robot or the intelligent device through the perception preprocessing module, so that the server can maintain or adjust the action path execution data of the first robot according to the state data.
Compared with the prior art, the embodiment divides the work task to be executed into a plurality of subtasks, and generates the task allocation data of each subtask based on the attribute information of the available robot, including: subtask content and a first robot that performs the subtask; generating action path planning data of each first robot based on task allocation data and a pre-acquired environment three-dimensional semantic map of a scene where a work task is located; performing simulation evaluation on the action path planning data of each first robot in an environmental three-dimensional semantic map; when the simulation result meets the preset requirement, sending the action path execution data generated according to the action path planning data to a corresponding first robot so as to control the first robot to execute a corresponding subtask; and monitoring state data in the sub-task executing process of the first robot, and maintaining or adjusting the action path execution data of the first robot according to the state data, so that the multi-robot cooperatively completes complex work tasks. The scheme has the following advantages:
(1) the work task is divided into a plurality of subtasks and distributed to a plurality of robots by adopting a centralized control mode, so that the cooperative distribution of the subtasks among the plurality of robots can be realized, and the problem of task conflict is solved more easily;
(2) before the robots actually execute tasks, simulation evaluation (trial and error) is carried out on the action path planning data of each robot, so that the global optimal solution during subtask distribution is easier to realize; based on lower cost and faster trial-and-error verification, a subtask allocation scheme which can achieve a target task can be directly verified and output through an allocation strategy without the need that an entity robot needs to be verified on line;
(3) the state data of the robot in the actual subtask executing process is monitored, and the action path executing data of the robot is maintained or adjusted, so that an end-to-end complete mechanism for optimizing the target subtask allocation in a continuous closed-loop manner is realized, and the multi-robot cooperation for completing the complex task has strong fault-tolerant capability and robustness.
A second embodiment of the present invention relates to a multi-robot control method, and is an improvement of the first embodiment, the improvement being: and detailing the process of generating the task allocation data of each subtask. As shown in fig. 2, the above step 101 may include the following sub-steps.
Substep 1011: splitting a work task to be executed into a plurality of subtasks, and generating a combination scheme of a plurality of task allocation data based on the functional information of the available robots, wherein the task allocation data comprises: subtask content and a first robot that performs the subtask.
Specifically, in practical applications, each robot may have multiple functions at the same time, or multiple robots may have common functions, and thus there may be multiple allocation schemes in forming task allocation data for respective subtasks. In this embodiment, a combination scheme of various task allocation data may be generated according to the subtasks split by the current work task and the attribute information of each available robot, mainly the function information in the attribute information. The task allocation data included in each combination scheme can realize the target work task integrally.
Substep 1012: and selecting the combination scheme with the highest comprehensive efficiency and the lowest power consumption of the first robot from the combination schemes as task allocation data of each subtask.
Specifically, in each combination scheme, the first robots and/or the subtasks executed by the first robots are not completely the same, and the corresponding execution efficiency and power consumption of the first robots are not completely the same when the first robots complete the assigned subtasks. Therefore, one combination plan can be selected from the combination plans obtained as described above, and the first robot has the highest overall efficiency and the lowest power consumption among the task assignment data included in the combination plan. And then taking the task allocation data contained in the selected combination scheme as the task allocation data of each subtask.
In addition, after a group of better combination schemes is selected, more optimal adjustment of the subtasks executed by the first robot in the combination schemes can be continued. Accordingly, after sub-step 1012, the following steps may also be continued for optimization adjustment within the combinatorial scheme.
Step one, aiming at the selected combined scheme, historical subtask execution data of the first robot in the combined scheme is obtained.
Specifically, the server may retrieve, from the history records, historical subtask execution data of the first robots in the selected combination scenarios. The historical subtask execution data may include: the history of subtask content, execution time, the first robot executed, and execution results describe data. Through the historical subtask execution data of the first robot, the historical subtask execution situation of each first robot can be known, and particularly, the content of the subtask which is good for the first robot to execute and execute more can be known.
And secondly, maintaining the subtasks to be executed currently of the first robot or adjusting the subtasks to be executed currently of the first robot in a combination scheme of the subtasks to be executed currently of the first robot based on the historical subtask execution data of the first robot and the subtasks to be executed currently of the first robot, so as to finally form task distribution data of each subtask.
For example, whether the subtask currently allocated to the first robot is suitable is judged through the historical subtask execution data of the first robot and the subtask to be executed currently; if the task assignment data is suitable, the corresponding subtasks of the first robot are maintained, and if the task assignment data is not suitable, the subtasks assigned by the first robot can be adjusted in the combination scheme, for example, the subtasks suitable for the first robot are replaced with other first robots in the combination scheme, so that the task assignment is further optimized, and the final task assignment data of each subtask is formed.
The method for judging whether the currently allocated subtask of the first robot is suitable may be to judge whether the historical subtask of the first robot is consistent with the currently executed subtask, or whether the historical subtask of the first robot is close to the currently executed subtask of the first robot with a high probability. For example, in the history subtasks, most of the subtasks are the floor cleaning tasks, and the currently assigned subtasks are also the floor cleaning tasks, it is determined that the subtask currently assigned by the first robot is suitable, otherwise, it is determined that it is not suitable.
In addition, in order to conveniently manage and control data related to the available robots in the server, management and control operations related to the entity robots can be realized by setting digital twins corresponding to the entity robots.
In one example, digital twins which correspond to the available robots one by one and contain attribute information of the available robots can be arranged in the server; accordingly, generating task allocation data for each subtask based on the attribute information of the available robots may include: task allocation data for each subtask is generated based on the digital twin configured by the service trainer for that subtask.
Specifically, the service trainer performs manual operation control on physical model parameters, roles, functions, executable actions, behavior blueprints, task sequences and the like corresponding to any one or more digital twins (each digital twins corresponds to one entity robot) through a robot service client, and the manual operation control includes: and changing the attribute value, the configuration parameter or the task allocation strategy corresponding to the designated digital twin body. Wherein, the service trainer configures corresponding digital twin bodies for each subtask in advance to designate a certain subtask to be executed by the designated available robot. The service trainer may specify respective digital twins for one or more, or even all, of the subtasks in advance to generate task allocation data for the subtasks. For subtasks where the service trainer does not configure the corresponding digital twin, corresponding task allocation data may still be generated by the server according to the allocation method described above. In this embodiment, the priority of the manual task allocation is higher than that of the server itself for allocating tasks according to the designated logic.
On this basis, the method of the embodiment further includes: configuring attribute information of the available robots based on parameter settings of the digital twins by the service trainer.
Specifically, the service trainer can configure various parameters of the corresponding digital twin in the server in time according to the change of the attribute information of the real robot, so that the two parameters are the same. And the server further controls the attribute information of the available robots used in the work task distribution based on the parameter setting of the digital twin body, so that the unification of the two is ensured.
Compared with the related art, the present embodiment generates a combination scheme of a plurality of kinds of task allocation data by based on the function information of the available robots; and selecting the combination scheme with the highest comprehensive efficiency and the lowest power consumption of the first robot from the combination schemes as task allocation data of each subtask, thereby realizing reasonable allocation of the subtasks. And simultaneously, digital twins which correspond to the entity robots one to one are introduced into the server, so that the relevant data of the entity robots are configured and controlled.
A third embodiment of the present invention is an improvement of the first embodiment, in which: the process of generating the movement path planning data for each first robot is refined. As shown in fig. 3, the step 102 may include the following sub-steps.
Substep 1021: and generating the movement path planning subdata of the first robot according to the current position of the first robot and the three-dimensional environment semantics corresponding to the work area involved by the subtask.
Specifically, the server may plan and judge a movement path in the space when each first robot executes a subtask according to a three-dimensional environment semantic corresponding to a work area related to the subtask and a position of the first robot in the environment three-dimensional semantic map based on the subtask allocated to each first robot (or the digital twin corresponding to the first robot), and finally generate movement path planning sub data of the first robot.
In one example, the process of generating the movement path plan sub-data of the first robot may be implemented by the following steps.
Step one, generating a plurality of groups of mobile path planning subdata corresponding to the first robot according to the current position of the first robot and the three-dimensional environment semantics corresponding to the work area related to the subtask.
Specifically, according to the current position of each first robot in the three-dimensional semantic map of the environment and the three-dimensional environment semantics corresponding to the work area involved in the subtask, multiple routes from the current position to the work area can be planned for each first robot, then multiple sets of movement path planning subdata corresponding to the work task are formed based on the routes planned by all the first robots, and each set of movement path planning subdata corresponds to a planning route combination scheme corresponding to when all the first robots cooperatively execute the work task.
And step two, selecting a group of data with the shortest moving path from the plurality of groups of moving path planning sub-data as the moving path planning sub-data of the first robot.
Specifically, in the planned route combination schemes, the lengths of the entire movement paths corresponding to each scheme are different, and a group of data with the shortest movement path can be selected from the schemes to serve as the movement path planning sub-data of the first robot, so that the shortest overall movement time of the first robot and the lowest power consumption caused by movement are ensured.
Substep 1022: and generating operation path planning subdata of each first robot according to the action three-dimensional environment semantics of the first robot for executing the subtasks in the working area.
Specifically, after determining the movement path planning sub-data of the first robot, a path of the limb operation behavior of each first robot, that is, the operation path planning sub-data, may be planned according to a movement position of the first robot in a work area during a specific subtask executed by the first robot and a three-dimensional environment semantic, that is, an action three-dimensional environment semantic, corresponding to a task action (task action sequence) to be executed by specific content of the subtask.
Compared with the related art, the mobile path planning subdata of the first robot is generated according to the current position of the first robot and the three-dimensional environment semantics corresponding to the work area related to the subtask; and generating operation path planning subdata of each first robot according to the action three-dimensional environment semantics of the first robot for executing the subtasks in the working area, thereby providing a specific implementation mode for generating action path planning data and conveniently and accurately obtaining a reasonable action path when each first robot cooperatively executes the subtasks.
A fourth embodiment of the present invention is an improvement of the first embodiment, in which: and refining the process of performing simulation evaluation on the action path planning data of each first robot in the environmental three-dimensional semantic map. As shown in fig. 4, the above step 103 may include the following sub-steps.
Substep 1031: and performing process simulation on the action path planning data of each first robot in the environmental three-dimensional semantic map to obtain action path simulation data.
Specifically, the action path planning data of each first robot may be subjected to process simulation in the environmental three-dimensional semantic map, and simulation result paths obtained in the process simulation may be sorted to obtain action path simulation data of each first robot. The action path simulation data may substantially mimic an action path of the first robot in a real environment.
In one example, obtaining the action path simulation data for each first robot may include: simulating the action path of each first robot in the environmental three-dimensional semantic map through pre-constructed physical simulation software; and generating action path simulation data according to the simulation result.
Specifically, the server can load an environmental three-dimensional semantic map to form a digital twin world through an operation engine inside the server; and then simulating the digital twin body corresponding to each first robot at the server end and the corresponding action path planning data in the digital twin world, so as to perform trial and error evaluation on the action path planning data according to the simulation result and judge the feasibility of the action path planning data. A plurality of feasibility requirements can be preset according to the simulation result, and when the simulation result meets the preset requirements, the planned action path planning data can be considered to be feasible.
Substep 1032: judging whether the action path simulation data meet preset requirements or not, wherein the preset requirements comprise: the action paths corresponding to any two first robots are not in conflict, each subtask can reach, and the execution time of a single subtask and the total execution time of the work tasks do not exceed the corresponding time threshold.
Specifically, a plurality of feasibility judgment requirements may be preset for the action path simulation data, where the requirements include, but are not limited to, that there is no conflict between action paths corresponding to any two first robots, each subtask is reachable, and the execution time of a single subtask and the total execution time of a work task do not exceed corresponding time thresholds. The action paths corresponding to any two first robots have conflict fingers, and the action paths corresponding to the two first robots do not have conflict simultaneously in time and space ranges. If two action paths have an intersection in the space range, but the action time corresponding to the intersection position of the action paths is different, the two action paths are considered to have no conflict. When the preset requirements are all satisfied, the action path planning data generated for each first robot before can be considered to be feasible.
Of course, after the action path planning data of each first robot is subjected to simulation evaluation in the environment three-dimensional semantic map, the generated simulation result may not meet the preset requirement, and for such a case, the simulation result may meet the preset requirement through the following steps. Namely:
and when the simulation result does not meet the preset requirement, adjusting the task allocation data or the action path execution data of the first robot until the simulation result meets the preset requirement.
In one example, adjusting the task allocation data or the action path planning data of the first robot comprises:
the method comprises the following steps: and when the action path simulation data represent that the subtasks are unreachable, regenerating task allocation data of the unreachable subtasks based on the attribute information of the remaining available robots.
Specifically, when a subtask is not reachable, the first robot assigned with the corresponding subtask may have an unsuitable parameter, a fault or other problems, and at this time, the subtask should be assigned to other available robots in time to ensure that the subtask is reachable. Namely: and regenerating the task allocation data of the unreachable subtask based on the attribute information of the remaining available robots, so that the allocation condition of the work task is quickly readjusted under the condition of not influencing the task allocation data of other reachable subtasks.
Step two: and when the action path simulation data represent that the subtasks are all reachable and the action paths corresponding to at least two first robots have conflicts, and/or the execution time of at least one subtask exceeds a corresponding time threshold, and/or the total execution time of the work tasks exceeds a corresponding time threshold, adjusting the action path planning data of each first robot.
Specifically, when each subtask can be reached, the first robot assigned with the corresponding subtask is characterized to have no problem and can normally execute the subtask; and when the conditions that the action paths corresponding to at least two first robots conflict and/or the execution time of at least one subtask exceeds a corresponding time threshold and/or the total execution time of the work task exceeds a corresponding time threshold simultaneously occur, the action path planning data allocated to each first robot is represented unreasonably, and at this time, the action path planning data of each first robot, such as a moving path and an action path in the action path, can be adjusted only to flexibly change the action path planning data, so that the simulation result corresponding to the action path planning data of each first robot meets the preset requirement. In order to reduce workload, only the action path planning data of the first robot which does not meet the preset requirements can be adjusted, so that the action path planning data of each first robot can be quickly readjusted without influencing the action path planning data of other first robots which meet the preset requirements.
Compared with the related art, the action path simulation data is obtained by performing process simulation on the action path planning data of each first robot in the environment three-dimensional semantic map; judging whether the action path simulation data meet preset requirements or not, wherein the preset requirements comprise: the action paths corresponding to any two first robots are not in conflict, each subtask can reach, and the execution time of a single subtask and the total execution time of the working tasks do not exceed the corresponding time threshold, so that the simulation process of the action path planning data is realized, and the feasibility of the action path planning data is ensured.
A fifth embodiment of the present invention is a modification of the first embodiment, and is characterized in that: and refining the process of monitoring the state data of the first robot in the process of executing the subtasks and maintaining or adjusting the action path execution data of the first robot according to the state data.
In one example, the status data may include: actual movement path data of the first robot.
Accordingly, as shown in fig. 5, the above step 105 may include the following sub-steps.
Substep 1051: and when the actual action path data indicates that the first robot has a fault or the difference between the actual action path data and the corresponding action path simulation data exceeds the limit value, taking the remaining unfinished work tasks as the work tasks to be executed, regenerating action path execution data corresponding to the work tasks to be executed, and sending the action path execution data to the updated first robot so as to control the updated first robot to execute the corresponding subtasks.
Specifically, when the actual action path data indicates that the first robot has a fault, or the difference between the actual action path data and the corresponding action path simulation data exceeds a limit value, the actual action path data indicates that the execution process of each current subtask cannot be performed according to feasible action path simulation data obtained through previous simulation evaluation. At this time, the remaining unfinished work tasks need to be redistributed to generate subtasks and to perform path planning on each subtask. Namely: and taking the remaining unfinished work tasks as the work tasks to be executed again, sequentially generating task distribution data, generating action path planning data of each first robot and performing simulation evaluation on the action path planning data of each first robot according to the method steps in the embodiment, and finally generating action path execution data. The action path execution data is the action path execution data corresponding to the regenerated work task to be executed. And sending the action path execution data to the updated first robot (the first robot adopted in task redistribution) so as to control the updated first robot to execute the corresponding subtask.
In another example, the status data may include: the first robot receives an external event.
Accordingly, as shown in fig. 6, the above step 105 may include the following sub-steps.
Substep 1052: when the first robot receives the external event, the rest work tasks and the work tasks corresponding to the external event are jointly used as the work tasks to be executed, the action path execution data corresponding to the work tasks to be executed are regenerated and issued to the updated first robot, and the updated first robot is controlled to execute the corresponding subtasks.
Specifically, when the first robot receives an external event (such as interaction with a human, avoidance) during normal execution of the subtasks, it is characterized that a new task may be generated. At this time, the remaining unfinished work tasks and the work tasks corresponding to the external events are required to be jointly used as the work tasks to be executed, and the work tasks are redistributed to generate the subtasks and perform path planning on the subtasks. Namely: and taking the remaining unfinished work tasks and the work tasks corresponding to the external events as the work tasks to be executed, sequentially generating task distribution data, action path planning data of each first robot and simulation evaluation on the action path planning data of each first robot according to the method steps in the embodiment, and finally generating action path execution data. The action path execution data is the action path execution data corresponding to the regenerated work task to be executed. And sending the action path execution data to the updated first robot (the first robot adopted in task redistribution) so as to control the updated first robot to execute the corresponding subtask.
Therefore, by monitoring the state data of the first robot in the sub-task executing process, the work task, the robot executing the work task and the corresponding action path are flexibly adjusted to adapt to the responsible work environment, and the normal execution of the work task is ensured.
In addition, on the basis of the method steps, the behavior state corresponding to the state data of each first robot can be simulated through physical simulation software which is constructed in advance.
Specifically, in the subtask executing process of the robot, the physical entity robot or the smart device thereon acquires environment change information based on various physical sensors arranged on the physical entity robot, and synchronously feeds back the environment change, the current interaction information with the human, and internal and external events capable of influencing the current robot state change to the server at the cloud end as state data in the subtask executing process of the first robot through the perception preprocessing module, specifically to the digital twin bodies corresponding to the first robots on the server, so as to ensure that all behaviors of the digital twin bodies on the server are kept in behavioral synchronization with the physical entity robot or the smart device. And simulating the behavior state corresponding to the state data of each first robot by the server through the pre-constructed physical simulation software through the synchronized state data related to the physical entity robot. For example, the digital twin body after the behavior state is synchronized is subjected to analog display in a digital twin world corresponding to the environmental three-dimensional semantic map, so that related personnel can monitor the working state of the entity robot conveniently.
Compared with the related art, in the embodiment, the actual action path data and the received external events in the sub-task executing process of the first robot are monitored, the to-be-executed work task is flexibly adjusted, the action path execution data corresponding to the to-be-executed work task is regenerated and issued to the updated first robot, so that the updated first robot is controlled to execute the corresponding sub-task, and the flexible adjustment of the executed sub-task of the robot based on the state data of the first robot is realized.
A sixth embodiment of the invention relates to an electronic device, as shown in FIG. 7, comprising at least one processor 202; and a memory 201 communicatively coupled to the at least one processor 202; wherein the memory 201 stores instructions executable by the at least one processor 202, the instructions being executable by the at least one processor 202 to enable the at least one processor 202 to perform any of the method embodiments described above.
Where the memory 201 and the processor 202 are coupled in a bus, the bus may comprise any number of interconnected buses and bridges that couple one or more of the various circuits of the processor 202 and the memory 201 together. The bus may also connect various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. A bus interface provides an interface between the bus and the transceiver. The transceiver may be one element or a plurality of elements, such as a plurality of receivers and transmitters, providing a means for communicating with various other apparatus over a transmission medium. The data processed by the processor 202 is transmitted over a wireless medium through an antenna, which further receives the data and transmits the data to the processor 202.
The processor 202 is responsible for managing the bus and general processing and may also provide various functions including timing, peripheral interfaces, voltage regulation, power management, and other control functions. And memory 201 may be used to store data used by processor 202 in performing operations.
A seventh embodiment of the present invention relates to a computer-readable storage medium storing a computer program. The computer program realizes any of the above-described method embodiments when executed by a processor.
That is, as can be understood by those skilled in the art, all or part of the steps in the method for implementing the embodiments described above may be implemented by a program instructing related hardware, where the program is stored in a storage medium and includes several instructions to enable a device (which may be a single chip, a chip, or the like) or a processor (processor) to execute all or part of the steps of the method described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
It will be understood by those of ordinary skill in the art that the foregoing embodiments are specific examples for carrying out the invention, and that various changes in form and details may be made therein without departing from the spirit and scope of the invention in practice.
Claims (17)
1. A multi-robot control method is applied to a server and comprises the following steps:
splitting a work task to be executed into a plurality of subtasks, and generating task allocation data of each subtask based on attribute information of an available robot, wherein the task allocation data comprises: subtask content and a first robot that performs the subtask;
generating action path planning data of each first robot based on the task allocation data and a pre-acquired environment three-dimensional semantic map of a scene where the work task is located;
performing simulation evaluation on the action path planning data of each first robot in the environmental three-dimensional semantic map;
when the simulation result meets a preset requirement, sending action path execution data generated according to the action path planning data to a corresponding first robot so as to control the first robot to execute a corresponding subtask;
and monitoring state data of the first robot in the sub-task executing process, and maintaining or adjusting the action path executing data of the first robot according to the state data.
2. The method according to claim 1, characterized in that the available robots' attribute information comprises at least: information of function, efficiency and power consumption;
the generating of task allocation data of each subtask based on the attribute information of the available robot includes:
generating a plurality of combined schemes of the task allocation data based on the functional information of the available robots;
and selecting the combination scheme with the highest comprehensive efficiency and the lowest power consumption of the first robot from the combination schemes as task allocation data of each subtask.
3. The method according to claim 2, wherein the selecting, from the combination solutions, a combination solution with the highest overall efficiency and the lowest power consumption of the first robot as the task allocation data of the subtasks further comprises:
aiming at the selected combined scheme, acquiring historical subtask execution data of the first robot in the combined scheme;
and maintaining the subtasks to be executed currently of the first robot or adjusting the subtasks to be executed currently of the first robot in the combination scheme based on the historical subtask execution data and the subtasks to be executed currently of the first robot, so as to finally form task allocation data of each subtask.
4. The method of claim 1, wherein obtaining the environmental three-dimensional semantic map of the scene in which the work task is located comprises:
and carrying out environmental scanning on the scene where the work task is located in advance through any available robot to form the environmental three-dimensional semantic map, wherein the environmental three-dimensional semantic map comprises the following steps: semantic objects, spatial attributes and texture attributes of semantic objects.
5. The method according to claim 1, characterized in that digital twins which correspond to the available robots one by one and contain attribute information of the available robots are provided in the server; the generating of task allocation data of each subtask based on the attribute information of the available robot includes:
and generating task allocation data of each subtask based on the digital twin configured by the service trainer for the subtask.
6. The method of claim 5, further comprising:
configuring attribute information of the available robots based on parameter settings of the digital twin by the service trainer.
7. The method according to claim 1, wherein the generating of the action path planning data for each first robot based on the task allocation data and a pre-acquired three-dimensional semantic map of the environment of the scene where the work task is located comprises:
generating movement path planning subdata of the first robot according to the current position of the first robot and the three-dimensional environment semantics corresponding to the work area related to the subtask;
and generating operation path planning subdata of each first robot according to the action three-dimensional environment semantics of the first robot for executing the subtasks in the working area.
8. The method of claim 7, wherein the generating the movement path plan sub-data of the first robot according to the current position of the first robot and the three-dimensional environment semantics corresponding to the work area involved in the subtask comprises:
generating a plurality of groups of mobile path planning subdata corresponding to the first robot according to the current position of the first robot and the three-dimensional environment semantics corresponding to the work area related to the subtask;
and selecting one group of data with the shortest moving path from the plurality of groups of moving path planning sub-data as the moving path planning sub-data of the first robot.
9. The method of claim 1, wherein the simulation evaluation of the action path planning data of each of the first robots in the three-dimensional semantic map of the environment comprises:
performing process simulation on the action path planning data of each first robot in the environment three-dimensional semantic map to obtain action path simulation data;
judging whether the action path simulation data meet preset requirements or not, wherein the preset requirements comprise: and the action paths corresponding to any two first robots do not conflict, each subtask can reach, and the execution time of a single subtask and the total execution time of the working tasks do not exceed the corresponding time threshold.
10. The method of claim 9, wherein after performing simulation evaluation on the action path planning data of each of the first robots in the three-dimensional semantic map of the environment, the method further comprises:
and when the simulation result does not meet the preset requirement, adjusting the task allocation data or the action path planning data of the first robot until the simulation result meets the preset requirement.
11. The method of claim 10, wherein adjusting the task allocation data or the action path planning data of the first robot when the simulation result does not meet a preset requirement comprises:
when the action path simulation data represent that the subtasks are unreachable, task allocation data of the unreachable subtasks are regenerated based on attribute information of the remaining available robots;
and when the action path simulation data represent that the subtasks are all reachable and conflict exists between action paths corresponding to at least two first robots, and/or the execution time of at least one subtask exceeds a corresponding time threshold, and/or the total execution time of the work task exceeds a corresponding time threshold, adjusting the action path planning data of each first robot.
12. The method of claim 9, wherein performing a process simulation on the action path planning data of each of the first robots in the three-dimensional semantic map of the environment to obtain action path simulation data comprises:
simulating the action path of each first robot in the environment three-dimensional semantic map through pre-constructed physical simulation software;
and generating the action path simulation data according to the simulation result.
13. The method of claim 9, wherein the status data comprises: actual movement path data of the first robot;
the monitoring state data of the first robot in the sub-task executing process, and maintaining or adjusting the action path executing data of the first robot according to the state data includes:
and when the actual action path data indicates that the first robot has a fault or the difference between the actual action path data and the corresponding action path simulation data exceeds a limit value, taking the remaining unfinished work tasks as the work tasks to be executed, regenerating the action path execution data corresponding to the work tasks to be executed, and sending the action path execution data to the updated first robot so as to control the updated first robot to execute the corresponding subtasks.
14. The method of claim 9, wherein the status data comprises: an external event received by the first robot;
the monitoring state data of the first robot in the sub-task executing process, and maintaining or adjusting the action path executing data of the first robot according to the state data includes:
when the first robot receives an external event, the rest work tasks and the work tasks corresponding to the external event are jointly used as the work tasks to be executed, the action path execution data corresponding to the work tasks to be executed are regenerated and issued to the updated first robot, and the updated first robot is controlled to execute corresponding subtasks.
15. The method of any one of claims 1, 13 or 14, further comprising:
and simulating the behavior state corresponding to the state data of each first robot through pre-constructed physical simulation software.
16. An electronic device, comprising:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the multi-robot control method of any of claims 1-15.
17. A computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the multi-robot control method of any one of claims 1 to 15.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2020115622506 | 2020-12-25 | ||
| CN202011562250.6A CN112659127A (en) | 2020-12-25 | 2020-12-25 | Multi-robot control method, device, system, storage medium and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114193447A true CN114193447A (en) | 2022-03-18 |
| CN114193447B CN114193447B (en) | 2023-07-07 |
Family
ID=75409068
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011562250.6A Pending CN112659127A (en) | 2020-12-25 | 2020-12-25 | Multi-robot control method, device, system, storage medium and electronic equipment |
| CN202111392307.7A Active CN114193447B (en) | 2020-12-25 | 2021-11-19 | Multi-robot control method, electronic device and storage medium |
Family Applications Before (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011562250.6A Pending CN112659127A (en) | 2020-12-25 | 2020-12-25 | Multi-robot control method, device, system, storage medium and electronic equipment |
Country Status (2)
| Country | Link |
|---|---|
| CN (2) | CN112659127A (en) |
| WO (1) | WO2022134732A1 (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114779795A (en) * | 2022-06-21 | 2022-07-22 | 山东金宇信息科技集团有限公司 | Accident dredging method, equipment and medium based on rail robot |
| CN115437372A (en) * | 2022-08-10 | 2022-12-06 | 中国科学院自动化研究所 | Robot path planning method and device, electronic equipment and storage medium |
| CN115464645A (en) * | 2022-09-13 | 2022-12-13 | 达闼机器人股份有限公司 | Task execution method, device, equipment and storage medium |
| CN116308006A (en) * | 2023-05-19 | 2023-06-23 | 安徽省赛达科技有限责任公司 | Digital rural comprehensive service cloud platform |
| CN116423515A (en) * | 2023-04-28 | 2023-07-14 | 燕山大学 | Digital twin control system of multiple robots and positioning and mapping method thereof |
Families Citing this family (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112659127A (en) * | 2020-12-25 | 2021-04-16 | 达闼机器人有限公司 | Multi-robot control method, device, system, storage medium and electronic equipment |
| CN113269874A (en) * | 2021-04-20 | 2021-08-17 | 达闼机器人有限公司 | Method and device for establishing three-dimensional map |
| CN113177327A (en) * | 2021-05-20 | 2021-07-27 | 广东博智林机器人有限公司 | Simulation method, device, storage medium and processor |
| CN113635302B (en) * | 2021-07-29 | 2022-11-15 | 深圳墨影科技有限公司 | Integrated mobile cooperative robot control system based on field bus |
| CN114485621A (en) * | 2022-02-08 | 2022-05-13 | 达闼机器人股份有限公司 | Navigation method, navigation device and computer readable storage medium |
| CN114676230B (en) * | 2022-05-30 | 2022-09-27 | 深圳市长亮科技股份有限公司 | Information interaction method and device based on digital twin technology |
| CN115422814B (en) * | 2022-11-04 | 2023-04-28 | 中国海洋大学 | Digital twin-driven closed-loop optimization design method for complex electromechanical product |
| CN116214542B (en) * | 2023-03-23 | 2023-11-10 | 广东省特种设备检测研究院东莞检测院 | Digital twin system of spherical tank inner wall climbing robot |
| CN116629011B (en) * | 2023-06-06 | 2024-06-18 | 中国人民解放军军事科学院***工程研究院 | Electronic countermeasure digital twin system |
| CN117406667B (en) * | 2023-11-20 | 2024-05-10 | 南京工程学院 | Stretch bender motion control method based on digital twin model |
| CN117901102A (en) * | 2024-01-22 | 2024-04-19 | 广东环境保护工程职业学院 | Production line robot synchronization method, device, system and medium |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007068828A (en) * | 2005-09-08 | 2007-03-22 | Motoyuki Fujiwara | Article supporting appliance |
| CN103699106A (en) * | 2013-12-30 | 2014-04-02 | 合肥工业大学 | Multi-unmanned aerial vehicle cooperative task planning simulation system based on VR-Forces simulation platform |
| CN106108761A (en) * | 2016-06-24 | 2016-11-16 | 武汉理工大学 | A kind of high-altitude glass curtain wall cleaning machine device people |
| US9671777B1 (en) * | 2016-06-21 | 2017-06-06 | TruPhysics GmbH | Training robots to execute actions in physics-based virtual environment |
| CN206475721U (en) * | 2016-08-08 | 2017-09-08 | 成都德荣汽车用品有限公司 | Automatic accomodation car clothing |
| CN107831685A (en) * | 2017-10-13 | 2018-03-23 | 南方科技大学 | Group robot control method and system |
| CN207498660U (en) * | 2017-09-22 | 2018-06-15 | 无锡小天鹅股份有限公司 | Washing machine and Combined washer |
| US20180365566A1 (en) * | 2014-09-18 | 2018-12-20 | Robert D. Pedersen | Distributed activity control systems and methods |
| CN208697467U (en) * | 2018-01-03 | 2019-04-05 | 江苏美之好机器人有限公司 | A kind of robot palletizer sucker gripper |
| CN109986581A (en) * | 2019-05-06 | 2019-07-09 | 北京云迹科技有限公司 | A kind of multitask service robot and service system |
| CN110308716A (en) * | 2018-03-27 | 2019-10-08 | 上海汽车集团股份有限公司 | A kind of method, apparatus and vehicle of the automatic driving vehicle based on cluster |
| US20190391597A1 (en) * | 2018-06-25 | 2019-12-26 | X Development Llc | Robot coordination in a shared workspace |
| CN111958594A (en) * | 2020-07-30 | 2020-11-20 | 国网智能科技股份有限公司 | Semantic intelligent substation inspection operation robot system and method |
| CN112008732A (en) * | 2020-09-09 | 2020-12-01 | 中科新松有限公司 | Robot reverse running method, device, terminal and storage medium |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106444739A (en) * | 2016-07-15 | 2017-02-22 | 鹿龙 | Multi-industrial-robot virtual offline co-simulation system and method |
| CN107234616B (en) * | 2017-07-07 | 2018-08-14 | 广州木木机器人技术有限公司 | Multirobot control method and device |
| CN111680893B (en) * | 2020-05-25 | 2023-05-30 | 北京科技大学 | Digital twin system of multi-self-addressing robot picking system and scheduling method |
| CN112659127A (en) * | 2020-12-25 | 2021-04-16 | 达闼机器人有限公司 | Multi-robot control method, device, system, storage medium and electronic equipment |
-
2020
- 2020-12-25 CN CN202011562250.6A patent/CN112659127A/en active Pending
-
2021
- 2021-09-30 WO PCT/CN2021/122448 patent/WO2022134732A1/en unknown
- 2021-11-19 CN CN202111392307.7A patent/CN114193447B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007068828A (en) * | 2005-09-08 | 2007-03-22 | Motoyuki Fujiwara | Article supporting appliance |
| CN103699106A (en) * | 2013-12-30 | 2014-04-02 | 合肥工业大学 | Multi-unmanned aerial vehicle cooperative task planning simulation system based on VR-Forces simulation platform |
| US20180365566A1 (en) * | 2014-09-18 | 2018-12-20 | Robert D. Pedersen | Distributed activity control systems and methods |
| US9671777B1 (en) * | 2016-06-21 | 2017-06-06 | TruPhysics GmbH | Training robots to execute actions in physics-based virtual environment |
| CN106108761A (en) * | 2016-06-24 | 2016-11-16 | 武汉理工大学 | A kind of high-altitude glass curtain wall cleaning machine device people |
| CN206475721U (en) * | 2016-08-08 | 2017-09-08 | 成都德荣汽车用品有限公司 | Automatic accomodation car clothing |
| CN207498660U (en) * | 2017-09-22 | 2018-06-15 | 无锡小天鹅股份有限公司 | Washing machine and Combined washer |
| CN107831685A (en) * | 2017-10-13 | 2018-03-23 | 南方科技大学 | Group robot control method and system |
| CN208697467U (en) * | 2018-01-03 | 2019-04-05 | 江苏美之好机器人有限公司 | A kind of robot palletizer sucker gripper |
| CN110308716A (en) * | 2018-03-27 | 2019-10-08 | 上海汽车集团股份有限公司 | A kind of method, apparatus and vehicle of the automatic driving vehicle based on cluster |
| US20190391597A1 (en) * | 2018-06-25 | 2019-12-26 | X Development Llc | Robot coordination in a shared workspace |
| CN109986581A (en) * | 2019-05-06 | 2019-07-09 | 北京云迹科技有限公司 | A kind of multitask service robot and service system |
| CN111958594A (en) * | 2020-07-30 | 2020-11-20 | 国网智能科技股份有限公司 | Semantic intelligent substation inspection operation robot system and method |
| CN112008732A (en) * | 2020-09-09 | 2020-12-01 | 中科新松有限公司 | Robot reverse running method, device, terminal and storage medium |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114779795A (en) * | 2022-06-21 | 2022-07-22 | 山东金宇信息科技集团有限公司 | Accident dredging method, equipment and medium based on rail robot |
| CN114779795B (en) * | 2022-06-21 | 2022-09-20 | 山东金宇信息科技集团有限公司 | Accident dredging method, equipment and medium based on rail robot |
| CN115437372A (en) * | 2022-08-10 | 2022-12-06 | 中国科学院自动化研究所 | Robot path planning method and device, electronic equipment and storage medium |
| CN115464645A (en) * | 2022-09-13 | 2022-12-13 | 达闼机器人股份有限公司 | Task execution method, device, equipment and storage medium |
| CN116423515A (en) * | 2023-04-28 | 2023-07-14 | 燕山大学 | Digital twin control system of multiple robots and positioning and mapping method thereof |
| CN116423515B (en) * | 2023-04-28 | 2023-10-03 | 燕山大学 | Digital twin control system of multiple robots and positioning and mapping method thereof |
| CN116308006A (en) * | 2023-05-19 | 2023-06-23 | 安徽省赛达科技有限责任公司 | Digital rural comprehensive service cloud platform |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112659127A (en) | 2021-04-16 |
| WO2022134732A1 (en) | 2022-06-30 |
| CN114193447B (en) | 2023-07-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114193447B (en) | Multi-robot control method, electronic device and storage medium | |
| AU2008353981B2 (en) | Robotics systems | |
| US7236861B2 (en) | Mission planning system with asynchronous request capability | |
| US5255181A (en) | Method of planning organizational activities | |
| US20200016754A1 (en) | Executing centralized and decentralized controlled plans collaboratively by autonomous robots | |
| Krueger et al. | A vertical and cyber–physical integration of cognitive robots in manufacturing | |
| CN112230677B (en) | Unmanned aerial vehicle group task planning method and terminal equipment | |
| US20210065085A1 (en) | Real-Time Optimization Of Aircraft Manufacturing Task Management | |
| CN111142490B (en) | AGV intelligent storage simulation method, system and device and computer readable storage medium | |
| CN114169748A (en) | Multi-robot task allocation method, system, device and readable storage medium | |
| Weyns et al. | Architectural design of a situated multiagent system for controlling automatic guided vehicles | |
| EP4020108A1 (en) | Automated machine collaboration | |
| Mayer et al. | Standardized framework for evaluating centralized and decentralized control systems in modular assembly systems | |
| CN113848752B (en) | Distributed real-time simulation method | |
| Weyns et al. | Decentralized control of automatic guided vehicles: applying multi-agent systems in practice | |
| US20210264317A1 (en) | Method and a system for applying machine learning to an application | |
| US12007239B2 (en) | Information processing apparatus, information processing method, computer program, and travel management system | |
| Jiang et al. | An adaptive agile manufacturing control infrastructure based on TOPNs-CS modelling | |
| Narapureddy et al. | Optimal scheduling methodology for machines, tool transporter and tools in a multi-machine flexible manufacturing system without tool delay using flower pollination algorithm | |
| Petronijević et al. | Integrated process planning and scheduling using multi-agent methodology | |
| Li et al. | Improved net rewriting system-based approach to model reconfiguration of reconfigurable manufacturing systems | |
| CN113487913A (en) | Digital twin remote operation and maintenance system for ship management | |
| Tsai et al. | Web-based distributed manufacturing control systems | |
| Chaile et al. | Agent simulator-based control architecture for rapid development of multi-robot systems | |
| McGuigan et al. | Cooperation Strategies in a Time-Stepped Simulation of Foraging Robots |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 200245 Building 8, No. 207, Zhongqing Road, Minhang District, Shanghai Applicant after: Dayu robot Co.,Ltd. Address before: 200245 2nd floor, building 2, no.1508, Kunyang Road, Minhang District, Shanghai Applicant before: Dalu Robot Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |