A method and system for dynamic matching and collaboration of robots based on capability discovery

Abstract

The application provides a robot dynamic matching and cooperation method and system based on capability discovery. The method comprises the following steps: obtaining physical capability parameter data and real-time running state parameter data by constructing an ecological integrated cooperative interface set, generating a dynamic capability evaluation graph, analyzing and processing task demand instructions to generate a task demand vector, intelligently matching and combining a preset robot digital twin model for analysis to obtain a dynamic resource scheduling strategy, controlling the robot to perform an action, obtaining execution state detection data, further processing to obtain an execution state abnormal evaluation parameter, and finally determining the dynamic matching and cooperation state of the robot through threshold comparison. The application constructs a multi-layer interface abstraction architecture, relies on a dynamic capability discovery mechanism, constructs a dynamic capability graph and a task demand vector, intelligently matches a dynamic resource scheduling strategy, and forms a closed loop processing by evaluating and feeding back the execution to realize the robot dynamic matching and cooperation based on capability discovery.

Description

Technical Field

[0001] This application relates to the field of robot collaboration and system integration technology, and more specifically, to a method and system for dynamic matching and collaboration of robots based on capability discovery. Background Technology

[0002] The rapid development of robots has expanded their application scenarios from single-operation environments to complex multi-device collaborative scenarios such as smart buildings, industrial parks, security, and logistics. Robots need to interact closely with elevators, access control systems, cameras, IoT peripherals, and third-party scheduling platforms to complete complex tasks. In traditional applications, the interface standards of robots and peripherals from different brands are not standardized, resulting in interface fragmentation. Existing integration solutions mostly remain at the device control layer, only achieving simple point-to-point control and failing to handle complex cross-system task collaboration. The understanding of robot and peripheral capabilities is static, acquiring capability parameters only once upon device access, without considering capability decay during device operation. This leads to a mismatch between task allocation and actual capabilities, such as reduced load capacity due to robot battery depletion. Therefore, there is an urgent need for a dynamic matching and collaboration method that enables unified access, dynamic capability matching, and cross-platform task collaboration between robots, peripherals, and third-party applications.

[0003] Effective technical solutions are urgently needed to address the above problems. Summary of the Invention

[0004] The purpose of this application is to provide a method and system for dynamic matching and collaboration of robots based on capability discovery. By constructing a multi-layer interface abstract architecture, relying on a dynamic capability discovery mechanism, constructing a dynamic capability map and task requirement vector, and intelligently matching dynamic resource scheduling strategies and evaluating execution feedback to form a closed-loop processing, the system can achieve dynamic matching and collaboration of robots based on capability discovery.

[0005] Firstly, this application provides a method for dynamic matching and cooperation of robots based on capability discovery, including the following steps:

[0006] Construct an integrated ecological collaborative interface set for robots;

[0007] Acquire the robot's physical capability parameters and real-time operating status parameters, construct a map based on the physical capability parameters and real-time operating status parameters, and generate a dynamic capability assessment map of the robot.

[0008] Obtain task requirement instructions, analyze and process them to generate task requirement vectors;

[0009] Matching analysis is performed based on the task requirement vector and dynamic capability assessment map, and the analysis is combined with a preset robot digital twin model to obtain a dynamic resource scheduling strategy.

[0010] According to the dynamic resource scheduling strategy, the robot is controlled to perform actions through the integrated ecological collaborative interface set, and the execution status detection data between the robot and the peripheral device is obtained. The execution status detection data is analyzed and processed to obtain execution status anomaly evaluation parameters.

[0011] The abnormal execution status evaluation parameters are compared with the preset execution status evaluation thresholds, and the dynamic matching and cooperation status of the robot is determined based on the threshold comparison results.

[0012] Optionally, in the robot dynamic matching and cooperation method based on capability discovery described in this application, the step of acquiring the robot's physical capability parameter data and real-time operating status parameter data, and constructing a map based on the physical capability parameter data and real-time operating status parameter data to generate a dynamic capability assessment map of the robot includes:

[0013] Acquire the robot's physical capability parameters and real-time operating status parameters. The physical capability parameters include the robot's workspace data, obstacle crossing limit data, response speed and rated load data. The real-time operating status parameters include the robot's real-time battery level and operation record data.

[0014] Based on the workspace data, obstacle crossing capability limit data, response speed and rated load data, parameter calibration and data standardization are performed to generate physical constraint parameters.

[0015] Obtain characteristic data of the robot's working environment type;

[0016] The real-time operating status vector is obtained by weighted fusion processing of the real-time power consumption and operation record data combined with the working environment type feature data.

[0017] The real-time operating state vector is correlated with the physical constraint parameters to generate a dynamic capability assessment map of the robot.

[0018] Optionally, in the robot dynamic matching and cooperation method based on capability discovery described in this application, the step of obtaining task requirement instructions and analyzing and processing the task requirement instructions to generate a task requirement vector includes:

[0019] Obtain task requirement instructions;

[0020] Based on the task requirement instructions, the subtask set is obtained by analyzing and processing the data through a preset subtask decomposition model.

[0021] Based on the subtask set, feature extraction is performed to obtain the spatiotemporal constraint feature data, task capability requirement data and task priority corresponding to the subtask;

[0022] Data processing is performed based on the spatiotemporal constraint feature data, task capability requirement data, and task priority to generate a task requirement vector.

[0023] Optionally, in the robot dynamic matching and collaboration method based on capability discovery described in this application, the step of performing matching analysis based on the task requirement vector and dynamic capability assessment map, and combining it with a preset robot digital twin model for analysis and processing to obtain a dynamic resource scheduling strategy, includes:

[0024] Based on the task requirement vector and dynamic capability assessment map, the corresponding matching degree is obtained by analyzing and processing them using a preset cosine similarity algorithm.

[0025] The matching scores are sorted in descending order, and the matching scheme with the highest matching score is determined as the initial matching scheme.

[0026] Based on the initial matching scheme, a twin simulation verification is performed using a preset robot digital twin model;

[0027] If a path conflict or insufficient capability matching is determined, the preset subtask decomposition model is optimized.

[0028] If the path is determined to be normal and the capacity is sufficient, then the initial matching scheme is determined to be a dynamic resource scheduling strategy.

[0029] Optionally, in the capability discovery-based robot dynamic matching and collaboration method described in this application, the step of controlling the robot to perform actions through the integrated ecosystem collaboration interface set according to the dynamic resource scheduling strategy, acquiring execution status detection data between the robot and peripherals, and analyzing and processing the execution status detection data to obtain execution status anomaly evaluation parameters includes:

[0030] According to the dynamic resource scheduling strategy, the robot is controlled to perform actions through the ecological integrated collaborative interface set, and the execution status detection data between the robot and peripheral devices is obtained, including power system status data, motion control status data, perception system status data, communication system status data, load execution status data and environmental interaction status data.

[0031] The preset number of power system status data, motion control status data, perception system status data, communication system status data, load execution status data and environmental interaction status data within a preset time period are input into a preset robot abnormal state prediction model for time-series abnormality detection, and the robot's operational abnormality assessment prediction value is obtained.

[0032] The preset number of power system status data, motion control status data, perception system status data, communication system status data, load execution status data and environmental interaction status data within a preset time period are input into a preset robot abnormal state multi-parameter correlation prediction model for parameter correlation analysis to obtain robot operation abnormality evaluation parameters.

[0033] The execution status anomaly evaluation parameters are obtained by weighted summation of the predicted execution anomaly assessment values ​​and the execution anomaly evaluation parameters.

[0034] Optionally, in the capability discovery-based robot dynamic matching and collaboration method described in this application, the step of controlling the robot to perform actions through the integrated ecosystem collaboration interface set according to the dynamic resource scheduling strategy, acquiring execution status detection data between the robot and peripherals, and analyzing and processing the execution status detection data to obtain execution status anomaly evaluation parameters includes:

[0035] According to the dynamic resource scheduling strategy, the robot is controlled to perform actions through the ecological integrated collaborative interface set, and the execution status detection data between the robot and peripheral devices is obtained, including power system status data, motion control status data, perception system status data, communication system status data, load execution status data and environmental interaction status data.

[0036] The preset number of power system status data, motion control status data, perception system status data, communication system status data, load execution status data and environmental interaction status data within a preset time period are input into a preset robot abnormal state prediction model for time-series abnormality detection, and the robot's operational abnormality assessment prediction value is obtained.

[0037] The preset number of power system status data, motion control status data, perception system status data, communication system status data, load execution status data and environmental interaction status data within a preset time period are input into a preset robot abnormal state multi-parameter correlation prediction model for parameter correlation analysis to obtain robot operation abnormality evaluation parameters.

[0038] The execution status anomaly evaluation parameters are obtained by weighted summation of the predicted execution anomaly assessment values ​​and the execution anomaly evaluation parameters.

[0039] Optionally, in the robot dynamic matching and cooperation method based on capability discovery described in this application, the step of comparing the execution state anomaly evaluation parameters with a preset execution state evaluation threshold, and determining the robot's dynamic matching and cooperation state based on the threshold comparison result, includes:

[0040] The execution state anomaly evaluation parameters are compared with preset execution state evaluation thresholds, wherein the preset execution state evaluation thresholds include a first preset execution state evaluation threshold, a second preset execution state evaluation threshold, and a third preset execution state evaluation threshold.

[0041] If the abnormal execution state evaluation parameter is less than or equal to the first preset execution state evaluation threshold, then the robot's dynamic matching and collaboration state is determined to be normal.

[0042] If the abnormal execution state evaluation parameter is greater than the first preset execution state evaluation threshold and less than or equal to the second preset execution state evaluation threshold, then the robot's dynamic matching and collaboration state is determined to be a minor fault.

[0043] If the abnormal execution state evaluation parameter is greater than the second preset execution state evaluation threshold and less than or equal to the third preset execution state evaluation threshold, then the robot's dynamic matching and cooperation state is determined to be a moderate fault.

[0044] If the abnormal execution status evaluation parameter is greater than the third preset execution status evaluation threshold, the robot's dynamic matching and collaboration status is determined to be a severe fault.

[0045] Secondly, this application provides a robot dynamic matching and cooperation system based on capability discovery. The system includes a memory and a processor. The memory includes a program for a robot dynamic matching and cooperation method based on capability discovery. When the program for the robot dynamic matching and cooperation method based on capability discovery is executed by the processor, it implements the following steps:

[0046] Construct an integrated ecological collaborative interface set for robots;

[0047] Acquire the robot's physical capability parameters and real-time operating status parameters, construct a map based on the physical capability parameters and real-time operating status parameters, and generate a dynamic capability assessment map of the robot.

[0048] Obtain task requirement instructions, analyze and process them to generate task requirement vectors;

[0049] Matching analysis is performed based on the task requirement vector and dynamic capability assessment map, and the analysis is combined with a preset robot digital twin model to obtain a dynamic resource scheduling strategy.

[0050] According to the dynamic resource scheduling strategy, the robot is controlled to perform actions through the integrated ecological collaborative interface set, and the execution status detection data between the robot and the peripheral device is obtained. The execution status detection data is analyzed and processed to obtain execution status anomaly evaluation parameters.

[0051] The abnormal execution status evaluation parameters are compared with the preset execution status evaluation thresholds, and the dynamic matching and cooperation status of the robot is determined based on the threshold comparison results.

[0052] Optionally, in the robot dynamic matching and collaboration system based on capability discovery described in this application, the step of acquiring the robot's physical capability parameter data and real-time operating status parameter data, and constructing a map based on the physical capability parameter data and real-time operating status parameter data to generate a dynamic capability evaluation map of the robot includes:

[0053] Acquire the robot's physical capability parameters and real-time operating status parameters. The physical capability parameters include the robot's workspace data, obstacle crossing limit data, response speed and rated load data. The real-time operating status parameters include the robot's real-time battery level and operation record data.

[0054] Based on the workspace data, obstacle crossing capability limit data, response speed and rated load data, parameter calibration and data standardization are performed to generate physical constraint parameters.

[0055] Obtain characteristic data of the robot's working environment type;

[0056] The real-time operating status vector is obtained by weighted fusion processing of the real-time power consumption and operation record data combined with the working environment type feature data.

[0057] The real-time operating state vector is correlated with the physical constraint parameters to generate a dynamic capability assessment map of the robot.

[0058] Optionally, in the robot dynamic matching and cooperation system based on capability discovery described in this application, the step of obtaining task requirement instructions and analyzing and processing the task requirement instructions to generate a task requirement vector includes:

[0059] Obtain task requirement instructions;

[0060] Based on the task requirement instructions, the subtask set is obtained by analyzing and processing the data through a preset subtask decomposition model.

[0061] Based on the subtask set, feature extraction is performed to obtain the spatiotemporal constraint feature data, task capability requirement data and task priority corresponding to the subtask;

[0062] Data processing is performed based on the spatiotemporal constraint feature data, task capability requirement data, and task priority to generate a task requirement vector.

[0063] Optionally, in the robot dynamic matching and collaboration system based on capability discovery described in this application, the step of performing matching analysis based on the task requirement vector and dynamic capability assessment map, and combining it with a preset robot digital twin model for analysis and processing to obtain a dynamic resource scheduling strategy, includes:

[0064] Based on the task requirement vector and dynamic capability assessment map, the corresponding matching degree is obtained by analyzing and processing them using a preset cosine similarity algorithm.

[0065] The matching scores are sorted in descending order, and the matching scheme with the highest matching score is determined as the initial matching scheme.

[0066] Based on the initial matching scheme, a twin simulation verification is performed using a preset robot digital twin model;

[0067] If a path conflict or insufficient capability matching is determined, the preset subtask decomposition model is optimized.

[0068] If the path is determined to be normal and the capacity is sufficient, then the initial matching scheme is determined to be a dynamic resource scheduling strategy.

[0069] As can be seen from the above, the robot dynamic matching and collaboration method and system based on capability discovery provided in this application, by constructing a multi-layer interface abstract architecture, relying on the dynamic capability discovery mechanism, constructing a dynamic capability map and task requirement vector, intelligently matching dynamic resource scheduling strategies and evaluating execution feedback to form a closed-loop processing, thereby realizing robot dynamic matching and collaboration based on capability discovery.

[0070] Other features and advantages of this application will be set forth in the following description and will be apparent in part from the description or may be learned by practicing embodiments of this application. The objectives and other advantages of this application may be realized and obtained by means of the structures particularly pointed out in the written description and the accompanying drawings. Attached Figure Description

[0071] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0072] Figure 1 A flowchart illustrating a robot dynamic matching and collaboration method based on capability discovery, provided for embodiments of this application;

[0073] Figure 2A flowchart illustrating the generation of a dynamic capability assessment map of a robot using a capability discovery-based robot dynamic matching and collaboration method, provided in an embodiment of this application.

[0074] Figure 3 This is a flowchart illustrating the generation of task requirement vectors for a robot dynamic matching and collaboration method based on capability discovery, as provided in an embodiment of this application. Detailed Implementation

[0075] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0076] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this application, the terms "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0077] Please refer to Figure 1 , Figure 1 This is a flowchart illustrating a capability-based robot dynamic matching and collaboration method according to some embodiments of this application. This capability-based robot dynamic matching and collaboration method is used in terminal devices, such as computers and mobile terminals. The capability-based robot dynamic matching and collaboration method includes the following steps:

[0078] S11. Construct an integrated ecological collaborative interface set for robots;

[0079] S12. Obtain the robot's physical capability parameter data and real-time operating status parameter data, construct a map based on the physical capability parameter data and real-time operating status parameter data, and generate a dynamic capability evaluation map of the robot.

[0080] S13. Obtain task requirement instructions, analyze and process them according to the task requirement instructions, and generate a task requirement vector.

[0081] S14. Perform matching analysis based on the task requirement vector and dynamic capability assessment map, and combine it with the preset robot digital twin model for analysis and processing to obtain a dynamic resource scheduling strategy.

[0082] S15. Control the robot to perform actions through the ecological integrated collaborative interface set according to the dynamic resource scheduling strategy, and obtain the execution status detection data between the robot and the peripheral device. Analyze and process the execution status detection data to obtain execution status anomaly evaluation parameters.

[0083] S16. The abnormal execution status evaluation parameters are compared with the preset execution status evaluation thresholds, and the dynamic matching and cooperation status of the robot is determined based on the threshold comparison results.

[0084] It should be noted that, to achieve dynamic matching and collaboration among robots, firstly, an integrated ecosystem collaboration interface set for robots is determined by constructing a device driver abstraction layer, a robot capability abstraction layer, an application service abstraction layer, and an ecosystem collaboration bus. Specifically, the device driver abstraction layer encapsulates the underlying protocols of peripherals into a unified driver interface, such as those for elevators, access control systems, and sensors. The robot capability abstraction layer abstracts the movement, grasping, and voice interaction capabilities of robots from different brands into standardized APIs. The application service abstraction layer provides a unified SDK interface for third-party applications such as security, building management, and ERP systems. The ecosystem collaboration bus serves as a unified message bus, thereby enabling data exchange and command distribution between robots, peripherals, and third-party applications. Then, a capability registration protocol is used to automatically upload... The robot's physical capability parameters and real-time operational status parameters are validated and standardized to construct a dynamic capability assessment map. Next, task requirement instructions in natural language from a third-party application are received, parsed using a pre-defined large language model, and feature extraction is performed to construct a task requirement vector. Then, based on the constructed task requirement vector and the dynamic capability assessment map, a cosine similarity algorithm is used to calculate the matching degree using a pre-defined robot digital twin model, generating an initial matching scheme. A twin pre-play is then performed, and a dynamic resource scheduling strategy is output based on the pre-play structure. Finally, based on the task execution flow, the abnormal execution status evaluation parameters between the robot and peripherals are assessed, and the robot's dynamic matching and collaboration status is determined through threshold comparison.

[0085] Please refer to Figure 2 , Figure 2 This is a flowchart illustrating the generation of a dynamic capability assessment map of a robot based on capability discovery-based robot dynamic matching and cooperation method, as described in some embodiments of this application. According to embodiments of the present invention, the step of acquiring the robot's physical capability parameter data and real-time operating status parameter data, and constructing a map based on the physical capability parameter data and real-time operating status parameter data to generate the robot's dynamic capability assessment map includes:

[0086] S21. Obtain the robot's physical capability parameter data and real-time operating status parameter data. The physical capability parameter data includes the robot's workspace data, obstacle crossing capability limit data, response speed and rated load data. The real-time operating status parameter data includes the robot's real-time battery power and operation record data.

[0087] S22. Based on the workspace data, obstacle crossing capability limit data, response speed and rated load data, perform parameter calibration and data standardization to generate physical constraint parameters;

[0088] S23. Obtain the robot's working environment type characteristic data;

[0089] S24. Based on the real-time power consumption and operation record data, combined with the working environment type feature data, a weighted fusion process is performed to obtain a real-time operation status vector;

[0090] S25. Perform data association processing between the real-time running state vector and the physical constraint parameters to generate a dynamic capability evaluation map of the robot.

[0091] It should be noted that the robot's capability boundaries are determined through static physical capability parameter data, constructing physical constraint parameters in the physical constraint dimension. Dynamic real-time operating state parameter data reflects real-time adaptability. Combined with the robot's working environment type characteristic data, a real-time operating state vector in the real-time state dimension is constructed. Real-time state influence factors are determined for the constructed physical constraint parameters. For example, if the maximum climbing angle in the physical constraint parameters is 30°, the corresponding real-time state influence factors are the real-time battery level and the motor temperature in the operation record data. The real-time battery level and motor temperature are normalized and then weighted and summed. Then, a two-dimensional matrix including physical constraints and real-time states is constructed with the physical constraint parameters as rows and the real-time operating state vector as columns. The two-dimensional matrix is ​​rendered to generate the final dynamic capability evaluation map of the robot. In this map, the robot's working environment type, such as rainy day or foggy day, is represented by different identifiers, and different weight values ​​are assigned according to different working environment types.

[0092] Please refer to Figure 3 , Figure 3 This is a flowchart illustrating the generation of a task requirement vector in a robot dynamic matching and collaboration method based on capability discovery, as described in some embodiments of this application. According to an embodiment of the present invention, the step of obtaining task requirement instructions and analyzing and processing them to generate a task requirement vector includes:

[0093] S31. Obtain task requirement instructions;

[0094] S32. Based on the task requirement instructions, analyze and process them using a preset subtask decomposition model to obtain a set of subtasks;

[0095] S33. Perform feature extraction based on the subtask set to obtain the spatiotemporal constraint feature data, task capability requirement data and task priority corresponding to the subtask;

[0096] S34. Based on the spatiotemporal constraint feature data, task capability requirement data, and task priority, perform data processing to generate a task requirement vector.

[0097] It should be noted that, firstly, the task requirement instructions in natural language are received and parsed using a pre-built large language model to obtain a set of subtasks. Then, the spatiotemporal constraint feature data, task capability requirement data, and task priority corresponding to the subtasks are extracted. The spatiotemporal constraint feature data includes the execution time window and spatial path restrictions, and the task capability requirement data includes motion accuracy, load capacity, and environmental adaptation requirements. Finally, a task requirement vector is constructed. The pre-set subtask decomposition model is obtained by training a large number of historical samples of task requirement instructions and corresponding subtask sets.

[0098] According to an embodiment of the present invention, the step of performing matching analysis based on the task requirement vector and dynamic capability assessment map, and combining it with a preset robot digital twin model for analysis and processing to obtain a dynamic resource scheduling strategy includes:

[0099] Based on the task requirement vector and dynamic capability assessment map, the corresponding matching degree is obtained by analyzing and processing them using a preset cosine similarity algorithm.

[0100] The matching scores are sorted in descending order, and the matching scheme with the highest matching score is determined as the initial matching scheme.

[0101] Based on the initial matching scheme, a twin simulation verification is performed using a preset robot digital twin model;

[0102] If a path conflict or insufficient capability matching is determined, the preset subtask decomposition model is optimized.

[0103] If the path is determined to be normal and the capacity is sufficient, then the initial matching scheme is determined to be a dynamic resource scheduling strategy.

[0104] It should be noted that, based on the determined task requirement vector and dynamic capability assessment map, the matching degree of the sub-tasks is obtained through analysis using a preset cosine similarity algorithm. The matching scheme with the highest matching degree is determined as the initial matching scheme. The initial matching scheme is pre-performed and verified in a virtual twin environment. If there are resource conflicts or capability mismatches, the preset sub-task decomposition model is triggered for optimization, the scheme is re-optimized, and the simulation is repeated to verify the results. Finally, a dynamic resource scheduling strategy is output. The preset cosine similarity algorithm and the preset robot digital twin model are pre-constructed by those skilled in the art and can be dynamically adjusted.

[0105] According to an embodiment of the present invention, the step of controlling the robot to perform actions through the ecological integrated collaborative interface set according to the dynamic resource scheduling strategy, acquiring execution status detection data between the robot and peripheral devices, and analyzing and processing the execution status detection data to obtain execution status anomaly evaluation parameters includes:

[0106] According to the dynamic resource scheduling strategy, the robot is controlled to perform actions through the ecological integrated collaborative interface set, and the execution status detection data between the robot and peripheral devices is obtained, including power system status data, motion control status data, perception system status data, communication system status data, load execution status data and environmental interaction status data.

[0107] The preset number of power system status data, motion control status data, perception system status data, communication system status data, load execution status data and environmental interaction status data within a preset time period are input into a preset robot abnormal state prediction model for time-series abnormality detection, and the robot's operational abnormality assessment prediction value is obtained.

[0108] The preset number of power system status data, motion control status data, perception system status data, communication system status data, load execution status data and environmental interaction status data within a preset time period are input into a preset robot abnormal state multi-parameter correlation prediction model for parameter correlation analysis to obtain robot operation abnormality evaluation parameters.

[0109] The execution status anomaly evaluation parameters are obtained by weighted summation of the predicted execution anomaly assessment values ​​and the execution anomaly evaluation parameters.

[0110] It should be noted that, in order to achieve closed-loop verification of the dynamic resource scheduling strategy, execution status detection data is collected in real time during robot execution. This includes power system status data, motion control status data, perception system status data, communication system status data, load execution status data, and environmental interaction status data. Specifically, power system status data includes motor current, motor temperature, battery charge, and battery voltage; motion control status data includes running speed, joint speed, motion error, and attitude angle; perception system status data includes sensor accuracy and sensor temperature; communication system status data includes communication latency, packet loss rate, and signal strength; load execution status data includes robotic arm load, gripping force, and actuator stroke; and environmental interaction status data includes ambient temperature, humidity, and obstacle distance. A preset robot abnormal state prediction model is used to detect temporal anomalies within a preset time period. The system obtains predicted values ​​for robot operation anomalies. Simultaneously, it performs parameter correlation analysis through a pre-set multi-parameter correlation prediction model for robot anomalies to obtain robot operation anomaly evaluation parameters. These parameters are then weighted and summed to obtain execution state anomaly evaluation parameters. The pre-set robot anomaly prediction model is trained using a large amount of historical sample data on the power system state, motion control state, perception system state, communication system state, load execution state, and environmental interaction state, along with the corresponding predicted operation anomaly values.

[0111] According to an embodiment of the present invention, the step of comparing the execution state anomaly evaluation parameters with a preset execution state evaluation threshold, and determining the robot's dynamic matching and cooperation state based on the threshold comparison result, includes:

[0112] The execution state anomaly evaluation parameters are compared with preset execution state evaluation thresholds, wherein the preset execution state evaluation thresholds include a first preset execution state evaluation threshold, a second preset execution state evaluation threshold, and a third preset execution state evaluation threshold.

[0113] If the abnormal execution state evaluation parameter is less than or equal to the first preset execution state evaluation threshold, then the robot's dynamic matching and collaboration state is determined to be normal.

[0114] If the abnormal execution state evaluation parameter is greater than the first preset execution state evaluation threshold and less than or equal to the second preset execution state evaluation threshold, then the robot's dynamic matching and collaboration state is determined to be a minor fault.

[0115] If the abnormal execution state evaluation parameter is greater than the second preset execution state evaluation threshold and less than or equal to the third preset execution state evaluation threshold, then the robot's dynamic matching and cooperation state is determined to be a moderate fault.

[0116] If the abnormal execution status evaluation parameter is greater than the third preset execution status evaluation threshold, the robot's dynamic matching and collaboration status is determined to be a severe fault.

[0117] It should be noted that the determined abnormal execution status evaluation parameters are compared with the preset execution status evaluation thresholds, and the dynamic matching and cooperation status of the robot is determined based on the threshold range it falls into.

[0118] It is worth mentioning that, according to an embodiment of the present invention, the step of analyzing and processing the task requirement vector and dynamic capability assessment map using a preset cosine similarity algorithm to obtain the corresponding matching degree includes:

[0119] Based on the task requirement vector and dynamic capability assessment map, obtain the capability similarity score, energy efficiency score, and historical reliability score between the robot and the sub-task;

[0120] The corresponding matching degree is obtained by weighting and summing the capability similarity score, energy efficiency score, and historical reliability score.

[0121] It should be noted that the capability similarity score refers to the degree of fit between the robot's capabilities and the requirements of the sub-task. It is obtained by extracting and analyzing parameters from the physical constraint parameters and real-time operating status parameters of the dynamic capability assessment map. For example, the requirements of the rubble rescue sub-task are: slope ≥30° and load ≥40kg. The corresponding capability parameters are extracted from the robot's dynamic capability assessment map and then calculated using cosine similarity. The energy efficiency score is used to evaluate the energy consumption of the robot in performing the sub-task. The higher the score, the lower the energy consumption. The historical reliability score represents the success rate of the robot in performing the same sub-task within a preset historical time period. The higher the score, the higher the success rate. The corresponding weight values ​​are dynamically adjusted by those skilled in the art based on factors such as task priority and environmental complexity.

[0122] This invention also discloses a robot dynamic matching and cooperation system based on capability discovery, including a memory and a processor. The memory includes a robot dynamic matching and cooperation method program based on capability discovery. When the capability discovery-based robot dynamic matching and cooperation method program is executed by the processor, it performs the following steps:

[0123] Construct an integrated ecological collaborative interface set for robots;

[0124] Acquire the robot's physical capability parameters and real-time operating status parameters, construct a map based on the physical capability parameters and real-time operating status parameters, and generate a dynamic capability assessment map of the robot.

[0125] Obtain task requirement instructions, analyze and process them to generate task requirement vectors;

[0126] Matching analysis is performed based on the task requirement vector and dynamic capability assessment map, and the analysis is combined with a preset robot digital twin model to obtain a dynamic resource scheduling strategy.

[0127] According to the dynamic resource scheduling strategy, the robot is controlled to perform actions through the integrated ecological collaborative interface set, and the execution status detection data between the robot and the peripheral device is obtained. The execution status detection data is analyzed and processed to obtain execution status anomaly evaluation parameters.

[0128] The abnormal execution status evaluation parameters are compared with the preset execution status evaluation thresholds, and the dynamic matching and cooperation status of the robot is determined based on the threshold comparison results.

[0129] It should be noted that, to achieve dynamic matching and collaboration among robots, firstly, an integrated ecosystem collaboration interface set for robots is determined by constructing a device driver abstraction layer, a robot capability abstraction layer, an application service abstraction layer, and an ecosystem collaboration bus. Specifically, the device driver abstraction layer encapsulates the underlying protocols of peripherals into a unified driver interface, such as those for elevators, access control systems, and sensors. The robot capability abstraction layer abstracts the movement, grasping, and voice interaction capabilities of robots from different brands into standardized APIs. The application service abstraction layer provides a unified SDK interface for third-party applications such as security, building management, and ERP systems. The ecosystem collaboration bus serves as a unified message bus, thereby enabling data exchange and command distribution between robots, peripherals, and third-party applications. Then, a capability registration protocol is used to automatically upload... The robot's physical capability parameters and real-time operational status parameters are validated and standardized to construct a dynamic capability assessment map. Next, task requirement instructions in natural language from a third-party application are received, parsed using a pre-defined large language model, and feature extraction is performed to construct a task requirement vector. Then, based on the constructed task requirement vector and the dynamic capability assessment map, a cosine similarity algorithm is used to calculate the matching degree using a pre-defined robot digital twin model, generating an initial matching scheme. A twin pre-play is then performed, and a dynamic resource scheduling strategy is output based on the pre-play structure. Finally, based on the task execution flow, the abnormal execution status evaluation parameters between the robot and peripherals are assessed, and the robot's dynamic matching and collaboration status is determined through threshold comparison.

[0130] According to an embodiment of the present invention, the step of acquiring the robot's physical capability parameter data and real-time operating status parameter data, and constructing a map based on the physical capability parameter data and real-time operating status parameter data to generate a dynamic capability evaluation map of the robot includes:

[0131] Acquire the robot's physical capability parameters and real-time operating status parameters. The physical capability parameters include the robot's workspace data, obstacle crossing limit data, response speed and rated load data. The real-time operating status parameters include the robot's real-time battery level and operation record data.

[0132] Based on the workspace data, obstacle crossing capability limit data, response speed and rated load data, parameter calibration and data standardization are performed to generate physical constraint parameters.

[0133] Obtain characteristic data of the robot's working environment type;

[0134] The real-time operating status vector is obtained by weighted fusion processing of the real-time power consumption and operation record data combined with the working environment type feature data.

[0135] The real-time operating state vector is correlated with the physical constraint parameters to generate a dynamic capability assessment map of the robot.

[0136] It should be noted that the robot's capability boundaries are determined through static physical capability parameter data, constructing physical constraint parameters in the physical constraint dimension. Dynamic real-time operating state parameter data reflects real-time adaptability. Combined with the robot's working environment type characteristic data, a real-time operating state vector in the real-time state dimension is constructed. Real-time state influence factors are determined for the constructed physical constraint parameters. For example, if the maximum climbing angle in the physical constraint parameters is 30°, the corresponding real-time state influence factors are the real-time battery level and the motor temperature in the operation record data. The real-time battery level and motor temperature are normalized and then weighted and summed. Then, a two-dimensional matrix including physical constraints and real-time states is constructed with the physical constraint parameters as rows and the real-time operating state vector as columns. The two-dimensional matrix is ​​rendered to generate the final dynamic capability evaluation map of the robot. In this map, the robot's working environment type, such as rainy day or foggy day, is represented by different identifiers, and different weight values ​​are assigned according to different working environment types.

[0137] According to an embodiment of the present invention, the step of obtaining task requirement instructions and analyzing and processing the task requirement instructions to generate a task requirement vector includes:

[0138] Obtain task requirement instructions;

[0139] Based on the task requirement instructions, the subtask set is obtained by analyzing and processing the data through a preset subtask decomposition model.

[0140] Based on the subtask set, feature extraction is performed to obtain the spatiotemporal constraint feature data, task capability requirement data and task priority corresponding to the subtask;

[0141] Data processing is performed based on the spatiotemporal constraint feature data, task capability requirement data, and task priority to generate a task requirement vector.

[0142] It should be noted that, firstly, the task requirement instructions in natural language are received and parsed using a pre-built large language model to obtain a set of subtasks. Then, the spatiotemporal constraint feature data, task capability requirement data, and task priority corresponding to the subtasks are extracted. The spatiotemporal constraint feature data includes the execution time window and spatial path restrictions, and the task capability requirement data includes motion accuracy, load capacity, and environmental adaptation requirements. Finally, a task requirement vector is constructed. The pre-set subtask decomposition model is obtained by training a large number of historical samples of task requirement instructions and corresponding subtask sets.

[0143] According to an embodiment of the present invention, the step of performing matching analysis based on the task requirement vector and dynamic capability assessment map, and combining it with a preset robot digital twin model for analysis and processing to obtain a dynamic resource scheduling strategy includes:

[0144] Based on the task requirement vector and dynamic capability assessment map, the corresponding matching degree is obtained by analyzing and processing them using a preset cosine similarity algorithm.

[0145] The matching scores are sorted in descending order, and the matching scheme with the highest matching score is determined as the initial matching scheme.

[0146] Based on the initial matching scheme, a twin simulation verification is performed using a preset robot digital twin model;

[0147] If a path conflict or insufficient capability matching is determined, the preset subtask decomposition model is optimized.

[0148] If the path is determined to be normal and the capacity is sufficient, then the initial matching scheme is determined to be a dynamic resource scheduling strategy.

[0149] It should be noted that, based on the determined task requirement vector and dynamic capability assessment map, the matching degree of the sub-tasks is obtained through analysis using a preset cosine similarity algorithm. The matching scheme with the highest matching degree is determined as the initial matching scheme. The initial matching scheme is pre-performed and verified in a virtual twin environment. If there are resource conflicts or capability mismatches, the preset sub-task decomposition model is triggered for optimization, the scheme is re-optimized, and the simulation is repeated to verify the results. Finally, a dynamic resource scheduling strategy is output. The preset cosine similarity algorithm and the preset robot digital twin model are pre-constructed by those skilled in the art and can be dynamically adjusted.

[0150] According to an embodiment of the present invention, the step of controlling the robot to perform actions through the ecological integrated collaborative interface set according to the dynamic resource scheduling strategy, acquiring execution status detection data between the robot and peripheral devices, and analyzing and processing the execution status detection data to obtain execution status anomaly evaluation parameters includes:

[0151] According to the dynamic resource scheduling strategy, the robot is controlled to perform actions through the ecological integrated collaborative interface set, and the execution status detection data between the robot and peripheral devices is obtained, including power system status data, motion control status data, perception system status data, communication system status data, load execution status data and environmental interaction status data.

[0152] The preset number of power system status data, motion control status data, perception system status data, communication system status data, load execution status data and environmental interaction status data within a preset time period are input into a preset robot abnormal state prediction model for time-series abnormality detection, and the robot's operational abnormality assessment prediction value is obtained.

[0153] The preset number of power system status data, motion control status data, perception system status data, communication system status data, load execution status data and environmental interaction status data within a preset time period are input into a preset robot abnormal state multi-parameter correlation prediction model for parameter correlation analysis to obtain robot operation abnormality evaluation parameters.

[0154] The execution status anomaly evaluation parameters are obtained by weighted summation of the predicted execution anomaly assessment values ​​and the execution anomaly evaluation parameters.

[0155] It should be noted that, in order to achieve closed-loop verification of the dynamic resource scheduling strategy, execution status detection data is collected in real time during robot execution. This includes power system status data, motion control status data, perception system status data, communication system status data, load execution status data, and environmental interaction status data. Specifically, power system status data includes motor current, motor temperature, battery charge, and battery voltage; motion control status data includes running speed, joint speed, motion error, and attitude angle; perception system status data includes sensor accuracy and sensor temperature; communication system status data includes communication latency, packet loss rate, and signal strength; load execution status data includes robotic arm load, gripping force, and actuator stroke; and environmental interaction status data includes ambient temperature, humidity, and obstacle distance. A preset robot abnormal state prediction model is used to detect temporal anomalies within a preset time period. The system obtains predicted values ​​for robot operation anomalies. Simultaneously, it performs parameter correlation analysis through a pre-set multi-parameter correlation prediction model for robot anomalies to obtain robot operation anomaly evaluation parameters. These parameters are then weighted and summed to obtain execution state anomaly evaluation parameters. The pre-set robot anomaly prediction model is trained using a large amount of historical sample data on the power system state, motion control state, perception system state, communication system state, load execution state, and environmental interaction state, along with the corresponding predicted operation anomaly values.

[0156] According to an embodiment of the present invention, the step of comparing the execution state anomaly evaluation parameters with a preset execution state evaluation threshold, and determining the robot's dynamic matching and cooperation state based on the threshold comparison result, includes:

[0157] The execution state anomaly evaluation parameters are compared with preset execution state evaluation thresholds, wherein the preset execution state evaluation thresholds include a first preset execution state evaluation threshold, a second preset execution state evaluation threshold, and a third preset execution state evaluation threshold.

[0158] If the abnormal execution state evaluation parameter is less than or equal to the first preset execution state evaluation threshold, then the robot's dynamic matching and collaboration state is determined to be normal.

[0159] If the abnormal execution state evaluation parameter is greater than the first preset execution state evaluation threshold and less than or equal to the second preset execution state evaluation threshold, then the robot's dynamic matching and collaboration state is determined to be a minor fault.

[0160] If the abnormal execution state evaluation parameter is greater than the second preset execution state evaluation threshold and less than or equal to the third preset execution state evaluation threshold, then the robot's dynamic matching and cooperation state is determined to be a moderate fault.

[0161] If the abnormal execution status evaluation parameter is greater than the third preset execution status evaluation threshold, the robot's dynamic matching and collaboration status is determined to be a severe fault.

[0162] It should be noted that the determined abnormal execution status evaluation parameters are compared with the preset execution status evaluation thresholds, and the dynamic matching and cooperation status of the robot is determined based on the threshold range it falls into.

[0163] It is worth mentioning that, according to an embodiment of the present invention, the step of analyzing and processing the task requirement vector and dynamic capability assessment map using a preset cosine similarity algorithm to obtain the corresponding matching degree includes:

[0164] Based on the task requirement vector and dynamic capability assessment map, obtain the capability similarity score, energy efficiency score, and historical reliability score between the robot and the sub-task;

[0165] The corresponding matching degree is obtained by weighting and summing the capability similarity score, energy efficiency score, and historical reliability score.

[0166] It should be noted that the capability similarity score refers to the degree of fit between the robot's capabilities and the requirements of the sub-task. It is obtained by extracting and analyzing parameters from the physical constraint parameters and real-time operating status parameters of the dynamic capability assessment map. For example, the requirements of the rubble rescue sub-task are: slope ≥30° and load ≥40kg. The corresponding capability parameters are extracted from the robot's dynamic capability assessment map and then calculated using cosine similarity. The energy efficiency score is used to evaluate the energy consumption of the robot in performing the sub-task. The higher the score, the lower the energy consumption. The historical reliability score represents the success rate of the robot in performing the same sub-task within a preset historical time period. The higher the score, the higher the success rate. The corresponding weight values ​​are dynamically adjusted by those skilled in the art based on factors such as task priority and environmental complexity.

[0167] This invention discloses a robot dynamic matching and collaboration method and system based on capability discovery. By constructing a multi-layer interface abstract architecture, relying on a dynamic capability discovery mechanism, constructing a dynamic capability map and task requirement vector, and intelligently matching dynamic resource scheduling strategies and evaluating execution feedback to form a closed-loop processing, thereby realizing robot dynamic matching and collaboration based on capability discovery.

[0168] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be electrical, mechanical, or other forms.

[0169] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units. They may be located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of this embodiment according to actual needs.

[0170] In addition, in the various embodiments of the present invention, each functional unit can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0171] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0172] Alternatively, if the integrated units of this invention are implemented as software functional modules and sold or used as independent products, they can also be stored in a readable storage medium. Based on this understanding, the technical solutions of the embodiments of this invention, or the parts that contribute to the prior art, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROM, RAM, magnetic disks, or optical disks.

Claims

1. A method for dynamic matching and cooperation of robots based on capability discovery, characterized in that, Includes the following steps: Construct an integrated ecological collaborative interface set for robots; Acquire the robot's physical capability parameters and real-time operating status parameters, construct a map based on the physical capability parameters and real-time operating status parameters, and generate a dynamic capability assessment map of the robot. Obtain task requirement instructions, analyze and process them to generate task requirement vectors; Matching analysis is performed based on the task requirement vector and dynamic capability assessment map, and the analysis is combined with a preset robot digital twin model to obtain a dynamic resource scheduling strategy. According to the dynamic resource scheduling strategy, the robot is controlled to perform actions through the integrated ecological collaborative interface set, and the execution status detection data between the robot and the peripheral device is obtained. The execution status detection data is analyzed and processed to obtain execution status anomaly evaluation parameters. The abnormal execution status evaluation parameters are compared with the preset execution status evaluation thresholds, and the dynamic matching and cooperation status of the robot is determined based on the threshold comparison results.

2. The robot dynamic matching and cooperation method based on capability discovery according to claim 1, characterized in that, The process of acquiring the robot's physical capability parameters and real-time operating status parameters, and constructing a dynamic capability assessment map based on these parameters to generate the robot's dynamic capability assessment map includes: Acquire the robot's physical capability parameters and real-time operating status parameters. The physical capability parameters include the robot's workspace data, obstacle crossing limit data, response speed and rated load data. The real-time operating status parameters include the robot's real-time battery level and operation record data. Based on the workspace data, obstacle crossing capability limit data, response speed and rated load data, parameter calibration and data standardization are performed to generate physical constraint parameters. Obtain characteristic data of the robot's working environment type; The real-time operating status vector is obtained by weighted fusion processing of the real-time power consumption and operation record data combined with the working environment type feature data. The real-time operating state vector is correlated with the physical constraint parameters to generate a dynamic capability assessment map of the robot.

3. The robot dynamic matching and cooperation method based on capability discovery according to claim 2, characterized in that, The process of obtaining task requirement instructions, analyzing and processing them to generate a task requirement vector includes: Obtain task requirement instructions; Based on the task requirement instructions, the subtask set is obtained by analyzing and processing the data through a preset subtask decomposition model. Based on the subtask set, feature extraction is performed to obtain the spatiotemporal constraint feature data, task capability requirement data and task priority corresponding to the subtask; Data processing is performed based on the spatiotemporal constraint feature data, task capability requirement data, and task priority to generate a task requirement vector.

4. The robot dynamic matching and cooperation method based on capability discovery according to claim 3, characterized in that, The process of matching and analyzing the task requirement vector and dynamic capability assessment map, combined with a preset robot digital twin model, to obtain a dynamic resource scheduling strategy includes: Based on the task requirement vector and dynamic capability assessment map, the corresponding matching degree is obtained by analyzing and processing them using a preset cosine similarity algorithm. The matching scores are sorted in descending order, and the matching scheme with the highest matching score is determined as the initial matching scheme. Based on the initial matching scheme, a twin simulation verification is performed using a preset robot digital twin model; If a path conflict or insufficient capability matching is determined, the preset subtask decomposition model is optimized. If the path is determined to be normal and the capacity is sufficient, then the initial matching scheme is determined to be a dynamic resource scheduling strategy.

5. The robot dynamic matching and cooperation method based on capability discovery according to claim 4, characterized in that, The process involves controlling the robot to perform actions through the integrated ecological collaboration interface set according to the dynamic resource scheduling strategy, acquiring execution status detection data between the robot and peripherals, analyzing and processing the execution status detection data to obtain execution status anomaly evaluation parameters, including: According to the dynamic resource scheduling strategy, the robot is controlled to perform actions through the integrated ecological collaborative interface set, and the execution status detection data between the robot and peripheral devices is obtained, including power system status data, motion control status data, perception system status data, communication system status data, load execution status data and environmental interaction status data. The preset number of power system status data, motion control status data, perception system status data, communication system status data, load execution status data and environmental interaction status data within a preset time period are input into a preset robot abnormal state prediction model for time-series abnormality detection, and the robot's operational abnormality assessment prediction value is obtained. The preset number of power system status data, motion control status data, perception system status data, communication system status data, load execution status data and environmental interaction status data within a preset time period are input into a preset robot abnormal state multi-parameter correlation prediction model for parameter correlation analysis to obtain robot operation abnormality evaluation parameters. The execution status anomaly evaluation parameters are obtained by weighted summation of the predicted execution anomaly assessment values ​​and the execution anomaly evaluation parameters.

6. The robot dynamic matching and cooperation method based on capability discovery according to claim 5, characterized in that, The step of comparing the abnormal execution state evaluation parameters with a preset execution state evaluation threshold, and determining the robot's dynamic matching and cooperation state based on the threshold comparison result, includes: The execution state anomaly evaluation parameters are compared with preset execution state evaluation thresholds, wherein the preset execution state evaluation thresholds include a first preset execution state evaluation threshold, a second preset execution state evaluation threshold, and a third preset execution state evaluation threshold. If the abnormal execution state evaluation parameter is less than or equal to the first preset execution state evaluation threshold, then the robot's dynamic matching and collaboration state is determined to be normal. If the abnormal execution state evaluation parameter is greater than the first preset execution state evaluation threshold and less than or equal to the second preset execution state evaluation threshold, then the robot's dynamic matching and cooperation state is determined to be a minor fault. If the abnormal execution state evaluation parameter is greater than the second preset execution state evaluation threshold and less than or equal to the third preset execution state evaluation threshold, then the robot's dynamic matching and cooperation state is determined to be a moderate fault. If the abnormal execution status evaluation parameter is greater than the third preset execution status evaluation threshold, the robot's dynamic matching and collaboration status is determined to be a severe fault.

7. A robot dynamic matching and cooperation system based on capability discovery, characterized in that, The system includes a memory and a processor. The memory contains a program for a capability-based robot dynamic matching and cooperation method. When the program for the capability-based robot dynamic matching and cooperation method is executed by the processor, it performs the following steps: Construct an integrated ecological collaborative interface set for robots; Acquire the robot's physical capability parameters and real-time operating status parameters, construct a map based on the physical capability parameters and real-time operating status parameters, and generate a dynamic capability assessment map of the robot. Obtain task requirement instructions, analyze and process them to generate task requirement vectors; Matching analysis is performed based on the task requirement vector and dynamic capability assessment map, and the analysis is combined with a preset robot digital twin model to obtain a dynamic resource scheduling strategy. According to the dynamic resource scheduling strategy, the robot is controlled to perform actions through the integrated ecological collaborative interface set, and the execution status detection data between the robot and the peripheral device is obtained. The execution status detection data is analyzed and processed to obtain execution status anomaly evaluation parameters. The abnormal execution status evaluation parameters are compared with the preset execution status evaluation thresholds, and the dynamic matching and cooperation status of the robot is determined based on the threshold comparison results.

8. The robot dynamic matching and cooperation system based on capability discovery according to claim 7, characterized in that, The process of acquiring the robot's physical capability parameters and real-time operating status parameters, and constructing a dynamic capability assessment map based on these parameters to generate the robot's dynamic capability assessment map includes: Acquire the robot's physical capability parameters and real-time operating status parameters. The physical capability parameters include the robot's workspace data, obstacle crossing limit data, response speed and rated load data. The real-time operating status parameters include the robot's real-time battery level and operation record data. Based on the workspace data, obstacle crossing capability limit data, response speed and rated load data, parameter calibration and data standardization are performed to generate physical constraint parameters. Obtain characteristic data of the robot's working environment type; The real-time operating status vector is obtained by weighted fusion processing of the real-time power consumption and operation record data combined with the working environment type feature data. The real-time operating state vector is correlated with the physical constraint parameters to generate a dynamic capability assessment map of the robot.

9. The robot dynamic matching and cooperation system based on capability discovery according to claim 8, characterized in that, The process of obtaining task requirement instructions, analyzing and processing them to generate a task requirement vector includes: Obtain task requirement instructions; Based on the task requirement instructions, the subtask set is obtained by analyzing and processing the data through a preset subtask decomposition model. Based on the subtask set, feature extraction is performed to obtain the spatiotemporal constraint feature data, task capability requirement data and task priority corresponding to the subtask; Data processing is performed based on the spatiotemporal constraint feature data, task capability requirement data, and task priority to generate a task requirement vector.

10. The robot dynamic matching and cooperation system based on capability discovery according to claim 9, characterized in that, The process of matching and analyzing the task requirement vector and dynamic capability assessment map, combined with a preset robot digital twin model, to obtain a dynamic resource scheduling strategy includes: Based on the task requirement vector and dynamic capability assessment map, the corresponding matching degree is obtained by analyzing and processing them using a preset cosine similarity algorithm. The matching scores are sorted in descending order, and the matching scheme with the highest matching score is determined as the initial matching scheme. Based on the initial matching scheme, a twin simulation verification is performed using a preset robot digital twin model; If a path conflict or insufficient capability matching is determined, the preset subtask decomposition model is optimized. If the path is determined to be normal and the capacity is sufficient, then the initial matching scheme is determined to be a dynamic resource scheduling strategy.

Images