Scene adaptation configuration method and device, scene matching scheduling method and device and scheduling instruction generation method and device

Abstract

The invention discloses a scene adaptation configuration method and device, a scene matching scheduling method and device and a scheduling instruction generation method and device, and the method comprises the steps: obtaining first configuration information of a target robot; determining a configuration strategy based on the difference between the first configuration information and a target configuration demand in a target scene task; and issuing the configuration strategy to the target robot, wherein the configuration strategy is used for the target robot to perform configuration updating so as to adapt to the target scene task.

Description

Technical Field

[0001] This application relates to the field of system scheduling technology, and in particular to a method and apparatus for scene adaptation configuration, scene matching scheduling, and scheduling instruction generation. Background Technology

[0002] Robot scheduling technology is a key component in achieving efficient operation of automated work systems, improving overall operational efficiency through the rational allocation of tasks and resources. With the widespread application of humanoid robots and heterogeneous robot systems, flexible and intelligent scenario matching and scheduling of robots has become a major focus in the industry. Related technologies typically employ fixed-configuration scheduling methods, pre-setting robot functions and task instructions for specific scenarios. However, such methods rely on pre-defined rules and manual operation, failing to dynamically adjust based on the robot's current capabilities and status. Furthermore, they lack support for flexible scheduling of "one robot, multiple roles" and heterogeneous robot collaboration, hindering rapid response to new task demands and impacting system flexibility and intelligence. Summary of the Invention

[0003] To address the aforementioned technical problems, embodiments of the present invention provide a method and apparatus for scene adaptation configuration, scene matching scheduling, and scheduling instruction generation.

[0004] The scenario adaptation configuration method provided in this application includes: Obtain the initial configuration information of the target robot; Based on the difference between the first configuration information and the target configuration requirements in the target scenario task, a configuration strategy is determined; The configuration strategy is sent to the target robot, and the configuration strategy is used by the target robot to update its configuration to adapt to the target scenario task.

[0005] The scene matching and scheduling method provided in this application includes: Obtain first identification information of one or more robots, wherein the first identification information includes second configuration information of the one or more robots; Based on the target configuration requirements in the target scenario task and the first identification information of the one or more robots, a scheduling decision is made to obtain a collaborative scheduling strategy.

[0006] The scheduling instruction generation method provided in this application includes: Obtain the initial configuration information of the target robot; The scheduling instruction is determined based on the first configuration information; The scheduling instruction is issued to the target robot, which instructs the target robot to perform a target scenario task.

[0007] The scenario adaptation configuration device provided in this application embodiment includes: The first acquisition unit is used to acquire the first configuration information of the target robot; The first determining unit is used to determine a configuration strategy based on the difference between the first configuration information and the target configuration requirements in the target scenario task; The first sending unit is used to send the configuration strategy to the target robot, and the configuration strategy is used by the target robot to update its configuration to adapt to the target scenario task.

[0008] The scene matching and scheduling device provided in this application embodiment includes: The second acquisition unit is used to acquire first identification information of one or more robots, wherein the first identification information includes second configuration information of the one or more robots; The second processing unit is used to make scheduling decisions based on the target configuration requirements in the target scenario task and the first identification information of the one or more robots, and to obtain a collaborative scheduling strategy.

[0009] The scheduling instruction generation apparatus provided in this application includes: The third acquisition unit is used to acquire the first configuration information of the target robot; The third determining unit is used to determine the scheduling instruction based on the first configuration information; The third sending unit is used to send the scheduling instruction to the target robot, the scheduling instruction being used to instruct the target robot to perform a target scene task.

[0010] The cross-scene and cross-robot scheduling system provided in this application includes: the above-mentioned scene adaptation configuration device, the above-mentioned scene matching scheduling device, and the above-mentioned scheduling instruction generation device.

[0011] The processing device provided in this application embodiment includes: a processor and a memory, the memory being used to store computer programs, and the processor being used to call and run the computer programs stored in the memory to execute any of the above-described scene adaptation configuration methods, scene matching scheduling methods, or scheduling instruction generation methods.

[0012] The computer-readable storage medium provided in this application embodiment is used to store a computer program that causes a computer to execute any of the above-described scenario adaptation configuration method, scenario matching scheduling method, or scheduling instruction generation method.

[0013] The computer program product provided in this application includes computer program instructions that cause a computer to execute any of the above-described scenario adaptation configuration methods, scenario matching scheduling methods, or scheduling instruction generation methods.

[0014] In the technical solution of this application embodiment, by obtaining the first configuration information of the target robot and determining a configuration strategy based on the difference between the first configuration information and the target configuration requirements in the target scenario task, a configuration strategy is issued to the target robot. The configuration strategy is used by the target robot to update its configuration to adapt to the target scenario task. Thus, by obtaining the first configuration information of the target robot and comparing it with the target configuration requirements in the target scenario task, a corresponding configuration strategy is generated based on the difference between the two. This configuration strategy can guide the target robot to flexibly adjust its own configuration, thereby quickly adapting to the target scenario task. This method not only improves the robot's adaptability to different scenarios and enables flexible scheduling of multiple roles, but also improves the system's flexibility and intelligence level. Attached Figure Description

[0015] Figure 1 This is a flowchart illustrating the scenario adaptation configuration method provided in the embodiments of this application; Figure 2 This is a flowchart illustrating the scene matching and scheduling method provided in the embodiments of this application; Figure 3 This is a flowchart illustrating the scheduling instruction generation method provided in an embodiment of this application; Figure 4 This is a flowchart illustrating a robot scene adaptation scheduling, dynamic function configuration, and instruction adaptive method provided in an embodiment of this application. Figure 5 This is a schematic diagram of the scene adaptation configuration device provided in the embodiments of this application; Figure 6 This is a schematic diagram of the scene matching and scheduling device provided in the embodiments of this application; Figure 7 This is a schematic diagram of the scheduling instruction generation device provided in the embodiments of this application; Figure 8 This is a schematic diagram of the cross-scenario, cross-robot scheduling system provided in the embodiments of this application; Figure 9 This is a schematic diagram of the processing device provided in the embodiments of this application. Detailed Implementation

[0016] The technical solutions of the embodiments of this application will now be described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0017] To facilitate understanding of the technical solutions of the embodiments of this application, the relevant technologies of the embodiments of this application are described below. The following relevant technologies are optional solutions and can be combined with the technical solutions of the embodiments of this application in any way, and they all fall within the protection scope of the embodiments of this application.

[0018] With the continuous development of humanoid robot technology, single-function robots are gradually becoming unable to meet the diverse task requirements. Currently, robots in traditional industries are mostly focused on specific functions, such as AGVs for material handling or robotic arms for picking. The emergence of more general-purpose and multi-functional robots, represented by humanoid robots, has provided new possibilities for realizing multiple roles with a single machine and has shown broad application prospects in logistics, manufacturing, and other fields.

[0019] Despite breakthroughs in some scenarios, shortcomings remain in areas such as flexible robot scheduling and heterogeneous collaboration. For example, robots in fixed environments struggle to quickly adapt to new task requirements; manual robot configuration is cumbersome and error-prone; and the system's instruction format does not differentiate based on the intelligence level of each robot, resulting in low instruction issuance efficiency. In related technologies, traditional robots are often designed for single functions, making it difficult to quickly adapt to different task requirements. Furthermore, manual configuration is inefficient and prone to errors. Additionally, the system's instruction format does not consider differences in robot intelligence level identifiers, leading to poor instruction compatibility and impacting the collaborative operation capabilities of heterogeneous robots.

[0020] To address the aforementioned technical challenges, this application proposes a scenario-matching scheduling method. This method acquires robot identification and status information, and dynamically matches it with scenario requirements to generate corresponding configuration strategies and scheduling instructions. This enables robots to flexibly adapt to different scenarios and operate efficiently. This approach not only enhances the task adaptability of robot clusters but also supports "one robot, multiple roles" and "heterogeneous robots within a single system," significantly improving equipment utilization and system intelligence.

[0021] To facilitate understanding of the technical solutions of the embodiments of this application, the technical solutions of this application are described in detail below through specific embodiments. The above-mentioned related technologies are optional solutions and can be arbitrarily combined with the technical solutions of the embodiments of this application, all of which fall within the protection scope of the embodiments of this application. The embodiments of this application include at least some of the following contents.

[0022] This application proposes a scenario-adaptive configuration method, which can be applied to a cross-scenario, cross-robot scheduling system. The cross-scenario, cross-robot scheduling system can be a cloud server, an edge computing device, or a robot control center. Figure 1 This is a flowchart illustrating the scenario adaptation configuration method provided in the embodiments of this application. Figure 1 ,like Figure 1 As shown, the method includes the following steps: Step 101: Obtain the first configuration information of the target robot.

[0023] In this embodiment, the system can obtain the first configuration information of the target robot from the data reported by the target robot. The first configuration information represents the current configuration of the target robot (a set of all hardware, software, and functional attributes it possesses at a given moment), including hardware configuration parameters, software configuration parameters, and intelligence level identifiers. For example, hardware configuration parameters may include the type of end effector (such as a gripper, suction cup, or welding torch), sensor configuration (such as 3D vision or barcode scanning modules), and chassis configuration (such as a fixed or mobile chassis and its load-bearing capacity). Software configuration parameters may include supported algorithm module versions, such as path planning V2.0 or object recognition V1.0. The intelligence level identifier indicates the target robot's autonomous decision-making capability level, for example, divided into three levels: L1, L2, and L3. An L1-level target robot can only execute preset actions (atomic instructions), an L2-level target robot has simple environmental adaptation capabilities and can execute simple task actions, and an L3-level target robot can perform multi-objective autonomous decision-making.

[0024] Step 102: Determine the configuration strategy based on the difference between the first configuration information and the target configuration requirements in the target scenario task.

[0025] In this embodiment, the first configuration information of the target robot can be compared and analyzed with the target configuration requirements (such as tool specifications) in the target scenario task. The differences (or matching degree) between the two can be analyzed, and a series of specific configuration operation suggestions can be generated based on the degree of difference between the two to form a configuration strategy. For example, in a logistics handling scenario, the target configuration requirement may require the target robot to be equipped with a smart chassis with a strong load-bearing capacity. If the target robot is not currently equipped with a chassis or the load-bearing capacity of the currently equipped chassis does not meet the load-bearing capacity required by the target configuration requirement, the scheduling system will generate a configuration strategy to add a smart chassis with a strong load-bearing capacity (such as 10kg) or replace it with a smart chassis with a stronger load-bearing capacity (such as from 5kg to 10kg).

[0026] Among them, the target configuration requirements include the configuration requirements explicitly indicated in the target scenario task (explicit requirements), and / or the configuration requirements implied in the target scenario task (implicit requirements). Implicit requirements are configuration requirements that are implicit in the scenario, task logic, general constraints or default rules, must be met but are not directly stated.

[0027] Based on this, the differences between the first configuration information and the target configuration requirements in the target scenario task also include: Based on the matching degree between the first configuration information and the target scenario task, the difference between the first configuration information and the target configuration requirements in the target scenario task is determined.

[0028] In some embodiments, the first configuration information includes hardware configuration parameters and / or software configuration parameters.

[0029] Hardware configuration parameters refer to the set of parameters describing the physical components and functional characteristics of the target robot, such as the type of end effector (gripper, suction cup, welding torch), the type of sensor (3D vision, barcode scanning module), and the chassis structure (fixed / mobile). These parameters determine the basic capability range of the target robot for a specific task. For example, a target robot with a high-precision gripper can perform precision assembly operations, while a target robot equipped with a heavy-duty chassis is suitable for material handling scenarios.

[0030] Software configuration parameters refer to a set of parameters describing the algorithm modules and their version information that the target robot relies on for operation, such as the path planning algorithm version and the object recognition algorithm version. These parameters affect the intelligence and flexibility of the target robot during task execution. For example, the obstacle avoidance algorithm in version 4.0 can support more complex dynamic obstacle avoidance compared to version 1.0.

[0031] In some embodiments, the configuration strategy includes configuration targets and / or configuration rules and / or configuration paths.

[0032] The configuration target refers to the expected configuration state determined by the system based on the gap between the current configuration state of the target robot and the target configuration requirements. Configuration targets may include hardware upgrades, software updates, and functional expansions. For example, when switching from picking mode to handling mode, configuration targets might include replacing grippers with ones that have a larger load capacity or loading new navigation algorithms.

[0033] Configuration rules refer to a series of logical judgments and control rules formulated by the system based on the task type and / or tool specifications and / or environmental constraint parameters in the target configuration requirements during the process of achieving the configuration goal. For example, when the task type is precision assembly, the configuration rules may require the use of high-precision grippers and require the vibration compensation mechanism to be turned off to avoid interference with the assembly process.

[0034] The configuration path refers to the software and hardware change process and / or robot movement path and / or pose changes of the robot's own components planned by the system to implement configuration rules. The software and hardware change process includes the download and installation order of software and hardware modules, and the robot movement path includes the route taken by the target robot to the designated workstation for hardware replacement. For example, the target robot can first update the navigation algorithm via OTA, then move to the workstation to replace the gripper, and finally perform a self-test to confirm that the configuration is complete.

[0035] In some embodiments, step 102 includes one or more of the following: Step 1021: Determine the configuration target based on the configuration differences between the hardware configuration parameters and / or software configuration parameters and the target configuration requirements.

[0036] In this embodiment, the configuration differences between the target robot's current hardware and / or software configuration parameters and the target configuration requirements can be analyzed to identify the mismatch between the target robot's current hardware and / or software configuration capabilities and the specific capabilities required by the target configuration requirements. Based on this mismatch, the capability standards that the target robot needs to achieve are formulated, forming a configuration target. For example, if the gripper currently equipped on the target robot only supports a gripping accuracy of ±5mm, while the assembly task requires the gripper to achieve a gripping accuracy of ±0.1mm, then the configuration target can be determined as replacing it with a higher precision gripper.

[0037] Step 1022: Extract the task type and / or tool specification and / or environment constraint parameters from the target configuration requirements based on the configuration goal, and determine the configuration rules based on the task type and / or tool specification and / or environment constraint parameters.

[0038] Here, the task type in the target configuration requirements refers to the type of work the target robot needs to perform, such as sorting, handling, and assembly. Different task types have different requirements for the robot's capabilities. Tool specifications refer to the specific tool models and functional parameters required to perform the target scenario task, such as ±0.1mm precision grippers and adaptive vacuum suction cups. Environmental constraint parameters refer to the external conditions that must be considered during the execution of the target scenario task, such as light intensity, ground flatness, and space limitations.

[0039] In this embodiment of the application, the task type and / or tool specifications and / or environmental constraint parameters in the target configuration requirements can be extracted according to the configuration target, and the specific configuration adjustment content that the target robot needs to perform can be formulated according to the task type and / or tool specifications and / or environmental constraint parameters, thus forming configuration rules.

[0040] Step 1023: Based on the configuration rules, plan the configuration order and / or movement path and / or pose of the target robot to obtain the configuration path.

[0041] In this embodiment, the required configuration update order (such as the order of software and hardware changes) and / or the required movement path and / or the required pose adjustment of the target robot can be planned according to the specific configuration adjustment content in the configuration rules. This results in a physical movement route and / or pose adjustment content that enables the target robot to complete the configuration update, forming a configuration path. For example, the configuration path may include first guiding the target robot to workstation 3 to replace the gripper, then adjusting the orientation of the gripper in the target robot, and then guiding the target robot to upgrade area B3 to complete the OTA software update.

[0042] In some embodiments, the above method further includes: Step S1: Obtain the state information of the target robot.

[0043] In this embodiment, the scheduling system can also obtain status information reported by the target robot to reflect its working capacity and availability. The target robot's status information includes current task progress (e.g., currently performing handling, assembly, or waiting for scheduling), remaining battery power, presence of fault codes, sensor functionality, and end effector readiness.

[0044] Step S2: Determine the configuration strategy based on the difference between the first configuration information and / or status information and the target configuration requirements.

[0045] In this embodiment of the application, the scheduling system can also compare and analyze the first configuration information and / or status information of the target robot with the target configuration requirements (such as task type, tool specifications, environmental constraint parameters) in the target scenario task, analyze the differences between the first configuration information and / or status information and the target configuration requirements, and generate a series of specific configuration operation suggestions based on the degree of difference to form a configuration strategy.

[0046] For example, if the target robot is currently configured with a precision gripper and a fixed workstation, and the target robot has sufficient battery power, but the target scenario requires a heavy-duty mobile chassis and obstacle avoidance algorithm, the scheduling system will generate a comprehensive configuration strategy that includes hardware replacement, software upgrades, and path planning parameter adjustments, and guide the target robot to the designated station for configuration updates.

[0047] By introducing the target robot's state information as a key input for dynamic configuration decisions, we can more accurately assess the matching degree between the target robot's current capabilities and state and the target scenario task, thereby generating a more targeted configuration strategy and reducing ineffective scheduling and resource waste.

[0048] In some embodiments, step S2 includes one or more of the following: Step S21: Determine the configuration target based on the configuration differences and / or status differences between the hardware configuration parameters and / or software configuration parameters and / or status information and the target configuration requirements.

[0049] In this embodiment, the configuration and state differences between the target robot's current hardware configuration parameters and / or software configuration parameters and / or status information and the target configuration requirements can be analyzed to obtain the mismatch between the target robot's current hardware configuration capabilities and / or software configuration capabilities and / or current operating status and the specific capabilities required by the target configuration requirements. Based on this mismatch, the capability standards that the target robot needs to achieve are formulated, forming configuration targets. For example, if the target robot's current gripper only supports a grasping accuracy of ±5mm, and the target robot's current battery level is less than a preset threshold and a fault code indicates that a key component is damaged, while the assembly task requires the gripper to achieve a grasping accuracy of ±0.1mm, and operating a gripper with a ±0.1mm grasping accuracy requires a battery level greater than a preset threshold and the support of key components, then the configuration targets can be determined as replacing the battery or charging the battery, replacing the damaged key component, and replacing the gripper with one of higher precision.

[0050] Step S22: Extract the task type and / or tool specification and / or environmental constraint parameters from the target configuration requirements based on the configuration target, and determine the configuration rules based on the status information and / or task type and / or tool specification and / or environmental constraint parameters.

[0051] In this embodiment, the task type and / or tool specifications and / or environmental constraint parameters in the target configuration requirements can be extracted based on the configuration goal. Then, based on the current operating status of the target robot and / or the task type and / or tool specifications and / or environmental constraint parameters in the target configuration requirements, specific configuration adjustments that the target robot needs to perform are formulated, forming configuration rules. These configuration rules determine the specific measures the target robot should take during the configuration update process, such as which precision gripper to replace, which version of the recognition algorithm module to update or download, which type of battery to replace, and how much to charge the battery to.

[0052] Step S23: Based on configuration rules and / or status information, plan the configuration sequence and / or movement path and / or pose of the target robot to obtain the configuration path.

[0053] In this embodiment, the configuration order (such as the order of software and hardware changes) and / or the required movement path and / or the required pose adjustment of the target robot can be planned according to the specific configuration adjustment content in the configuration rules and / or the current operating state of the target robot. This results in a physical movement route and / or pose adjustment content that enables the target robot to complete the configuration update, forming a configuration path. For example, the configuration path may include first guiding the target robot to the nearest charging station to charge to a preset threshold, then guiding the target robot to workstation 3 to replace the gripper, then adjusting the orientation of the gripper in the target robot, and finally guiding the target robot to upgrade area B3 to complete the OTA software update.

[0054] The above methods enable refined management and automated scheduling of target robot configurations, thereby responding to changing task requirements and improving the robot's overall task adaptability and operational efficiency.

[0055] Step 103: Send the configuration strategy to the target robot. The configuration strategy is used by the target robot to update its configuration to adapt to the target scenario task.

[0056] In this embodiment, the scheduling system distributes the generated configuration strategy to the target robot, enabling it to perform relevant configuration update operations. The configuration update can be performed remotely automatically (e.g., OTA upgrade), semi-automatically (e.g., the robot guides personnel to replace hardware), or completely manually (e.g., a technician manually replaces the gripper). The specific content of the configuration strategy determines how the target robot responds. For example, if the configuration strategy is to load a new version of the path planning algorithm, the target robot will initiate a software update process; if the configuration strategy is to replace the gripper, the target robot may navigate to a designated replacement point, wait for the replacement to complete, and then continue performing its self-check task.

[0057] In practice, the scheduling system determines whether additional manual assistance is needed based on the complexity of the configuration strategy and the execution method. For simple software updates, the scheduling system can directly push the update package and trigger execution; while for complex hardware replacements, the scheduling system generates a guidance path and notifies personnel to go to the replacement site to assist in the operation, thereby improving configuration efficiency while ensuring security.

[0058] In some embodiments, the configuration policy type includes one or more of the following: Software updates, which can be performed remotely on the target robot and / or upgrade its functionality. Hardware replacement can be performed by guiding the target robot to a workstation for manual or automatic hardware replacement. Instruction set switching is performed by sending a switching instruction set to the target robot to adapt to the target scenario task.

[0059] Specifically, software updates refer to pushing new software versions or functional modules to the target robot via wireless or wired connections to enhance functionality, optimize performance, or fix vulnerabilities. Remote updates can be completed without interrupting the robot's operation, avoiding the efficiency losses associated with traditional manual downtime maintenance. Functional upgrades, on the other hand, add new capabilities or expand the scope of application on top of existing functions, such as adding new path planning algorithms or object recognition modules.

[0060] Hardware replacement refers to the process where, when the hardware currently installed on the target robot cannot meet the task requirements, the target robot is guided by a scheduling system to a designated workstation for manual replacement by personnel, replacement with the assistance of automated equipment, or replacement of relevant hardware components autonomously. For example, if a higher load-bearing capacity is required in a handling task, it may be necessary to replace it with an adaptive vacuum suction cup; in a precision assembly task, it may be necessary to replace it with a high-precision gripper.

[0061] Instruction set switching refers to dynamically adjusting the types of instructions that a target robot can execute based on its current configuration information (first configuration information) and / or the target scenario task (target configuration requirements). For example, for a target robot with a low intelligence level, the system will issue simple and clear atomic instructions, such as moving to point A or picking up materials; while for a target robot with a high intelligence level, the system can issue complex instructions, such as completing the sorting process, autonomously avoiding obstacles, and optimizing the path.

[0062] By subdividing the configuration strategy into three types—software update, hardware replacement, and instruction set switching—and providing corresponding execution methods for each, the system can select the most suitable configuration method according to different task requirements and target robot status. This can effectively improve the task adaptability and resource utilization of the robot cluster, thereby enabling the system to achieve an efficient scheduling mode, significantly reducing operation and maintenance costs, and improving the overall intelligence level of the system.

[0063] In some embodiments, the above method further includes: Obtain information indicating the completion of the configuration policy execution.

[0064] Here, after the configuration policy is sent to the target robot, the target robot receives the configuration policy and updates its configuration accordingly. Once the target robot has completed the configuration update required by the configuration policy, the scheduling system receives execution completion information from the target robot regarding the configuration policy. Execution completion information refers to a set of feedback information collected by the scheduling system after the target robot receives and executes the configuration policy, including whether the configuration was successful, key data during the configuration process, and the final state. This execution completion information may include whether hardware replacement was completed, whether software updates were successful, sensor calibration results, and the loading status of the path planning module.

[0065] For example, in a logistics warehouse handling scenario, the system will issue configuration strategies to guide the robot in replacing its end effector, upgrading its navigation algorithm, and adding sensing devices. After completing all changes, the robot will generate and upload execution completion information, such as the end effector being replaced, the navigation algorithm being upgraded, and the sensing devices being added. Upon receiving the execution completion information, the system can confirm that the robot is ready to perform the handling task. At this point, the system can add the robot to the available resource pool for subsequent scheduling.

[0066] In some embodiments, before obtaining the execution completion information of the configuration information, a self-check task corresponding to the configuration strategy may be issued to the target robot.

[0067] Here, the system can also issue self-check tasks corresponding to the configuration strategy to the target robot. These tasks verify whether the configuration update was successful or met requirements after the target robot completes the necessary configuration update. Self-check tasks typically include hardware function testing, software algorithm verification, and functional stability checks. By executing these self-check tasks, the system ensures that the target robot has stable operational capabilities in the target scenario, guaranteeing the safety and reliability of task execution.

[0068] In practical implementation, self-testing tasks for different capability levels can be designed based on the specific configuration items in the configuration strategy and the intelligence level identifier in the target robot's first configuration information. For example, for a target robot with a low intelligence level identifier (L1), the self-testing task generated by the system may only include basic action verification; for a target robot with a high intelligence level identifier (L3), the self-testing task generated by the system may include autonomous decision-making capability testing in complex environments.

[0069] In some embodiments, after issuing a self-check task corresponding to the configuration strategy to the target robot and obtaining the execution completion information of the configuration strategy, the execution completion information may include a self-check report corresponding to the self-check task.

[0070] The self-inspection report is a detailed document of test results generated after the target robot completes its self-inspection task. It reflects whether the configuration items of the target robot meet the expected requirements after configuration updates. The self-inspection report typically includes key indicators such as hardware status verification results (e.g., end effector stress test results), software module operating status (e.g., path planning algorithm verification results), and sensor calibration data.

[0071] In practice, the target robot will execute each test item according to the process in the self-inspection task and upload a self-inspection report. If any test item in the self-inspection task fails to meet the expected requirements, an exception handling mechanism will be triggered, prompting the user to intervene manually. If all test items in the self-inspection task pass the test (meet the expected requirements), it proves that the target robot's current configuration and / or status meets the target configuration requirements in the target scenario task. For example, after the target robot changes its gripper, the system will automatically trigger a gripper gripping force test task and record the test data and judgment results in the self-inspection report. When the gripper gripping force test fails, the system will mark the gripper gripping force test as abnormal in the self-inspection report and prompt the user to intervene manually.

[0072] In some embodiments, after obtaining the completion information of the configuration strategy, the system can issue a scheduling instruction to the target robot, which is used to instruct the target robot to perform the target scenario task.

[0073] In the technical solution provided in this application embodiment, a configuration strategy is determined based on the difference between the first configuration information and the target configuration requirements in the target scenario task, and then the configuration strategy is issued to the target robot. The configuration strategy is used by the target robot to update its configuration to adapt to the target scenario task. Thus, by obtaining the first configuration information of the target robot and comparing it with the target configuration requirements in the target scenario task, a corresponding configuration strategy is generated based on the difference between the two. This configuration strategy can guide the target robot to flexibly adjust its configuration, thereby quickly adapting to the target scenario task. This method not only improves the robot's adaptability to different scenarios and enables flexible scheduling of multiple roles, but also improves the system's flexibility and intelligence level.

[0074] This application proposes a scene matching scheduling method, which can be applied to a cross-scene and cross-robot scheduling system. The cross-scene and cross-robot scheduling system can be a cloud server, an edge computing device, or a robot control center. Figure 2 This is a flowchart illustrating the scene matching and scheduling method provided in the embodiments of this application. Figure 2 ,like Figure 2 As shown, the method includes the following steps: Step 201: Obtain first identification information of one or more robots, the first identification information including second configuration information of one or more robots.

[0075] In this embodiment, the scheduling system can obtain first identification information reported by one or more robots. The first identification information includes second configuration information of one or more robots. The second configuration information represents the configuration supported by the robot itself, including the functional range and hardware and software configuration that the robot can support. The second configuration information includes one or more of the following: device identifier, configuration identifier option, hardware configuration option, software configuration option, and intelligence level identifier option supported by the robot.

[0076] Step 202: Based on the target configuration requirements in the target scenario task and the first identification information of one or more robots, make scheduling decisions to obtain a collaborative scheduling strategy.

[0077] In this embodiment, the robot capability configuration required to complete the target scenario task can be determined according to the target configuration requirements in the target scenario task, including hardware and software configuration and intelligent level identifier selection. Then, combined with the first identifier information of each robot, the capability configuration of each robot is determined. Next, a comprehensive evaluation and scheduling decision are made based on the robot capability configuration required for the target scenario task and the capability configuration of each robot to generate the optimal collaborative scheduling strategy, which is used to determine which robots can participate in the target scenario task, how to assign the target scenario task to these robots, and whether it is necessary to dynamically adjust the configuration of a certain robot among these robots.

[0078] By comprehensively evaluating and making scheduling decisions based on the robot capability configuration required for the target scenario task and the capability configuration of each robot, it is possible to ensure that the target scenario task is allocated reasonably, avoid the failure or inefficient execution of the target scenario task due to insufficient or mismatched robot capabilities, and thus achieve high efficiency and flexibility in multi-robot collaborative operation.

[0079] In some embodiments, the first identification information may further include one or more of the following: status information of one or more robots, first configuration information, and historical matching information.

[0080] Here, the system can further obtain information related to the operating status, current configuration, and historical task execution of one or more robots, including one or more of the status information, first configuration information, and historical matching information of one or more robots.

[0081] Status information refers to the real-time status of one or more robots during their operation, such as task progress, battery level, and whether there are any malfunctions. Status information reflects whether one or more robots are currently capable of performing new tasks.

[0082] The first configuration information represents the current hardware and software configuration and intelligence level of one or more robots, such as the type of end effector, sensor type, navigation algorithm version, and L3 intelligence level identifier. This first configuration information can determine whether one or more robots possess the hardware capabilities, software support, and intelligence level required to complete a specific task.

[0083] Historical matching information records data such as the types of tasks, matching status, and task completion quality that one or more robots have participated in over a period of time. This historical matching information helps prioritize robots that are highly compatible with the current task requirements, thereby improving operational efficiency and task completion rates.

[0084] In some embodiments, the second configuration information includes one or more of the following: device identifier; configuration identifier option; hardware configuration option; software configuration option; intelligence level identifier option.

[0085] Among them, equipment identification refers to the code or number that uniquely identifies a certain type of equipment or a specific piece of equipment, such as the serial number, MAC address or RFID tag of a robot, used to distinguish different individual robots.

[0086] Configuration identifiers refer to the classification labels for the overall configuration status of the robot, such as picking mode, handling mode, and quality inspection mode. Configuration identifiers are used to quickly locate the types of functional configurations supported by the robot, making it easier for the system to determine whether the supported configuration identifiers meet the requirements of the target task.

[0087] Hardware configuration options refer to configuration items that describe the hardware modules that the robot can be equipped with and the parameters of those hardware modules, such as the types of end effectors that can be equipped (e.g., grippers, suction cups), the types of sensors (e.g., LiDAR, depth cameras), and the chassis load capacity.

[0088] Software configuration options refer to configuration items that describe the software versions and functional modules that the robot supports running, such as the supported path planning algorithm version, visual recognition algorithm version, etc.

[0089] The intelligence level labeling option refers to multiple different levels based on the robot's autonomous decision-making capabilities, including one or more different autonomous decision-making capability levels supported by the robot.

[0090] In some embodiments, the first configuration information includes one or more of the following: configuration identifier; hardware configuration parameters; software configuration parameters; and intelligence level identifier.

[0091] The configuration identifier is information used to uniquely identify the robot's current configuration status. It is usually stored as a string or in encoded form, which facilitates the system's quick location and management of different configuration versions. For example, a robot may have multiple configuration identifiers such as Config_V1.0 and Config_V1.1, each corresponding to different combinations of functions.

[0092] Hardware configuration parameters refer to the physical components currently installed on the robot and their specifications, such as the type of end effector (gripper, suction cup), sensor model (3D vision, LiDAR), chassis structure (fixed, mobile), and load capacity.

[0093] Software configuration parameters refer to the algorithm modules currently running on the robot and their version information, such as the path planning algorithm version, object recognition algorithm version, obstacle avoidance logic version, etc.

[0094] Intelligence level labeling is a technical indicator that measures a robot's autonomous decision-making ability, and is divided into three levels: L1, L2, and L3. An L1-level robot can only execute preset actions (atomic instructions), such as moving from point A to point B; an L2-level robot can adaptively adjust its behavior in simple environments, such as avoiding obstacles and transporting C to area D; an L3-level robot possesses multi-objective autonomous decision-making capabilities, such as optimizing assembly sequences to complete orders or packaging goods.

[0095] In some embodiments, step 202 includes: Step 2021: Match the first identification information of one or more robots with the target configuration requirements to obtain the matching degree of one or more robots.

[0096] In this embodiment of the application, by matching the first identification information (second configuration information, and one or more of the status information, first configuration information, and historical matching information) of one or more robots with the target configuration requirements, the degree of fit between the capability configuration supported by one or more robots themselves and / or the capability configuration currently possessed and / or the historical task execution status and / or the current operating status, and the robot capability configuration required for the target scenario task can be quantitatively evaluated, and the matching degree of one or more robots can be obtained.

[0097] For example, if the target scenario requires a high-precision gripper and L3-level intelligent decision-making capabilities, and a robot possesses both, then the robot is highly compatible with the target scenario.

[0098] Step 2022: Make scheduling decisions based on the matching degree of one or more robots to obtain a collaborative scheduling strategy.

[0099] In this embodiment, a collaborative scheduling strategy can be obtained by assigning tasks and making scheduling decisions to one or more robots based on their matching degree. During the scheduling decision-making process, it is considered whether an individual robot meets the target configuration requirements of the target scenario task, while simultaneously considering the collaborative resource utilization and task completion efficiency of multiple robots.

[0100] For example, in multi-robot handling tasks, the system will prioritize selecting one or more robots that are highly compatible with the target configuration requirements and are in a spatial state to form an optimal combination, thereby ensuring that the task is completed on time and reducing energy consumption.

[0101] In some embodiments, the above-mentioned collaborative scheduling strategy includes a scheduling strategy, which is used to confirm that one or more first target robots perform target scenario tasks.

[0102] Among them, the scheduling strategy in the collaborative scheduling strategy can determine the optimal one or more first target robots to perform the target scenario task by comparing the robot capability configuration required for the target scenario task with the capability configuration supported by one or more robots themselves and / or the current capability configuration and / or the historical task execution status and / or the current running status.

[0103] In some embodiments, the above-described cooperative scheduling strategy further includes a configuration strategy, which is used to adjust the first configuration information of one or more second target robots.

[0104] In this process, after determining the optimal one or more first target robots from among one or more robots to perform the target scenario task, the configuration strategy in the collaborative scheduling strategy can identify one or more second target robots from among the one or more first target robots that need configuration updates by comparing the robot capability configuration required for the target scenario task with the current capability configuration and / or current operating status of the one or more first target robots. This ensures that the current configuration and / or current operating status of the one or more second target robots meets the target configuration requirements. For example, in a picking scenario, if a robot with gripper adaptation capability does not have a gripper that meets the specifications in its current configuration and / or operating status, then the robot needs to be configured to meet the task requirements.

[0105] In the technical solution provided in this application embodiment, by acquiring first identification information of one or more robots, the first identification information including second configuration information of one or more robots; and by making scheduling decisions based on the target configuration requirements in the target scenario task and the first identification information of one or more robots, a collaborative scheduling strategy is obtained. Thus, by comprehensively analyzing the configuration information of one or more robots and the target scenario task requirements, the system can formulate an optimal collaborative scheduling strategy for one or more robots, thereby achieving efficient allocation and utilization of resources.

[0106] This application proposes a method for generating scheduling instructions, which can be applied to a scheduling system, such as a cloud server, edge computing device, or robot control center. Figure 3 This is a flowchart illustrating the scheduling instruction generation method provided in the embodiments of this application. Figure 3 ,like Figure 3 As shown, the method includes the following steps: Step 301: Obtain the first configuration information of the target robot.

[0107] Step 302: Determine the scheduling instruction based on the first configuration information.

[0108] In this embodiment, the system can obtain the first configuration information of the target robot from the data reported by the target robot. The first configuration information represents the current configuration of the target robot (the set of all hardware, software, and functional attributes it possesses at a certain moment), including hardware configuration parameters, software configuration parameters, and intelligence level identifiers. Then, the system maps the first capability information of the target robot based on the first configuration information, and thus determines a scheduling instruction that matches the capabilities of the target robot based on the first capability information of the target robot.

[0109] In some embodiments, step 302 includes: Step 3021: Determine the instruction complexity corresponding to the target robot based on the intelligence level identifier.

[0110] In this embodiment, the first configuration information of the target robot includes an intelligence level identifier, which indicates the autonomous decision-making ability and / or task execution level of the target robot. Based on the intelligence level identifier of the target robot, the corresponding second capability information of the target robot can be determined. The first capability information of the target robot may include the corresponding second capability information. For example, the intelligence level identifier can be divided into L1, L2, and L3. The second capability information corresponding to the L1 level is the ability to execute preset actions (atomic instructions), the second capability information corresponding to the L2 level is the ability to adapt to simple tasks and / or environments, and the second capability information corresponding to the L3 level is the ability to autonomously make decisions on multiple objectives. By identifying the intelligence level identifier, the scheduling system can determine the processing capability of the target robot, including whether it can handle complex task instructions or can only execute atomic instruction operations. The intelligence level identifier is usually generated by a comprehensive evaluation of the target robot's hardware and software and uploaded to the scheduling system during initialization or each state update.

[0111] Intelligence level identification can also be used to determine the set of functions that a target robot possesses. For example, by combining level and / or capability information, a Level 3 robot may support multiple capabilities such as three-dimensional dynamic obstacle avoidance, multi-task collaboration, and adaptive grasping, while a Level 1 robot may only have fixed-path movement and basic grasping functions.

[0112] Instruction complexity is an indicator of the difficulty a robot faces in executing scheduling instructions. It reflects factors such as the computational load, action sequence length, and real-time response capability required for the scheduling instructions. Instruction complexity can be determined based on the target robot's capability information, including the structural complexity of the instructions that the target robot can recognize or parse (instruction complexity). For example, a target robot capable of autonomously making multi-objective decisions (Level 3) can recognize or parse instruction structures containing advanced functions such as multi-objective path planning, obstacle avoidance, and dynamic adjustment. However, for a target robot capable of executing preset actions (Level 1), complex instructions need to be broken down into multiple atomic operations, such as moving to point A → grasping an object → placing it at point B.

[0113] In some embodiments, step 3022 includes one of the following: If the intelligence level is identified as Level 1, then the instruction complexity is determined to be an atomic action sequence; If the intelligence level is identified as Level 2, then the instruction complexity is determined to be a subtask sequence; If the intelligence level is identified as Level 3, then the instruction complexity is determined to be the autonomous decision-making target instruction.

[0114] If the target robot is at Level 1, it means that the target robot's capability information indicates that it can only perform preset action tasks. Therefore, the complexity of the instructions that the target robot can recognize or parse is determined to be an atomic action sequence. An atomic action sequence refers to decomposing a high-level task into a series of smallest executable units of operation instructions. These operations typically have clear input and output conditions, such as moving to a certain coordinate point, grasping an object, or releasing an object. Each atomic action is an indivisible basic behavior, suitable for robots with low intelligence levels (such as Level 1).

[0115] If the target robot is at Level 2, it means that the target robot's capability information indicates that it can adapt to simple environmental tasks. Therefore, the complexity of the instructions that the target robot can recognize or parse is determined as a subtask sequence. A subtask sequence is a set of task modules that are combined and logically arranged based on atomic action sequences. Each subtask may consist of multiple atomic actions, and their order is adjusted according to context. For example, moving an object to a designated area can be broken down into a subtask sequence of object recognition → grasping → obstacle avoidance → placement. Subtask sequences are suitable for intermediate-level intelligent robots (such as Level 2 robots) with a certain level of environmental perception and path planning capabilities, enabling them to adapt to simple dynamic environments.

[0116] In practice, there is a hierarchical relationship between atomic action sequences and subtask sequences. A subtask sequence consists of several atomic actions, and atomic actions are the basic building blocks of the subtask sequence. Therefore, before generating a subtask sequence, it is necessary to ensure that all involved atomic actions have been defined and verified to be feasible.

[0117] If the target robot is at Level 3, it means that the target robot's capability information indicates that it can perform multi-objective autonomous decision-making tasks. Therefore, the complexity of the instructions that the target robot can recognize or parse is determined as the autonomous decision-making target instruction. An autonomous decision-making target instruction refers to abstracting the task into a high-level objective description, which the robot intelligently decides how to achieve. For example, when packaging goods or optimizing an assembly sequence, the robot can make the optimal decision based on the current environmental state, its own capabilities, and historical experience. Robots with high intelligence levels (such as Level 3) possess strong environmental modeling, task reasoning, and multi-objective coordination capabilities. By encapsulating these into autonomous decision-making target instructions, the system can reduce intervention in specific operational details, enabling the robot to efficiently complete tasks even in complex and unstructured scenarios.

[0118] Step 3022: Determine the scheduling instructions based on instruction complexity.

[0119] In this embodiment, a comprehensive judgment can be made based on the capability information corresponding to the target robot to generate a scheduling instruction suitable for the target robot to execute; or, based on the capability information corresponding to the target robot and combined with the target configuration requirements in the target scenario task, a scheduling instruction suitable for the target robot to execute can be generated to ensure that the target robot can complete the target scenario task without exceeding the capability boundary of the target robot.

[0120] Step 303: Issue a scheduling instruction to the target robot. The scheduling instruction is used to instruct the target robot to perform the target scenario task.

[0121] In this embodiment, the scheduling system issues the final generated scheduling instructions to the target robot to guide it in executing the target scenario task. The structural complexity of the scheduling instructions matches the capability level of the target robot and meets the target configuration requirements of the target scenario task. For example, in an electronics assembly workshop, the scheduling system may issue an instruction to an L3-level robot with high-precision grippers to complete the packaging of goods, while issuing an instruction to an L2-level robot to execute according to a preset sorting scheme.

[0122] In practical implementation, during the execution of scheduling instructions, the system can also monitor the target robot's status in real time and intervene or adjust the content of the scheduling instructions when necessary. For example, if the target robot encounters an obstacle during execution, the scheduling system can regenerate new scheduling instructions based on real-time data to guide the target robot to detour or change the execution order. This gives the entire scheduling system a high degree of dynamic adaptability, enabling it to cope with constantly changing task requirements and environmental conditions.

[0123] In the technical solution of this application embodiment, by obtaining the first configuration information of the target robot, determining the scheduling instruction based on the first configuration information, and issuing the scheduling instruction to the target robot, the scheduling instruction is used to instruct the target robot to perform a target scenario task. Thus, by generating scheduling instructions based on the robot's configuration information, the system can ensure that the issued scheduling instructions match the robot's capabilities, thereby improving the success rate of task execution.

[0124] This application also proposes a robot scene adaptation scheduling, dynamic function configuration, and instruction adaptation method to address issues such as robot scene binding, lack of robot autonomy classification, and single system instruction format support. The solution proposes a closed loop of "scene requirements → dynamic robot hardware configuration → adaptive system instruction generation," allowing the system to dynamically configure robot capability combinations and adapt robot intelligence level identifiers based on dynamic task requirements, thereby generating and issuing robot instructions, improving the task adaptability of robot clusters, and achieving support for "one robot with multiple roles" and "multiple robots in a single system." Figure 4This is a flowchart illustrating a robot scene adaptation scheduling, dynamic function configuration, and instruction adaptive method provided in an embodiment of this application. Figure 4 As shown, the method includes the following steps: Step 401: The robot reports its current configuration and status information to the system.

[0125] The robot's current configuration information allows the system to extract robot features or capabilities based on this information. The current configuration information can also be feature information itself. This information includes one or more of the robot's configuration identifier, hardware configuration parameters, software configuration parameters, and intelligence level identifier. Status information includes current task progress, remaining battery level, and fault codes. Simultaneously, the robot performs real-time status and operational monitoring to update its status information and report it to the system.

[0126] Hardware configuration parameters: type of end effector (such as gripper, suction cup, welding gun, etc.), type of sensor (such as 3D vision device, barcode scanner, etc.), type of chassis (such as fixed equipment, mobile equipment, load capacity, etc.). Software configuration parameters: Supported or installed algorithm module types and / or versions (such as path planning algorithm V2.0, object recognition algorithm V1.5); Intelligent level labeling: It can determine the robot's corresponding capability information based on the robot's autonomous decision-making ability; Status information: task progress, remaining battery level, fault codes, etc.; The mapping relationship between the robot's intelligence level identifier, capability information, and instruction complexity is shown in Table 1 below.

[0127] Table 1

[0128] Step 402: The system triggers scene scheduling and generates a robot upgrade package based on the target scene task, the robot's current configuration information and status information.

[0129] The robot's current configuration and status information represent its identifiers or characteristics, capabilities, qualifications, intelligence level, hardware degrees of freedom, etc.; the target scenario task may include other fields such as task type, required tools, environmental information, safety level, and time requirements. Examples of target scenario tasks are shown in Tables 2 and 3 below.

[0130] Table 2

[0131] Table 3

[0132] Specifically, the system will trigger scene matching and scheduling based on the current target scenario task, combined with the robot's current configuration and status information, and dynamically generate the robot's configuration strategy. The matching logic may include the following methods: (1) Match the robot's capabilities mapped in the robot's current configuration information with the current target scenario task to obtain the robot's configuration strategy; (2) Based on the robot's state information, combined with the robot's historical matching records or the robot's historical operation information and fault information, the robot's configuration strategy is obtained by matching it with the current target scenario task; (3) The robot’s configuration strategy is obtained by matching the robot’s current configuration information and status information with the current target scenario task.

[0133] After generating the robot's configuration strategy, the system will create a robot upgrade package based on the configuration strategy, and then use the robot upgrade package as the carrier of the configuration strategy.

[0134] Step 403: The system pushes the robot upgrade package to the robot.

[0135] The configuration strategies in the robot upgrade package include different configuration types, each with a different execution method, as detailed in Table 4 below.

[0136] Table 4

[0137] Optionally, the robot upgrade package may include a self-test package, which is used for the robot to perform functional self-tests after completing the configuration update, such as gripper pressure tests, algorithm module verification, and other self-test processes. After the self-test is passed, the robot will report {"status": "success", "checklist": [...]} to the system.

[0138] Step 404: After the robot completes the configuration update based on the robot upgrade package pushed by the system, it confirms the configuration completion with the system.

[0139] The information the robot sends to the system to confirm that the configuration is complete may include the robot's self-test confirmation report.

[0140] Optionally, the robot can autonomously complete the software and hardware configuration based on the robot upgrade package, or personnel can assist the robot in completing the relevant configuration.

[0141] Step 405: The system generates a parseable scheduling instruction for the robot based on the robot's intelligence level identifier and / or the current target scenario task.

[0142] The system generates scheduling instructions that the robot can recognize based on the capability information mapped by the intelligence level identifier in the robot's current configuration information and / or the current target scenario task. Robots with different capability information correspond to scheduling instructions with different instruction complexities.

[0143] For example, if the robot's intelligence level is L3 and the target scenario task is to complete the sorting of materials on the production line, a scheduling instruction can be generated to instruct the robot to autonomously plan the sorting path; if the robot's intelligence level is L2 and the target scenario task is to complete the sorting of materials on the production line, a scheduling instruction can be generated to instruct the robot to perform material sorting according to a preset sorting scheme; if the robot's intelligence level is L1 and the target scenario task is to complete the sorting of materials on the production line, an atomic scheduling instruction with verification steps can be generated, such as "move to the sorting table → grab the material → place it in area B".

[0144] It should be noted that when scheduling robots with lower intelligence levels, atomic instructions with verification steps need to be sent to such robots, including atomic operations that include memory state verification steps during execution, so that such robots can better understand the content of the instructions.

[0145] Step 406: The system issues a scheduling command to the robot.

[0146] The scheduling instructions are used to instruct the robot to perform tasks related to the current target scenario.

[0147] When the current target scenario task changes, the system needs to issue scenario adaptation instructions to the robot, that is, switch to different business flow instructions, such as sorting, handling, picking, etc.

[0148] The following provides specific implementation examples of robot scene adaptation scheduling and dynamic function configuration.

[0149] Example 1: Switching from warehouse picking scenario to warehouse handling scenario (1) The robot is initially in picking mode, and its current configuration information is shown in Table 5 below: Table 5

[0150] (2) The system detects the handling scenario task and, in conjunction with the robot's current configuration information and / or status information and / or historical matching records and / or historical operation information, generates a comprehensive upgrade plan for the robot. The specific upgrade content is shown in Table 6 below: Table 6

[0151] (3) After the robot is upgraded and configured, a self-test process is performed. The self-test content and results are shown in Table 7 below: Table 7

[0152] Example 2: Switching from Warehouse Handling Scenario to Precision Assembly Scenario (1) The robot reports its current configuration information, which is shown in Table 8 below: Table 8

[0153] (2) The system requires tools to achieve an accuracy of ±0.1mm for the assembly scene task. Therefore, a configuration scheme is generated based on the robot's current configuration information. The specific configuration content is shown in Table 9 below: Table 9

[0154] (3) After the robot replaces the gripper according to the configuration scheme, it checks whether the gripper accuracy meets the standard. If it does, it activates the assembly instruction set.

[0155] The specific replacement plan can be implemented autonomously by robots, by auxiliary devices at the replacement station, or by personnel.

[0156] This application also proposes a scene adaptation configuration device 500. Figure 5 This is a schematic diagram of the scene adaptation configuration device provided in the embodiments of this application, as shown below. Figure 5 As shown, the device includes: The first acquisition unit 501 is used to acquire the first configuration information of the target robot.

[0157] The first determining unit 502 is used to determine a configuration strategy based on the difference between the first configuration information and the target configuration requirements in the target scenario task.

[0158] The first sending unit 503 is used to send a configuration strategy to the target robot. The configuration strategy is used by the target robot to update its configuration to adapt to the target scenario task.

[0159] In some embodiments, the first acquisition unit 501 is further configured to acquire the state information of the target robot.

[0160] In some embodiments, the first determining unit 502 is further configured to determine a configuration strategy based on the difference between the first configuration information and / or status information and the target configuration requirements.

[0161] In some embodiments, the first configuration information includes hardware configuration parameters and / or software configuration parameters; the configuration strategy includes configuration targets and / or configuration rules and / or configuration paths; wherein, the first determining unit 502 is specifically used for one or more of the following: The configuration target is determined based on the configuration difference between the hardware configuration parameters and / or software configuration parameters and the target configuration requirements. Based on the configuration objectives, extract the task type and / or tool specification and / or environment constraint parameters from the target configuration requirements, and determine the configuration rules based on the task type and / or tool specification and / or environment constraint parameters; Based on configuration rules, the configuration order and / or movement path and / or pose of the target robot for configuration updates are planned to obtain the configuration path.

[0162] In some embodiments, the first configuration information includes hardware configuration parameters and / or software configuration parameters; the configuration strategy includes configuration targets and / or configuration rules and / or configuration paths; wherein, the first determining unit 502 is further specifically used for one or more of the following: The configuration target is determined based on the configuration differences and / or status differences between the hardware configuration parameters and / or software configuration parameters and / or status information and the target configuration requirements. Based on the configuration goal, extract the task type and / or tool specification and / or environmental constraint parameters from the target configuration requirements, and determine the configuration rules based on the status information and / or task type and / or tool specification and / or environmental constraint parameters; The configuration path is obtained by planning the configuration sequence and / or movement path and / or pose of the target robot based on configuration rules and / or status information.

[0163] In some embodiments, the configuration policy type includes one or more of the following: Software updates, which can be performed remotely on the target robot and / or upgrade its functionality. Hardware replacement can be performed by guiding the target robot to a workstation for manual or automatic hardware replacement. Instruction set switching is performed by sending a switching instruction set to the target robot to adapt to the target scenario task.

[0164] In some embodiments, the first acquisition unit 501 is further configured to acquire information on the completion of the configuration policy execution.

[0165] In some embodiments, the first sending unit 503 is further configured to send a self-test task corresponding to the configuration strategy to the target robot.

[0166] In some embodiments, the completion information includes a self-test report corresponding to the self-test task.

[0167] In some embodiments, the first sending unit 503 is further configured to send a scheduling instruction to the target robot, the scheduling instruction being used to instruct the target robot to perform a target scene task.

[0168] This application also proposes a scene matching and scheduling device 600. Figure 6 This is a schematic diagram of the scene matching and scheduling device provided in the embodiments of this application, as shown below. Figure 6 As shown, the device includes: The second acquisition unit 601 is used to acquire first identification information of one or more robots, the first identification information including second configuration information of one or more robots.

[0169] The second processing unit 602 is used to make scheduling decisions based on the target configuration requirements in the target scenario task and the first identification information of one or more robots, and obtain a collaborative scheduling strategy.

[0170] In some embodiments, the first identification information may further include one or more of the following: status information of one or more robots, first configuration information, and historical matching information.

[0171] In some embodiments, the second processing unit 602 is specifically used for: The first identification information of one or more robots is matched with the target configuration requirements to obtain the matching degree of one or more robots; Scheduling decisions are made based on the matching degree of one or more robots to obtain a collaborative scheduling strategy.

[0172] In some embodiments, the collaborative scheduling strategy includes a scheduling strategy for confirming that one or more first target robots perform target scenario tasks.

[0173] In some embodiments, the collaborative scheduling strategy further includes a configuration strategy for adjusting the first configuration information of one or more second target robots.

[0174] In some embodiments, the second configuration information includes one or more of the following: Equipment identification; Configure identification options; Hardware configuration options; Software configuration options; Smart level identification option.

[0175] In some embodiments, the first configuration information includes one or more of the following: Configuration identifier; Hardware configuration parameters; Software configuration parameters; Intelligent level identification.

[0176] This application also proposes a scheduling instruction generation device 700. Figure 7 This is a schematic diagram of the scheduling instruction generation device provided in the embodiments of this application, as shown below. Figure 7 As shown, the device includes: The third acquisition unit 701 is used to acquire the first configuration information of the target robot.

[0177] The third determining unit 702 is used to determine the scheduling instruction based on the first configuration information.

[0178] The third sending unit 703 is used to send scheduling instructions to the target robot, which instruct the target robot to perform the target scene task.

[0179] In some embodiments, the first configuration information includes an intelligence level identifier; wherein, the third determining unit 702 is specifically used for: Based on the intelligence level identifier, determine the instruction complexity corresponding to the target robot; The scheduling instructions are determined based on the complexity of the instructions.

[0180] In some embodiments, the third determining unit 702 is further specifically used for one of the following: If the intelligence level is identified as Level 1, then the instruction complexity is determined to be an atomic action sequence; If the intelligence level is identified as Level 2, then the instruction complexity is determined to be a subtask sequence; If the intelligence level is identified as Level 3, then the instruction complexity is determined to be the autonomous decision-making target instruction.

[0181] Those skilled in the art should understand that Figure 5 The scene adaptation configuration device shown Figure 6 The scene matching and scheduling device shown Figure 7 The functions of each unit in the scheduling instruction generation device shown can be understood by referring to the relevant description of the aforementioned method. Figure 5 The scene adaptation configuration device shown Figure 6 The scene matching and scheduling device shown Figure 7 The functions of each unit in the scheduling instruction generation device shown can be implemented by a program running on the processor or by specific logic circuits.

[0182] Figure 8 This is a schematic diagram of the cross-scene, cross-robot scheduling system provided in this application embodiment. The cross-scene, cross-robot scheduling system includes the scene adaptation configuration device 500, the scene matching scheduling device 600, and the scheduling instruction generation device 700 provided in the above embodiment.

[0183] Figure 9 This is a schematic diagram of the processing device provided in an embodiment of this application. The processing device may be a terminal device or a network device. Figure 9The processing device shown includes a processor 901, which can call and run computer programs from memory to implement the methods in the embodiments of this application.

[0184] Optionally, such as Figure 9 As shown, the processing device may further include a memory 902. The processor 901 can retrieve and run computer programs from the memory 902 to implement the methods described in the embodiments of this application.

[0185] The memory 902 can be a separate device independent of the processor 901, or it can be integrated into the processor 901.

[0186] Optionally, such as Figure 9 As shown, the processing device may also include a transceiver 903, which the processor 901 can control to communicate with other devices. Specifically, it can send information or data to other devices or receive information or data sent by other devices.

[0187] The transceiver 903 may include a transmitter and a receiver. The transceiver 903 may further include an antenna, which may be one or more.

[0188] The processing device may specifically be a scene adaptation configuration device, a scene matching scheduling device, or a scheduling instruction generation device according to the embodiments of this application. The processing device can implement the corresponding processes of the various methods implemented in the embodiments of this application. For the sake of brevity, it will not be described in detail here.

[0189] It should be understood that the processor in the embodiments of this application may be an integrated circuit chip with signal processing capabilities. In implementation, the steps of the above method embodiments can be completed by integrated logic circuits in the processor's hardware or by instructions in software form. The processor described above can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules can be located in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method.

[0190] It is understood that the memory in the embodiments of this application can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDR SDRAM), Enhanced Synchronous DRAM (ESDRAM), Synchlink DRAM (SLDRAM), and Direct Rambus RAM (DR RAM). It should be noted that the memory used in the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0191] This application also provides a computer-readable storage medium for storing a computer program. This computer-readable storage medium can be applied to the processing device in this application embodiment, and the computer program causes the computer to execute the corresponding processes implemented by the various methods in this application embodiment; for brevity, further details are omitted here.

[0192] This application also provides a computer program product, including computer program instructions. This computer program product can be applied to the processing device in this application embodiment, and the computer program instructions cause the computer to execute the corresponding processes implemented by the various methods in this application embodiment; for brevity, further details are omitted here.

[0193] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0194] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0195] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0196] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0197] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0198] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0199] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A scenario-adaptive configuration method, characterized in that, The method includes: Obtain the initial configuration information of the target robot; Based on the difference between the first configuration information and the target configuration requirements in the target scenario task, a configuration strategy is determined; The configuration strategy is sent to the target robot, and the configuration strategy is used by the target robot to update its configuration to adapt to the target scenario task.

2. The method according to claim 1, characterized in that, The method further includes: Obtain the state information of the target robot; The configuration strategy is determined based on the difference between the first configuration information and / or the status information and the target configuration requirements.

3. The method according to claim 1, characterized in that, The first configuration information includes hardware configuration parameters and / or software configuration parameters; the configuration strategy includes configuration targets and / or configuration rules and / or configuration paths; The step of determining a configuration strategy based on the difference between the first configuration information and the target configuration requirements in the target scenario task includes one or more of the following: The configuration target is determined based on the configuration differences between the hardware configuration parameters and / or the software configuration parameters and the target configuration requirements; Based on the configuration objective, extract the task type and / or tool specification and / or environmental constraint parameters from the target configuration requirements, and determine the configuration rules based on the task type and / or tool specification and / or environmental constraint parameters; The configuration path is obtained by planning the configuration order and / or movement path and / or pose of the target robot based on the configuration rules.

4. The method according to claim 2, characterized in that, The first configuration information includes hardware configuration parameters and / or software configuration parameters; the configuration strategy includes configuration targets and / or configuration rules and / or configuration paths; The step of determining the configuration strategy based on the difference between the first configuration information and / or the status information and the target configuration requirement includes one or more of the following: The configuration target is determined based on the configuration differences and / or status differences between the hardware configuration parameters and / or the software configuration parameters and / or the status information and the target configuration requirements. Based on the configuration objective, extract the task type and / or tool specification and / or environmental constraint parameters from the target configuration requirements, and determine the configuration rules based on the status information and / or the task type and / or tool specification and / or environmental constraint parameters; The configuration path is obtained by planning the configuration order and / or movement path and / or pose of the target robot based on the configuration rules and / or the state information.

5. The method according to any one of claims 1 to 4, characterized in that, The configuration policy type includes one or more of the following: Software update, wherein the software update is performed by means of remotely updating and / or upgrading the function of the target robot; Hardware replacement, wherein the hardware replacement is performed by guiding the target robot to a workstation for manual or automatic hardware replacement; Instruction set switching, wherein the execution method of the instruction set switching includes issuing a switching instruction set to the target robot to adapt to the target scene task.

6. The method according to any one of claims 1 to 4, characterized in that, The method further includes: Obtain the execution completion information of the configuration strategy.

7. The method according to claim 6, characterized in that, The method further includes: Send the self-check task corresponding to the configuration strategy to the target robot.

8. The method according to claim 7, characterized in that, The execution completion information includes the self-test report corresponding to the self-test task.

9. The method according to claim 6, characterized in that, The method further includes: A scheduling instruction is issued to the target robot, which instructs the target robot to perform a target scenario task.

10. A scene matching and scheduling method, characterized in that, The method includes: Obtain first identification information of one or more robots, wherein the first identification information includes second configuration information of the one or more robots; Based on the target configuration requirements in the target scenario task and the first identification information of the one or more robots, a scheduling decision is made to obtain a collaborative scheduling strategy.

11. The method according to claim 10, characterized in that, The first identification information also includes one or more of the status information of the one or more robots, the first configuration information, and the historical matching information.

12. The method according to claim 10 or 11, characterized in that, The scheduling decision based on the target configuration requirements in the target scenario task and the first identification information of the one or more robots, to obtain a collaborative scheduling strategy, includes: The first identification information of the one or more robots is matched with the target configuration requirements to obtain the matching degree of the one or more robots; The scheduling decision is made based on the matching degree of the one or more robots to obtain the collaborative scheduling strategy.

13. The method according to claim 10, characterized in that, The collaborative scheduling strategy includes a scheduling strategy, which is used to confirm that one or more first target robots will perform the target scenario task.

14. The method according to claim 11, characterized in that, The collaborative scheduling strategy also includes a configuration strategy, which is used to adjust the first configuration information of one or more second target robots.

15. The method according to claim 10, characterized in that, The second configuration information includes one or more of the following: Equipment identification; Configure identification options; Hardware configuration options; Software configuration options; Smart level identification option.

16. The method according to claim 11, characterized in that, The first configuration information includes one or more of the following: Configuration identifier; Hardware configuration parameters; Software configuration parameters; Intelligent level identification.

17. A method for generating scheduling instructions, characterized in that, The method includes: Obtain the initial configuration information of the target robot; The scheduling instruction is determined based on the first configuration information; The scheduling instruction is issued to the target robot, which instructs the target robot to perform a target scenario task.

18. The method according to claim 17, characterized in that, The first configuration information includes an intelligence level identifier; The step of determining the scheduling instruction based on the first configuration information includes: Based on the intelligence level identifier, the instruction complexity corresponding to the target robot is determined; The scheduling instruction is determined based on the instruction complexity.

19. The method according to claim 18, characterized in that, The determination of the instruction complexity corresponding to the target robot based on the intelligence level identifier includes one of the following: If the intelligence level is identified as the first level, then the instruction complexity is determined to be an atomic action sequence; If the intelligence level is identified as the second level, then the instruction complexity is determined to be a subtask sequence; If the intelligence level is identified as level three, then the instruction complexity is determined to be an autonomous decision-making target instruction.

20. A scene-adaptive configuration device, characterized in that, The device includes: The first acquisition unit is used to acquire the first configuration information of the target robot; The first determining unit is used to determine a configuration strategy based on the difference between the first configuration information and the target configuration requirements in the target scenario task; The first sending unit is used to send the configuration strategy to the target robot, and the configuration strategy is used by the target robot to update its configuration to adapt to the target scenario task.

21. A scene matching and scheduling device, characterized in that, The device includes: The second acquisition unit is used to acquire first identification information of one or more robots, wherein the first identification information includes second configuration information of the one or more robots; The second processing unit is used to make scheduling decisions based on the target configuration requirements in the target scenario task and the first identification information of the one or more robots, and to obtain a collaborative scheduling strategy.

22. A scheduling instruction generation device, characterized in that, The device includes: The third acquisition unit is used to acquire the first configuration information of the target robot; The third determining unit is used to determine the scheduling instruction based on the first configuration information; The third sending unit is used to send the scheduling instruction to the target robot, the scheduling instruction being used to instruct the target robot to perform a target scene task.

23. A cross-scenario, cross-robot scheduling system, characterized in that, The system includes: the scene adaptation configuration device as described in claim 20, the scene matching scheduling device as described in claim 21, and the scheduling instruction generation device as described in claim 22.

24. A processing device, characterized in that, include: A processor and a memory for storing a computer program, the processor for calling and running the computer program stored in the memory to perform the method as described in any one of claims 1 to 19.

25. A computer-readable storage medium, characterized in that, Used to store a computer program that causes a computer to perform the method as described in any one of claims 1 to 19.

26. A computer program product, characterized in that, It includes computer program instructions that cause a computer to perform the method as described in any one of claims 1 to 19.

Images