Industrial robot cooperative control method, system and device and storage medium

Abstract

The invention relates to an industrial robot cooperative control method, system and device and a storage medium. The method comprises the following steps: acquiring machine system information, working environment conditions, task demand contents and cooperative mode information of a plurality of industrial robots; performing spatial analysis on the working environment condition to obtain environment structure characteristics; performing task decomposition on the task demand content according to the cooperation mode information to obtain a sub-task list; mapping the machine system information into the environment structure features to obtain a corresponding mapping relationship, and performing association analysis on the mapping relationship to obtain a task allocation scheme; performing individual optimization on the comprehensive control parameters based on a task allocation scheme to obtain robot control parameters; and performing cooperative strategy analysis according to the sub-task list and the robot control parameters to obtain robot cooperative strategies, and performing comprehensive analysis on all the robot cooperative strategies to obtain an overall cooperative control strategy. According to the invention, the whole industrial robot system can be more suitable for complex and changeable actual production scenes.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial robots, and in particular to an industrial robot collaborative control method, system, device and storage medium. Background Art

[0002] As an indispensable automation equipment in modern manufacturing, industrial robots play an important role in improving production efficiency, reducing production costs and ensuring product quality. However, existing collaborative control methods for industrial robots often only focus on a single aspect, such as the performance parameters of the robot itself or simple task allocation, while ignoring the comprehensive consideration of multiple factors such as the working environment, task requirements and collaboration mode. This simplified method is difficult to give full play to the overall advantages of the multi-robot system, and may lead to problems such as unreasonable resource allocation and low collaborative efficiency. At the same time, due to the lack of comprehensive analysis of tasks and environments, it is also difficult to flexibly adapt to complex and changing actual production scenarios. Summary of the invention

[0003] The main purpose of the present invention is to provide an industrial robot collaborative control method, system, device and storage medium, which can make the entire industrial robot system more adaptable to complex and changeable actual production scenarios, and improve the flexibility and adaptability of the multi-robot system.

[0004] To achieve the above object, the present invention provides an industrial robot collaborative control method, comprising: Obtain machine system information, working environment conditions, task requirements and collaboration mode information of multiple industrial robots; Performing spatial analysis on the working environment conditions to obtain environmental structural characteristics; Decomposing the task requirements according to the collaboration mode information to obtain a subtask list; Mapping the machine system information to the environment structure characteristics to obtain a corresponding mapping relationship, and performing correlation analysis on the mapping relationship according to the subtask list to obtain a task allocation plan; Performing an overall performance analysis on the machine system information according to the task requirements to obtain comprehensive control parameters, and performing individual optimization on the comprehensive control parameters based on the task allocation plan to obtain robot control parameters; The collaborative strategy analysis is performed based on the subtask list and robot control parameters to obtain the robot collaborative strategy, and all robot collaborative strategies are comprehensively analyzed to obtain the overall collaborative control strategy.

[0005] Furthermore, the obtaining of machine system information, working environment conditions, task requirements and collaboration mode information of the multiple industrial robots includes: Acquire environmental sensor data of all the industrial robots, filter the real-time sensor data, and obtain preliminary environmental status information; Extracting features from the preliminary environmental condition information to obtain an environmental feature vector, and performing matching analysis on the environmental feature vector according to a preset environmental database to obtain the working environment condition; Acquiring robot parameter information, clustering the robot parameter information to obtain robot type information, matching the robot type information with a preset robot capability database to obtain the machine system information; Perform semantic analysis on the received task instructions and extract keywords to obtain task features, and match the task features with a predefined task template library to obtain the task requirement content; Analyzing the spatial position relationship of the industrial robots according to the machine system information and the task requirements to obtain a preliminary collaborative relationship; The preliminary collaboration relationship is optimized and calculated and combined with the working environment conditions to obtain the collaboration mode information.

[0006] Furthermore, the spatial analysis of the working environment to obtain the environmental structural characteristics includes: Reconstructing the working environment status data into a three-dimensional point cloud to obtain a three-dimensional point cloud representation of the environment, and optimizing the three-dimensional point cloud representation to obtain optimized point cloud data; Performing plane segmentation and contour extraction on the point cloud data to obtain contour plane and contour information in the environment; Perform feature matching based on the contour plane and the contour information to identify structural elements in the environment and obtain preliminary structural features; Performing spatial relationship analysis on the relative positions and directions between the structural elements of the preliminary structural features to obtain a spatial topological relationship; Constructing a hierarchical structure framework of the environment according to the spatial topological relationship to obtain a hierarchical structure representation of the environment; Labeling each structural element in the hierarchical structure representation with functional attributes related to the industrial robot operation to obtain a semantic environment structure description; Performing accessibility analysis on each area in the environment based on the environmental structure description to obtain an accessibility map; The accessibility map is divided into a working area and an obstacle area of ​​the industrial robot to obtain an area classification result; The environmental structure feature is generated according to the region classification result and the environmental structure description.

[0007] Furthermore, the task requirement content is decomposed according to the collaboration mode information to obtain a subtask list, including: Extracting keywords and task objectives from the task requirements to obtain task semantic features; Matching a preset task template library according to the task semantic features to obtain a preliminary task structure, hierarchically decomposing the preliminary task structure and constructing a task hierarchy tree to obtain a multi-level task structure; Performing parallelism analysis on the multi-level task structure according to the collaboration mode information to obtain a task parallelism sequence matrix, and performing resource demand calculation on the task parallelism sequence matrix according to a preset resource calculation rule to obtain a subtask resource demand table; Prioritize the subtasks according to the subtask resource requirement table to obtain a subtask priority list; Performing time dependency analysis on the subtask priority list to obtain a subtask timing relationship; Calculate the earliest start time and the latest end time of each subtask according to the subtask timing relationship to obtain a subtask time window; The subtask priority list, the subtask resource requirement table and the subtask time window are integrated to generate the subtask checklist.

[0008] Furthermore, mapping the machine system information to the environment structure characteristics to obtain a corresponding mapping relationship, and performing association analysis on the mapping relationship according to the subtask list to obtain a task allocation plan includes: Performing multi-dimensional feature extraction on the machine system information to obtain a robot capability feature tensor; Performing adaptive octree spatial division on the environmental structural features to obtain a multi-resolution environmental grid representation; Performing a tensor convolution operation on the multi-resolution environment grid representation according to the robot capability feature tensor to obtain a robot adaptability four-dimensional tensor; Performing a multi-level analysis on the subtask list to obtain a multi-level task requirement matrix; A framework is constructed based on the robot adaptability four-dimensional tensor and the multi-level task requirement matrix to obtain a hybrid planning framework under multiple constraints, and a scheme analysis is performed on the hybrid planning framework according to a preset genetic algorithm to obtain a preliminary allocation scheme; Performing conflict weight analysis on the preliminary task allocation scheme to obtain a weighted conflict task graph; Resolving conflicts in the preliminary allocation plan according to the conflicting task graph to obtain an optimized allocation plan; Performing a multi-objective resource balance analysis on the optimized task allocation scheme to obtain a resource allocation tensor; The optimized allocation plan is dynamically fine-tuned according to the resource allocation tensor to obtain the task allocation plan with adaptability.

[0009] Furthermore, the overall performance analysis of the machine system information is performed according to the task requirements to obtain comprehensive control parameters, and the comprehensive control parameters are individually optimized based on the task allocation plan to obtain robot control parameters, including: Extracting task features from the task requirement content to obtain a task feature set; Performing multi-dimensional feature analysis on the machine system information to obtain a machine system feature set; Perform matching analysis on the task feature set and the machine system feature set to obtain a performance matching degree between the task and the machine; Performing a multi-objective parameter optimization analysis on the machine system information according to the performance matching degree and the task requirements to obtain initial control parameters; Performing sensitivity analysis on the initial control parameters according to a preset sensitivity rule to obtain parameter sensitivity; Optimizing and adjusting the initial control parameters according to the parameter sensitivity to obtain the comprehensive control parameters; Performing task characteristic analysis on the task allocation scheme to obtain task characteristic indicators; Performing parameter mapping on the comprehensive control parameters according to the task characteristic index to obtain initial individual control parameters; Performing constraint condition analysis on the initial individual control parameters to obtain a parameter constraint set, and performing feasibility evaluation on the initial individual control parameters based on the parameter constraint set to obtain a feasible parameter set; Performing individual performance evaluation based on the feasible parameter set combined with the machine system feature set to obtain individual performance indicators; Performing stability evaluation on the individual performance indicators according to preset stability evaluation rules to obtain a stability score; According to the stability score, corresponding parameters are extracted from all the initial individual control parameters. The optimal parameter combination is selected to obtain the robot control parameters.

[0010] Furthermore, the collaborative strategy analysis is performed based on the subtask list and the robot control parameters to obtain the robot collaborative strategy, and all robot collaborative strategies are comprehensively analyzed to obtain the overall collaborative control strategy, including: Performing task requirement analysis on the subtask list to obtain specific task requirement parameters for each subtask, and prioritizing the specific task requirement parameters to obtain a subtask priority list; Perform parameter task matching on the robot control parameters and the subtask priority list to obtain a subtask matching relationship; Performing workload balancing analysis on the subtask matching relationship to obtain a load balancing solution; Simulating and mapping the load balancing solution to each of the industrial robots to obtain load distribution of each of the industrial robots; Performing path planning on the working paths of the industrial robots according to the load distribution to obtain a preliminary planning scheme; Performing path optimization processing on the preliminary planning scheme to obtain an optimized path scheme; Performing scheduling analysis on the execution order of each of the industrial robots according to the optimized path plan to obtain an execution order arrangement; Performing motion coordination analysis on the coordinated motions of the industrial robots according to the optimized path plan to obtain a motion coordination plan; Performing time synchronization analysis on the execution sequence arrangement and the action coordination scheme to obtain a time synchronization strategy; Integrate the execution sequence arrangement, the action coordination scheme and the time synchronization strategy to obtain a comprehensive synchronization strategy; All the industrial robots are comprehensively coordinated according to the comprehensive synchronization strategy to obtain the overall collaborative control strategy.

[0011] The present invention further provides an industrial robot collaborative control system, which is applied to any one of the above industrial robot collaborative control methods, comprising: A collection module, which is used to obtain machine system information, working environment conditions, task requirements and collaboration mode information of multiple industrial robots; An analysis module, the analysis module is used to perform spatial analysis on the working environment conditions to obtain environmental structural characteristics; An association module, the association module is used to decompose the task requirements according to the collaboration mode information to obtain a subtask list; A processing module, the processing module is used to map the machine system information to the environmental structure characteristics to obtain a corresponding mapping relationship, and perform association analysis on the mapping relationship according to the subtask list to obtain a task allocation plan; A control module is used to perform an overall performance analysis on the machine system information according to the task requirements to obtain comprehensive control parameters, and to perform individual optimization on the comprehensive control parameters based on the task allocation plan to obtain robot control parameters.

[0012] The execution module is used to perform collaborative strategy analysis based on the subtask list and robot control parameters to obtain the robot collaborative strategy, and to perform comprehensive analysis on all robot collaborative strategies to obtain the overall collaborative control strategy.

[0013] The present invention also provides an industrial robot collaborative control device, comprising: Memory, used to store programs; The processor is used to execute the program to implement each step of the method for quantifying the heat load of an air source heat pump system as described in any one of the above.

[0014] The present invention also provides a storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute any of the above methods.

[0015] The present invention provides an industrial robot collaborative control method, system, device and storage medium, which have the following beneficial effects: By spatially analyzing the working environment and decomposing the task requirements in combination with the collaborative mode information, the characteristics and requirements of different subtasks can be evaluated more accurately, thereby improving the rationality of task allocation and providing a more reliable basis for the collaborative operation of multi-robot systems. By mapping the machine system information to the environmental structure characteristics and performing correlation analysis based on the subtask list, a refined matching of different robot capabilities and task requirements is achieved, which helps to give full play to the advantages of each robot and avoid resource waste. An overall performance analysis of the machine system information based on the task requirements can ensure that the system can operate efficiently in different task scenarios, reduce unnecessary performance loss, and improve the overall operation efficiency of the system. By comprehensively analyzing all robot collaborative strategies, a more reasonable overall collaborative control strategy is formulated, which effectively improves the collaborative efficiency of the multi-robot system and reduces production time and cost. At the same time, by considering the collaborative mode information, the control strategy can be flexibly adjusted according to different types of collaborative requirements, making the system more adaptable to complex and changeable actual production scenarios, and improving the flexibility and adaptability of the multi-robot system. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a flow chart of an industrial robot collaborative control method provided by the present invention; Figure 2 This is a structural diagram of an industrial robot collaborative control system provided by the present invention; Figure 3 This is a structural diagram of an industrial robot collaborative control device provided by the present invention.

[0017] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0019] The present invention is further described below in conjunction with the accompanying drawings and specific implementation methods.

[0020] Reference Figure 1 As shown, a collaborative control method for industrial robots includes: Step S1: obtaining machine system information, working environment conditions, task requirements and collaboration mode information of multiple industrial robots; Step S2: Perform spatial analysis on the working environment to obtain the environmental structural characteristics; Step S3: Decompose the task requirements according to the collaboration mode information to obtain a subtask list; Step S4: Map the machine system information to the environment structure characteristics to obtain the corresponding mapping relationship, perform correlation analysis on the mapping relationship according to the subtask list, and obtain the task allocation plan; Step S5: Perform an overall performance analysis on the machine system information according to the task requirements to obtain comprehensive control parameters, and perform individual optimization on the comprehensive control parameters based on the task allocation plan to obtain robot control parameters; Step S6: Perform collaborative strategy analysis based on the subtask list and robot control parameters to obtain the robot collaborative strategy, and perform comprehensive analysis on all robot collaborative strategies to obtain the overall collaborative control strategy.

[0021] Based on the above steps, the detailed process is as follows: Step S1: Obtain the unique identification of each industrial robot through the database. Read the configuration file of each industrial robot, including mechanical structure, sensor type, actuator parameters, etc. Monitor the status information of each industrial robot in real time, such as battery power, working status (idle, working, faulty), location, etc.

[0022] Use environmental sensors (such as lidar, cameras, infrared sensors, etc.) to collect real-time data of the work environment. Build a 3D model or 2D floor plan of the work environment based on sensor data, including information such as obstacles, workstation locations, and path planning.

[0023] Extract task requirements from task description files, including task name, task type, priority, time requirement, etc. Analyze specific task parameters, such as weight, size, destination, etc. of items in handling tasks.

[0024] Read predefined collaboration mode information, such as parallel operation mode, assembly line operation mode, master-slave control mode, etc. Analyze the rules and constraints in the collaboration mode, such as task allocation rules, communication coordination mechanism, etc.

[0025] Step S2: Remove noise and invalid data from sensor data. Fuse data from different sensors to obtain more accurate environmental information.

[0026] Identify and mark fixed and mobile obstacles in the work environment. Perform path planning based on the environment model to determine feasible and infeasible paths. Identify the location and attributes of each workstation in the work environment, such as workbenches, assembly points, storage areas, etc.

[0027] Build a topological diagram of the environment, showing the relationships between various workstations, obstacles, and paths. Create a geometric model of the environment, showing the shape, size, and position of various objects.

[0028] Step S3: Identify the task type (such as handling, assembly, inspection, etc.) according to the task requirements. Determine the execution order of the tasks according to the priority information in the task description. Decompose the tasks according to the decomposition rules in the collaboration mode information. Decompose the tasks into several subtasks, each of which contains clear goals, inputs, outputs, and execution conditions.

[0029] Sort the generated subtasks according to task priority and collaboration mode. Optimize subtasks, remove redundant tasks, merge similar tasks, and improve task execution efficiency. Record the final subtask list in the task management system.

[0030] Step S4: Map the current position and working range of each industrial robot to the environment structure model to determine its specific position and reach in the environment. Map the operating capabilities of each industrial robot (such as handling weight, walking speed, accuracy, etc.) to the capability requirements required for the task. Map the real-time status of the robot (such as power, fault conditions, working status) to the corresponding position and task node in the environment.

[0031] According to the requirements in the subtask list, match the capabilities and status of each industrial robot to determine whether it can complete a subtask. Based on the characteristics of the environmental structure, analyze the feasibility of the robot's path from the current position to the task location, including path length, obstacle detour, etc. Apply predefined task allocation strategies (such as nearby allocation, load balancing allocation, capability priority allocation, etc.) to allocate appropriate robots to each subtask. Optimize the preliminary allocation plan to reduce the number of task switching and improve task execution efficiency. Record the final task allocation plan in the task management system for subsequent execution.

[0032] Step S5: Define the overall performance indicators of the robot (such as energy consumption, execution time, accuracy, stability, etc.). Collect the performance data of each industrial robot in different tasks to form a historical performance data set. Based on the task requirements and historical performance data, evaluate the current performance of each industrial robot to obtain comprehensive control parameters. According to the task allocation plan, associate the comprehensive control parameters with specific tasks to determine the control requirements of each industrial robot when performing a specific task.

[0033] Control parameter adjustment: Based on task requirements and actual conditions, optimize and adjust comprehensive control parameters, such as adjusting path planning parameters, action execution speed, torque control, etc.

[0034] Individual control parameter generation: Generate control parameters for each industrial robot when performing a specific task to ensure that the task is completed efficiently and safely.

[0035] The optimized robot control parameters are stored in the control system for real-time task scheduling.

[0036] The generated control parameters are simulated and verified to ensure their feasibility and effectiveness.

[0037] Step S6: Analyze the task dependencies in the subtask list and determine which tasks need to be completed collaboratively. Design coordination mechanisms between robots, such as communication protocols, synchronization strategies, task switching mechanisms, etc. Detect possible task conflicts (such as path conflicts, resource contention, etc.) and design corresponding solutions.

[0038] Plan the execution order and method of collaborative tasks to ensure the efficiency and safety of the robots working together. Set the coordination parameters between robots (such as communication frequency, synchronization signal, task switching conditions, etc.) to ensure the smooth progress of collaborative work.

[0039] The control strategies executed by each robot individually and the collaborative control strategy are integrated to form an overall collaborative control strategy. The overall collaborative control strategy is optimized to reduce interference between robots and improve the overall work efficiency of the system. The feasibility and effectiveness of the overall collaborative control strategy are verified through simulation and actual testing.

[0040] Deploy the final collaborative control strategy to the robot control system. Monitor the execution of tasks by each robot in real time, adjust and optimize the collaborative control strategy in a timely manner, and ensure stable operation of the system.

[0041] The industrial robot collaborative control method provided by the present invention can more accurately evaluate the characteristics and requirements of different subtasks by spatially analyzing the working environment conditions and decomposing the task requirements in combination with the collaborative mode information, thereby improving the rationality of task allocation and providing a more reliable basis for the collaborative operation of the multi-robot system. The machine system information is mapped to the environmental structure characteristics, and the association analysis is performed based on the subtask list, so as to achieve the refined matching of different robot capabilities and task requirements, which helps to give full play to the advantages of each robot and avoid resource waste. The overall performance analysis of the machine system information based on the task requirement content can ensure that the system can operate efficiently in different task scenarios, reduce unnecessary performance loss, and improve the overall operation efficiency of the system. By comprehensively analyzing all robot collaborative strategies, a more reasonable overall collaborative control strategy is formulated, thereby effectively improving the collaborative efficiency of the multi-robot system and reducing production time and cost. At the same time, by considering the collaborative mode information, the control strategy can be flexibly adjusted according to different types of collaborative requirements, so that the system is more adaptable to complex and changeable actual production scenarios, and the flexibility and adaptability of the multi-robot system are improved.

[0042] In one embodiment, machine system information, working environment conditions, task requirements and collaboration mode information of multiple industrial robots are obtained, including: Obtain environmental sensor data for all industrial robots. Environmental sensor data refers to real-time data about the robot's surroundings, such as temperature, humidity, light intensity, and the location of obstacles. Filter these real-time sensor data to remove noise and interference and obtain preliminary environmental status information.

[0043] Extract features from the preliminary environmental information to obtain an environmental feature vector. The environmental feature vector is a multidimensional vector used to describe environmental conditions, which contains the characteristic values ​​of various environmental parameters. Perform matching analysis on the environmental feature vector based on the preset environmental database to determine the current working environment conditions. For example, if the temperature in the workshop is too high and the light is insufficient, the system will identify this special environment and feed it back to the control system.

[0044] Obtain the parameter information of each industrial robot, including the robot model, motion capability, load capacity, etc. Cluster the robot parameter information, group robots with similar functions into one category, and obtain robot type information. Match the robot type information with the preset robot capability database to generate machine system information. For example, classify all welding robots into one category and match them with the capability database to determine their welding capability and motion range.

[0045] After receiving the task instruction, the task instruction is semantically analyzed and keywords are extracted to obtain the task features. The task feature is a refined description of the task instruction, such as "carry a heavy object to a specified location". The task feature is matched with the predefined task template library to obtain the task requirement content. For example, the system recognizes that the task is "carrying heavy objects" and determines its specific requirements such as weight, carrying path, etc.

[0046] Based on the machine system information and task requirements, the spatial position relationship of the industrial robots is analyzed to obtain a preliminary collaborative relationship. The preliminary collaborative relationship is a preliminary setting of how the robots should work together, such as which robot is responsible for handling and which robot is responsible for assembly.

[0047] The preliminary collaborative relationship is optimized and calculated in combination with the working environment to obtain the final collaborative mode information. The collaborative mode information is the specific strategy for the collaborative work of the robots, including the task allocation, path planning and working sequence of each robot. For example, the movement speed and path of the robot are adjusted according to the environmental conditions to avoid collisions and improve work efficiency.

[0048] This embodiment effectively filters out noise and interference by acquiring and processing environmental sensor data, ensuring the accuracy of environmental status information, thereby providing a reliable basis for subsequent decision-making. Secondly, cluster analysis and matching based on the robot's parameter information make the machine system information more accurate, facilitate reasonable task allocation according to the characteristics of different robots, and improve resource utilization. Furthermore, through semantic analysis and keyword extraction, it is possible to accurately understand task requirements and ensure the accuracy and rationality of task allocation.

[0049] By optimizing the preliminary collaborative relationship in combination with the working environment, the collaborative mode between robots can be dynamically adjusted to adapt to the real-time changing environment, thus improving the flexibility and adaptability of the system. The final collaborative mode information can effectively guide the robots to perform tasks and reduce the decline in work efficiency caused by path conflicts or task overlaps. Overall, this method not only improves the collaborative work efficiency of the multi-robot system, but also significantly improves the stability and reliability of the system. It is suitable for complex and changeable industrial environments and greatly promotes the development of intelligent manufacturing.

[0050] In one embodiment, spatial analysis is performed on the working environment to obtain environmental structural features, including: The working environment condition data is reconstructed into a 3D point cloud. By using sensors such as lidar or depth cameras, point cloud data in the environment is collected and reconstructed into a 3D point cloud representation through calculation methods. Then, the 3D point cloud representation is optimized, and filtering and noise reduction algorithms are used to remove noise points and redundant points, thereby obtaining optimized point cloud data.

[0051] The optimized point cloud data is segmented and contour extracted. The point cloud data is divided into several contour plane areas using clustering algorithms and boundary detection techniques, and the contour information of each area is extracted. Feature matching is performed based on these contour planes and contour information. By comparing similarity metrics and geometric features, structural elements in the environment, such as walls, tables, machinery and equipment, are identified to obtain preliminary structural features.

[0052] The spatial relationship analysis is performed on the relative positions and directions of the structural elements in the preliminary structural features, and the spatial position and direction relationship of each element is determined using the topological analysis method to obtain the spatial topological relationship. Based on the spatial topological relationship, a hierarchical structural framework of the environment is constructed, and a multi-level structural representation is constructed based on the spatial relationship. For example, a room is divided into multiple areas, and the relationship between each area is described to obtain a hierarchical structural representation of the environment.

[0053] On this basis, each structural element in the hierarchical representation is labeled with the functional attributes related to the operation of the industrial robot to form an environmental description with semantic information, such as marking a certain area as a robot work area or a restricted area, thereby forming a semantic environmental structure description. Next, based on the environmental structure description, the accessibility of each area in the environment is analyzed, and the accessibility of the robot in each area is determined through the path planning algorithm and the accessibility evaluation method, and the accessibility map is generated. The accessibility map is used to describe the information graph of the accessibility of each area.

[0054] The reachability map is divided into the working area and obstacle area of ​​the industrial robot, and the area in the reachability map is divided into the working area where the robot can operate safely and the obstacle area that needs to be avoided, so as to obtain the area classification result. Based on these area classification results and the previous environmental structure description, the final environmental structure features are generated.

[0055] This embodiment can accurately obtain the three-dimensional point cloud representation of the environment and perform optimization processing by performing spatial analysis on the working environment conditions, thereby improving the accuracy and reliability of the data. Through plane segmentation and contour extraction, the structural elements in the environment can be effectively identified, which is convenient for subsequent feature matching and spatial relationship analysis. The hierarchical structure framework constructed based on spatial topological relationships can clearly describe the hierarchical structure of the environment, which helps industrial robots navigate and operate in complex environments. By annotating the functional attributes of the structural elements and generating a semantic description of the environmental structure, the robot can understand the functions and limitations of each area, thereby improving the intelligent level of operation. Accessibility analysis and regional classification processing ensure the safe operation of the robot in each area, avoid obstacles, and improve work efficiency and safety. The overall method provides precise guidance for the collaborative control of industrial robots through detailed analysis and description of the environment, significantly improving the adaptability and operating efficiency of the robot in complex environments.

[0056] In one embodiment, the task requirements are decomposed according to the collaboration mode information to obtain a subtask list, including: Keywords and task objectives are extracted from the task requirements, such as "assembly", "part A", "part B", "final product", etc. These keywords and task objectives together constitute the semantic features of the task.

[0057] According to the extracted task semantic features, the preset task template library is matched. The task template library is a predefined task structure set, which contains decomposition templates of various typical tasks. Through matching, a preliminary task structure is obtained, which contains the basic framework of the main task and subtasks. Then, the preliminary task structure is hierarchically decomposed to construct a task hierarchy tree. The task hierarchy tree is a multi-level task structure, and each level represents a different degree of refinement of the task. In this way, a multi-level task structure is finally obtained.

[0058] Based on the cooperation mode information, the multi-level task structure is analyzed for parallelism. The cooperation mode information refers to the interaction mode and coordination mechanism when multiple robots work together. Through the parallelism analysis, the task parallelism sequence matrix is ​​obtained, which describes the parallel relationship between each subtask. According to the preset resource calculation rules, the resource demand calculation of the task parallelism sequence matrix is ​​performed. The resource calculation rule refers to the criterion for allocating resources according to the nature of the task and the capabilities of the robot, and finally the subtask resource demand table is obtained.

[0059] According to the subtask resource requirement table, the subtasks are prioritized to generate a subtask priority list. Priority sorting is to determine the order in which each subtask is executed. The subtask priority list is subjected to time dependency analysis to determine the time relationship between each subtask and obtain the subtask timing relationship.

[0060] According to the subtask timing relationship, the earliest start time and the latest end time of each subtask are calculated. These time points together constitute the subtask time window. The subtask time window refers to the time range in which each subtask can be executed.

[0061] Combine the subtask priority list, subtask resource requirement table and subtask time window to generate a subtask checklist. The subtask checklist is a comprehensive document that lists the details of all subtasks, including priority, resource requirements and time schedule.

[0062] This embodiment can quickly and accurately construct a preliminary task structure and hierarchical decomposition tasks by extracting task semantic features and matching the preset task template library, significantly improving the efficiency of task planning. Secondly, by using the multi-level task structure and parallelism analysis, the parallelism of tasks can be scientifically evaluated and optimized, thereby achieving the rational allocation and utilization of resources and improving overall production efficiency. Resource demand calculation and priority sorting ensure the orderly execution of subtasks, avoiding resource conflicts and task delays. Time dependency analysis and time window calculation provide a clear time range for each subtask, ensuring the timely completion of the task. The final generated subtask list combines priorities, resource requirements and time arrangements, provides comprehensive execution guidance for the robot group, and is conducive to improving the coordination and accuracy of collaborative work. Overall, this method can significantly improve the execution efficiency and reliability of complex tasks in industrial environments, reduce human intervention, and improve the intelligence level of production systems.

[0063] In one embodiment, the machine system information is mapped to the environment structure characteristics to obtain the corresponding mapping relationship, and the mapping relationship is analyzed according to the subtask list to obtain the task allocation plan, including: Collect the system information of each robot, including their respective working range, accuracy, speed, load capacity, etc., and use multi-dimensional feature extraction technology to form a robot capability feature tensor. The robot capability feature tensor is a multi-dimensional array that represents the various capability features of the robot. Perform adaptive octree spatial division on the workshop environment structure to form a multi-resolution environment grid representation. Octree is a space division algorithm that subdivides the workshop environment into grids of different resolutions through octree spatial division, thereby more accurately describing the structural characteristics of the robot working environment.

[0064] The obtained robot capability feature tensor and multi-resolution environment grid representation are subjected to tensor convolution operation to obtain a robot adaptability four-dimensional tensor. Tensor convolution operation is to fuse information of different dimensions together to obtain the robot's adaptability performance in a specific environment. Each task is decomposed in detail to form a subtask list, and a multi-level task requirement matrix is ​​constructed through multi-level analysis. This matrix describes in detail the requirements of each task at different levels.

[0065] After obtaining the robot's adaptability four-dimensional tensor and the multi-level task requirement matrix, a hybrid planning framework is constructed based on the two, and the scheme is analyzed using the preset genetic algorithm to obtain a preliminary scheme.

[0066] By analyzing the conflict weights of the preliminary plan, a weighted conflict task graph is formed. The conflict task graph intuitively shows which tasks are in conflict and the severity of the conflict. Based on the conflict task graph, the preliminary plan is conflict resolved to obtain an optimized plan.

[0067] Perform multi-objective resource balance analysis on the optimization scheme to obtain the resource allocation tensor. The resource allocation tensor indicates how to allocate resources between different tasks to achieve the optimal balance. Based on the resource allocation tensor, the optimization scheme is dynamically fine-tuned to finally obtain an adaptive task allocation scheme.

[0068] This embodiment can accurately match the capabilities and task requirements of each robot by mapping the robot system information to the environmental structural features and performing correlation analysis, thereby achieving efficient task allocation and improving overall production efficiency. The adaptive octree space partitioning technology can refine the structural features of the workshop environment, so that the robot can also operate flexibly in a complex environment, enhancing the accuracy and adaptability of the operation. By fusing multi-dimensional information through tensor convolution operations, the generated robot adaptability four-dimensional tensor can comprehensively evaluate the performance of the robot in a specific environment and ensure the rationality of task allocation. The genetic algorithm is used for scheme optimization to effectively solve the conflict problem in complex task allocation and improve the quality of the task allocation scheme. Through multi-objective resource balance analysis and dynamic fine-tuning, the optimal allocation of resources is ensured, resource waste is reduced, and the continuity and efficiency of production are improved. In the face of unexpected situations, this method can adaptively adjust the task allocation scheme to ensure the stability and flexibility of workshop production. In summary, this method has significant efficiency improvement and resource optimization effects in practical applications.

[0069] In one embodiment, the overall performance analysis of the machine system information is performed according to the task requirements to obtain comprehensive control parameters, and the comprehensive control parameters are individually optimized based on the task allocation plan to obtain robot control parameters, including: The task requirements are used to extract task features. The task requirements refer to the specific requirements and goals of the task, such as accuracy, speed, load, etc. Through a detailed analysis of the task requirements, a task feature set can be extracted. The task feature set includes the key features of the task, such as position, trajectory, force, etc.

[0070] Perform multi-dimensional feature analysis on machine system information, which refers to various types of information related to industrial robots, including mechanical structure, kinematic parameters, dynamic characteristics, sensor data, etc. Perform multi-dimensional feature analysis on machine system information to obtain a machine system feature set, which covers various performance indicators of the robot when performing tasks.

[0071] The task feature set and the machine system feature set are matched and analyzed to obtain the performance matching degree between the task and the machine. The performance matching degree reflects whether the current machine system is suitable for performing a specific task and the possible execution effect. Based on the performance matching degree and combined with the task requirements, the machine system information is subjected to multi-objective parameter optimization analysis to obtain the initial control parameters, which are the initial settings of the robot in task execution.

[0072] According to the preset sensitivity rules, the initial control parameters are subjected to sensitivity analysis to obtain parameter sensitivity. Parameter sensitivity refers to the degree of influence of different parameters on task results during task execution. According to parameter sensitivity, the initial control parameters are optimized and adjusted to obtain comprehensive control parameters. The comprehensive control parameters will serve as the basic data for task allocation.

[0073] The task allocation scheme refers to decomposing the entire task and allocating it to different robots. By analyzing the task characteristics of the task allocation scheme, we can obtain the task characteristic index, which specifically characterizes the characteristics of each subtask. According to the task characteristic index, the comprehensive control parameters are mapped to obtain the initial individual control parameters, which are the initial control settings of each robot.

[0074] The constraint analysis of the initial individual control parameters is performed to obtain the parameter constraint set. The parameter constraint set refers to the value range and restriction conditions of each parameter in the task execution. The feasibility evaluation of the initial individual control parameters is performed based on the parameter constraint set to obtain a feasible parameter set, which is a verified feasible control setting.

[0075] Based on the feasible parameter set combined with the machine system feature set, individual performance evaluation is performed to obtain individual performance indicators. Individual indicators reflect the specific performance of each robot in task execution. Based on the preset stability evaluation rules, individual performance indicators are evaluated for stability and a stability score is obtained. The stability score is the result of evaluating the performance of the robot in long-term task execution.

[0076] According to the stability score, the corresponding parameters are extracted from all the initial individual control parameters, the optimal parameter combination is selected, and finally the robot control parameters are obtained.

[0077] This embodiment can accurately evaluate the performance matching degree between tasks and machines by performing overall performance analysis on task requirements and machine system information, and extracting task feature sets and machine system feature sets, thereby improving the accuracy of task allocation and execution, and providing a more reliable basis for robot collaborative control. By matching and analyzing the task feature set with the machine system feature set, and performing multi-objective parameter optimization analysis based on the performance matching degree, the optimization adjustment of the initial control parameters is realized, which helps to realize personalized and precise robot control and avoid resource waste. The sensitivity analysis of the initial control parameters based on the preset sensitivity rules ensures that the system can operate efficiently under different task scenarios and demand changes, reduces unnecessary parameter adjustments, and improves the overall operation efficiency. By performing task characteristic analysis on the task allocation scheme and parameter mapping on the comprehensive control parameters, more reasonable individual control parameters can be formulated, and through constraint analysis and parameter mapping, the optimization of robot control parameters is realized to ensure that all robots perform best in task execution. By comprehensively analyzing the task characteristic indicators and individual performance indicators, a more reasonable task allocation scheme is formulated, and the optimized operation of the entire machine system is realized through a comprehensive adjustment strategy, thereby effectively utilizing resources and reducing energy consumption and errors during execution. Taking into account the diversity of task requirements and machine system characteristics, the control strategy is flexibly adjusted to make the system more adaptable to diverse task scenarios and changes in demand, thereby improving the adaptability and stability of robot collaborative control.

[0078] In one embodiment, a collaborative strategy analysis is performed based on the subtask list and the robot control parameters to obtain the robot collaborative strategy, and a comprehensive analysis is performed on all robot collaborative strategies to obtain an overall collaborative control strategy, including: Perform task requirement analysis on each subtask according to the subtask list to obtain specific task requirement parameters. For example, assuming that the subtask list includes three subtasks: welding, handling, and assembly, the task requirement parameters may include welding accuracy, handling weight, assembly accuracy, etc. Prioritize these task requirement parameters to obtain a subtask priority list, for example: welding > assembly > handling.

[0079] Match the control parameters of the industrial robot (such as load capacity, accuracy, speed, etc.) with the subtask priority list. Assume that there are three robots R1, R2, and R3. R1 has high-precision welding capability, R2 has large load handling capability, and R3 has high-precision assembly capability. Through matching, the subtask matching relationship is obtained: the welding task is assigned to R1, the handling task is assigned to R2, and the assembly task is assigned to R3.

[0080] Perform workload balancing analysis on the subtask matching relationship to ensure that each robot is loaded evenly. For example, if the welding task has a large workload and the handling task has a small workload, you may need to adjust the tasks or add collaborative robots to achieve load balancing and obtain a load balancing solution. Simulate and map the load balancing solution to each industrial robot to determine the load distribution of each industrial robot. For example, R1 is responsible for 70% of the welding task, while R2 and R3 are responsible for 15% of the welding task respectively to achieve load balancing.

[0081] According to the load distribution, preliminary path planning is performed for the working paths of each industrial robot. For example, R1 needs to weld at multiple locations on the workpiece, so a preliminary welding path is planned; R2 is responsible for transporting materials, so a material transport path is planned; R3 is responsible for assembly at a fixed location, so an assembly path is planned. The preliminary planning scheme is path optimized to reduce path conflicts and energy consumption, and an optimized path scheme is obtained. For example, through the path optimization algorithm, the welding path of R1 is shortened, unnecessary movement is reduced, and welding efficiency is improved.

[0082] According to the optimized path plan, the execution order of each industrial robot is scheduled and analyzed to obtain the execution order arrangement. For example, R1 performs welding first, R2 performs handling later, and R3 performs assembly last to ensure the orderly progress of the task. According to the optimized path plan, the coordinated actions of each industrial robot are analyzed to obtain the action coordination plan. For example, at some task points, R1 and R2 need to perform welding and handling at the same time, and coordinate their actions to avoid conflicts. The execution order arrangement and action coordination plan are analyzed for time synchronization to ensure that the actions of each robot are synchronized and coordinated in time. For example, through the time synchronization algorithm, it is ensured that R2 starts handling immediately after R1 completes welding, and R3 starts assembly after R2 completes handling.

[0083] The execution sequence arrangement, motion coordination scheme and time synchronization strategy are integrated to obtain a comprehensive synchronization strategy. For example, the sequence, time and path of all robot movements are considered comprehensively to form an overall control strategy. All industrial robots are comprehensively coordinated according to the comprehensive synchronization strategy, and each robot is commanded to perform tasks according to the comprehensive strategy to obtain an overall collaborative control strategy. For example, the control system sends the comprehensive strategy to each robot to ensure that they work together according to the strategy to achieve efficient and conflict-free task execution.

[0084] This embodiment can accurately match each subtask with the most suitable robot by performing collaborative strategy analysis on the subtask list and robot control parameters, ensuring the efficiency and accuracy of task completion. Load balancing analysis and simulation mapping ensure the workload balance of each robot, avoid excessive load on individual robots, and improve the stability and reliability of the overall system. Path optimization processing reduces path conflicts and energy consumption, shortens the robot movement path through optimization algorithms, and improves production efficiency. Time synchronization analysis and motion coordination schemes ensure the coordination of each robot's actions in time and space, avoiding conflicts and delays during task execution. The comprehensive synchronization strategy integrates the execution order, motion coordination and time synchronization strategies, so that multiple robots can work together seamlessly in actual operations, further improving the overall performance of the system. The overall collaborative control strategy realizes an efficient and conflict-free production process by commanding each robot to perform tasks according to the optimization strategy, greatly improving the collaborative work efficiency of industrial robots and the overall effectiveness of the production line.

[0085] Reference Figure 2 As shown, the present invention also provides an industrial robot collaborative control system, which is applied to any of the above industrial robot collaborative control methods, including: The acquisition module is used to obtain machine system information, working environment conditions, task requirements and collaboration mode information of multiple industrial robots; Analysis module: The analysis module is used to perform spatial analysis on the working environment conditions and obtain the environmental structural characteristics; The association module is used to decompose the task requirements according to the collaboration mode information to obtain a subtask list; The processing module is used to map the machine system information to the environmental structure characteristics, obtain the corresponding mapping relationship, perform correlation analysis on the mapping relationship according to the subtask list, and obtain the task allocation plan; The control module is used to perform an overall performance analysis of the machine system information according to the task requirements, obtain comprehensive control parameters, and individually optimize the comprehensive control parameters based on the task allocation plan to obtain the robot control parameters.

[0086] The execution module is used to perform collaborative strategy analysis based on the subtask list and robot control parameters to obtain the robot collaborative strategy, and to perform a comprehensive analysis of all robot collaborative strategies to obtain the overall collaborative control strategy.

[0087] Reference Figure 3 As shown, the present invention also provides an industrial robot collaborative control device, comprising: Memory, used to store programs; The processor is used to execute the program to implement each step of any one of the above-mentioned methods for quantifying the heat load of an air source heat pump system.

[0088] In this embodiment, the processor and the memory may be connected via a bus or other means. The memory may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a read-only memory, a flash memory, a hard disk, or a solid-state drive. The processor may be a general-purpose processor, such as a central processing unit, a digital signal processor, an application-specific integrated circuit, or one or more integrated circuits configured to implement the embodiments of the present invention.

[0089] The present invention also provides a storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute any of the above methods.

[0090] It should be noted that technicians in the relevant technical field can clearly understand that for the convenience and conciseness of description, the specific working process of the system and each module described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0091] The above description is only a preferred embodiment of the present invention, and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A collaborative control method for industrial robots, characterized in that: include: Obtain machine system information, working environment conditions, task requirements and collaboration mode information of multiple industrial robots; Performing spatial analysis on the working environment conditions to obtain environmental structural characteristics; Decomposing the task requirements according to the collaboration mode information to obtain a subtask list; Mapping the machine system information to the environment structure characteristics to obtain a corresponding mapping relationship, and performing correlation analysis on the mapping relationship according to the subtask list to obtain a task allocation plan; Performing an overall performance analysis on the machine system information according to the task requirements to obtain comprehensive control parameters, and performing individual optimization on the comprehensive control parameters based on the task allocation plan to obtain robot control parameters; The collaborative strategy analysis is performed based on the subtask list and robot control parameters to obtain the robot collaborative strategy, and all robot collaborative strategies are comprehensively analyzed to obtain the overall collaborative control strategy.

2. The industrial robot collaborative control method according to claim 1, characterized in that: The obtaining of machine system information, working environment conditions, task requirements and collaboration mode information of multiple industrial robots includes: Acquire environmental sensor data of all the industrial robots, filter the real-time sensor data, and obtain preliminary environmental status information; Extracting features from the preliminary environmental condition information to obtain an environmental feature vector, and performing matching analysis on the environmental feature vector according to a preset environmental database to obtain the working environment condition; Acquiring robot parameter information, clustering the robot parameter information to obtain robot type information, matching the robot type information with a preset robot capability database to obtain the machine system information; Perform semantic analysis on the received task instructions and extract keywords to obtain task features, and match the task features with a predefined task template library to obtain the task requirement content; Analyzing the spatial position relationship of the industrial robots according to the machine system information and the task requirements to obtain a preliminary collaborative relationship; The preliminary collaboration relationship is optimized and calculated and combined with the working environment conditions to obtain the collaboration mode information.

3. The industrial robot collaborative control method according to claim 1, characterized in that: The spatial analysis of the working environment to obtain the environmental structural characteristics includes: Reconstructing the working environment status data into a three-dimensional point cloud to obtain a three-dimensional point cloud representation of the environment, and optimizing the three-dimensional point cloud representation to obtain optimized point cloud data; Performing plane segmentation and contour extraction on the point cloud data to obtain contour plane and contour information in the environment; Perform feature matching based on the contour plane and the contour information to identify structural elements in the environment and obtain preliminary structural features; Performing spatial relationship analysis on the relative positions and directions between the structural elements of the preliminary structural features to obtain a spatial topological relationship; Constructing a hierarchical structure framework of the environment according to the spatial topological relationship to obtain a hierarchical structure representation of the environment; Labeling each structural element in the hierarchical structure representation with functional attributes related to the industrial robot operation to obtain a semantic environment structure description; Performing accessibility analysis on each area in the environment based on the environmental structure description to obtain an accessibility map; The accessibility map is divided into a working area and an obstacle area of ​​the industrial robot to obtain an area classification result; The environmental structure feature is generated according to the region classification result and the environmental structure description.

4. The industrial robot collaborative control method according to claim 1, characterized in that: Decomposing the task requirements according to the collaboration mode information to obtain a subtask list includes: Extracting keywords and task objectives from the task requirements to obtain task semantic features; Matching a preset task template library according to the task semantic features to obtain a preliminary task structure, hierarchically decomposing the preliminary task structure and constructing a task hierarchy tree to obtain a multi-level task structure; Performing parallelism analysis on the multi-level task structure according to the collaboration mode information to obtain a task parallelism sequence matrix, and performing resource demand calculation on the task parallelism sequence matrix according to a preset resource calculation rule to obtain a subtask resource demand table; Prioritize the subtasks according to the subtask resource requirement table to obtain a subtask priority list; Performing time dependency analysis on the subtask priority list to obtain a subtask timing relationship; Calculate the earliest start time and the latest end time of each subtask according to the subtask timing relationship to obtain a subtask time window; The subtask priority list, the subtask resource requirement table and the subtask time window are integrated to generate the subtask checklist.

5. The industrial robot collaborative control method according to claim 1, characterized in that: The mapping of the machine system information to the environment structure characteristics to obtain a corresponding mapping relationship, and performing association analysis on the mapping relationship according to the subtask list to obtain a task allocation plan includes: Performing multi-dimensional feature extraction on the machine system information to obtain a robot capability feature tensor; Performing adaptive octree spatial division on the environmental structural features to obtain a multi-resolution environmental grid representation; Performing a tensor convolution operation on the multi-resolution environment grid representation according to the robot capability feature tensor to obtain a robot adaptability four-dimensional tensor; Performing a multi-level analysis on the subtask list to obtain a multi-level task requirement matrix; A framework is constructed based on the robot adaptability four-dimensional tensor and the multi-level task requirement matrix to obtain a hybrid planning framework under multiple constraints, and a scheme analysis is performed on the hybrid planning framework according to a preset genetic algorithm to obtain a preliminary allocation scheme; Performing conflict weight analysis on the preliminary task allocation scheme to obtain a weighted conflict task graph; Resolving conflicts in the preliminary allocation plan according to the conflicting task graph to obtain an optimized allocation plan; Performing a multi-objective resource balance analysis on the optimized task allocation scheme to obtain a resource allocation tensor; The optimized allocation plan is dynamically fine-tuned according to the resource allocation tensor to obtain the task allocation plan with adaptability.

6. The industrial robot collaborative control method according to claim 1, characterized in that: The overall performance analysis of the machine system information is performed according to the task requirements to obtain comprehensive control parameters, and the comprehensive control parameters are individually optimized based on the task allocation plan to obtain robot control parameters, including: Extracting task features from the task requirement content to obtain a task feature set; Performing multi-dimensional feature analysis on the machine system information to obtain a machine system feature set; Perform matching analysis on the task feature set and the machine system feature set to obtain a performance matching degree between the task and the machine; Performing a multi-objective parameter optimization analysis on the machine system information according to the performance matching degree and the task requirements to obtain initial control parameters; Performing sensitivity analysis on the initial control parameters according to a preset sensitivity rule to obtain parameter sensitivity; Optimizing and adjusting the initial control parameters according to the parameter sensitivity to obtain the comprehensive control parameters; Performing task characteristic analysis on the task allocation scheme to obtain task characteristic indicators; Performing parameter mapping on the comprehensive control parameters according to the task characteristic index to obtain initial individual control parameters; Performing constraint condition analysis on the initial individual control parameters to obtain a parameter constraint set, and performing feasibility evaluation on the initial individual control parameters based on the parameter constraint set to obtain a feasible parameter set; Performing individual performance evaluation based on the feasible parameter set combined with the machine system feature set to obtain individual performance indicators; Performing stability evaluation on the individual performance indicators according to preset stability evaluation rules to obtain a stability score; According to the stability score, corresponding parameters are extracted from all the initial individual control parameters. The optimal parameter combination is selected to obtain the robot control parameters.

7. The industrial robot collaborative control method according to claim 1, characterized in that: The collaborative strategy analysis is performed based on the subtask list and the robot control parameters to obtain the robot collaborative strategy, and all robot collaborative strategies are comprehensively analyzed to obtain the overall collaborative control strategy, including: Performing task requirement analysis on the subtask list to obtain specific task requirement parameters for each subtask, and prioritizing the specific task requirement parameters to obtain a subtask priority list; Perform parameter task matching on the robot control parameters and the subtask priority list to obtain a subtask matching relationship; Performing workload balancing analysis on the subtask matching relationship to obtain a load balancing solution; Simulating and mapping the load balancing solution to each of the industrial robots to obtain load distribution of each of the industrial robots; Performing path planning on the working paths of the industrial robots according to the load distribution to obtain a preliminary planning scheme; Performing path optimization processing on the preliminary planning scheme to obtain an optimized path scheme; Performing scheduling analysis on the execution order of each of the industrial robots according to the optimized path plan to obtain an execution order arrangement; Performing motion coordination analysis on the coordinated motions of the industrial robots according to the optimized path plan to obtain a motion coordination plan; Performing time synchronization analysis on the execution sequence arrangement and the action coordination scheme to obtain a time synchronization strategy; Integrate the execution sequence arrangement, the action coordination scheme and the time synchronization strategy to obtain a comprehensive synchronization strategy; All the industrial robots are comprehensively coordinated according to the comprehensive synchronization strategy to obtain the overall collaborative control strategy.

8. An industrial robot collaborative control system, characterized in that: The industrial robot collaborative control method applied to any one of claims 1 to 7 above comprises: A collection module, which is used to obtain machine system information, working environment conditions, task requirements and collaboration mode information of multiple industrial robots; An analysis module, the analysis module is used to perform spatial analysis on the working environment conditions to obtain environmental structural characteristics; An association module, the association module is used to decompose the task requirements according to the collaboration mode information to obtain a subtask list; A processing module, the processing module is used to map the machine system information to the environmental structure characteristics to obtain a corresponding mapping relationship, and perform association analysis on the mapping relationship according to the subtask list to obtain a task allocation plan; A control module, the control module is used to perform an overall performance analysis on the machine system information according to the task requirements to obtain comprehensive control parameters, and to perform individual optimization on the comprehensive control parameters based on the task allocation scheme to obtain robot control parameters; The execution module is used to perform collaborative strategy analysis based on the subtask list and robot control parameters to obtain the robot collaborative strategy, and to perform comprehensive analysis on all robot collaborative strategies to obtain the overall collaborative control strategy.

9. An industrial robot collaborative control device, characterized in that: include: Memory, used to store programs; The processor is used to execute the program to implement the various steps of the method for quantifying the heat load of an air source heat pump system as described in any one of claims 1 to 7.

10. A storage medium, characterized in that: Computer instructions are stored, and the computer instructions are used to make a computer execute the method according to any one of claims 1 to 7.

Images