Cooperative control method of industrial production robot

Abstract

The invention discloses a cooperative control method of an industrial production robot, and relates to the technical field of robot control, and the method comprises the steps: building a cooperative control group of the industrial production robot; configuring control data of the first cooperative robot according to the first task based on the cooperative control group, and controlling the first cooperative robot to execute the first task by using the configured control data; establishing environment influence data, task progress data and task path data; a comprehensive collaborative efficiency network is configured, and a collaborative efficiency optimization result is generated; and performing cooperative control of the second cooperative robot according to the cooperative control data. The technical problems that in existing robot control, multiple robots depend on a fixed task sequence and preset control data, are lack of coordination and are difficult to flexibly deal with complex tasks, task execution conflicts are caused, waiting time is long, and production efficiency is reduced are solved. The technical effects that the cooperative efficiency of task execution of the multiple robots is improved, and the waiting time between the tasks is shortened are achieved.

Description

Technical Field

[0001] The present application relates to the technical field related to robot control, and in particular to a collaborative control method for industrial production robots. Background Art

[0002] With the development of industrial automation and intelligence, robots are increasingly widely used in industrial production, and have become a key force in improving production efficiency, ensuring product quality, and reducing labor costs. Tasks in industrial production usually involve multiple links, and there is a close task dependency between different links, such as the sequential execution of multiple steps such as assembly, handling, and processing. Faced with increasingly complex production tasks and changing production environments, a single robot operation mode has been difficult to meet the needs of efficient and flexible production. Traditional robot control often focuses on the independent operation of a single robot and the execution of preset tasks alone. Although it has improved production efficiency to a certain extent, it ignores the collaborative operation capabilities between robots in the face of complex production scenarios and multi-task collaborative work. The lack of coordination between robots can easily cause problems such as long waiting time and task execution time conflicts, resulting in reduced production efficiency. In addition, in a complex industrial production environment, environmental factors such as temperature, humidity, and light, as well as dynamic interference from people or other equipment in the workshop, will affect the robot's task execution. Traditional methods are difficult to make flexible adjustments based on real-time task flow changes, which may lead to task failure or reduced execution efficiency.

[0003] In the current industrial production robot control-related technologies, there are multiple robots that rely on a fixed task sequence and preset control data. They lack coordination with each other and find it difficult to flexibly respond to complex tasks, which in turn leads to technical problems such as task execution conflicts, long waiting times and reduced production efficiency. Summary of the invention

[0004] The present application provides a collaborative control method for industrial production robots, thereby solving the technical problem that multiple robots in existing robot control rely on a fixed task sequence and preset control data, lack coordination with each other and find it difficult to flexibly respond to complex tasks, which in turn leads to task execution conflicts, long waiting times and reduced production efficiency. The application achieves the technical effect of improving the collaborative efficiency of multiple robots in performing tasks and reducing the waiting time between tasks.

[0005] The present application provides a collaborative control method for industrial production robots, including: establishing a collaborative control group of industrial production robots, the collaborative control group including a first collaborative robot and a second collaborative robot, the first collaborative robot being used to perform a first task, the second collaborative robot being used to perform a second task, and the first task and the second task being in a task sequential execution relationship; configuring control data of the first collaborative robot according to the first task based on the collaborative control group, and controlling the first collaborative robot to perform the first task using the configured control data; monitoring the execution of the first task, establishing environmental impact data, task progress data, and task path data; acquiring the execution environment requirements of the second task, and configuring a comprehensive collaborative efficiency network in the collaborative control group, inputting the environmental impact data, task progress data, task path data, and execution environment requirements into the comprehensive collaborative efficiency network, and generating a collaborative efficiency optimization result; calling the collaborative control data of the second collaborative robot according to the collaborative efficiency optimization result, and performing collaborative control of the second collaborative robot with the collaborative control data.

[0006] In a possible implementation, the environmental impact data, task progress data, task path data, and execution environment requirements are input into the comprehensive collaborative efficiency network to generate a collaborative efficiency optimization result, and the following processing is also performed: the comprehensive collaborative efficiency calculation layer of the comprehensive collaborative efficiency network is activated, and the calculation is performed at the comprehensive collaborative efficiency calculation layer, as follows: ; in, For comprehensive collaborative efficiency, Representation in time After that, the difference between the impact of the first collaborative robot on the environment and the execution environment requirement of the second collaborative robot is , Characterize environmental impact data, To meet the execution environment requirements, is the upper tolerance environment of the second collaborative robot, Indicates the duration of the first task and the second task being performed simultaneously. Represents the total time of the first task and the second task, Representation in time The coordination between the task progress data of the first collaborative robot and the task requirements of the second collaborative robot, is the weight of the environmental compensation item, is the weight of the task overlapping time item, is the weight of the task coordination item; the comprehensive collaborative efficiency calculation layer is used to optimize the collaborative efficiency.

[0007] In a possible implementation, the calculation is performed at the comprehensive collaborative efficiency calculation layer, and the following processing is also performed: according to the sequential execution relationship between the first task and the second task, path constraints for the first collaborative robot and the second collaborative robot are established, and the path constraints are constraints that allow the second collaborative robot to execute the path after the first collaborative robot executes; the robot working areas of the first collaborative robot and the second collaborative robot are obtained, and path interference constraints are established according to the robot working areas; and the duration calculation constraints are performed simultaneously for the first task and the second task through path constraints and path interference constraints.

[0008] In a possible implementation, the collaborative control method of the industrial production robot also performs the following processing: establishing a self-updating weight allocation channel, and establishing a communication connection between the self-updating weight allocation channel and the comprehensive collaborative efficiency calculation layer; using the first task and the second task as matching data, using the self-updating weight allocation channel to perform task similarity matching, and establishing initial allocation weights based on the task similarity matching results; synchronizing the initial allocation weights to the comprehensive collaborative efficiency calculation layer, and using the initial allocation weights to set the weights of the environmental compensation item, the task overlap time item, and the task coordination item.

[0009] In a possible implementation, the collaborative control method of the industrial production robot also performs the following processing: obtaining collaborative efficiency optimization feedback, and establishing a self-update amplitude based on the collaborative efficiency optimization feedback; performing additional collection of environmental data, task progress data, and path data within a preset time window to establish an additional data set; feeding back the additional data set and the self-update amplitude to the self-update weight allocation channel, performing an adaptive update of the initial allocation weights, and optimizing the comprehensive collaborative efficiency calculation layer according to the adaptive update results.

[0010] In a possible implementation, the collaborative control method of the industrial production robot also performs the following processing: determining whether the coordination meets a preset threshold after a preset adjustment stage; if the coordination cannot meet the preset threshold, establishing an optimized reward factor based on the coordination value; obtaining the additional cost of the newly added collaborative robot, and using the newly added robot and the first collaborative robot to perform execution fitting of the first task, re-establishing the collaborative control fitting of the second collaborative robot based on the execution fitting result, and establishing cost savings based on the collaborative control fitting result; generating an optimized penalty factor after a balance analysis of the additional cost and the cost savings; making a retention decision for the newly added collaborative robot based on the optimized reward factor and the optimized penalty factor, and performing collaborative control based on the retention decision result.

[0011] In a possible implementation, the collaborative control method of the industrial production robot also performs the following processing: integrating a robot self-check controller in the collaborative control group; using the robot self-check controller to monitor the working data of the first collaborative robot and the second collaborative robot, and establishing a time-series working data set; performing data timing anomaly authentication of the time-series working data set based on the self-check controller, and reporting self-check anomalies based on the data timing anomaly authentication; and performing collaborative control management based on the self-check anomalies.

[0012] In a possible implementation, the collaborative control method of an industrial production robot also performs the following processing: using the configured control data and collaborative control data to establish data compensation for a timing work data set; using the data compensation to optimize timing anomaly authentication, and correcting self-inspection anomalies based on the optimization results.

[0013] It is intended to establish a collaborative control group of industrial production robots through the collaborative control method of industrial production robots proposed in this application; configure the control data of the first collaborative robot according to the first task based on the collaborative control group, and use the configured control data to control the first collaborative robot to perform the first task; establish environmental impact data, task progress data, and task path data; configure a comprehensive collaborative efficiency network, input the environmental impact data, task progress data, task path data, and execution environment requirements into the comprehensive collaborative efficiency network to generate a collaborative efficiency optimization result; and perform collaborative control of the second collaborative robot with the collaborative control data. This solves the technical problem that multiple robots in existing robot control rely on a fixed task sequence and preset control data, lack coordination with each other, and are unable to flexibly respond to complex tasks, which in turn leads to task execution conflicts, long waiting times, and reduced production efficiency, and achieves the technical effect of improving the collaborative efficiency of multiple robots in performing tasks and reducing the waiting time between tasks. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the accompanying drawings of the embodiment of the present invention will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the system according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0015] Figure 1 A schematic diagram of a process flow of a collaborative control method for an industrial production robot provided in an embodiment of the present application; Figure 2 A schematic diagram of the flow chart of calculations performed at the comprehensive collaborative efficiency calculation layer in the collaborative control method for industrial production robots provided in an embodiment of the present application. DETAILED DESCRIPTION

[0016] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0017] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0018] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0019] The present application embodiment provides a collaborative control method for industrial production robots, such as Figure 1 As shown, the method includes: Step S100, establishing a collaborative control group of industrial production robots, wherein the collaborative control group includes a first collaborative robot and a second collaborative robot, the first collaborative robot is used to perform a first task, the second collaborative robot is used to perform a second task, and the first task and the second task are in a task sequence execution relationship.

[0020] Preferably, a collaborative control group of industrial production robots is established, which specifically means that in the industrial production process, multiple robots (including a first collaborative robot and a second collaborative robot) are teamed up so that they can coordinate with each other when performing their respective tasks. Each robot is assigned a different task, and these tasks have a certain execution order. Specifically, the collaborative control group is composed of multiple robots, each collaborative robot is responsible for performing different tasks, and these tasks are interrelated and coordinated with each other. Through the control mechanism within the group, the collaborative control group ensures that multiple robots can effectively collaborate in the same production line or the same production process, avoid task conflicts, and improve overall work efficiency.

[0021] Preferably, the first collaborative robot is responsible for executing the first task in the production process, and the second collaborative robot is responsible for executing the second task in the production process, and the first task and the second task are in a task order execution relationship, which means that the second task must be started after the first task is completed, that is, there is a dependency relationship between the work of the two collaborative robots. For example, the first collaborative robot needs to complete a certain processing step before the second collaborative robot can take over the processed product for subsequent processing, ensuring that the robots complete tasks in the correct order and avoiding conflicts and duplications in task execution. For example, in the automobile manufacturing process, the first collaborative robot first assembles a certain part of the car body, and then the second collaborative robot welds the assembled car body parts. This sequential execution relationship ensures the continuity and efficiency of the entire production process. The two robots collaborate through the mechanism of the collaborative control group to ensure the sequential execution of tasks, avoid task conflicts or delays, improve the automation level of the production line, reduce manual intervention, and improve production efficiency and precision.

[0022] Step S200, based on the collaborative control group, configures control data of the first collaborative robot according to the first task, and uses the configured control data to control the first collaborative robot to perform the first task.

[0023] Preferably, the control parameters of the first collaborative robot are configured through the collaborative control group to ensure that each robot can complete the task in an orderly and efficient manner. Under the framework of the collaborative control group, relevant control parameters and data are allocated and configured for the first collaborative robot according to the requirements of the first task to ensure that it can perform the task correctly. These configured control data are then used to command and operate the first collaborative robot to perform the designated first task. Specifically, the task that the first collaborative robot is responsible for performing is the first task, such as assembling parts, handling materials, welding, spraying and other production tasks. Control data is configured for the first collaborative robot according to the specific requirements of the first task, which usually includes motion trajectory, the motion path or operation trajectory of the robot when performing the task (such as the motion path of the robot arm); motion parameters, the specific operation parameters required to perform the task (such as speed, acceleration, torque, etc.); workflow, the specific sequence of steps of the task, and how to adjust or optimize task execution under specific conditions. For example, if the first task is to transport parts to a specified location, the control data may include the motion trajectory of the robot arm, the force used when grasping, the speed of transport, and the precise position during the transport process. After the control data is fully configured for the first collaborative robot, the various operations of the first collaborative robot are controlled in real time according to these control data to ensure that it performs the first task according to the predetermined process and parameters. By configuring the required motion trajectory, operation steps, control parameters and other data for the collaborative robot according to the task requirements, the robot can efficiently and accurately perform complex industrial tasks to ensure the working order and task coordination of the robot in the collaborative control group, while improving production efficiency.

[0024] Step S300, monitoring the execution of the first task, and establishing environmental impact data, task progress data, and task path data.

[0025] Preferably, by monitoring the entire process of the first collaborative robot performing the first task, information such as environmental changes involved in the task execution process, task completion status, and the actual operation path of the robot is collected and analyzed, namely, environmental impact data, task progress data, and task path data. Specifically, during the process of the first collaborative robot performing the first task, its operation process, external environment, task status, etc. are monitored in real time to ensure that the task is carried out as planned, and problems or abnormal situations can be discovered in time to adjust the robot operation, including monitoring of the robot's motion, the speed and accuracy of task execution, changes in task status, whether obstacles are encountered, etc.; during the task execution process, the external environment (such as temperature, humidity, light, noise, vibration, etc.) affects the task execution. These environmental data can be monitored and collected in real time through various sensors (such as temperature sensors, humidity sensors, visual sensors, etc.). For example, in a welding task, changes in ambient temperature will affect the welding quality, and monitoring of environmental impact data is used to adjust welding parameters in real time.

[0026] Preferably, task progress data refers to real-time tracking information on task completion and execution progress, recording the start time of the task, the status of each stage of execution, and the current progress node of the task. Task progress data includes the completed part of the task, the estimated completion time of the task, and the current status of the task (such as completed, in progress, paused, etc.). By real-time monitoring of the execution progress of the task, it is ensured that the task is carried out as planned and task delays are avoided. If the progress is not as expected, adjustment measures are taken, such as dispatching other robots to keep the production line running normally.

[0027] Preferably, the task path data refers to the actual movement trajectory and operation path of the robot during the execution of the task, which is used to analyze whether the robot completes the task according to the predetermined path and action sequence. The task path data includes the specific position coordinates, movement speed, operation route and other information of the robot's movement. By monitoring the actual movement path of the robot, any deviation or abnormality can be found. For example, if the robot encounters an obstacle and deviates from the predetermined route, the path planning can be adjusted. For example, on an automobile production line, the first collaborative robot is responsible for assembling an automobile part, monitoring the task, collecting environmental impact data such as temperature and humidity of the working environment, and monitoring the task progress (such as the completion of the part assembly) and the path data executed by the robot. If the robot encounters environmental changes or route deviations during the assembly process, the robot operation can be adjusted in real time to ensure the smooth completion of the assembly task. By performing monitoring and collecting data, the reliability and efficiency of task execution can be ensured, the accuracy of tasks can be improved, the risk of task delays can be reduced, and the efficiency of the entire production process can be improved.

[0028] Step S400, obtain the execution environment requirements of the second task, and configure a comprehensive collaborative efficiency network in the collaborative control group, input the environmental impact data, task progress data, task path data, and execution environment requirements into the comprehensive collaborative efficiency network to generate a collaborative efficiency optimization result.

[0029] Furthermore, step S400 further includes step S410, activating the comprehensive collaborative efficiency calculation layer of the comprehensive collaborative efficiency network, and performing calculations with the comprehensive collaborative efficiency calculation layer, as follows: ; in, For comprehensive collaborative efficiency, Representation in time After that, the difference between the impact of the first collaborative robot on the environment and the execution environment requirement of the second collaborative robot is , Characterize environmental impact data, To meet the execution environment requirements, is the upper tolerance environment of the second collaborative robot, Indicates the duration of the first task and the second task being performed simultaneously. Represents the total time of the first task and the second task, Representation in time The coordination between the task progress data of the first collaborative robot and the task requirements of the second collaborative robot, is the weight of the environmental compensation item, is the weight of the task overlapping time item, is the weight of the task coordination item; step S420, using the comprehensive collaborative efficiency calculation layer to optimize the collaborative efficiency.

[0030] Preferably, before the second collaborative robot performs the second task, it collects and analyzes the execution conditions and environmental requirements required for the second task, and utilizes the comprehensive collaborative efficiency network of multiple robots working together, combined with the environmental data, progress data and path data during the execution of the first task, to optimize the collaborative efficiency and generate a collaborative control optimization result to ensure that the second task can be completed efficiently and accurately. Specifically, the specific environmental requirements of the second task are obtained through sensors, environmental monitoring equipment or preset conditions in task planning. The execution environment requirements of the second task refer to the specific environmental conditions required for the second collaborative robot when performing the task, which may include physical environment requirements, such as temperature, humidity, workspace, material location, etc., and may also include equipment status, tool configuration, etc.

[0031] Preferably, the comprehensive collaborative efficiency network is a mathematical model for evaluating the collaborative work efficiency of multiple robots. The network performs a comprehensive evaluation based on various task-related input data, that is, by analyzing and calculating multiple variables (such as environmental requirements, impacts, task progress, paths, etc.) to optimize the overall efficiency of the robots' collaborative work and find the best task execution plan. The optimization results of the comprehensive collaborative efficiency network are used to adjust the collaborative working relationship between multiple robots in real time, so that different robots can perform their respective tasks at the right time and in the best manner, thereby improving overall production efficiency. For example, according to the completion status of the first task and the execution requirements of the second task, the start-up time, path and operating parameters of the second collaborative robot are adjusted to avoid task conflicts or waste of resources.

[0032] Preferably, the environmental impact data, task progress data, task path data of the first task and the execution environment requirements of the second task are input into the comprehensive collaborative efficiency network, and the comprehensive collaborative efficiency calculation layer of the comprehensive collaborative efficiency network is activated. Then, the comprehensive collaborative efficiency calculation layer calculates and optimizes the collaborative efficiency, comprehensively evaluates the influence of various factors, and ensures that the second task can be executed under appropriate conditions. Not only the current environment is considered, but also the relationship and synergy between tasks are analyzed to improve the overall work efficiency. Finally, the collaborative efficiency optimization result is output, which includes how to best configure the second collaborative robot to perform the control parameters of the second task, usually including start-up time (based on the progress of the first task, determine when the second collaborative robot starts the second task), path planning (based on the current task path and working environment, plan the optimal operation route for the second collaborative robot to ensure that the task can be completed without conflicting with other robots) and operation parameter adjustment (based on environmental data, optimize the operation parameters of the second collaborative robot, such as speed, force, angle, etc., to ensure the accuracy and efficiency of task execution), thereby effectively improving the efficiency of robot collaborative work and ensuring smooth connection between tasks and optimal utilization of resources.

[0033] Preferably, the calculation is performed at the comprehensive collaborative efficiency calculation layer as follows: ; in, For comprehensive collaborative efficiency, Representation in time After that, the difference between the impact of the first collaborative robot on the environment and the execution environment requirement of the second collaborative robot is , Characterize environmental impact data, To meet the execution environment requirements, is the upper tolerance environment of the second collaborative robot, Indicates the duration of the first task and the second task being performed simultaneously. Represents the total time of the first task and the second task, Representation in time The coordination between the task progress data of the first collaborative robot and the task requirements of the second collaborative robot, is the weight of the environmental compensation item, is the weight of the task overlapping time item, is the weight of the task coordination item.

[0034] Preferably, the comprehensive collaborative efficiency calculation layer is a module in the comprehensive collaborative efficiency network, which includes a data input unit (receiving data such as task progress, task path, environmental changes, etc.), a core calculation unit (processing and analyzing multidimensional data through pre-set optimization algorithms, such as linear programming, genetic algorithms, deep learning, etc., to calculate the optimal solution for collaborative efficiency) and an output unit (outputting optimized control parameters and strategies), which is used to integrate various factors that affect the robot's work efficiency, such as task sequence, environmental conditions, task paths, etc., and generate collaborative efficiency optimization results through complex calculations and analysis, so as to find the optimal configuration plan for the collaborative work of robots, ensure that all robots work together under the best conditions, reduce task execution time, waste of resources, and interference or conflict between robots, thereby improving overall production efficiency.

[0035] like Figure 2 As shown, step S410 further includes step S411, establishing path constraints for the first collaborative robot and the second collaborative robot according to the sequential execution relationship between the first task and the second task, wherein the path constraint is a constraint that allows the second collaborative robot to execute the path after the first collaborative robot executes; step S412, acquiring the robot working areas of the first collaborative robot and the second collaborative robot, and establishing path interference constraints according to the robot working areas; step S413, performing duration calculation constraints for the first task and the second task simultaneously through path constraints and path interference constraints.

[0036] Preferably, in the process of multi-robot collaborative work, in order to ensure smooth task connection and avoid task conflicts, the robot's path and work area are constrained through path planning and workspace analysis to ensure that multiple robots can efficiently and safely collaborate in the same working environment. Specifically, according to the sequential execution relationship between the first task and the second task, the path constraints of the first collaborative robot and the second collaborative robot are established, that is, the second collaborative robot must perform the task on the designated path after the first collaborative robot completes its task (the second collaborative robot cannot enter the same work area before the first collaborative robot completes its task), ensuring that the tasks between the two robots are performed alternately, avoiding conflicts caused by the two robots operating in the same area at the same time, for example, the first collaborative robot must complete the installation of a component before the second collaborative robot can enter the area along the same path for welding.

[0037] Preferably, each collaborative robot occupies a certain space during the working process, which is called the robot working area, which includes not only the actual floor space of the robot, but also the spatial range covered by its operating arm, tools and possible motion trajectory. When multiple robots work collaboratively in the same working environment, by analyzing the working areas of the first and second collaborative robots, it is predicted whether the paths of the two robots will overlap or interfere with each other during the working process, thereby establishing a path interference constraint to prevent conflict, which is used to ensure that there is no interference between the working paths and working areas of the robots, that is, to ensure that multiple robots will not collide due to simultaneous operation; then based on the path constraints and path interference constraints, the time for multiple robots to perform tasks in the same working area is restricted, that is, the execution order and duration of the tasks are further optimized, so that the two tasks can be performed as synchronously as possible without conflict. Specifically, by reasonably calculating the execution time of the first task and the second task, the robot's workflow is optimized, the waiting time between robots is reduced, and work efficiency is maximized. For example, if the first collaborative robot completes a part of the task, the second collaborative robot can enter the non-interference area in advance to start operation without waiting for the entire task to be completely completed, thereby improving the smoothness of task connection and reducing unnecessary waiting time, thereby optimizing overall production efficiency.

[0038] Step S410 further includes step S414, establishing a self-update weight allocation channel, and establishing a communication connection between the self-update weight allocation channel and the comprehensive collaborative efficiency calculation layer; step S415, using the first task and the second task as matching data, using the self-update weight allocation channel to perform task similarity matching, and establishing initial allocation weights based on the task similarity matching results; step S416, synchronizing the initial allocation weights to the comprehensive collaborative efficiency calculation layer, and using the initial allocation weights to set the weights of the environmental compensation item, the task overlap time item, and the task coordination item.

[0039] Preferably, by establishing a self-updating weight allocation channel and communicating with the comprehensive collaborative efficiency calculation layer, the weights of task allocation can be dynamically adjusted according to factors such as task similarity, environmental conditions and task coordination, thereby improving work efficiency. Specifically, the self-updating weight allocation channel is a channel based on an automated weight adjustment mechanism that dynamically allocates weights according to real-time changes in tasks, that is, the weight priority during task allocation is automatically adjusted according to the execution status of the current task, environmental changes, and the relationship between tasks, to ensure that the efficiency of the entire collaborative work is continuously optimized. The communication connection between the self-updating weight allocation channel and the comprehensive collaborative efficiency calculation layer allows the two modules to share data and information. The comprehensive collaborative efficiency calculation layer obtains the weight information adjusted by the weight allocation channel through the communication connection, analyzes the overall efficiency of multi-robot collaborative work, and further optimizes the order and parameters of task execution.

[0040] Preferably, the tasks that need to be currently executed (such as the first task and the second task respectively executed by two collaborative robots) are used as input data to analyze the similarity between these tasks. Specifically, the analysis is performed through the self-updating weight allocation channel, and the characteristics of different tasks are compared to determine their similarity, so as to reasonably allocate resources and adjust the execution strategy. For example, if two tasks involve similar conditions (such as matching task types, workspaces, resource requirements, time arrangements, etc.), they are considered to have high similarity, and initial allocation weights are established based on the task similarity matching results. The calculated initial allocation weights are then passed to the comprehensive collaborative efficiency calculation layer, which further optimizes the task scheduling. Collaboration between robots, that is, determining the priority and resource allocation of tasks according to weight values, thereby optimizing the execution order and strategy of the entire collaborative work, including using the initial allocation weights to set the weights of environmental compensation items, task overlap time items, and task coordination items. Environmental compensation items refer to the adjustment of task weights under different environmental conditions; task overlap time items refer to the adjustment of task weights according to the execution time of tasks and the overlap time between them, thereby reducing conflicts or waiting time between tasks and ensuring smoother collaborative work; task coordination items refer to weights set according to the degree of collaboration between tasks. If two tasks are highly dependent on each other, the weight of the task coordination item will be higher to ensure that the two tasks can be smoothly connected. By adjusting the environmental compensation, overlap time, and coordination of tasks, efficient and flexible task scheduling and robot collaboration can be achieved, thereby ensuring the maximum efficiency and coordination of task execution in complex industrial scenarios.

[0041] Step S420 further includes step S421, obtaining collaborative efficiency optimization feedback, and establishing a self-update amplitude based on the collaborative efficiency optimization feedback; step S422, performing additional collection of environmental data, task progress data, and path data within a preset time window to establish an additional data set; step S423, feeding back the additional data set and the self-update amplitude to the self-update weight allocation channel, performing an adaptive update of the initial allocation weights, and optimizing the comprehensive collaborative efficiency calculation layer according to the adaptive update results.

[0042] Preferably, in multi-robot collaborative work, optimization feedback information is obtained based on factors such as task execution effect and resource utilization efficiency, which reflects the efficiency of the current collaborative work. Specifically, the collaborative work efficiency of each robot is calculated and analyzed, including task execution time, path planning, environmental adaptability, etc. The generated feedback information is used to adjust task scheduling and operating parameters. Based on these feedbacks, a dynamic adjustment amplitude is calculated, called the self-update amplitude, which is a key parameter for adjusting task allocation weights. The amplitude depends on the change in collaborative efficiency reflected by the feedback data. If the change in collaborative efficiency is more obvious, the self-update amplitude is increased to adjust the task weight to a greater extent; if the efficiency change is small, the self-update amplitude is small, indicating that only slight adjustments are required; that is, the scheduling strategy is flexibly changed according to the effect of task execution to improve the overall collaborative efficiency.

[0043] Preferably, the preset time window is a set time period, and environmental data, task progress data, and path data are collected within the preset time window to establish an additional data set, wherein the environmental data includes dynamic factors in the working environment, such as temperature, humidity, light intensity, noise level, etc.; the task progress data records the execution of the task, including the percentage of completion of each task, delays, whether the task is progressing as planned, etc.; the path data refers to the actual operation path of the robot or task execution, and these path data are recorded and compared with the predetermined path to analyze whether there is deviation, conflict or optimization space; then the collected additional data set and the self-update amplitude established according to the collaborative efficiency feedback are fed back to the self-update weight allocation channel, and the initial allocation weight is adaptively updated, that is, according to the latest information of the additional data set (such as environmental changes, task progress, path deviation The self-update amplitude is used to dynamically reallocate the execution priority, path planning, and time arrangement of tasks. For example, if a task is delayed due to changes in environmental conditions, the priority and resource allocation of the task are increased to speed up the execution progress. Finally, the comprehensive collaborative efficiency calculation layer is optimized according to the adaptive update results, that is, the adjusted task allocation weights are synchronized to the comprehensive collaborative efficiency calculation layer. Through these updated data, task scheduling, resource allocation, path planning, etc. are recalculated and optimized to ensure that robots or task systems work together in the best way in the new environment, including adjustment of task scheduling order, reallocation of resources, optimization of robot operation paths, replanning of execution time, etc., to achieve more optimized scheduling and task execution plans, to ensure that multiple robots or task systems can work together efficiently and reduce resource waste and time delays.

[0044] Step S500, calling the collaborative control data of the second collaborative robot according to the collaborative efficiency optimization result, and executing the collaborative control of the second collaborative robot with the collaborative control data.

[0045] Preferably, according to the generated collaborative efficiency optimization result, the control parameters and operation instructions required by the second collaborative robot are called from the pre-set control database to ensure that the second collaborative robot can perform the second task in an optimized manner. Specifically, the collaborative efficiency optimization result includes the optimal configuration of the second collaborative robot when performing the task, such as the operation path, start time, speed, action sequence, etc., to ensure the maximum collaborative efficiency between multiple robots and optimize the use of resources and time. The collaborative control data is the pre-configured operation instructions and control parameters required for the second collaborative robot to perform the task, covering detailed information on how to perform a specific task. According to the collaborative efficiency optimization result, the control data matching the second task is called from the repository, including the operation path, execution parameters (such as moving speed, operation force, execution angle, etc.), start time, and action sequence, etc. By calling the appropriate collaborative control data, the second collaborative robot can accurately connect with the previous task (the task completed by the first collaborative robot) to avoid time waste or operation conflicts. For example, when the first collaborative robot completes the assembly task, the second collaborative robot can quickly enter the work area to complete the welding task; collaborative control data not only determines when the robot performs the task, but also determines how the task is performed, ensuring that the robot achieves the best accuracy and efficiency when performing the task. For example, in the handling task, the control data will guide the robot on how to grab, carry and place items to ensure the shortest handling path and the least energy consumption. By calling collaborative control data, efficient collaboration between multiple robots is achieved, and tasks are seamlessly connected between different robots, which is convenient for optimizing task execution efficiency, reducing time waste, and maximizing the overall collaborative efficiency of the production line.

[0046] Step S500 further includes step S510, determining whether the coordination meets the preset threshold after the preset adjustment stage; step S520, if the coordination cannot meet the preset threshold, establishing an optimization reward factor based on the coordination value; step S530, obtaining the additional cost of the newly added collaborative robot, and using the newly added robot and the first collaborative robot to perform execution fitting of the first task, re-establishing the collaborative control fitting of the second collaborative robot based on the execution fitting result, and establishing cost savings based on the collaborative control fitting result; step S540, after performing a balance analysis on the additional cost and the cost savings, generating an optimization penalty factor; step S550, making a retention decision for the newly added collaborative robot based on the optimization reward factor and the optimization penalty factor, and performing collaborative control based on the retention decision result.

[0047] Preferably, coordination is a measure of the degree of mutual cooperation among multiple collaborative robots when performing tasks, reflecting the synchronization of task execution between robots, the smoothness of connection, the rationality of task allocation, etc. The preset adjustment phase is a period of operation used to observe and evaluate the collaborative effect of robot task execution. The preset threshold is the preset minimum standard for robot collaborative work. If the coordination is lower than this threshold, it means that there are problems in the collaboration between robots, such as task conflicts, execution delays, path interference, etc., and an optimization reward factor is established based on the coordination value, that is, by establishing a reward mechanism to motivate robots to optimize. The optimization reward factor guides adjustments in task allocation, path optimization, resource utilization, etc. The lower the coordination, the higher the optimization reward factor.

[0048] Preferably, the additional cost of adding a new collaborative robot to the collaborative work system is the additional cost, which may include the robot's hardware cost, operating cost, maintenance cost, and additional resource consumption. Execution fitting refers to evaluating the effect of the newly added collaborative robot and the existing collaborative robot (such as the first collaborative robot) performing tasks together through simulation, analyzing the collaborative efficiency and resource consumption between the two robots, and readjusting the task execution plan and control strategy of the second collaborative robot (and other robots) according to the task fitting results between the newly added robot and the first robot. Then, through collaborative control fitting, it is calculated how the newly added robot helps to improve overall efficiency, shorten task time, or reduce resource consumption, thereby establishing cost savings and reflecting the efficiency improvement brought about by the introduction of the new robot; by comparing the costs brought by the new robot (the additional cost ) and the resources or time saved (cost savings), a cost-benefit analysis is conducted. If the cost savings are greater than the additional cost, the new robot is beneficial; otherwise, an optimization penalty factor needs to be introduced to adjust the task allocation strategy to remind the team to reduce the allocation of resources to the new robot. Finally, considering the optimization reward factor and the optimization penalty factor, a decision is made whether to retain the new collaborative robot based on whether the new robot improves the overall collaborative efficiency, reduces resource consumption, or reduces the task execution time. If the optimization reward factor is large, it indicates that the new robot has effectively improved the efficiency, and the robot is retained. If the optimization penalty factor is large, it indicates that the cost brought by the new robot is higher than the benefit, and the robot is not retained. Finally, based on the result of the retention decision, the task allocation, path planning, and resource scheduling of the collaborative work of the robots are updated for collaborative control.

[0049] Step S500 further includes step S560, integrating a robot self-check controller in the collaborative control group; step S570, using the robot self-check controller to monitor the working data of the first collaborative robot and the second collaborative robot, and establishing a time-series working data set; step S580, performing data timing anomaly authentication of the time-series working data set based on the self-check controller, and reporting a self-check anomaly based on the data timing anomaly authentication; step S590, performing collaborative control management based on the self-check anomaly.

[0050] Preferably, a self-check controller is configured for each robot in the collaborative control group, so that each robot can monitor its own working status in real time. The self-check controller is used to monitor the robot in real time and is responsible for self-checking the working status of the robot, such as detecting potential problems in the operation of the robot, such as hardware failure, task execution deviation, sensor abnormality, etc., to ensure independent monitoring of the operating status of each robot, while ensuring the operational reliability of the entire collaborative system; then the robot self-check controller is used to collect various working data of the first and second collaborative robots when performing tasks in real time, which may include motion path, speed, execution time, execution accuracy, sensor data, workload, etc., and these collected data are recorded as a time series working data set in chronological order; then the time series working data set is subjected to data timing anomaly authentication, that is, by analyzing the time series working data set, anomalies in the robot's working state are detected. Specifically, the actual working data is compared with the preset normal working mode to detect any behavior or state that exceeds the preset range. For example, whether the robot's running speed suddenly slows down at a specific time point, whether the execution path deviates from the predetermined trajectory, whether the task execution time has exceeded, etc. If the self-checking controller finds an abnormality through timing data authentication, it will generate a self-checking abnormality report containing specific information about the abnormality, including the time when the abnormality occurred, related task data, possible causes of the abnormality, etc. Finally, the task allocation and execution strategy of the entire collaborative control group are adjusted according to the self-checking abnormality report. That is, when a robot has an abnormality, different management measures are taken according to the severity and type of the abnormality, such as reallocating tasks, adjusting execution strategies, or shutting down for maintenance. Through collaborative control management, timely adjustments are ensured when abnormalities occur to maintain the smooth execution of tasks, while avoiding the spread of abnormalities or causing larger problems.

[0051] Step 570 further includes step S571, using the configured control data and collaborative control data to establish data compensation for the timing work data set; step S572, using the data compensation to optimize the timing anomaly authentication, and correcting the self-test anomaly according to the optimization result.

[0052] Preferably, based on the configured control data (such as task path, speed, action sequence, accuracy requirements and other parameters) and collaborative control data (control data for coordinating task allocation, path planning, time management, etc. between each robot), errors or data deficiencies that may exist in the robot's working process are supplemented and corrected. For example, if the robot encounters external interference or sensor failure during the execution of the task, resulting in incomplete or deviated data, these erroneous or missing data are compensated by referring to the preset control data; then the compensated data is used to re-optimize the timing anomaly authentication process, that is, by re-analyzing the compensated complete data, abnormal situations can be more accurately identified, and the possibility of false alarms or missed abnormalities can be reduced. The optimized authentication helps to correct or fill in the data deviations and omissions in the working process, thereby making the timing anomaly authentication more accurate; when abnormal situations in the robot's working process are found through the timing anomaly authentication, these abnormal situations are re-evaluated based on the optimized data to see if they are real abnormalities. If the optimized results show that the previous abnormality detection is incorrect (such as a false alarm caused by data loss or deviation), correction is performed to avoid unnecessary intervention or adjustment caused by false alarms, thereby avoiding unnecessary intervention and adjustment, and improving the reliability and accuracy of the robot collaborative control.

[0053] The above specific implementation manner does not constitute a limitation to the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiment and can still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A collaborative control method for industrial production robots, characterized in that: The method comprises: Establishing a collaborative control group of industrial production robots, wherein the collaborative control group includes a first collaborative robot and a second collaborative robot, wherein the first collaborative robot is used to perform a first task, and the second collaborative robot is used to perform a second task, and the first task and the second task are in a task sequential execution relationship; Based on the collaborative control group configuring control data of the first collaborative robot according to the first task, using the configured control data to control the first collaborative robot to perform the first task; Performing execution monitoring on the first task to establish environmental impact data, task progress data, and task path data; Obtain the execution environment requirements of the second task, and configure a comprehensive collaborative efficiency network in the collaborative control group, input the environmental impact data, task progress data, task path data, and execution environment requirements into the comprehensive collaborative efficiency network, and generate a collaborative efficiency optimization result; The collaborative control data of the second collaborative robot is called according to the collaborative efficiency optimization result, and the collaborative control of the second collaborative robot is executed by the collaborative control data.

2. The collaborative control method of an industrial production robot according to claim 1, characterized in that: The step of inputting the environmental impact data, task progress data, task path data, and execution environment requirements into the comprehensive collaborative efficiency network to generate collaborative efficiency optimization results also includes: Activate the comprehensive collaborative efficiency calculation layer of the comprehensive collaborative efficiency network and perform calculations using the comprehensive collaborative efficiency calculation layer as follows: ； in, For comprehensive collaborative efficiency, Representation in time After that, the difference between the impact of the first collaborative robot on the environment and the execution environment requirement of the second collaborative robot is , Characterize environmental impact data, To meet the execution environment requirements, is the upper tolerance environment of the second collaborative robot, Indicates the duration of the first task and the second task being performed simultaneously. Represents the total time of the first task and the second task, Representation in time The coordination between the task progress data of the first collaborative robot and the task requirements of the second collaborative robot, is the weight of the environmental compensation item, is the weight of the task overlapping time item, is the weight of the task coordination item; The comprehensive collaborative efficiency calculation layer is used to optimize the collaborative efficiency.

3. The collaborative control method of an industrial production robot according to claim 2, characterized in that: The calculation at the comprehensive collaborative efficiency calculation layer also includes: Establishing a path constraint between the first collaborative robot and the second collaborative robot according to a sequential execution relationship between the first task and the second task, wherein the path constraint is a constraint that the second collaborative robot is allowed to execute after the first collaborative robot executes the path; Acquire robot working areas of the first collaborative robot and the second collaborative robot, and establish path interference constraints according to the robot working areas; The duration calculation constraints are performed simultaneously on the first task and the second task through path constraints and path interference constraints.

4. The collaborative control method of an industrial production robot according to claim 2, characterized in that: The method further comprises: Establish a self-updating weight distribution channel, and establish a communication connection between the self-updating weight distribution channel and the comprehensive collaborative efficiency calculation layer; The first task and the second task are used as matching data, and the task similarity matching is performed using the self-updating weight allocation channel, and the initial allocation weight is established according to the task similarity matching results; The initial allocation weights are synchronized to the comprehensive collaborative efficiency calculation layer, and the weights of the environmental compensation item, the task overlap time item, and the task coordination item are set using the initial allocation weights.

5. The collaborative control method of an industrial production robot according to claim 4, characterized in that: The method further comprises: Obtain collaborative efficiency optimization feedback, and establish a self-update amplitude based on the collaborative efficiency optimization feedback; Perform additional collection of environmental data, task progress data, and path data within a preset time window to establish an additional data set; The additional data set and the self-update amplitude are fed back to the self-update weight allocation channel, and the adaptive update of the initial allocation weights is performed. The comprehensive collaborative efficiency calculation layer is optimized according to the adaptive update results.

6. The collaborative control method of an industrial production robot according to claim 2, characterized in that: The method further comprises: Determine whether the coordination meets a preset threshold after a preset adjustment phase; If the coordination fails to meet the preset threshold, an optimization reward factor is established based on the coordination value; Obtain the additional cost of the newly added collaborative robot, and use the newly added robot and the first collaborative robot to perform execution fitting of the first task, re-establish the collaborative control fitting of the second collaborative robot based on the execution fitting result, and establish cost saving based on the collaborative control fitting result; After balancing the added costs and the saved costs, an optimization penalty factor is generated; The retention decision of the newly added collaborative robot is made according to the optimized reward factor and the optimized penalty factor, and the collaborative control is performed according to the retention decision result.

7. The collaborative control method of an industrial production robot according to claim 1, characterized in that: The method further comprises: Integrate the robot self-test controller in the collaborative control group; Using the robot self-checking controller to monitor the working data of the first collaborative robot and the second collaborative robot, and establishing a time-series working data set; Perform data timing anomaly authentication of the timing work data set based on the self-check controller, and report self-check anomalies based on the data timing anomaly authentication; Conduct collaborative control management based on self-check anomalies.

8. The collaborative control method of an industrial production robot according to claim 7, characterized in that: The method further comprises: Using the configured control data and cooperative control data to establish data compensation for the sequential working data set; The data compensation is used to optimize the timing anomaly authentication, and the self-check anomaly is corrected according to the optimization result.

Images