Automated installation system and method using industrial-grade robotic arms

Abstract

The present invention belongs to the technical field of smart factories. An automated installation system and method using industrial-grade robotic arms are provided. The method comprises: obtaining a number of assembly tasks to be implemented, matching the task attributes of each assembly task to obtain an industrial-grade robotic arm of a corresponding type; performing an assembly difficulty assessment based on the assembly efficiency data and task attributes of the industrial-grade robotic arm of the corresponding type, and obtaining a corresponding task difficulty assessment value; inputting the task difficulty assessment value, regional assembly line length, and assembly line transmission speed corresponding to each assembly task into a Transformer prediction model, and obtaining the number of industrial-grade robotic arms corresponding to each assembly task; controlling each industrial-grade robotic arm to go to the regional assembly line corresponding to each assembly task, and collaboratively completing each of the assembly tasks for the motorcycle. The present invention determines an appropriate number of industrial-grade robotic arms for each regional assembly line based on the assembly task, significantly improving the efficiency of motorcycle assembly.

Description

Technical Field

[0001] The present invention relates to the technical field of smart factories, and in particular to an automated installation system and method using an industrial-grade robotic arm. Background Art

[0002] With the development and advancement of technology, motorcycle assembly lines have implemented automated assembly using industrial-grade robotic arms, significantly improving production efficiency. Existing motorcycle assembly lines are equipped with multiple industrial-grade robotic arms, each of which can be assigned different assembly tasks. Each group of industrial-grade robotic arms is dedicated to completing a specific motorcycle assembly process, such as Group A for vibration damping assembly and Group B for headlights. Furthermore, each group includes a specific number of industrial-grade robotic arms, each dedicated to assembling a different motorcycle, further improving assembly efficiency.

[0003] However, existing motorcycle assembly lines based on industrial-grade robotic arms have fixed placements and are assigned fixed assembly tasks, while motorcycle assembly tasks vary. This means that existing motorcycle assembly lines based on industrial-grade robotic arms cannot dynamically adjust the layout and task allocation of the robotic arms based on changes in motorcycle assembly tasks. This results in motorcycle assembly efficiency that falls short of actual needs and requires improvement. Summary of the Invention

[0004] In this regard, the present invention provides an automated installation method, system, electronic device, computer storage medium and computer program product using an industrial-grade robotic arm to solve the above-mentioned technical problems.

[0005] The present invention discloses an automated installation method using an industrial-grade robotic arm, the method comprising the following steps:

[0006] Acquire a number of assembly tasks to be implemented, and match the task attributes of each assembly task to obtain an industrial-grade robotic arm of a corresponding type;

[0007] Performing an assembly difficulty assessment based on the assembly efficiency data of the corresponding type of industrial-grade robotic arm and the task attributes to obtain a corresponding task difficulty assessment value;

[0008] Inputting the task difficulty assessment value, regional assembly line length, and assembly line transmission speed corresponding to each assembly task into the Transformer prediction model, and obtaining the number of industrial-grade robotic arms corresponding to each assembly task predicted by the Transformer prediction model;

[0009] The industrial-grade robotic arms of the corresponding type and number are controlled to go to the regional assembly lines corresponding to the respective assembly tasks, and collaboratively complete the respective assembly tasks for the motorcycle.

[0010] Preferably, the obtaining of several assembly tasks to be performed includes:

[0011] receiving assembly task data sent by an assembly task issuing server, and determining whether the assembly task data is structured data or unstructured data;

[0012] If the assembly task data is structured data, directly parsing the assembly task data to obtain each assembly task;

[0013] If the assembly task data is unstructured data, calling a semantic analysis module to perform semantic analysis on the assembly task data to obtain each assembly task;

[0014] The assembly tasks are arranged in order of assembly.

[0015] Preferably, the matching of the task attributes of each assembly task to obtain a corresponding type of industrial-grade robotic arm includes:

[0016] Communicate with each industrial-grade robotic arm in an idle state to obtain each locally installed assembly function plug-in and assembly function description information corresponding to each assembly task plug-in;

[0017] semantically matching the task attributes of the assembly task with the assembly function description information corresponding to each assembly task plug-in, and if the match is successful, associating the industrial-grade robot arm with the assembly task;

[0018] Repeat the above steps to complete the association between all idle industrial-grade robotic arms and the assembly tasks.

[0019] Preferably, performing assembly difficulty assessment based on assembly efficiency data of a corresponding type of industrial-grade robotic arm and the task attributes to obtain a corresponding task difficulty assessment value includes:

[0020] Obtaining a motorcycle assembly structure diagram corresponding to the assembly task, identifying each assembly node in the motorcycle assembly structure diagram according to the task attributes, and extracting geometric features of each assembly node; wherein the geometric features include the depth of the assembly node, the width of the entrance of the assembly node, and the orientation of the assembly node;

[0021] An assembly difficulty assessment is performed based on the assembly efficiency data of the corresponding type of industrial-grade robotic arm and the geometric features to obtain a corresponding task difficulty assessment value; wherein, the assembly efficiency data is obtained based on historical data of the same type of industrial-grade robotic arm performing assembly tasks with the same task attributes.

[0022] Preferably, the task difficulty assessment value, regional assembly line length, and assembly line transmission speed corresponding to each assembly task are input into a Transformer prediction model to obtain the number of industrial-grade robotic arms corresponding to each assembly task predicted by the Transformer prediction model, including:

[0023] Inputting the task difficulty evaluation value, the length of the regional assembly line, and the transmission speed of the assembly line corresponding to each assembly task into the Transformer prediction model, and the Transformer prediction model predicting a first layout quantity corresponding to the assembly task;

[0024] Obtaining the received record data of the assembly task, calculating the number of similar assembly tasks corresponding to each assembly task according to the record data, and determining an adjustment weight according to the number of similar assembly tasks; wherein the adjustment weight is a value greater than 1;

[0025] A second placement quantity is calculated based on the adjustment weight and the first placement quantity.

[0026] Preferably, the controlling of the arranged number of industrial-grade robotic arms of corresponding types to go to the regional assembly lines corresponding to the respective assembly tasks comprises:

[0027] Randomly selecting the number of industrial-grade robotic arms deployed from the industrial-grade robotic arms associated with the assembly task, and controlling the selected industrial-grade robotic arms to go to the regional assembly line corresponding to the assembly task;

[0028] After arriving at the corresponding regional assembly line, each industrial-grade robotic arm is evenly spaced and combined with a ground fixture to achieve fixation.

[0029] The present invention also discloses an automated installation system using an industrial-grade robotic arm. The system includes a control module and a storage module. The control module is electrically connected to the storage module and calls program code in the storage module to implement the following processing steps:

[0030] Acquire a number of assembly tasks to be implemented, and match the task attributes of each assembly task to obtain an industrial-grade robotic arm of a corresponding type;

[0031] Performing an assembly difficulty assessment based on the assembly efficiency data of the corresponding type of industrial-grade robotic arm and the task attributes to obtain a corresponding task difficulty assessment value;

[0032] Inputting the task difficulty assessment value, regional assembly line length, and assembly line transmission speed corresponding to each assembly task into the Transformer prediction model, and obtaining the number of industrial-grade robotic arms corresponding to each assembly task predicted by the Transformer prediction model;

[0033] The industrial-grade robotic arms of the corresponding type and number are controlled to go to the regional assembly lines corresponding to the respective assembly tasks, and collaboratively complete the respective assembly tasks for the motorcycle.

[0034] The present invention also discloses an electronic device, characterized in that it is applied to the system as described in any of the above items, and includes: at least one processor, a memory, and a computer program stored in the memory and capable of running on the at least one processor.

[0035] The present invention further discloses a computer storage medium, characterized in that: applied to the system as described in any of the above items, the computer storage medium stores a computer program.

[0036] The present invention further discloses a computer program product, characterized in that: it is applied to the system as described in any of the above items, and includes a computer program stored on a non-transitory computer-readable medium.

[0037] The beneficial effect lies in that the solution of the present invention changes the traditional method of fixedly installing industrial-grade robotic arms on existing motorcycle assembly lines. Instead, it can determine the appropriate number of corresponding industrial-grade robotic arms for each regional assembly line based on the specific assembly task, thereby ensuring that these industrial-grade robotic arms collaboratively complete the assembly of all motorcycles on the regional assembly line, significantly improving the efficiency of motorcycle assembly. Moreover, because the number of industrial-grade robotic arms deployed in each regional assembly line is determined based on the goal of completing the corresponding assembly task for all motorcycles entering the regional assembly line before leaving the regional assembly line, this can also minimize the number of industrial-grade robotic arms deployed, thereby reducing deployment costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0039] Figure 1 This is a flow chart of an automated installation method using an industrial-grade robotic arm disclosed in an embodiment of the present invention;

[0040] Figure 2 This is a schematic diagram of a process for determining a task difficulty evaluation value disclosed in an embodiment of the present invention;

[0041] Figure 3 This is a structural diagram of an automated installation system using an industrial-grade robotic arm disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0042] The following specific embodiments illustrate the implementation of this application. Those familiar with the art can easily understand the other advantages and functions of this application from the content disclosed in this specification. Obviously, the described embodiments are part of the embodiments of this application, but not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0043] In addition, the technical features involved in the different embodiments of the present application described below can be combined with each other as long as they do not conflict with each other.

[0044] Existing motorcycle assembly lines are equipped with multiple industrial-grade robotic arms, each assigned different assembly tasks. Each group of robotic arms is dedicated to completing a specific motorcycle assembly process, such as Group A for vibration damping assembly and Group B for headlights. Furthermore, each group includes a specific number of robotic arms, each dedicated to assembling a specific motorcycle, further improving assembly speed.

[0045] However, existing motorcycle assembly lines based on industrial-grade robotic arms have fixed placements and are assigned fixed assembly tasks, while motorcycle assembly tasks vary. This means that existing motorcycle assembly lines based on industrial-grade robotic arms cannot dynamically adjust the layout and task allocation of the robotic arms based on changes in motorcycle assembly tasks. This results in motorcycle assembly efficiency that falls short of actual needs and requires improvement.

[0046] In response to the above technical issues, such as Figure 1 As shown, an embodiment of the present invention discloses an automated installation method using an industrial-grade robotic arm, the method comprising the following steps:

[0047] Acquire a number of assembly tasks to be implemented, and match the task attributes of each assembly task to obtain an industrial-grade robotic arm of a corresponding type;

[0048] Performing an assembly difficulty assessment based on the assembly efficiency data of the corresponding type of industrial-grade robotic arm and the task attributes to obtain a corresponding task difficulty assessment value;

[0049] Inputting the task difficulty assessment value, regional assembly line length, and assembly line transmission speed corresponding to each assembly task into the Transformer prediction model, and obtaining the number of industrial-grade robotic arms corresponding to each assembly task predicted by the Transformer prediction model;

[0050] The industrial-grade robotic arms of the corresponding type and number are controlled to go to the regional assembly lines corresponding to the respective assembly tasks, and collaboratively complete the respective assembly tasks for the motorcycle.

[0051] Compared to the existing motorcycle assembly line based on industrial-grade robotic arms, which uses fixed deployment of industrial-grade robotic arms, the present invention sets the deployment position of industrial-grade robotic arms to dynamic, and dynamically adjusts the number of industrial-grade robotic arms based on the actual assembly task. The details are as follows:

[0052] First, several assembly tasks to be performed are obtained. Each assembly task corresponds to a specific assembly step in the motorcycle assembly process, such as the vibration damping assembly step or the headlight assembly step. The corresponding type of industrial-grade robotic arm is then matched to the task attributes of each assembly task. The present invention deploys multiple types of industrial-grade robotic arms in the assembly workshop, each of which is suitable for a specific assembly task, such as a handling robot arm, an installation robot arm, a painting robot arm, or a quality inspection robot arm.

[0053] Then, for each assembly task, the corresponding task difficulty assessment value is obtained based on the assembly efficiency data of various types of industrial-grade robotic arms and the task attribute evaluation of the assembly task. The task difficulty assessment value is used to characterize the difficulty of the corresponding type of industrial-grade robotic arm in implementing the assembly task. The task difficulty assessment value can be represented by the assembly time.

[0054] Next, a motorcycle assembly line consists of multiple regional assembly lines, each of which corresponds one-to-one to each of the aforementioned assembly links. The length of each regional assembly line and the transmission speed of the conveyor are known. The task difficulty assessment value, regional assembly line length, and assembly line transmission speed corresponding to each assembly task are input into the pre-built Transformer prediction model. The Transformer prediction model can then analyze and determine the number of industrial-grade robotic arms that should be deployed in each regional assembly line. When determining the number of industrial-grade robotic arms to be deployed, the Transformer prediction model assumes that all motorcycles entering the regional assembly line can complete the corresponding assembly task before leaving the regional assembly line. This can also minimize the number of industrial-grade robotic arms deployed, thereby reducing deployment costs.

[0055] Finally, the corresponding number of industrial robotic arms of the correct type is selected from the industrial robotic arm storage system and directed to the corresponding regional assembly lines. When the assembly operation begins, these industrial robotic arms assemble the motorcycles transferred to their operating areas to complete the corresponding assembly task. Several industrial robotic arms of different types on multiple regional assembly lines can collaboratively complete the various motorcycle assembly tasks.

[0056] The present invention, therefore, changes the traditional approach of fixedly deploying industrial-grade robotic arms on motorcycle assembly lines. Instead, it assigns an appropriate number of corresponding types of industrial-grade robotic arms to each regional assembly line based on specific assembly tasks. This ensures that these industrial-grade robotic arms collaboratively complete the assembly of all motorcycles on the regional assembly line, significantly improving motorcycle assembly efficiency. Furthermore, because the number of industrial-grade robotic arms deployed in each regional assembly line is determined to ensure that all motorcycles entering that regional assembly line complete their corresponding assembly tasks before leaving, this minimizes the number of deployed industrial-grade robotic arms, thereby reducing deployment costs.

[0057] Preferably, the obtaining of several assembly tasks to be performed includes:

[0058] receiving assembly task data sent by an assembly task issuing server, and determining whether the assembly task data is structured data or unstructured data;

[0059] If the assembly task data is structured data, directly parsing the assembly task data to obtain each assembly task;

[0060] If the assembly task data is unstructured data, calling a semantic analysis module to perform semantic analysis on the assembly task data to obtain each assembly task;

[0061] The assembly tasks are arranged in order of assembly.

[0062] In this embodiment of the present invention, a motorcycle manufacturer deploys an assembly task publishing server. Relevant personnel create corresponding assembly task data based on the production tasks for the corresponding motorcycles and submit this data to the assembly task publishing server. Each assembly task data has a specific trigger time. When the trigger time is reached and the motorcycle assembly line has completed the previous round of assembly tasks, the assembly task publishing server sends the new assembly task data to the motorcycle assembly line's scheduling server for execution.

[0063] At the same time, when formulating assembly task data, relevant personnel can choose appropriate data types on their own, mainly including structured data and unstructured data. Among them, structured data mainly refers to the assembly task table format, and unstructured data refers to assembly task data in the format of pictures, texts, etc. For structured data, the multiple assembly tasks involved in this assembly operation can be directly extracted from it; for unstructured data, the multiple assembly tasks involved in this assembly operation cannot be directly extracted from it. At this time, it is necessary to call the semantic analysis module to perform semantic analysis on the unstructured assembly task data, so as to indirectly obtain the multiple assembly tasks involved in this assembly operation. The distinction between structured data and unstructured data can be judged based on the above-mentioned information format, for example.

[0064] Preferably, the matching of the task attributes of each assembly task to obtain a corresponding type of industrial-grade robotic arm includes:

[0065] Communicate with each industrial-grade robotic arm in an idle state to obtain each locally installed assembly function plug-in and assembly function description information corresponding to each assembly task plug-in;

[0066] semantically matching the task attributes of the assembly task with the assembly function description information corresponding to each assembly task plug-in, and if the match is successful, associating the industrial-grade robot arm with the assembly task;

[0067] Repeat the above steps to complete the association between all idle industrial-grade robotic arms and the assembly tasks.

[0068] In an embodiment of the present invention, the industrial-grade robotic arm in the present invention is not a robotic arm with a single assembly function, but a universal type. Different types of assembly function plug-ins are downloaded and installed to the industrial-grade robotic arm in advance according to design requirements, and the industrial-grade robotic arm then has the corresponding assembly function. For example, if a certain industrial-grade robotic arm downloads and installs a rotation operation plug-in, it will have the assembly functions of screwing and punching. Of course, after downloading and installing the corresponding assembly function plug-in (each assembly function plug-in should belong to an industrial robotic arm of the same functional type, such as an assembly function plug-in for screwing and an assembly function plug-in for knocking belonging to an assembly robotic arm, and an assembly function plug-in for painting and an assembly function plug-in for cleaning belonging to a spraying robotic arm), the industrial-grade robotic arm can implement or switch the corresponding assembly function by replacing the operating head.

[0069] On the basis of the above, the dispatch server of the motorcycle assembly line of the present invention communicates with each industrial-grade robotic arm in an idle state, so that the assembly function plug-ins installed on each industrial-grade robotic arm and the assembly function description information of these assembly task plug-ins can be obtained. Among them, the assembly function description information is used to describe the type of assembly operation that can be achieved by the assembly function plug-in, such as screwing, knocking, etc. The task attributes of a specific assembly task are semantically analyzed and matched with the assembly function description information of a certain industrial-grade robotic arm, and the successfully matched industrial-grade robotic arm is associated with the corresponding assembly task. For example, if the task attribute is screw fixing of the fuel tank, and it is found that the assembly function description information of a certain assembly function plug-in corresponds to the screwing operation, the two are associated. Then, the association of each industrial-grade robotic arm in all idle states with the corresponding assembly tasks is completed one by one. At this point, each assembly task is associated with multiple adapted industrial-grade robotic arms.

[0070] Preferably, if Figure 2 As shown, the assembly difficulty evaluation is performed based on the assembly efficiency data of the corresponding type of industrial-grade robotic arm and the task attributes to obtain the corresponding task difficulty evaluation value, including:

[0071] Obtaining a motorcycle assembly structure diagram corresponding to the assembly task, identifying each assembly node in the motorcycle assembly structure diagram according to the task attributes, and extracting geometric features of each assembly node; wherein the geometric features include the depth of the assembly node, the width of the entrance of the assembly node, and the orientation of the assembly node;

[0072] An assembly difficulty assessment is performed based on the assembly efficiency data of the corresponding type of industrial-grade robotic arm and the geometric features to obtain a corresponding task difficulty assessment value; wherein, the assembly efficiency data is obtained based on historical data of the same type of industrial-grade robotic arm performing assembly tasks with the same task attributes.

[0073] In an embodiment of the present invention, the assembly task publishing server also sends a collection of motorcycle assembly structure drawings to the scheduling server of the motorcycle assembly line. The collection includes motorcycle assembly structure drawings corresponding to various assembly steps. Based on the assembly task, the collection of motorcycle assembly structure drawings can be filtered to obtain motorcycle assembly structure drawings suitable for the assembly line in the region. Each assembly node in the motorcycle assembly structure drawing is identified based on the task attributes. For example, a screwing operation corresponds to a screw hole, and a knocking operation corresponds to a protrusion. Geometric features of the identified assembly nodes are then extracted, including their depth, entry width, and orientation. The deeper the depth of the assembly node, the less favorable it is for industrial-grade robotic arm assembly, the longer the assembly time, and the higher the corresponding task difficulty assessment value. Conversely, the deeper the depth of the assembly node, the less favorable it is for industrial-grade robotic arm assembly, the shorter the assembly time, and the lower the corresponding task difficulty assessment value. Conversely, the wider the entry width of the assembly node, the more favorable it is for industrial-grade robotic arm assembly, the shorter the assembly time, and the lower the corresponding task difficulty assessment value. Conversely, the wider the entry width of the assembly node, the more favorable it is for industrial-grade robotic arm assembly, the shorter the assembly time, and the lower the corresponding task difficulty assessment value. Conversely, the wider the entry width of the assembly node, the more favorable it is for industrial-grade robotic arm assembly, the shorter the assembly time, and the lower the corresponding task difficulty assessment value. Conversely, the wider the entry width of the assembly node, the more favorable it is for industrial-grade robotic arm assembly, the shorter the assembly time, and the lower the corresponding task difficulty assessment value.

[0074] Then, based on the assembly efficiency data of the corresponding type of industrial-grade robotic arms and the aforementioned geometric features, the assembly difficulty of the assembly task of the assembly line in the region is evaluated to obtain a corresponding task difficulty evaluation value. The task difficulty evaluation value can be the aforementioned assembly time.

[0075] Among them, a corresponding evaluation model can be configured for the evaluation process, and historical assembly operation data of the same type of industrial-grade robotic arms performing the same type of assembly tasks can be collected. A set of training data can be constructed based on the historical assembly operation data. Each piece of training data can be [the historical assembly efficiency of the same type of industrial-grade robotic arms performing a specific type of assembly task, the geometric features of each assembly node on the motorcycle, and the actual assembly time]. Among them, the actual assembly time is used as the label data of the training data. Therefore, the above-mentioned evaluation model is trained using this set of training data until the training goal is achieved. The evaluation model obtained after training can synchronously analyze the assembly efficiency data and geometric features of the corresponding type of industrial-grade robotic arms, thereby predicting the assembly time required for the corresponding type of industrial-grade robotic arms to perform the current assembly task, that is, the time required to complete the assembly task of a motorcycle. The evaluation model is preferably constructed based on a graph convolutional network. The present invention does not limit the specific structure of the evaluation model.

[0076] Furthermore, the assembly efficiency data for a given type of industrial robotic arm is derived from historical data on the same type of industrial robotic arm performing assembly tasks with the same attributes. For example, statistical analysis is performed on the time taken by each industrial robotic arm of the same type to perform a screwing operation, yielding the corresponding average time. This average time is then used as the assembly efficiency data for the corresponding type of industrial robotic arm.

[0077] Preferably, the task difficulty assessment value, regional assembly line length, and assembly line transmission speed corresponding to each assembly task are input into a Transformer prediction model to obtain the number of industrial-grade robotic arms corresponding to each assembly task predicted by the Transformer prediction model, including:

[0078] Inputting the task difficulty evaluation value, the length of the regional assembly line, and the transmission speed of the assembly line corresponding to each assembly task into the Transformer prediction model, and the Transformer prediction model predicting a first layout quantity corresponding to the assembly task;

[0079] Obtaining the received record data of the assembly task, calculating the number of similar assembly tasks corresponding to each assembly task according to the record data, and determining an adjustment weight according to the number of similar assembly tasks; wherein the adjustment weight is a value greater than 1;

[0080] A second placement quantity is calculated based on the adjustment weight and the first placement quantity.

[0081] In an embodiment of the present invention, the Transformer prediction model can perform a comprehensive analysis of the task difficulty assessment value, regional assembly line length, and assembly line transmission speed corresponding to each assembly task, and then predict the first layout quantity corresponding to the assembly task.

[0082] Since the above-mentioned first layout quantity is actually an ideal value, it is also necessary to consider the "capacity" of the industrial-grade robotic arm to appropriately increase the first layout quantity. Specifically, during the actual assembly operation, engineers will evaluate the efficiency and accuracy of the industrial-grade robotic arm when executing each assembly task, and optimize the assembly task plug-in of the industrial-grade robotic arm based on the evaluation results, thereby improving its assembly efficiency and accuracy. Based on this, the present invention is further configured to obtain the recorded data of the assembly tasks received (i.e., executed) by the motorcycle assembly line, perform semantic similarity analysis on the current assembly task and each assembly task in the recorded data, determine the similarity above the similarity threshold as a similar assembly task, and then determine the adjustment weight based on the number of executions of these similar assembly tasks. Among them, the greater the number of similar assembly tasks executed, the more times or the greater the probability that the corresponding assembly task plug-in of the industrial-grade robotic arm configured on the assembly line has been optimized, and the greater the probability that it can complete the assembly task efficiently. At this time, the smaller the adjustment weight is set accordingly; conversely, the larger the adjustment weight is set accordingly, so as to ensure that all motorcycles on the assembly line in the area can complete the corresponding assembly tasks by appropriately increasing the number of industrial-grade robotic arms. It should be noted that the present invention does not require a specific limitation on the conversion method between the adjustment weight and the number of similar assembly tasks executed. It can be in the form of a specific formula or a comparison table, as long as it ensures that the adjustment weight and the number of similar assembly tasks executed meet the negative correlation relationship.

[0083] Preferably, the controlling of the arranged number of industrial-grade robotic arms of corresponding types to go to the regional assembly lines corresponding to the respective assembly tasks comprises:

[0084] Randomly selecting the number of industrial-grade robotic arms deployed from the industrial-grade robotic arms associated with the assembly task, and controlling the selected industrial-grade robotic arms to go to the regional assembly line corresponding to the assembly task;

[0085] After arriving at the corresponding regional assembly line, each industrial-grade robotic arm is evenly spaced and combined with a ground fixture to achieve fixation.

[0086] In an embodiment of the present invention, after determining the number of industrial-grade manipulators of the corresponding type required for each assembly task, the industrial-grade manipulators of the corresponding number can be randomly selected from the aforementioned association relationship, and these industrial-grade manipulators can be controlled to go to the regional assembly lines corresponding to the assembly tasks. After arriving at the corresponding regional assembly lines, they are arranged in a uniformly spaced manner and combined with ground fixing devices to achieve fixation, power supply, and communication, and then they can wait for subsequent formal assembly commands. Among them, the industrial-grade manipulator is equipped with a self-propelled mechanism, which can be wheeled, tracked, or tracked, without specific limitation.

[0087] It should be noted that the ground fixture comprises both a fixing mechanism and an electrical mechanism. The fixing mechanism temporarily secures the industrial robotic arm in place, preventing it from shaking or even collapsing during assembly operations, but the specific structural type of the fixing mechanism is not limited. The electrical mechanism includes a power cord / plug and a communication network to power the industrial robotic arm and establish a wired communication connection with the motorcycle assembly line's dispatch server (receiving instructions from the dispatch server via a more reliable wired communication method during the assembly process).

[0088] like Figure 3 As shown, an embodiment of the present invention further discloses an automated installation system using an industrial-grade robotic arm, the system comprising a control module and a storage module. The control module is electrically connected to the storage module and calls the program code in the storage module to implement the following processing steps:

[0089] Acquire a number of assembly tasks to be implemented, and match the task attributes of each assembly task to obtain an industrial-grade robotic arm of a corresponding type;

[0090] Performing an assembly difficulty assessment based on the assembly efficiency data of the corresponding type of industrial-grade robotic arm and the task attributes to obtain a corresponding task difficulty assessment value;

[0091] Inputting the task difficulty assessment value, regional assembly line length, and assembly line transmission speed corresponding to each assembly task into the Transformer prediction model, and obtaining the number of industrial-grade robotic arms corresponding to each assembly task predicted by the Transformer prediction model;

[0092] The industrial-grade robotic arms of the corresponding type and number are controlled to go to the regional assembly lines corresponding to the respective assembly tasks, and collaboratively complete the respective assembly tasks for the motorcycle.

[0093] The present invention also discloses an electronic device, which is applied to the system as described in any of the above items, and includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor.

[0094] An embodiment of the present invention further discloses a computer storage medium, which is applied to the system as described in any of the above items, and the computer storage medium stores a computer program.

[0095] An embodiment of the present invention further discloses a computer program product, which is applied to the system as described in any of the preceding items, and includes a computer program stored on a non-transitory computer-readable medium.

[0096] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0097] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0098] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps for the function specified in one or more boxes.

[0099] The above description is merely a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention.

Claims

1. An automated installation method using an industrial-grade robotic arm, characterized in that: The method comprises the following steps: Obtaining a number of assembly tasks to be implemented, each assembly task corresponding to each assembly link of the motorcycle assembly, and matching the task attributes of each assembly task to obtain a corresponding type of industrial-grade robotic arm; Performing an assembly difficulty assessment based on the assembly efficiency data of the corresponding type of industrial-grade robotic arm and the task attributes to obtain a corresponding task difficulty assessment value; Inputting the task difficulty assessment value, regional assembly line length, and assembly line transmission speed corresponding to each assembly task into the Transformer prediction model, and obtaining the number of industrial-grade robotic arms corresponding to each assembly task predicted by the Transformer prediction model, including: Inputting the task difficulty evaluation value, the length of the regional assembly line, and the transmission speed of the assembly line corresponding to each assembly task into the Transformer prediction model, and the Transformer prediction model predicting a first layout quantity corresponding to the assembly task; Obtaining the received record data of the assembly task, calculating the number of similar assembly tasks corresponding to each assembly task according to the record data, and determining an adjustment weight according to the number of similar assembly tasks; wherein the adjustment weight is a value greater than 1; Calculating a second layout quantity based on the adjustment weight and the first layout quantity; The number of arrangements corresponds to the number of motorcycles that can complete the corresponding assembly tasks before leaving the assembly line in the area. Controlling the deployed number of industrial-grade robotic arms of corresponding types to go to the regional assembly lines corresponding to the respective assembly tasks, and collaboratively completing the respective assembly tasks for the motorcycle; The matching of the task attributes of each assembly task to obtain a corresponding type of industrial-grade robotic arm includes: Communicate with each industrial-grade robotic arm in an idle state to obtain each locally installed assembly function plug-in and assembly function description information corresponding to each assembly task plug-in; semantically matching the task attributes of the assembly task with the assembly function description information corresponding to each assembly task plug-in, and if the match is successful, associating the industrial-grade robot arm with the assembly task; Repeat the above steps to complete the association between all idle industrial-grade robotic arms and the assembly tasks; The performing of the assembly difficulty assessment based on the assembly efficiency data of the corresponding type of industrial-grade robotic arm and the task attributes to obtain the corresponding task difficulty assessment value includes: Obtaining a motorcycle assembly structure diagram corresponding to the assembly task, identifying each assembly node in the motorcycle assembly structure diagram according to the task attributes, and extracting geometric features of each assembly node; wherein the geometric features include the depth of the assembly node, the width of the entrance of the assembly node, and the orientation of the assembly node; An assembly difficulty assessment is performed based on the assembly efficiency data of the corresponding type of industrial-grade robotic arm and the geometric features to obtain a corresponding task difficulty assessment value; wherein, the assembly efficiency data is obtained based on historical data of the same type of industrial-grade robotic arm performing assembly tasks with the same task attributes.

2. The automated installation method using an industrial-grade robotic arm according to claim 1, characterized in that: The obtaining of several assembly tasks to be performed includes: receiving assembly task data sent by an assembly task issuing server, and determining whether the assembly task data is structured data or unstructured data; If the assembly task data is structured data, directly parsing the assembly task data to obtain each assembly task; If the assembly task data is unstructured data, calling a semantic analysis module to perform semantic analysis on the assembly task data to obtain each assembly task; The assembly tasks are arranged in order of assembly.

3. The automated installation method using an industrial-grade robotic arm according to claim 1, characterized in that: The controlling of the arranged number of industrial-grade robotic arms of corresponding types to go to the regional assembly lines corresponding to the respective assembly tasks includes: Randomly selecting the number of industrial-grade robotic arms deployed from the industrial-grade robotic arms associated with the assembly task, and controlling the selected industrial-grade robotic arms to go to the regional assembly line corresponding to the assembly task; After arriving at the corresponding regional assembly line, each industrial-grade robotic arm is evenly spaced and combined with a ground fixing device for fixation.

4. An automated installation system using an industrial-grade robotic arm, comprising a control module and a storage module, characterized in that: The control module is electrically connected to the storage module and calls the program code in the storage module to implement the following processing steps: Acquire a number of assembly tasks to be implemented, and match the task attributes of each assembly task to obtain an industrial-grade robotic arm of a corresponding type; Performing an assembly difficulty assessment based on the assembly efficiency data of the corresponding type of industrial-grade robotic arm and the task attributes to obtain a corresponding task difficulty assessment value; Inputting the task difficulty assessment value, regional assembly line length, and assembly line transmission speed corresponding to each assembly task into the Transformer prediction model, and obtaining the number of industrial-grade robotic arms corresponding to each assembly task predicted by the Transformer prediction model, including: Inputting the task difficulty evaluation value, the length of the regional assembly line, and the transmission speed of the assembly line corresponding to each assembly task into the Transformer prediction model, and the Transformer prediction model predicting a first layout quantity corresponding to the assembly task; Obtaining the received record data of the assembly task, calculating the number of similar assembly tasks corresponding to each assembly task according to the record data, and determining an adjustment weight according to the number of similar assembly tasks; wherein the adjustment weight is a value greater than 1; Calculating a second layout quantity based on the adjustment weight and the first layout quantity; The number of arrangements corresponds to the number of motorcycles that can complete the corresponding assembly tasks before leaving the assembly line in the area. Controlling the deployed number of industrial-grade robotic arms of corresponding types to go to the regional assembly lines corresponding to the respective assembly tasks, and collaboratively completing the respective assembly tasks for the motorcycle; The matching of the task attributes of each assembly task to obtain a corresponding type of industrial-grade robotic arm includes: Communicate with each industrial-grade robotic arm in an idle state to obtain each locally installed assembly function plug-in and assembly function description information corresponding to each assembly task plug-in; semantically matching the task attributes of the assembly task with the assembly function description information corresponding to each assembly task plug-in, and if the match is successful, associating the industrial-grade robot arm with the assembly task; Repeat the above steps to complete the association between all idle industrial-grade robotic arms and the assembly tasks; The performing of the assembly difficulty assessment based on the assembly efficiency data of the corresponding type of industrial-grade robotic arm and the task attributes to obtain the corresponding task difficulty assessment value includes: Obtaining a motorcycle assembly structure diagram corresponding to the assembly task, identifying each assembly node in the motorcycle assembly structure diagram according to the task attributes, and extracting geometric features of each assembly node; wherein the geometric features include the depth of the assembly node, the width of the entrance of the assembly node, and the orientation of the assembly node; An assembly difficulty assessment is performed based on the assembly efficiency data of the corresponding type of industrial-grade robotic arm and the geometric features to obtain a corresponding task difficulty assessment value; wherein, the assembly efficiency data is obtained based on historical data of the same type of industrial-grade robotic arm performing assembly tasks with the same task attributes.

5. An electronic device, characterized in that: The method applied to any one of claims 1 to 3 comprises: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor.

6. A computer storage medium, characterized in that: Applied to the method according to any one of claims 1 to 3, the computer storage medium stores a computer program.

7. A computer program product, characterized in that: The method as claimed in any one of claims 1 to 3, comprising a computer program stored on a non-transitory computer readable medium.

Images