Robot teaching method, device and equipment based on virtual demonstrator and medium

Abstract

The invention discloses a robot teaching method, device and equipment based on a virtual demonstrator and a medium. The method is applied to a virtual demonstrator system, and comprises the following steps: receiving a voice instruction input by an operator and a selected to-be-trained robot; converting the voice instruction into a text instruction, and generating an initial code instruction from the text instruction through a preset large model; and correcting the initial code instruction to determine a target code instruction, and sending the target code instruction to the to-be-trained robot through a virtual demonstrator. By implementing the method, the problem of low teaching training efficiency of the industrial robot in the prior art can be solved.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial automation, and in particular to a robot teaching method, device, equipment and medium based on a virtual teaching pendant. Background Art

[0002] As the core equipment of modern advanced manufacturing industry, industrial robots have been widely used in many key fields such as 3C electronics, material handling, assembly and automobile manufacturing. With its high precision and high efficiency, it is known as the jewel in the crown of manufacturing industry. Traditional industrial robot control systems rely on teaching pendants for teaching control debugging, and coordinate the operation of multiple servo motors through motion controllers and servo drivers to achieve complex motion trajectory control. However, in the traditional industrial manufacturing model, the teaching pendant usually exists as an isolated on-site teaching terminal, lacking a unified management and coordination mechanism, resulting in low efficiency of industrial robot training in existing technologies, which not only limits the improvement of production efficiency, but also leads to a huge waste of human resources. Summary of the invention

[0003] The embodiments of the present invention provide a robot teaching method, device, equipment and medium based on a virtual teaching pendant, aiming to solve the problem of low teaching training efficiency of industrial robots in the prior art.

[0004] In the first aspect, an embodiment of the present invention provides a robot teaching method based on a virtual teach pendant, which is applied to a virtual teach pendant system, and includes: receiving voice instructions input by an operator and a selected robot to be trained; converting the voice instructions into text instructions, and generating initial code instructions from the text instructions through a preset large model; correcting the initial code instructions to determine target code instructions, and sending the target code instructions to the robot to be trained through the virtual teach pendant.

[0005] In the second aspect, an embodiment of the present invention also provides a robot teaching device based on a virtual teach pendant, which is applied to a virtual teach pendant system, and includes: an instruction receiving unit, used to receive voice instructions input by an operator and a selected robot to be trained; a generating unit, used to convert the voice instructions into text instructions, and generate initial code instructions from the text instructions through a preset large model; a sending unit, used to correct the initial code instructions to determine the target code instructions, and send the target code instructions to the robot to be trained through the virtual teach pendant.

[0006] In a third aspect, an embodiment of the present invention further provides a computer device, which includes a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the above method when executing the computer program.

[0007] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein the storage medium stores a computer program, wherein the computer program includes program instructions, and the program instructions can implement the above method when executed by a processor.

[0008] The embodiment of the present invention provides a robot teaching method, device, equipment and medium based on a virtual teaching pendant. The method is applied to a virtual teaching pendant system, which includes: receiving a voice instruction input by an operator and a selected robot to be trained; converting the voice instruction into a text instruction, and generating an initial code instruction from the text instruction through a preset large model; correcting the initial code instruction to determine a target code instruction, and sending the target code instruction to the robot to be trained through a virtual teaching pendant. The embodiment of the present invention can receive a voice instruction input by an operator and a selected robot to be trained, greatly improving the convenience and efficiency of operation, and accurately converting the voice instruction into a text instruction using speech recognition technology, providing a reliable basis for subsequent code generation. The text instruction is automatically parsed and the corresponding code instruction is generated through a preset large model, reducing the workload of manual code writing and improving the efficiency and accuracy of code generation. Finally, the target code instruction for teaching the robot to be trained is determined according to the code instruction detected by the operator and the virtual teaching pendant, so that the teaching process can be completed without actually contacting the robot, reducing the teaching cost and improving safety, and the virtual teaching pendant can simulate the real robot operating environment, so that the robot can be efficiently trained and learned, improving the training efficiency and effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying any creative work.

[0010] Figure 1 A schematic diagram of a flow chart of a robot teaching method based on a virtual teaching pendant provided in an embodiment of the present invention;

[0011] Figure 2 A schematic diagram of a sub-process of a robot teaching method based on a virtual teaching pendant provided in an embodiment of the present invention;

[0012] Figure 3 A schematic diagram of a sub-process of a robot teaching method based on a virtual teaching pendant provided in an embodiment of the present invention;

[0013] Figure 4 A schematic diagram of a sub-process of a robot teaching method based on a virtual teaching pendant provided in an embodiment of the present invention;

[0014] Figure 5 A schematic diagram of a sub-process of a robot teaching method based on a virtual teaching pendant provided in an embodiment of the present invention;

[0015] Figure 6 A schematic diagram of a sub-process of a robot teaching method based on a virtual teaching pendant provided in an embodiment of the present invention;

[0016] Figure 7 A schematic diagram of a sub-process of a robot teaching method based on a virtual teaching pendant provided in an embodiment of the present invention;

[0017] Figure 8 A schematic block diagram of a robot teaching device based on a virtual teaching pendant provided in an embodiment of the present invention;

[0018] Fig. 9 A schematic block diagram of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0021] It should also be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0022] It should be further understood that the term "and / or" used in the present description and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0023] See also Figure 1 , Figure 1A flow chart of a robot teaching method based on a virtual teaching pendant provided in an embodiment of the present invention. The robot teaching method based on a virtual teaching pendant in this embodiment can be applied to a virtual teaching system. A 5G communication module is installed on each industrial robot to receive and transmit information to the Internet of Things cloud platform in the virtual teaching system. The virtual teaching system also includes a virtual teaching pendant, which is used to receive instructions sent by the cloud platform and transmit these instructions to the industrial robot. By implementing the method of the present invention, the robot can be continuously trained and learned, thereby improving the training efficiency and effect.

[0024] Figure 1 The figure is a flow chart of a robot teaching method based on a virtual teaching pendant provided by an embodiment of the present invention. As shown in the figure, the method includes the following steps S110-S130.

[0025] S110, receiving the voice command input by the operator and the selected robot to be trained.

[0026] In this embodiment, the robot to be trained is the robot selected by the operator for demonstration training. It should be noted that the robot to be trained can be multiple robots with the same or similar motion paths, or a robot with a special motion trajectory. The voice command input by the operator and the selected robot to be trained are received. Specifically, the operator can send voice information to the Internet of Things cloud platform through a voice transmission device such as a microphone in a remote device, and select a batch or one robot to be trained that needs to be trained in the platform. By receiving the voice command input by the operator and the selected robot to be trained, the training requirements and training goals can be obtained, which facilitates the subsequent demonstration training of the robot.

[0027] S120: Convert the voice command into a text command, and generate an initial code command from the text command through a preset large model.

[0028] In this embodiment, the text instruction is an instruction in text form. The initial code instruction is the code generated by the preset large model according to the initial text instruction. The preset large model is a machine learning model that is trained with a large amount of text data and can understand and generate human language. These models can receive text input and generate grammatically correct text output related to the input. In this embodiment, the preset large model is a generative pretrained language model (GPT), which is a deep learning model based on the Transformer architecture, specifically used for natural language generation and understanding tasks. The voice instruction is converted into a text instruction. Specifically, the voice instruction can be converted into a text instruction through an integrated speech recognition technology (such as Google Speech-to-Text, IBM Watson, etc.), wherein the specific speech recognition technology is not limited, and the speech can be accurately converted. The text instruction is generated into an initial code instruction through a preset large model. Specifically, the large language model is used to receive the text instruction and generate the initial code instruction corresponding to it according to the preset generation template. These code instructions are code snippets of programming languages, which are used to implement the requirements in the text instructions. By generating initial code instructions based on a preset large model, the code for training the robot can be efficiently generated, thereby improving training efficiency.

[0029] In one embodiment, if Figure 2 As shown, the step S120 also includes steps S1201-S1202.

[0030] S1201, collect historical operation instructions and preset operation information to build a training data set;

[0031] S1202, obtaining a target data set by preprocessing the training data set, and performing data training on the preset large model according to the target data set.

[0032] In this embodiment, the historical operation instructions refer to all the instructions related to the industrial robot previously input by the operator, and the preset operation information is pre-designed operation information, such as the user teaching pendant operation manual. The historical operation instructions and the preset operation information are collected to construct a training data set. Specifically, the collected historical operation instructions and the preset operation information are subjected to text extraction to form training data to construct a training data set. These training data will be used to train the preset large model. The training data set is pre-processed by data cleaning, format conversion, feature extraction, etc. to obtain the neat and standard target data set. The preset large model is fine-tuned or re-trained using the pre-processed target data set so that it can accurately convert the text instructions into the corresponding initial code instructions. During the training process, the preset large model will continuously adjust its parameters to minimize the error between the predicted results and the actual results. After the training is completed, the model will be able to receive text instructions in actual applications and generate corresponding initial code instructions. By constructing a target data set to train the preset large model with data, the preset large model can convert the text instructions more accurately, effectively avoiding unnecessary work caused by inaccurate initial code instructions.

[0033] In one embodiment, if Figure 3 As shown, the step S1202 also includes steps S12021-S12023.

[0034] S12021. Cleaning the training data in the training data set;

[0035] S12022. Construct a training vocabulary table according to the cleaned training data, and convert the training data into an ID sequence according to the training vocabulary table;

[0036] S12023. Construct the target data set according to the ID sequence.

[0037] In this embodiment, the data cleaning is a process of removing or correcting errors, anomalies or irrelevant information in the data to improve data quality and model training effect. The training data in the training data set is cleaned, specifically, the invalid data in the training data set is removed to delete data with too many missing values, format errors or data that obviously does not meet the requirements, identify and process extreme values ​​or values ​​that do not conform to the normal distribution in the data, and the training data is format converted, punctuation is removed, stop word filtering is performed, and duplicate records are deleted to avoid introducing redundant information during the training process. All vocabulary, including words, phrases or symbols, are extracted from the cleaned training data. Duplicate vocabulary is deleted to ensure that each vocabulary in the vocabulary is unique. The vocabulary is sorted according to the frequency of occurrence or other criteria to construct a training vocabulary, and finally the vocabulary in the training data is replaced with the sequence obtained after their index (i.e., ID) in the training vocabulary. Specifically, a vocabulary to ID mapping table is created, in which each vocabulary corresponds to a unique ID. Each vocabulary in the training data is replaced with the corresponding ID using the mapping table to obtain an ID sequence, and the target dataset for training the model is determined according to the ID sequence. By cleaning the training data in the training data set and constructing a training vocabulary, and determining the target data set according to the ID sequence, high-quality training data is prepared for the preset large model, thereby training a model with superior performance.

[0038] In one embodiment, if Figure 4 As shown, the step S120 includes steps S121-S122.

[0039] S121, performing task analysis on the text instruction according to preset operation steps through the preset large model to determine movement information, and performing path planning according to the movement information;

[0040] S122: Generate corresponding primary code instructions according to the path planning route and the movement information.

[0041] In this embodiment, the preset large model is a pre-trained model that can understand and process text instructions. In this embodiment, the preset large model is a generative pre-trained language model (GPT), and the text instructions are instructions provided by the operator, usually task requirements expressed in natural language. For example, "Please move from point A to point B". The preset operation steps are a series of steps or rules defined inside the model for parsing text instructions. These steps include identifying key information in the instructions (such as starting point, end point), understanding the intention of the instructions (such as moving, grabbing, etc.), and converting the instructions into a form that the model can process. Task parsing is performed according to the preset operation steps to determine the movement information and perform path planning. For example, the cloud platform converts the voice into a text instruction "Let the robot grab the goods and move from point A to point B", then the large model parses the task according to the preset operation steps as follows: a. Start the robot, b. Identify the position and size of the object to be grabbed, c. Plan the movement path from point A to point B, d. Move to point B. The path planning route is the optimal path from the starting point to the end point, and the movement information includes all information related to the movement. The preset large model generates a series of code instructions based on the path planning route and movement information. These instructions are written in machine language or some high-level programming language and are used to control the movement of robots, automated equipment or intelligent systems. By generating primary code instructions corresponding to the path planning route and the movement information, the code instructions for controlling industrial robots can be automatically and intelligently generated, thereby reducing the overall training time.

[0042] S130, modifying the initial code instruction to determine a target code instruction, and sending the target code instruction to the robot to be trained through a virtual teaching pendant.

[0043] In this embodiment, the initial code instruction refers to the code instruction generated by the preset large model. The initial code instruction is corrected to determine the target code instruction. Specifically, the initial code instruction is reviewed to identify possible problems. This may include syntax errors, logical errors, performance problems, etc. The code is executed and analyzed step by step using debugging tools and methods to locate and solve errors. On the basis of correcting the errors, the code is optimized to improve its efficiency, readability and maintainability. Among them, the initial code instruction can also be checked and adjusted by the operator, and the target code instruction is determined according to the adjusted code instruction, and the target code instruction is used to guide the behavior of the robot. The target code instruction is sent to the robot to be trained through a virtual teach pendant, wherein the virtual teach pendant is a software tool that simulates the function of a traditional teach pendant but provides more flexibility and functions. Through the virtual teach pendant, the user can write, edit and send code instructions to the robot on a computer. Specifically, the target code instruction is first sent to the virtual teach pendant, and the target code instruction is sent to the robot to be trained through the interface or command line tool of the virtual teach pendant. After receiving the instruction, the robot to be trained will parse and execute it. By sending the target code instruction to the robot to be trained through the virtual teaching device, the robot to be trained is taught and trained to ensure that the robot to be trained can correctly and accurately perform the expected task, thereby achieving automated and intelligent operation.

[0044] In one embodiment, if Figure 5 As shown, the step S130 includes steps S131-S132.

[0045] S131, determining whether the primary code instruction has been modified;

[0046] S132: If modified, determine the target code instruction according to the modified initial code instruction and the selection instruction.

[0047] In this embodiment, the primary code instruction can be displayed to the operator through a display, and the operator can modify the primary code instruction. To determine whether the primary code instruction has been modified, specifically, the difference between the original code instruction and the current code instruction can be compared to make a judgment, or by checking the editor's history, undo / redo stack, etc. to determine whether the primary code instruction has been modified. The selection instruction is an instruction triggered by the operator to determine that the current code is the target code. Specifically, when the operator modifies the primary code instruction and determines that there is no problem with the modified code instruction, a selection instruction will be generated, and the target code instruction can be determined based on the modified initial code instruction and the selection instruction, and the target code instruction is sent to the virtual teach pendant according to the selection instruction. By judging whether the primary code instruction has been modified, the target code instruction can be determined based on the modified initial code instruction and the selection instruction, thereby improving the availability and reliability of the target code instruction.

[0048] In one embodiment, if Figure 6 As shown, step S130 includes steps S1301-S1302.

[0049] S1301, determining whether the path planning route has been modified;

[0050] S1302: If modified, teaching the robot to be trained according to the modified path planning route.

[0051] In this embodiment, after the IoT cloud platform in the virtual teaching system sends the target code instruction to the virtual teaching pendant, the virtual teaching pendant in the virtual teaching system can determine whether the path planning route has been modified. Specifically, the operator can use the virtual teaching pendant on the remote platform to manually adjust the path of the robot to ensure that the robot can accurately complete the task. Therefore, it is necessary to determine whether the path planning route has been modified. Specifically, the difference between the original path planning route and the current path planning route can be compared to make a judgment. If it is modified, the robot to be trained is taught according to the modified path planning route. Specifically, if the operator modifies the path planning route through the virtual teaching pendant at any time, the new route will be sent to the industrial robot. Then, the robot will simulate the new route in a virtual environment without actual load to ensure that there is no collision or other problems. Once the virtual test is successful, the robot will carry goods according to the new route in the real environment to complete the training process. By teaching the robot to be trained according to the modified path planning route, it is ensured that the robot can perform tasks according to the latest and most optimized path planning, thereby improving work efficiency and safety.

[0052] In one embodiment, if Figure 7 As shown, step S1302 includes steps S1303-S1304.

[0053] S1303, receiving and storing the operation data fed back by the trained robot;

[0054] S1304: Analyze the operation data in real time using a preset data analysis algorithm, and generate anomaly detection results based on the analysis results.

[0055] In this embodiment, the trained robot is a robot that has been trained according to the target code instructions. The robots are all equipped with 5G communication modules, temperature sensors, current sensors and position sensors. The robot collects corresponding operation data in real time through the 5G module, wherein the operation data includes the sensor data. The robot sends the operation data to the IoT cloud platform in the virtual teaching system through the 5G module, and the cloud platform receives and stores the operation data fed back by the trained robot, and analyzes the operation data in real time through a preset data analysis algorithm, wherein the preset data analysis algorithm is specially designed for processing and analyzing robot operation data. These algorithms may include statistical methods, machine learning algorithms, deep learning algorithms, etc. The choice of algorithm depends on the specific application scenario and requirements, such as anomaly detection, performance evaluation, fault diagnosis, etc., which are not limited. Anomaly detection results can be generated by real-time analysis of the operation data, wherein the anomaly detection results may include information such as the type, location, time, and severity of the anomaly. And when an anomaly is detected, such as temperature anomaly detection, the robot is immediately controlled to stop operating. By performing real-time analysis on the operation data according to a preset data analysis algorithm and generating abnormal detection results at any time based on the analysis results, it is intended to connect the isolated industrial robot nodes in the factory through the cloud platform and 5G wireless communication technology, so that any robot can be monitored at any time, thereby ensuring the stability of the robot production process and product quality.

[0056] Figure 8 is a schematic block diagram of a robot teaching device 200 based on a virtual teaching pendant provided in an embodiment of the present invention. Figure 8 As shown, corresponding to the above robot teaching method based on virtual teaching pendant, the present invention also provides a robot teaching device based on virtual teaching pendant. The robot teaching device based on virtual teaching pendant includes a unit for executing the above robot teaching method based on virtual teaching pendant, and the device can be configured in a desktop computer, tablet computer, laptop computer, etc. Specifically, please refer to Figure 8 The robot teaching device based on the virtual teaching pendant includes an instruction receiving unit 210, a generating unit 220, and a sending unit 230.

[0057] The instruction receiving unit 210 is used to receive the voice instruction input by the operator and the selected robot to be trained.

[0058] The generating unit 220 is used to convert the voice instruction into a text instruction, and generate an initial code instruction from the text instruction through a preset large model.

[0059] In one embodiment, the generating unit 220 includes a collecting unit and a training unit.

[0060] A collection unit, used to collect historical operation instructions and preset operation information to construct a training data set;

[0061] The training unit is used to obtain a target data set by preprocessing the training data set, and perform data training on the preset large model according to the target data set.

[0062] In one embodiment, the generating unit 220 includes a cleaning unit, a converting unit, and a building unit.

[0063] A cleaning unit, used for cleaning the training data in the training data set;

[0064] a conversion unit, configured to construct a training vocabulary according to the cleaned training data, and convert the training data into an ID sequence according to the training vocabulary;

[0065] A construction unit is used to construct the target data set according to the ID sequence.

[0066] In one embodiment, the generating unit 220 includes a planning unit and an instruction generating unit.

[0067] A planning unit, configured to perform task analysis on the text instruction according to preset operation steps through the preset large model to determine movement information, and perform path planning according to the movement information;

[0068] The instruction generating unit is used to generate corresponding primary code instructions according to the path planning route and the movement information.

[0069] The sending unit 230 is used to modify the initial code instruction to determine the target code instruction, and send the target code instruction to the robot to be trained through the virtual teaching device.

[0070] In one embodiment, the sending unit 230 includes a first judging unit and a first determining unit.

[0071] A first judging unit, used for judging whether the primary code instruction has been modified;

[0072] The first determining unit is used to determine the target code instruction according to the modified initial code instruction and the selection instruction if it is modified.

[0073] In one embodiment, the sending unit 230 includes a second judging unit and a second determining unit.

[0074] A second judgment unit, used to judge whether the path planning route is modified;

[0075] The second determining unit is used to teach the robot to be trained according to the modified path planning route if it is modified.

[0076] In one embodiment, the sending unit 230 includes an instruction receiving unit and an analyzing unit.

[0077] An instruction receiving unit, used for receiving and storing operation data fed back by the trained robot;

[0078] The analysis unit is used to perform real-time analysis on the operation data through a preset data analysis algorithm, and generate an abnormality detection result according to the analysis result.

[0079] It should be noted that technicians in the relevant field can clearly understand that the specific implementation process of the above-mentioned robot teaching device 200 based on the virtual teaching pendant and each unit can refer to the corresponding description in the aforementioned method embodiment, and for the convenience and conciseness of the description, it will not be repeated here.

[0080] The robot teaching device based on the virtual teaching device can be implemented in the form of a computer program. Fig. 9 Runs on the computer device shown.

[0081] See also Fig. 9 , Fig. 9 5 is a schematic block diagram of a computer device provided in an embodiment of the present application. The computer device 500 may be a terminal or a server, wherein the terminal may be an electronic device with communication functions such as a smart phone, a tablet computer, a laptop computer, a desktop computer, a personal digital assistant, and a wearable device. The server may be an independent server or a server cluster composed of multiple servers.

[0082] See also Fig. 9 The computer device 500 includes a processor 502 , a memory and a network interface 505 connected via a system bus 501 , wherein the memory may include a non-volatile storage medium 503 and an internal memory 504 .

[0083] The non-volatile storage medium 503 can store an operating system 5031 and a computer program 5032. The computer program 5032 includes program instructions, and when the program instructions are executed, the processor 502 can execute a robot teaching method based on a virtual teaching pendant.

[0084] The processor 502 is used to provide computing and control capabilities to support the operation of the entire computer device 500 .

[0085] The internal memory 504 provides an environment for the operation of the computer program 5032 in the non-volatile storage medium 503. When the computer program 5032 is executed by the processor 502, the processor 502 can execute a robot teaching method based on a virtual teaching pendant.

[0086] The network interface 505 is used to communicate with other devices over the network. Fig. 9 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present application, and does not constitute a limitation on the computer device 500 to which the solution of the present application is applied. The specific computer device 500 may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0087] The processor 502 is used to run a computer program 5032 stored in the memory to implement the steps of the above method.

[0088] It should be understood that in the embodiment of the present application, the processor 502 may be a central processing unit (CPU), and the processor 502 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0089] It can be understood by those skilled in the art that all or part of the processes in the method for implementing the above embodiment can be completed by instructing the relevant hardware through a computer program. The computer program includes program instructions, and the computer program can be stored in a storage medium, which is a computer-readable storage medium. The program instructions are executed by at least one processor in the computer system to implement the process steps of the embodiment of the above method.

[0090] Therefore, the present invention also provides a storage medium. The storage medium may be a computer-readable storage medium. The storage medium stores a computer program, wherein the computer program includes program instructions. When the program instructions are executed by a processor, the processor executes the steps of the above method.

[0091] The storage medium may be a USB flash drive, a mobile hard disk, a read-only memory (ROM), a magnetic disk, or an optical disk, etc., which are computer-readable storage media that can store program codes.

[0092] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0093] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of each unit is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0094] The steps in the method of the embodiment of the present invention can be adjusted in order, combined and deleted according to actual needs. The units in the device of the embodiment of the present invention can be combined, divided and deleted according to actual needs. In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0095] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, terminal, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention.

[0096] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A robot teaching method based on a virtual teaching pendant, characterized in that: The method is applied to a virtual teaching pendant system, and the method comprises: Receiving the voice command input by the operator and the robot to be trained selected; Convert the voice command into a text command, and generate an initial code command from the text command through a preset macro model; The initial code instruction is modified to determine the target code instruction, and the target code instruction is sent to the robot to be trained through a virtual teaching pendant.

2. The method according to claim 1, characterized in that Before the step of generating the initial code instruction by using the text instruction through the preset large model, the method includes: Collect historical operation instructions and preset operation information to build a training data set; The training data set is preprocessed to obtain a target data set, and the preset large model is trained according to the target data set.

3. The method according to claim 2, characterized in that The step of obtaining a target data set by preprocessing the training data set comprises: Performing data cleaning on the training data in the training data set; Building a training vocabulary based on the cleaned training data, and converting the training data into an ID sequence based on the training vocabulary; The target data set is constructed according to the ID sequence.

4. The method according to claim 1, characterized in that: The step of generating an initial code instruction from the text instruction through a preset large model comprises: The preset large model performs task analysis on the text instruction according to preset operation steps to determine movement information, and performs path planning according to the movement information; Generate corresponding primary code instructions according to the path planning route and the movement information.

5. The method according to claim 4, characterized in that The step of modifying the initial code instruction to determine the target code instruction comprises: determining whether the primary code instruction has been modified; If modified, the target code instruction is determined according to the modified initial code instruction and the selection instruction.

6. The method according to claim 5, characterized in that After the step of sending the target code instruction to the robot to be trained via a virtual teaching pendant, the method further comprises: Determining whether the path planning route has been modified; If it is modified, the robot to be trained is taught according to the modified path planning route.

7. The method according to claim 6, characterized in that After the step of teaching the robot to be trained according to the modified path planning route, the method further comprises: Receive and store operational data fed back by the trained robot; The operation data is analyzed in real time by a preset data analysis algorithm, and an abnormality detection result is generated according to the analysis result.

8. A robot teaching device based on a virtual teaching pendant, characterized in that: The device is applied to a virtual teaching pendant system, and comprises: An instruction receiving unit, used for receiving the voice instruction input by the operator and the selected robot to be trained; A generating unit, used for converting the voice instruction into a text instruction, and generating an initial code instruction from the text instruction through a preset macro model; The sending unit is used to modify the initial code instruction to determine the target code instruction, and send the target code instruction to the robot to be trained through the virtual teaching device.

9. A computer device, characterized in that: The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the method according to any one of claims 1 to 7 when executing the computer program.

10. A storage medium, characterized in that: The storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the method according to any one of claims 1 to 7 can be implemented.

Images