Robot arm control system for teaching

Abstract

The invention discloses a robot arm control system for teaching, and relates to the technical field of robot arms, and the robot arm control system comprises a position sensing module which is used for obtaining first position information corresponding to a robot arm; the wafer carrying task receiving module is used for receiving a wafer carrying task; the initial carrying module is used for carrying the wafer according to the manipulator, the first position information and the second position information based on a wafer carrying route planning model; the carrying reference deviation detection module is used for carrying out carrying reference deviation detection on the wafer according to the carrying reference deviation detection network based on the carrying target device to obtain a carrying reference deviation detection result; and the carrying teaching module is used for carrying out carrying calibration on the wafer according to the carrying reference deviation detection result and the manipulator based on the carrying deviation evaluation threshold value. The technical problems of low teaching precision and efficiency in the prior art are solved, and the technical effects of automatic teaching and accurate control of the wafer carrying manipulator are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of robot arms, and in particular to a robot arm control system for teaching. Background Art

[0002] In the semiconductor manufacturing process, wafers need to be accurately transferred between multiple processing devices, including rotating and non-rotating processing devices. Since semiconductor equipment requires extremely high processing accuracy, the robot must accurately position the wafer at the reference position of each processing device when handling the wafer.

[0003] At present, the teaching work of wafer handling robots mainly relies on manual operation and teaching pendants. The teaching personnel control the robot to hold the teaching pendant and use the naked eye to find the teaching position in the vertical and horizontal directions. However, this method leads to low teaching accuracy and efficiency. Summary of the invention

[0004] The present application provides a robot control system for teaching, which is used to solve the technical problems of low teaching accuracy and efficiency in the prior art.

[0005] In view of the above problems, the present application provides a robot control system for teaching.

[0006] The present application provides a robot control system for teaching, the system comprising:

[0007] A position sensing module, wherein the position sensing module is used to obtain first position information corresponding to a manipulator, wherein the manipulator has a wafer; a wafer handling task receiving module, wherein the wafer handling task receives a handling task of the wafer, wherein the handling task includes a handling target device and second position information corresponding to the handling target device; an initial handling module, wherein the initial handling module is used to handle the wafer according to the manipulator, the first position information and the second position information based on a wafer handling route planning model; a handling reference deviation detection module, wherein the handling reference deviation detection module is used to perform handling reference deviation detection on the wafer based on the handling target device and a handling reference deviation detection network to obtain a handling reference deviation detection result; a handling teaching module, wherein the handling teaching module is used to perform handling calibration on the wafer based on a handling deviation evaluation threshold, the handling reference deviation detection result and the manipulator.

[0008] In a second aspect, the present application provides an electronic device comprising: a processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the steps of the system described in any one of the above-mentioned first aspects.

[0009] In a third aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the steps of the system described in any one of the first aspects above when executed.

[0010] The technical solution provided in this application has at least the following technical effects or advantages:

[0011] The position sensing module of the present application is used to obtain the first position information corresponding to the manipulator, wherein the manipulator has a wafer; the wafer handling task receiving module is used to receive the handling task of the wafer, wherein the handling task includes a handling target device and the second position information corresponding to the handling target device; the initial handling module is used to carry the wafer according to the manipulator, the first position information and the second position information based on the wafer handling route planning model; the handling reference deviation detection module is used to perform handling reference deviation detection on the wafer based on the handling target device and the handling reference deviation detection network to obtain the handling reference deviation detection result; the handling teaching module is used to perform handling calibration on the wafer based on the handling reference deviation evaluation threshold and the handling reference deviation detection result and the manipulator. The present invention solves the technical problem that the prior art cannot adapt to the dynamic changes in the welding process in real time, resulting in unstable welding quality and low production efficiency. By intelligently fitting the weld path, automatic planning and optimization of the welding path are realized, thereby achieving the technical effect of improving welding quality and production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0013] Figure 1 A schematic diagram of the structure of a robot control system for teaching provided in an embodiment of the present application;

[0014] Figure 2 A schematic diagram of a flow chart of a robot arm control method for teaching provided in an embodiment of the present application;

[0015] Figure 3 It is a schematic diagram of the structure of an exemplary electronic device of the present application.

[0016] Explanation of the reference numerals: position sensing module 11 , wafer transport task receiving module 12 , initial transport module 13 , transport reference deviation detection module 14 , transport teaching module 15 , electronic device 300 , memory 301 , processor 302 , communication interface 303 , bus architecture 304 . DETAILED DESCRIPTION

[0017] The present application provides a robot control system for teaching, aiming to solve the technical problems of low teaching accuracy and efficiency in the prior art, and achieves the technical effect of automatic teaching and precise control of wafer handling robots by integrating sensor technology, real-time data analysis algorithms and automatic calibration mechanisms.

[0018] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0019] It should be noted that any variations of the terms "include" and "have" are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or inherent to these processes, methods, products or devices.

[0020] like Figure 1 As shown, the present application provides a robot control system for teaching, which is used to perform the following Figure 2 The robot arm control method for teaching shown in the figure, the system comprises:

[0021] The position sensing module 11 is used to obtain first position information corresponding to a robot arm, wherein a wafer is disposed on the robot arm.

[0022] In the embodiment of the present application, the position sensing module integrates a variety of sensor technologies, such as photoelectric encoders, optical sensors, ultrasonic sensors, etc. These sensors detect the movement state of the manipulator in real time and convert it into corresponding digital signals.

[0023] The robot is positioned by the position sensing module to obtain the first position information and the position of the wafer on the robot is obtained at the same time.

[0024] The wafer transport task receiving module 12 is used to receive the wafer transport task, wherein the transport task includes a transport target device and second position information corresponding to the transport target device.

[0025] In an embodiment of the present application, a wafer handling task receiving module receives a wafer handling task. The task content usually includes specific information of the wafer to be handled, such as model, quantity, status, etc.; identity identification of the target device to be handled, such as equipment number, container ID, etc.; and second position information corresponding to the target device, such as coordinates, etc.

[0026] The operator sends the prepared handling tasks to the wafer handling task receiving module through communication interfaces such as network and serial port. The wafer handling task receiving module monitors these communication interfaces in real time to ensure that the tasks issued can be received in time.

[0027] The initial transport module 13 is used to transport the wafer based on a wafer transport route planning model, according to the robot, the first position information and the second position information.

[0028] In the embodiment of the present application, the initial handling module first receives information about the current position of the wafer, namely, the first position information, including the specific position of the wafer in the storage container or the production line, and simultaneously receives the position information of the handling target device, namely, the second position information.

[0029] Next, based on the wafer handling route planning model, the optimal path from the starting position to the target position is analyzed, including obstacle avoidance information and path selection, to ensure that the path is the shortest, safe and can avoid obstacles. Next, the wafer is transported according to the generated handling route.

[0030] The transport reference deviation detection module 14 is used to perform transport reference deviation detection on the wafer based on the transport target device and a transport reference deviation detection network to obtain a transport reference deviation detection result.

[0031] In an embodiment of the present application, the transport reference deviation detection module is based on the transport target device, and the position deviation of the wafer is accurately detected through the transport reference deviation detection network, so as to obtain the transport reference deviation detection result. Specifically, the real-time position information of the wafer is first collected, that is, the real-time coordinates of the wafer during the transport process. At the same time, the transport reference deviation detection module will also obtain the wafer transport target position parameters of the transport target device, that is, the ideal coordinates or reference position information of the wafer at the target position. Next, the real-time position information and the wafer reference position information are input into the transport reference deviation detection network, and these data are analyzed to calculate the deviation between the current position and the reference position. Through this process, the transport reference deviation detection result is output, that is, the offset value of the wafer from the target position during the transport process, including the direction and distance of the deviation.

[0032] The transport teaching module 15 is used to perform transport calibration on the wafer based on a transport deviation evaluation threshold, the transport reference deviation detection result and the robot.

[0033] In an embodiment of the present application, the handling teaching module performs precise handling calibration on the wafer based on the handling deviation evaluation threshold, combined with the handling reference deviation detection result and the current position of the manipulator. Specifically, first obtain the "handling reference deviation detection result", that is, the deviation between the current position of the wafer and the target reference position, including the direction and distance of the offset. Then, perform deviation detection according to the preset handling deviation evaluation threshold to determine whether the current deviation exceeds the allowable range. The handling deviation evaluation threshold defines an acceptable error range. When the deviation exceeds this threshold, it means that the handling error has exceeded the normal range and needs to be calibrated.

[0034] If the detected deviation is greater than or equal to the handling deviation evaluation threshold, a handling calibration instruction is generated. This instruction contains correction adjustment parameters for the position and posture of the robot, such as moving distance, rotation angle, etc., to ensure that the position of the wafer accurately returns to the preset trajectory. After the handling calibration instruction is sent to the robot, the robot will make fine adjustments according to the instruction to compensate for the deviation.

[0035] Furthermore, the initial transport module 13 in the system provided in the embodiment of the application is also used for:

[0036] Collect the transportation obstacle information between the first position information and the second position information to obtain transportation obstacle characteristic data; based on the wafer transportation route planning model, generate a transportation route according to the transportation obstacle characteristic data, the first position information and the second position information; based on the transportation route, control the robot to perform the transportation of the wafer.

[0037] In the embodiment of the present application, the handling obstacle information is first collected, that is, the obstacle data that may exist on the path between the first position information (starting position) and the second position information (target position) of the manipulator. This obstacle information is collected in real time by a variety of sensors, such as laser sensors, visual cameras or ultrasonic sensors, etc., which are used to detect static and dynamic obstacles in the path. The collected handling obstacle feature data includes key information such as the location, size, and shape of the obstacle.

[0038] After collecting the handling obstacle feature data, path planning is performed based on the wafer handling route planning model. The handling route planning model is an algorithmic system composed of a deep learning model that can handle different path conditions and generate the optimal route. The model combines the starting position, target position and obstacle feature data to calculate a handling route that avoids obstacles and has the shortest distance.

[0039] Once the transport route is generated, it is used as a motion instruction for the robot, and the robot is controlled to perform wafer transport based on the transport route.

[0040] Furthermore, the initial handling module 13 is also used for:

[0041] Obtain a wafer transport route planning record set; perform data cleaning according to the wafer transport route planning record set to obtain a wafer transport route planning data set; build the wafer transport route planning model based on the wafer transport route planning data set based on a neural network; output the transport route based on the wafer transport route planning model based on the transport obstacle feature data, the first position information and the second position information.

[0042] In an embodiment of the present application, route planning records for wafer transport are retrieved from a historical database, and these records include manually input data, sensor data, machine vision data, etc. The route planning records include the starting position of the transport, the target position, information on obstacles encountered during the transport process, and the actual transport route used.

[0043] The collected wafer handling route planning record set is cleaned to remove duplicate, invalid or abnormal data records. For missing data, interpolation, prediction and other methods are used to complete it. The data format and measurement unit are standardized to ensure the consistency and accuracy of the data. The cleaned data is organized into a wafer handling route planning data set in a specific format, which will be used as the input of the neural network model.

[0044] According to the characteristics of the wafer handling route planning problem, a suitable neural network structure is selected. In this application, a recurrent neural network is selected. Key features such as handling obstacle feature data, first position information, second position information, etc. are selected from the wafer handling route planning data set as input features of the model. The neural network model is trained using the wafer handling route planning data set, and the model parameters are adjusted through optimization methods such as back propagation algorithm and gradient descent to improve the prediction accuracy of the model. During the training process, cross-validation and other techniques are used to evaluate the performance of the model and prevent overfitting. The construction of the wafer handling route planning model is completed through the above process.

[0045] When a new wafer handling task occurs, the starting position, target position, and obstacle feature data of the handling process are passed as input data to the trained neural network model. The neural network model outputs the predicted handling route based on the input data.

[0046] Furthermore, the handling reference deviation detection module 14 is also used for:

[0047] The real-time position information of the wafer is obtained; the wafer transport target position parameters of the transport target device are collected to obtain the wafer reference position information; the real-time position information and the wafer reference position information are input into the transport reference deviation detection network to obtain the transport reference deviation detection result.

[0048] In the embodiment of the present application, the current position coordinates of the wafer, that is, the real-time position information of the wafer, are first obtained in real time through devices such as laser sensors, visual sensors or RFID. The visual sensor captures image data through a camera and uses image processing techniques such as target detection and image segmentation to identify the position coordinates of the wafer. The laser sensor determines the three-dimensional position of the wafer by measuring the time difference of the laser reflection back. These data are integrated with the information of each sensor through sensor fusion algorithms, such as Kalman filtering, to eliminate noise and obtain more accurate real-time position information.

[0049] At the same time, the target position parameters, i.e., the reference position information, are collected from the handling target device. The reference position information is stored in the system database or manually entered at the beginning of the task. The reference position information is the reference point or ideal position of the handling task. When collecting this data, format standardization and data conversion are performed to convert the reference position parameters into a coordinate format that matches the real-time position information to ensure that the two can be directly compared and analyzed. This data format standardization is completed through a coordinate transformation algorithm, such as homogeneous coordinate transformation, which unifies the coordinates of different reference systems into the same coordinate system.

[0050] After obtaining the real-time position information and the reference position information, these two sets of data are input into the handling reference deviation detection network. The detection network is based on deep learning technology and uses convolutional neural networks or long short-term memory networks to process and analyze position deviations in the handling path. The detection network is trained before formal application. During the training process, a training data set containing a large number of historical deviation instances is used. The data set includes deviations and labels of various handling positions. Through back propagation and gradient descent algorithms, the model continuously adjusts its parameters to minimize the error between the deviation prediction and the true value. In addition, cross-validation technology is introduced in network training to evaluate model performance, prevent overfitting, and ensure its generalization ability in real scenarios.

[0051] After sufficient training, the real-time position information and wafer reference position information are input into the handling reference deviation detection network. The network performs forward calculations, extracts the features of the input data layer by layer, and finally outputs the handling reference deviation detection result, that is, the difference between the actual position of the wafer and the reference position.

[0052] Furthermore, the handling reference deviation detection module 14 is also used for:

[0053] Based on the transport deviation evaluation threshold, deviation detection is performed according to the transport reference deviation detection result to generate a transport calibration instruction; based on the transport calibration instruction, transport calibration is performed on the wafer according to the robot and the transport reference deviation detection result.

[0054] In the embodiment of the present application, the handling reference deviation detection result is first obtained from the handling reference deviation detection module, which contains the deviation information between the current position and the reference position, including key indicators such as the offset direction and distance. The detection result is then compared with the handling deviation evaluation threshold, which is a preset error range used to define the acceptable error range during the handling process to ensure the accuracy and stability of the handling operation.

[0055] Next, a deviation detection is performed. If the detected deviation value is greater than or equal to the handling deviation evaluation threshold, a handling calibration instruction is generated. The handling calibration instruction contains the adjustment parameters for the robot, including detailed correction information such as the moving direction, moving distance and angle. The process of generating this instruction uses a control algorithm, such as a PID controller, to calculate the optimal adjustment amount so that the robot can quickly compensate for the detected deviation.

[0056] Once the handling calibration instruction is generated, it is sent to the robot control module. The robot performs position and angle correction according to the parameters in the instruction and readjusts the position of the wafer. The robot's correction action is fed back to the deviation detection module in real time to ensure that the adjusted wafer position gradually approaches the reference position information. When the deviation value is detected to be lower than the handling deviation evaluation threshold, the handling calibration instruction stops being issued, indicating that the handling has reached the ideal accuracy standard.

[0057] Through the above process, the wafer handling calibration is completed.

[0058] Furthermore, the handling reference deviation detection module 14 is also used for:

[0059] The deviation degree is evaluated according to the transport reference deviation detection result to obtain a deviation evaluation coefficient; whether the deviation evaluation coefficient is greater than / equal to the transport deviation evaluation threshold is determined; if the deviation evaluation coefficient is greater than / equal to the transport deviation evaluation threshold, the transport calibration instruction is generated.

[0060] In the embodiment of the present application, the handling deviation is first analyzed based on the handling reference deviation detection result to evaluate the severity of the deviation. The deviation detection result includes the distance and direction information between the current position and the reference position, and the deviation evaluation coefficient is obtained by calculating these deviation values. The deviation evaluation coefficient is a quantitative indicator used to evaluate the degree to which the current position deviates from the reference position, and is calculated by the Euclidean distance formula or the weighted distance.

[0061] The deviation evaluation coefficient is then compared with the handling deviation evaluation threshold. The handling deviation evaluation threshold is a preset standard value that defines the maximum deviation range that the system can accept. The purpose of this comparison is to determine whether the current deviation exceeds the allowable range, so as to determine whether the motion trajectory of the robot needs to be adjusted. If the deviation evaluation coefficient is greater than or equal to the threshold, it means that the deviation exceeds the acceptable range and calibration is required; otherwise, no calibration is required.

[0062] When the deviation exceeds the threshold, a handling calibration instruction is generated, which contains the adjustment information required to correct the deviation, such as detailed parameters such as moving direction, adjustment distance and angle.

[0063] In the embodiments of the present application, in summary, the embodiments of the present application have at least the following technical effects:

[0064] The position sensing module of the present application is used to obtain the first position information corresponding to the manipulator, wherein the manipulator has a wafer; the wafer handling task receiving module is used to receive the handling task of the wafer, wherein the handling task includes a handling target device and the second position information corresponding to the handling target device; the initial handling module is used to carry the wafer according to the manipulator, the first position information and the second position information based on the wafer handling route planning model; the handling reference deviation detection module is used to perform handling reference deviation detection on the wafer based on the handling target device and the handling reference deviation detection network to obtain the handling reference deviation detection result; the handling teaching module is used to perform handling calibration on the wafer based on the handling reference deviation evaluation threshold and the handling reference deviation detection result and the manipulator. The present invention solves the technical problem that the prior art cannot adapt to the dynamic changes in the welding process in real time, resulting in unstable welding quality and low production efficiency. By intelligently fitting the weld path, automatic planning and optimization of the welding path are realized, thereby achieving the technical effect of improving welding quality and production efficiency.

[0065] Reference below Figure 3 To describe the electronic device of the embodiment of the present application:

[0066] The electronic device 300 includes: a processor 302, a communication interface 303, and a memory 301. Optionally, the electronic device 300 may also include a bus architecture 304. The communication interface 303, the processor 302, and the memory 301 may be interconnected via the bus architecture 304; the bus architecture 304 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus architecture 304 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0067] The processor 302 may be a CPU, a microprocessor, an ASIC, or one or more integrated circuits for controlling the execution of the program of the present application.

[0068] The communication interface 303 uses any transceiver-like device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), wired access networks, etc.

[0069] The memory 301 may be a ROM or other types of static storage devices that can store static information and instructions, a RAM or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory may exist independently and be connected to the processor via a bus architecture 304. The memory may also be integrated with the processor, wherein the memory 301 is used to store computer-executable instructions for executing the solution of the present application, and the execution is controlled by the processor 302. The processor 302 is used to execute the computer-executable instructions stored in the memory 301.

[0070] An embodiment of the present application further provides a computer-readable storage medium, which stores computer instructions, and the computer instructions are used to enable a processor to implement the robot arm control system for teaching in the aforementioned embodiment when executed.

[0071] Any steps of the system described above may be stored as computer instructions or programs in an unlimited computer memory, and may be called and recognized by an unlimited computer processor to implement any method in the embodiments of the present application, without any unnecessary restrictions.

[0072] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. The processes depicted in the accompanying drawings do not necessarily require the specific order and continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0073] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0074] This specification and the drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, those skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A robot control system for teaching, characterized in that: The system comprises: A position sensing module, the position sensing module is used to obtain first position information corresponding to the robot, wherein the robot has a wafer; A wafer handling task receiving module, the wafer handling task receiving module is used to receive a handling task of the wafer, wherein the handling task includes a handling target device and second position information corresponding to the handling target device; An initial handling module, the initial handling module is used to carry the wafer according to the manipulator, the first position information and the second position information based on a wafer handling route planning model; A handling reference deviation detection module, wherein the handling reference deviation detection module is used to perform a handling reference deviation detection on the wafer based on the handling target device and according to a handling reference deviation detection network to obtain a handling reference deviation detection result; A transport teaching module is used to perform transport calibration on the wafer based on a transport deviation evaluation threshold, according to the transport reference deviation detection result and the robot.

2. The system according to claim 1, characterized in that The initial transport module is used to transport the wafer according to the manipulator, the first position information and the second position information based on a wafer transport route planning model, and includes: Collecting transport obstacle information between the first position information and the second position information to obtain transport obstacle feature data; Based on the wafer transport route planning model, generating a transport route according to the transport obstacle feature data, the first position information and the second position information; The robot is controlled to transfer the wafer based on the transfer route.

3. The system according to claim 2, characterized in that Based on the wafer transport route planning model, generating a transport route according to the transport obstacle feature data, the first position information and the second position information, including: Obtain a wafer transport route planning record set; Performing data cleaning according to the wafer transport route planning record set to obtain a wafer transport route planning data set; Based on the neural network, the wafer transport route planning model is constructed according to the wafer transport route planning data set; Based on the transport obstacle feature data, the first position information and the second position information, the transport route is output according to the wafer transport route planning model.

4. The system according to claim 1, characterized in that The transport reference deviation detection module is used to perform transport reference deviation detection on the wafer based on the transport target device and according to the transport reference deviation detection network to obtain a transport reference deviation detection result, including: Obtaining real-time position information of the wafer; Collecting wafer transport target position parameters of the transport target device to obtain wafer reference position information; The real-time position information and the wafer reference position information are input into the transport reference deviation detection network to obtain the transport reference deviation detection result.

5. The system according to claim 1, wherein: The handling teaching module is used to perform handling calibration on the wafer based on a handling deviation evaluation threshold, according to the handling reference deviation detection result and the manipulator, and includes: Based on the handling deviation evaluation threshold, deviation detection is performed according to the handling reference deviation detection result to generate a handling calibration instruction; Based on the transport calibration instruction, transport calibration is performed on the wafer according to the robot and the transport reference deviation detection result.

6. The system according to claim 5, characterized in that Based on the handling deviation evaluation threshold, deviation detection is performed according to the handling reference deviation detection result, and a handling calibration instruction is generated, including: Evaluate the degree of deviation according to the handling benchmark deviation detection result to obtain a deviation evaluation coefficient; Determining whether the deviation evaluation coefficient is greater than / equal to the handling deviation evaluation threshold; If the deviation evaluation coefficient is greater than / equal to the transport deviation evaluation threshold, the transport calibration instruction is generated.

7. An electronic device, characterized in that: The electronic device comprises: At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the robot arm control system for teaching as described in any one of claims 1-6.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the robot arm control system for teaching according to any one of claims 1 to 6 when executed.

Images