Digital teaching method and device thereof

Abstract

Disclosed are a digital teaching method and a device thereof. The present invention: sets reference information about an object in a virtual space; generates teaching information including a task position and a movement path of a robot on the basis of the set reference information; and transmits the teaching information to the robot so that the robot may automatically perform a task. When changing the object, the robot is taught to transform coordinates by means of a translation and perform the same task on the basis of an object at the translated position.

Description

Digital teaching method and device

[0001] The present invention relates to industrial automation technology, and more specifically to robot teaching technology.

[0002] Generally, a robot is a machine that automatically processes or operates assigned tasks based on its own capabilities. Robot applications are typically classified into various fields, including industrial, medical, space, and underwater sectors. In industrial settings, robots can not only perform tasks that humans cannot but also handle large workloads with minimal time and cost. However, significant costs are incurred in industrial environments due to the redeployment and testing of robots caused by frequent changes in operations.

[0003] In robot work sites, teaching is performed to control the robot so that it can perform specific tasks at specific locations. This teaching is carried out by the user before the process on the target object begins, or more specifically, during robot installation.

[0004] This teaching task is performed by a user manually operating the robot using a control device or the like. For example, the user manually operates the robot to move it to a specific position and then sets it to perform a task at that specific position. This manual method has the problem that the precision of the teaching task varies depending on the user's skill level and fatigue, and the task takes a long time.

[0005] According to one embodiment, a digital teaching method and apparatus are proposed that can effectively apply a robot to a manufacturing process by automatically controlling the robot through accurate, rapid, and user-friendly digital teaching of the robot.

[0006] A digital teaching method according to one embodiment includes the steps of: acquiring three-dimensional data of an object captured through a camera; generating a camera coordinate system in three-dimensional space from the acquired three-dimensional data and generating reference information representing the three-dimensional position of the object in the generated camera coordinate system and registering it as a model; generating teaching information including at least one of a robot's work position and movement path based on the three-dimensional position of the object in the camera coordinate system; and converting the camera coordinate system in which the teaching information was generated into a robot coordinate system and transmitting the converted robot coordinate system to the robot to teach the robot.

[0007] In the step of acquiring three-dimensional data of an object, three-dimensional data of the object can be acquired using Structured Light Scanning technology based on a structured light pattern.

[0008] In the registration step, the object may be registered by creating three or more points, a combination of points and lines, a combination of surfaces, lines and points, or the object itself as reference information.

[0009] In the robot teaching stage, the robot coordinate system and the camera coordinate system can be aligned through calibration between the robot and the camera, or a coordinate system transformation matrix between the robot coordinate system and the camera coordinate system can be calculated and the camera coordinate system can be transformed into the robot coordinate system using the calculated transformation matrix.

[0010] The digital teaching method may further include the step of acquiring 3D data by photographing the new work object through a camera when the object is changed to a new work object with a different position from the object, and the step of teaching the robot to perform the same task based on the object with the changed position by performing a coordinate transformation from the 3D data of the new work object by the position changed in 3D space.

[0011] The step of teaching the robot may include the step of generating a camera coordinate system in 3D space from 3D data of a new work object, and setting matching information that matches the reference information of a previously registered object in the camera coordinate system to match the position.

[0012] The step of teaching the robot may further include, after matching, a step of calculating a coordinate transformation matrix that transforms a previously registered object position in a camera coordinate system into a new work object position, a step of transforming teaching information at a previously registered object position into teaching information at a new work object position using the calculated coordinate transformation matrix, and a step of transforming the transformed teaching information into a robot coordinate system and transmitting the transformed robot coordinate system to the robot to teach the robot.

[0013] A digital teaching device according to another embodiment includes a data acquisition unit that acquires three-dimensional data of an object captured through a camera, and a control unit that generates a camera coordinate system in three-dimensional space from the acquired three-dimensional data, generates reference information representing the three-dimensional position of the object in the generated camera coordinate system and registers it as a model, generates teaching information including at least one of a robot's work position and movement path based on the three-dimensional position of the object in the camera coordinate system, converts the camera coordinate system in which the teaching information is generated into a robot coordinate system, and transmits the converted robot coordinate system to the robot to teach the robot.

[0014] The data acquisition unit can acquire three-dimensional data of an object using Structured Light Scanning technology based on a structured light pattern.

[0015] The control unit can register the object as reference information, which may be three or more points of the object, a combination of points and lines, a combination of surfaces, lines and points, or the object itself.

[0016] The control unit can align the robot coordinate system and the camera coordinate system through correction between the robot and the camera, or calculate a coordinate system transformation matrix between the robot coordinate system and the camera coordinate system and use the calculated coordinate system transformation matrix to transform the camera coordinate system into the robot coordinate system.

[0017] When the data acquisition unit changes to a new work target that is different in position from the above target, it can acquire 3D data by photographing the new work target through a camera, and the control unit can teach the robot to perform the same task based on the changed position of the target by performing coordinate transformation from the 3D data of the new work target by the changed position in 3D space.

[0018] The control unit can generate a camera coordinate system in 3D space from the 3D data of a new work object and set matching information that matches the reference information of a previously registered object in the camera coordinate system to match the position.

[0019] After matching, the control unit calculates a coordinate transformation matrix that transforms the previously registered object position in the camera coordinate system into a new work object position, uses the coordinate transformation matrix to transform teaching information at the previously registered object position into teaching information at the new work object position, transforms the transformed teaching information into a robot coordinate system, and transmits the transformed robot coordinate system to the robot to teach the robot.

[0020] The present invention can establish a virtual process using a robot. For example, a virtual manufacturing environment can be proactively established by 3D modeling of car body parts, jigs, welding guns, etc., and a robot teaching program can be written in advance.

[0021] The present invention can drastically reduce robot teaching time and provide cost-saving effects as a result. For example, by automatically controlling the movement of the robot through digital teaching of the robot in a virtual space, the operational efficiency of the facility can be improved and robot teaching time can be reduced.

[0022] This invention is user-friendly as it allows non-experts to easily teach robot tasks requiring complex motion control within a short period of time. For example, when preparing a production line, it can significantly reduce the cumbersome tasks previously performed by robot operators compared to conventional manual teaching methods.

[0023] The present invention can contribute to improving the productivity of manufacturers and industrial automation, and enables rapid and efficient production transitions without interrupting the operation of process equipment.

[0024] The present invention can teach a robot to perform the same task based on an object with a changed position by performing coordinate transformation by the amount of the changed position, even if the object is changed during the robot process.

[0025] FIG. 1 is a diagram illustrating the configuration of a digital teaching system according to an embodiment of the present invention.

[0026] FIG. 2 is a diagram illustrating the configuration of the digital teaching device of FIG. 1 according to an embodiment of the present invention.

[0027] FIG. 3 is a diagram illustrating the flow of a digital teaching method according to an embodiment of the present invention.

[0028] FIG. 4 is a diagram illustrating the calculation of a coordinate transformation matrix and the transformation of teaching information for a new work object in a camera coordinate system according to an embodiment of the present invention.

[0029] The advantages and features of the present invention and the methods for achieving them will become clear by referring to the embodiments described below in detail together with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below but can be implemented in various different forms. These embodiments are provided merely to ensure that the disclosure of the present invention is complete and to fully inform those skilled in the art of the scope of the invention, and the present invention is defined only by the scope of the claims. Throughout the specification, the same reference numerals refer to the same components.

[0030] In describing the embodiments of the present invention, if it is determined that a detailed description of known functions or configurations may unnecessarily obscure the essence of the invention, such detailed description will be omitted. Furthermore, the terms described below are defined considering the functions in the embodiments of the present invention, and these may vary depending on the intentions or conventions of the user or operator. Therefore, such definitions should be based on the content throughout this specification.

[0031] Additionally, each block or each step may represent a module, segment, or part of code containing one or more executable instructions for executing specific logical functions, and it should be noted that in some alternative embodiments, the functions mentioned in the blocks or steps may occur out of order. For example, two blocks or steps described in succession may actually be performed substantially simultaneously, and the blocks or steps may also be performed in the reverse order of the corresponding functions as needed.

[0032] Hereinafter, embodiments of the present invention will be described in detail with reference to the attached drawings. However, the embodiments of the present invention exemplified below may be modified in various different forms, and the scope of the present invention is not limited to the embodiments described below. The embodiments of the present invention are provided to more completely explain the present invention to those skilled in the art to which this invention pertains.

[0033] FIG. 1 is a diagram illustrating the configuration of a digital teaching system according to one embodiment of the present invention.

[0034] Referring to FIG. 1, the digital teaching system (1) includes a digital teaching device (10), an object (12), a camera (14), and a robot (16).

[0035] A digital teaching system (1) is a system that acquires three-dimensional data by photographing an object (12) with a camera (14), and a digital teaching device (10) uses the acquired three-dimensional data to digitally teach a robot (16). Digital teaching means automatically controlling the work position, movement path, movement speed, etc. of the robot (16). In contrast to manual teaching of the robot (16), where an engineer must teach the robot (16) movement in advance one by one, digital teaching automatically controls the movement of the robot (16). Through digital teaching of the robot (16) in a virtual space, the operational efficiency of the equipment can be improved and the robot teaching time can be shortened. When preparing a production line, the cumbersome work performed by the robot operator can be significantly reduced compared to the existing manual teaching method.

[0036] When the digital teaching device (10) sets reference information by a user operation signal and sets teaching information including the position and movement path where the robot (16) wants to work, the robot (16) can automatically move from the work position and perform work according to the teaching information.

[0037] The camera (14) captures the object (12) to obtain an image of the object (12). The camera (14) may be a 3D vision camera that obtains a 3D image of the object (12). The camera (14) may be separated from the robot (16) and positioned independently to capture the object (12). In some cases, the camera (14) may be coupled to the robot (16) to capture the object (12). During operation, the object (12) may be continuously changed. When changed, the position of the object (12) may also be changed.

[0038] A robot (16) is a machine that automatically processes or operates a given task based on its own capabilities. The robot (16) performs work in an actual workspace. The robot (16) may be located in the center of the actual workspace. The robot (16) may have multiple hands capable of moving in horizontal and vertical directions, and moving forward, backward, or rotating on a horizontal plane. Each hand is capable of independent operation.

[0039] A digital teaching device (10) generates teaching information including a work position and movement path of a robot (16) in a virtual space based on a three-dimensional image of an object (12), and transmits this to the robot (16) to digitally teach the robot (16). The robot path teaching device (10) can be implemented as a stationary device or a movable device, such as a desktop computer, a laptop, a tablet PC, a smartphone, a wearable device, etc.

[0040] Conventionally, to teach a robot, a robot engineer holds a pendant (robot controller) and moves the robot to a specific position to set it to perform a specific task at that specific position, which takes a lot of time and effort. To solve this problem, a digital teaching device (10) can simply teach the robot (16) by capturing an object (12) with a camera (14) to obtain three-dimensional data, setting teaching information including the movement position and movement path of the robot (16) in a virtual three-dimensional space, converting it into a robot coordinate system, and transmitting it to the robot (16).

[0041] The object (12) is continuously changed during the work process. For example, in an automobile production plant, the car body is continuously changed and introduced, and the position of the car body may shift slightly. Accordingly, the work position and movement path of the robot (16) must be changed by the amount of the shifted position, and the digital teaching device (10) automatically performs coordinate transformation by the amount of the shifted position. Accordingly, the digital teaching device (10) can teach the robot (16) so that even if the position of the object (12) changes, the robot (16) can perform the same work at the position where it needs to work based on the object (12) whose position has changed. The detailed configuration of the digital teaching device (10) will be described later with reference to FIG. 2.

[0042] FIG. 2 is a diagram illustrating the configuration of the digital teaching device of FIG. 1 according to an embodiment of the present invention.

[0043] Referring to FIGS. 1 and 2, the digital teaching device (10) includes a data acquisition unit (101), a communication unit (102), an input unit (103), a control unit (104), a display unit (105), a storage unit (106), and a sensing unit (107).

[0044] The data acquisition unit (101) acquires three-dimensional data of the object (12) by analyzing an image captured through a camera (14) that captures the object (12).

[0045] The data acquisition unit (101) can generate three-dimensional data of an object (12) using structured light scanning technology. Structured light scanning is a technology that digitizes the shape and surface of an object (12) in three dimensions. This technology uses a structured light pattern to precisely measure the shape of the object (12).

[0046] When the camera (14) captures the object (12) using a light pattern, the data acquisition unit (101) analyzes the image captured through the camera (14) to generate three-dimensional data of the object (12). The data acquisition unit (101) can generate a very precise three-dimensional model through structural light scanning, and since scanning is possible without physical contact with the object (12), there is a low risk of damage. In addition, it is efficient because multiple points can be measured simultaneously quickly.

[0047] The communication unit (102) can transmit and receive data with external devices such as a robot (16) or a server using wired or wireless communication technology. For example, the communication unit (102) can transmit and receive sensor information, user input, learning models, control signals, etc., with external devices.

[0048] The input unit (103) receives information from the user.

[0049] The control unit (104) can control the components of the digital teaching device (10) to perform a determined operation. To this end, the control unit (104) can request, search, receive, or utilize data from the storage unit (106), and controls the components of the digital teaching device (10) to execute a predicted operation or an operation determined to be desirable among at least one executable operation.

[0050] At this time, if the control unit (104) requires the connection of an external device to perform a determined operation, it can generate a control signal to control the external device and transmit the generated control signal to the external device.

[0051] The control unit (104) obtains a user operation signal through the input unit (103) and can operate based on the user operation signal.

[0052] The control unit (104) can collect history information including the operation details of the digital teaching device (10) or user feedback on the operation, and store it in the storage unit (106) or transmit it to an external device such as a robot or a server.

[0053] The control unit (104) can control at least some of the components of the digital teaching device (10) to run an application program stored in the storage unit (106). Furthermore, the control unit (104) can operate two or more of the components included in the digital teaching device (10) in combination with each other to run the application program.

[0054] A control unit (104) according to one embodiment teaches the working position of the robot and the movement path of the robot (16) based on three-dimensional data captured by the object (12). For example, the control unit (104) generates a camera coordinate system in three-dimensional space from three-dimensional data obtained through the camera (14), generates reference information of the object (12) in the camera coordinate system to set the three-dimensional position of the object (12), and registers a model based on the set three-dimensional position of the object. The reference information is characteristic information of the reference object (12), and may be three or more points of the object (12), a combination of points and lines, a combination of a surface, lines and points, or the object itself.

[0055] The control unit (104) teaches the robot (16) by generating teaching information including at least one of the work position and movement path of the robot (16) in the camera coordinate system and transmitting it to the robot (16). At this time, the control unit (104) can convert the teaching information generated in the camera coordinate system into the robot coordinate system and transmit it to the robot (16). The digital teaching process of the control unit (104) will be described later with reference to FIG. 3.

[0056] A control unit (104) according to one embodiment can train a model composed of an artificial neural network using training data. Here, the trained artificial neural network may be referred to as a training model. The training model can be used to infer a result value for new input data other than the training data, and the inferred value can be used as a basis for judgment to perform a certain operation.

[0057] The display unit (105) displays an image of the object (12).

[0058] The storage unit (106) can store data that supports various functions of the digital teaching device (10). For example, the storage unit (106) can store input data obtained from the input unit (103), image data of an object, robot path teaching information, etc.

[0059] The sensing unit (107) can acquire at least one of internal information of the digital teaching device (10), surrounding environment information of the digital teaching device (10), and user information using various sensors. At this time, the sensors included in the sensing unit (107) include a proximity sensor, an illuminance sensor, an accelerometer, a magnetic sensor, a gyroscope, an inertial sensor, an RGB sensor, an IR sensor, an ultrasonic sensor, a light sensor, a microphone, a lidar, a radar, etc.

[0060] FIG. 3 is a diagram illustrating the flow of a digital teaching method according to one embodiment of the present invention.

[0061] Referring to FIGS. 1 and FIGS. 3, the digital teaching device (10) acquires three-dimensional data of an object captured through a camera (14) (S310).

[0062] In the step of acquiring three-dimensional data of an object (S310), the digital teaching device (10) can acquire three-dimensional data of an object using structured light scanning technology based on a structured light pattern.

[0063] Next, the digital teaching device (10) generates a camera coordinate system in three-dimensional space from the acquired three-dimensional data and generates reference information representing the three-dimensional position of an object in the generated camera coordinate system and registers it as a model (S320).

[0064] In the reference information registration step (S320), the reference information may be three or more points of an object, a combination of points and lines, a combination of a surface, lines and points, or the object itself.

[0065] Next, the digital teaching device (10) generates teaching information including at least one of the robot's work position and movement path based on the 3D position of the object in the camera coordinate system (S330). At this time, the teaching information can be generated by a user operation signal.

[0066] For example, when a digital teaching device (10) receives a user operation signal requesting the setting of teaching information for a robot, it can set coordinate values ​​indicating the positions of movement path points on the 3D coordinates of an object in a 3D camera coordinate system, movement path lines connecting the movement path points, and the order of movement of the robot for the movement path points. For example, based on a user operation signal that sequentially designates movement path points on the 3D coordinates of an object in a camera coordinate system, it can set coordinate values ​​of the movement path points, distance values ​​between the movement path points, and the order of movement of the robot for the movement path points.

[0067] Next, the digital teaching device (10) converts the camera coordinate system in which teaching information is generated into a robot coordinate system and transmits the converted robot coordinate system to the robot (16) to teach the robot (16) (S340).

[0068] In the robot teaching step (S340), the digital teaching device (10) can align the robot coordinate system and the camera coordinate system through correction between the robot and the camera, or calculate a coordinate system transformation matrix between the robot coordinate system and the camera coordinate system and convert the camera coordinate system to the robot coordinate system using the calculated coordinate system transformation matrix.

[0069] Next, when the digital teaching device (10) changes the object to a new work object that is different in position from the existing object, it can obtain 3D data by photographing the new work object through a camera (S350).

[0070] Next, the digital teaching device (10) can generate a camera coordinate system in three-dimensional space from the three-dimensional data of a new work object and set matching information that matches the reference information of a previously registered object in the camera coordinate system to match the position (S360). The matching information of the new work object may be a feature point corresponding to the position of the reference information of a previously registered object.

[0071] After matching, the digital teaching device (10) can calculate a coordinate transformation matrix that converts a previously registered object position in the camera coordinate system into a new work object position (S370).

[0072] Next, the digital teaching device (10) can convert teaching information at a previously registered object position into teaching information at a new work object position using a coordinate transformation matrix (S380).

[0073] Next, the digital teaching device (10) can convert the converted teaching information into a robot coordinate system and transmit it to the robot (16) to teach the robot (S390).

[0074] Calculation of the coordinate transformation matrix for the new work object and implementation of teaching information transformation will be described later with reference to FIG. 4.

[0075] FIG. 4 is a diagram illustrating the calculation of a coordinate transformation matrix and the transformation of teaching information for a new work object in a camera coordinate system according to an embodiment of the present invention.

[0076] In FIG. 4, C represents the camera coordinate system, R represents the robot coordinate system, s represents the reference object coordinate system, and q represents the new work object coordinate system.

[0077] Referring to FIGS. 1 and 4, when a digital teaching device (10) calculates a coordinate system transformation matrix Mcr (420) that corrects the coordinates between a camera (14) and a robot (16) and sets teaching information for an object in the camera coordinate system, it can convert the camera coordinate system into a robot coordinate system corresponding to the set teaching information using the coordinate system transformation matrix Mcr (420).

[0078] However, the teaching purpose of the digital teaching device (10) is to specify a specific location of an object. Therefore, a series of teaching information is input along a specific location of an object in the camera coordinate system, but if the position of the object is subsequently misaligned or if another object of the same shape is photographed at a location other than the initial position, the camera coordinate values ​​do not match the coordinate values ​​of the object.

[0079] At this time, in order to change the teaching information, it is necessary to know how the coordinates have changed from the position where the reference object (12a) was placed when setting the teaching information in the initial camera coordinate system to the position where the new work object (12b) is placed when shooting the new work object (12b).

[0080] In this regard, the digital teaching device (10) can perform the same work at the location where the robot (16) is to work based on the changed object (12b) even when the location where the reference object (12a) is placed is changed to the location of the new work object (12b).

[0081] For example, as illustrated in FIG. 4, when a digital teaching device (10) sets teaching information, it stores values ​​in the camera coordinate system, but can register reference information placed on the reference object (12a) so that the coordinate values ​​where the reference object (12a) is placed in the camera coordinate system can be known. The reference information may be, for example, three or more points of the reference object (12a), a combination of points and lines, a combination of a surface, lines and points, or the reference object (12a) itself.

[0082] The digital teaching device (10) may specify the position of an object placed in three-dimensional space by registering reference information of a reference object (12a) in a camera coordinate system, or specify the position and direction of an object placed in three-dimensional space by matching the shape of the whole or part of the object in three dimensions. The process of registering reference information placed on the reference object (12a) in order to specify the three-dimensional position of the reference object (12a) in this way is defined as model registration.

[0083] When registering a model, the coordinates of the model can be registered based on the position where the reference object (12a) is placed when the robot is first taught. For example, as shown in FIG. 4, when the reference object (12a) is first placed, the model can be registered with the camera coordinate values ​​of this position.

[0084] Next, when a new work object (12b) is captured, the digital teaching device (10) searches for points that match the model, such as feature points, lines, or surfaces, on the new work object (12b) in order to match the new work object (12b) with the reference object (12a).

[0085] For example, as shown in FIG. 5, if reference information in the reference object (12a) is s1, s2, s3, and reference information in the new work object (12b) after matching is q1, q2, q3, then a coordinate transformation matrix Msq (410) can be calculated in which s1, s2, s3 are transformed into q1, q2, q3. For convenience of explanation, s1, q1, etc. are set as bottom surface vertices in FIG. 4, but are not limited thereto.

[0086] By substituting teaching information P1 and P2 into this coordinate transformation matrix Msq (410), new teaching information coordinates Q1 and Q2 in the new work object (12b) can be obtained. The digital teaching device (10) can convert the teaching information Q1 and Q2 into a robot coordinate system using the coordinate system transformation matrix Mcr and then transmit it to the robot (16).

[0087] The present invention has been described above with reference to its embodiments. Those skilled in the art will understand that the present invention may be implemented in modified forms without departing from the essential characteristics of the invention. Therefore, the disclosed embodiments should be considered in an illustrative rather than a restrictive sense. The scope of the invention is defined by the claims, not by the foregoing description, and all variations within the scope of the claims should be interpreted as being included in the invention.

Claims

1. A step of acquiring 3D data of an object captured through a camera; A step of generating a camera coordinate system in 3D space from acquired 3D data, generating reference information representing the 3D position of an object in the generated camera coordinate system, and registering it as a model; A step of generating teaching information including at least one of a robot's working position and movement path based on the 3D position of an object in a camera coordinate system; and A step of converting the camera coordinate system in which teaching information is generated into a robot coordinate system and transmitting the converted robot coordinate system to the robot to teach the robot; A digital teaching method characterized by including 2. In claim 1, the step of acquiring three-dimensional data of an object A digital teaching method characterized by acquiring three-dimensional data of an object using Structured Light Scanning technology based on a structured light pattern.

3. In Paragraph 1, the step of registration A digital teaching method characterized by creating and registering reference information that is three or more points of an object, a combination of points and lines, a combination of surfaces, lines, and points, or the object itself.

4. In claim 1, the step of teaching the robot A digital teaching method characterized by aligning the robot coordinate system and the camera coordinate system through correction between the robot and the camera, or calculating a coordinate system transformation matrix between the robot coordinate system and the camera coordinate system and transforming the camera coordinate system into the robot coordinate system using the calculated coordinate system transformation matrix.

5. In claim 1, the digital teaching method When the object is changed to a new work object with a different location from the above object, the step of capturing the new work object through a camera to acquire 3D data; and A step of teaching a robot to perform the same task based on the object with the changed position by performing a coordinate transformation from the 3D data of a new work object by the position changed in 3D space; A digital teaching method characterized by including 6. In Clause 5, the step of teaching the robot A step of generating a camera coordinate system in 3D space from 3D data of a new work object, and matching a position by setting matching information that matches the reference information of a previously registered object in the camera coordinate system; A digital teaching method characterized by including 7. In Clause 6, the step of teaching the robot After matching, a step of calculating a coordinate transformation matrix that transforms a previously registered object position in the camera coordinate system into a new work object position; A step of converting teaching information at a previously registered target position into teaching information at a new work target position using a calculated coordinate transformation matrix; and A step of converting the transformed teaching information into a robot coordinate system and transmitting the transformed robot coordinate system to the robot to teach the robot; A digital teaching method characterized by further including 8. A data acquisition unit for acquiring three-dimensional data of an object captured through a camera; and A control unit that generates a camera coordinate system in three-dimensional space from acquired three-dimensional data, generates reference information representing the three-dimensional position of an object in the generated camera coordinate system and registers it as a model, generates teaching information including at least one of a robot's work position and movement path based on the three-dimensional position of the object in the camera coordinate system, converts the camera coordinate system in which the teaching information is generated into a robot coordinate system, and transmits the converted robot coordinate system to the robot to teach the robot; A digital teaching device characterized by including 9. In claim 8, the data acquisition unit A digital teaching device characterized by acquiring three-dimensional data of an object using Structured Light Scanning technology based on a structured light pattern.

10. In claim 8, the control unit A digital teaching device characterized by generating and registering reference information that is three or more points of an object, a combination of points and lines, a combination of surfaces, lines, and points, or the object itself.

11. In claim 8, the control unit A digital teaching device characterized by aligning the robot coordinate system and the camera coordinate system through correction between the robot and the camera, or calculating a coordinate system transformation matrix between the robot coordinate system and the camera coordinate system and transforming the camera coordinate system into the robot coordinate system using the calculated coordinate system transformation matrix.

12. In claim 8, the data acquisition unit When the work object is changed to a new work object with a different location from the above object, the new work object is photographed through a camera to acquire 3D data, and The control unit A digital teaching device characterized by teaching a robot to perform the same task based on the object with the changed position by performing a coordinate transformation from the 3D data of a new work object by the amount of the changed position in 3D space.

13. In Clause 12, the control unit A digital teaching device characterized by generating a camera coordinate system in 3D space from 3D data of a new work object, and matching a position by setting matching information that matches reference information of a previously registered object in the camera coordinate system.

14. In claim 13, the control unit After matching, calculate a coordinate transformation matrix that transforms the previously registered object position in the camera coordinate system into the new work object position, and Using a coordinate transformation matrix, teaching information at a previously registered object location is transformed into teaching information at a new work object location, and A digital teaching device characterized by converting converted teaching information into a robot coordinate system and transmitting the converted robot coordinate system to the robot to teach the robot.

Images