Robot teaching system

Abstract

The present invention provides a robot teaching system that uses an image captured by a camera to generate an operation program that can appropriately perform welding at a welding position. The robot teaching system (200) includes: a photographing unit (211) that photographs an image including a welding object and a marker provided on an industrial robot; a camera coordinate system setting unit (212) that sets a camera coordinate system based on the marker included in the image; a motion path setting unit (213) that sets a motion path of the industrial robot in the camera coordinate system based on the welding position of the welding object included in the image; and a program generation unit (214) that transforms the motion path of the industrial robot set by the motion path setting unit (213) from the camera coordinate system into a robot coordinate system set in a robot control device (2) based on the setting position of the marker provided on the industrial robot, and generates an operation program for operating the industrial robot.

Description

Technical Field

[0001] The present invention relates to a robot teaching system. Background Art

[0002] In recent years, a large number of robots have been popularized in the industrial world. Such robots are used, for example, in the assembly, welding, and transportation of electronic components and mechanical components, aiming at the efficiency and automation of factory production lines. Such robots need to create a program for performing a desired action and pre-store it as so-called teaching data. An operator uses a teach pendant and cooperates with a robot control device to operate an actual robot, thereby recording its actions and generating the teaching data.

[0003] In order for an operator to actually move a robot using a teach pendant while creating teaching data, it is highly dependent on the operator's skills and sometimes takes a long time. Especially when recording precise movements of a robot, it must rely on a skilled person who thoroughly understands the movements of the robot and is accustomed to operating the teach pendant.

[0004] Moreover, in order to reduce the burden on the operator, a robot system that uses an AR device and markers to recognize the position of a robot has been disclosed (for example, Patent Document 1).

[0005] In the robot system disclosed in Patent Document 1, it is configured to use a plurality of reference markers and a robot coordinate system determination marker to recognize the position and orientation of a coordinate system set on the robot coordinate system determination marker with respect to the plurality of reference markers. Thus, the position or orientation of the robot can be recognized using an AR device.

[0006] Prior Art Documents

[0007] Patent Documents

[0008] Patent Document 1: Japanese Patent Laid-Open No. 2021-62463

[0009] However, in the robot system disclosed in Patent Document 1, it is necessary to set a plurality of reference markers and a robot coordinate system determination marker. In addition, in a robot teaching system, there is a problem that it is necessary to grasp the positions of the robot and the welding part and consider appropriate robot movements to appropriately generate an operation program. Summary of the Invention

[0010] Therefore, an object of the present invention is to provide a robot teaching system that uses an image captured by a camera to create an operation program that can appropriately weld at a welding position.

[0011] A robot teaching system according to one embodiment of the present invention includes: an imaging unit that images an image including a welding object and a marker provided on an industrial robot; a camera coordinate system setting unit that sets a camera coordinate system based on the marker included in the image; a motion path setting unit that sets a motion path of the industrial robot in the camera coordinate system based on the welding position of the welding object included in the image; and a program generation unit that transforms the motion path of the industrial robot set by the motion path setting unit from the camera coordinate system into a robot coordinate system set in a robot control device based on the setting position of the marker provided on the industrial robot, and generates an operation program for operating the industrial robot.

[0012] According to this embodiment, the imaging unit images an image including a welding object and a marker provided on an industrial robot, and the camera coordinate system setting unit sets a camera coordinate system based on the marker included in the image. Further, the program generation unit transforms the motion path of the industrial robot set in the camera coordinate system into a robot coordinate system set in a robot control device based on the setting position of the marker provided on the industrial robot, and generates an operation program for operating the industrial robot. Thereby, an operation program that can appropriately perform welding at the welding position can be generated. In addition, since the welding object and the marker can be imaged simultaneously, calibration for transformation from the camera coordinate system to the robot coordinate system can be performed, and the welding position of the welding object can be detected simultaneously. Furthermore, since the marker is provided on the industrial robot, even in a situation where a marker cannot be provided near the welding object, the welding position of the welding object can be appropriately detected based on the marker provided on the industrial robot.

[0013] In the above embodiment, the marker may be provided at the front end of the industrial robot that moves in the same manner as the end effector mounted at the front end of the robot arm.

[0014] According to this embodiment, since the marker is provided at the front end of the industrial robot that moves in the same manner as the end effector mounted at the front end of the robot arm, when the robot arm moves, the imaging unit can image the image in a state where the marker is close to the welding position of the welding object. Thereby, the relative position between the marker and the welding position becomes closer, and the closer this relative position is, the less likely an error is to occur.

[0015] In the above embodiment, the motion path setting unit may detect a welding position candidate by performing image processing on the image, and set the motion path of the industrial robot based on the welding position extracted from the welding position candidate.

[0016] According to this method, by performing image processing on an image to detect candidate welding positions, the welding positions are extracted from the candidate welding positions. Thus, the motion path setting unit can set the motion path of the industrial robot based on the more appropriately extracted welding positions.

[0017] In the above method, it may also be that the motion path setting unit further sets the motion path of the industrial robot for the welding positions based on the set welding sequence.

[0018] According to this method, since the motion path setting unit sets the motion path of the industrial robot for the welding positions based on the further set welding sequence, it can also consider the set welding sequence to more appropriately set the motion path of the industrial robot.

[0019] In the above method, it may also be that the motion path setting unit selects the necessity of welding and / or sets the welding sequence corresponding to the distance between the welding position and the torch to set the motion path of the industrial robot.

[0020] According to this method, since the motion path setting unit appropriately sets the necessity of welding and / or the welding sequence corresponding to the distance between the welding position and the torch, it can more appropriately set the motion path of the industrial robot.

[0021] In the above method, it may also be that the welding sequence is sequentially selected from a specific direction.

[0022] According to this method, regarding the welding sequence, as the specific direction, among the welding positions included in the image, it is sequentially set from the top, bottom, left, or right of the image, or sequentially set in the upward direction from the bottom with respect to the gravity direction. Thus, it is possible to reduce the docking error caused by the thermal strain of the workpiece during welding corresponding to the assembly of the workpiece, etc., and in addition, it is possible to reduce the dripping of the weld bead, etc.

[0023] Effects of the Invention

[0024] According to the present invention, it is possible to provide a robot teaching system that uses an image captured by a camera to generate an operation program that can appropriately perform welding at a welding position. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 FIG. is a diagram illustrating the structure of a welding robot system 100 including a robot teaching system according to an embodiment of the present invention.

[0026] Figure 2 FIG. is a diagram illustrating the functional structure of a robot teaching system 200 according to an embodiment of the present invention.

[0027] Figure 3This is a diagram showing a workpiece W to be welded and a welding robot system provided with a marker M.

[0028] Figure 4 This is a diagram showing the situation where the marker M is brought close to the workpiece W.

[0029] Figure 5 This is a diagram showing an image captured to include the workpiece W and the marker M.

[0030] Figure 6 This is a diagram showing the situation where a camera coordinate system is set based on the marker M included in the captured image.

[0031] Figure 7 This is a diagram showing the situation where an operation path of the welding robot is set based on the welding position of the workpiece W included in the image in the camera coordinate system.

[0032] Figure 8 This is a flowchart showing the process of a robot teaching method M100 executed by a robot teaching system 200 according to an embodiment of the present invention.

[0033] Explanation of reference numerals

[0034] 1... Imaging terminal, 2... Robot control device, 3... Manipulator, 11... Control unit, 12... Imaging unit, 13... Communication unit, 14... Display unit, 21... Control unit, 22... Storage unit, 23... Communication unit, 24... Welding power supply unit, 31... Multi-joint arm, 32... Torch, 100... Welding robot system, 200... Robot teaching system, 211... Imaging unit, 212... Camera coordinate system setting unit, 213... Operation path setting unit, 214... Program generation unit, C... Communication cable, M... Marker, N... Network, W, Wa, Wb, Wc... Workpieces, L1, L2, L3... Welding lines, M100... Robot teaching method, S101 to S104... Steps of the robot teaching method M100 Detailed implementation manners

[0035] The embodiments of the present invention will be specifically described below with reference to the drawings. In addition, the embodiments described below are merely specific examples for implementing the present invention and do not limit the present invention in an explanatory manner. Further, for easy understanding of the description, the same reference numerals are used to label the same components in the respective drawings as much as possible, and there may be repeated descriptions.

[0036] <One embodiment>

[0037] [Basic structure of welding robot system]

[0038] Figure 1 FIG. is a diagram showing the structure of a welding robot system 100 that exemplifies a robot teaching system according to an embodiment of the present invention. As Figure 1 shown, the welding robot system 100 includes, for example, an imaging terminal 1, a robot control device 2, and a robot arm 3. The imaging terminal 1 and the robot control device 2 are connected via a network N, and the robot control device 2 and the robot arm 3 are connected via a communication cable C. The network N can be wired (including communication cables) or wireless. In addition, a teaching pendant may be included in the welding robot system 100. The teaching pendant is an operation device for an operator to teach the movement of the robot arm 3.

[0039] The robot arm 3 is a welding robot (industrial robot) that performs arc welding according to the construction conditions set in the robot control device 2. The robot arm 3 has, for example: a multi-joint arm 31 provided on a base member fixed to the floor of a factory or the like; and a torch 32 (end effector) connected to the tip of the multi-joint arm 31.

[0040] The robot control device 2 is a control component that controls the movement of the robot arm 3, and includes, for example, a control unit 21, a storage unit 22, a communication unit 23, and a welding power supply unit 24.

[0041] The control unit 21 controls the robot arm 3 and the welding power supply unit 24 by, for example, a processor executing a job program stored in the storage unit 22.

[0042] The communication unit 23 controls communication with the imaging terminal 1 connected via the network N and communication with the robot arm 3 connected via the communication cable C.

[0043] The welding power supply unit 24 supplies welding current, welding voltage, etc. to the robot arm 3 according to predetermined welding construction conditions in order to generate an arc between the tip of the welding wire and the workpiece. The welding construction conditions include, for example, data items such as welding conditions, welding start position, welding end position, arc discharge time, welding distance, torch attitude, and torch movement speed. The welding power supply unit 24 may be provided separately from the robot control device 2.

[0044] The imaging terminal 1 is, for example, a digital camera, and may be a movable type terminal with a digital camera. The movable type terminal includes, for example, terminals that can be carried and moved, such as a tablet terminal, a smart phone, a personal digital assistant (PDA), and a notebook PC (personal computer). The imaging terminal 1 includes, for example, a control unit 11, an imaging unit 12, a communication unit 13, and a display unit 14.

[0045] The control unit 11 controls each part of the imaging terminal 1 by a processor executing a given program stored in the memory.

[0046] The photographing unit 12 includes, for example, a lens and an imaging element (image sensor), and converts the light of the subject that has received light through the lens into an electrical signal (digital image data).

[0047] The communication unit 13 controls communication with the robot control device 2 connected via the network N.

[0048] The display unit 14 is, for example, a display with a touch panel, displays the image of the subject obtained by the photographing unit 12, and accepts input such as operation instructions from the operator. The display unit 14 can be, for example, a display device with a touch panel, and is provided separately from the photographing terminal 1.

[0049] [Structure of Robot Teaching System]

[0050] Figure 2 This is a diagram illustrating the functional structure of the robot teaching system 200 according to an embodiment of the present invention. As Figure 2 shown, the robot teaching system 200 has, for example, a photographing unit 211, a camera coordinate system setting unit 212, a motion path setting unit 213, and a program generation unit 214 as functional structures. Among these functions, the photographing unit 211 is a function of the photographing terminal 1. On the other hand, the camera coordinate system setting unit 212, the motion path setting unit 213, and the program generation unit 214 can be entirely provided by either the photographing terminal 1 or the robot control device 2, or the functions can be distributed between the photographing terminal 1 and the robot control device 2. In addition, it is also possible that a device other than the photographing terminal 1 and the robot control device 2 provides a part or all of the above functions.

[0051] The photographing unit 211 is the same as the photographing unit 12 of the photographing terminal 1. The photographing unit 211 according to the present embodiment photographs an image including a workpiece and a marker provided on the robot hand 3. For example, the photographing unit 211 photographs an image including both a workpiece and a marker provided on the welding torch 32 attached to the front end of the robot hand 3. In addition, information related to the position and posture of the robot hand 3 controlled by the robot control device 2 at the time of photographing this image is stored in association with this image, and is used in the calibration of the camera coordinate system and the robot coordinate system described later.

[0052] The camera coordinate system setting unit 212 sets a camera coordinate system based on the marker included in the image photographed by the photographing unit 211. For example, the camera coordinate system setting unit 212 sets a three-dimensional orthogonal coordinate system composed of an X axis, a Y axis, and a Z axis that are orthogonal to each other at the origin, with the position of the marker as the origin, in the image photographed by the photographing unit 211, as the camera coordinate system.

[0053] The motion path setting unit 213 sets the motion path of the robot arm 3 in the camera coordinate system set by the camera coordinate system setting unit 212 based on the welding position of the workpiece included in the image captured by the imaging unit 211. For example, in the image captured by the imaging unit 211, the motion path setting unit 213 manually selects the motion path of the robot arm 3 (torch 32) by the user, or calculates the distance between the welding position and the torch 32 to automatically set the motion path of the robot arm 3 (torch 32) so that the torch 32 mounted at the front end of the robot arm 3 moves along the welding position of the workpiece. Additionally, the welding position can also be detected as a welding position candidate by performing image processing on the image captured by the imaging unit 211, and extracted by the user's selection from the welding position candidates. Furthermore, the welding position is not limited to being extracted by the user's selection from the welding position candidates. For example, it can also be automatically extracted from the welding position candidates according to preset conditions.

[0054] The program generation unit 214 transforms the motion path of the robot arm 3 set by the motion path setting unit 213 from the camera coordinate system into the robot coordinate system set in the robot control device 2 based on the setting position of the marker provided on the robot arm 3, and generates an operation program for operating the robot arm 3.

[0055] Specifically, as described above, the motion path setting unit 213 sets the motion path of the robot arm 3 in the camera coordinate system set by the camera coordinate system setting unit 212 based on the image captured by the imaging unit 211. On the other hand, the robot control device 2 knows the setting position of the marker provided on the robot arm 3 and maintains the robot coordinate system based on the setting position of the marker. The program generation unit 214 transforms the motion path of the robot arm 3 in the camera coordinate system into the robot coordinate system based on the setting position of the marker, sets the path for the robot arm 3 to actually move, and generates an operation program to perform welding appropriately at the welding position.

[0056] Here, the transformation from the camera coordinate system to the robot coordinate system is described. The program generation unit 214 obtains information related to the position and orientation of the robot hand 3 based on the image captured by the imaging unit 211. More specifically, it obtains at least information related to the position and orientation of the welding torch 32 in the camera coordinate system set based on the fiducial. On the other hand, the program generation unit 214 obtains information related to the position and orientation of the robot hand 3 controlled by the robot control device 2 at the time of capturing the image. The information related to the position and orientation of the robot hand 3 controlled by the robot control device 2 is information related to the angles of the respective axes of the robot hand 3 controlled by the robot control device 2, etc., and the position and orientation of the robot hand 3 (robot coordinate system) can be grasped from this information. Then, based on the information related to the position and orientation of the welding torch 32 in the camera coordinate system (camera coordinate system) set based on the fiducial contained in the image captured by the imaging unit 211, and the information related to the position and orientation of the robot hand 3 controlled by the robot control device 2 at the time of capturing the image (robot coordinate system), the transformation from the camera coordinate system to the robot coordinate system can be performed.

[0057] That is, calibration is performed to make the camera coordinate system based on the fiducial (origin) contained in the image captured by the imaging unit 211 and the robot coordinate system based on the angles of the respective axes controlled by the robot control device 2 at the time of capturing the image coincide. In addition, since the imaging terminal 1 and the robot control device 2 are connected by the network N as described above, at the time of capturing the image on the imaging terminal 1, it is sufficient to store information related to the angles of the respective axes of the robot hand 3 controlled by the robot control device 2.

[0058] As described above, the program generation unit 214 uses the information related to the position and orientation of the robot hand 3 contained in the image captured by the imaging unit 211 (camera coordinate system) and the information related to the position and orientation of the robot hand 3 grasped by the robot control device 2 at the time of capturing the image (robot coordinate system) to transform the motion path of the robot hand 3 in the camera coordinate system into the robot coordinate system and set the path for the robot hand 3 to actually perform the motion.

[0059] In this way, in the robot teaching system 200, an operation program for appropriately welding the robot hand 3 at the welding position is generated using the image containing the workpiece and the fiducial captured by the imaging unit 211. Then, the operation program is stored in the storage unit in the robot control device 2, and the robot control device 2 controls the motion of the robot hand 3 based on the operation program. Thus, as a welding robot system, welding can be appropriately performed at the welding position of the workpiece.

[0060] [Specific situations in each process of the robot teaching system]

[0061] Next, a specific situation from using the imaging terminal 1 to capture an image to generating an operation procedure suitable for welding at the welding position will be described in detail.

[0062] Figure 3 It is a diagram showing a workpiece W to be welded and a welding robot system with a setting mark M. As Figure 3 shown, the workpiece W is a structure composed of one workpiece Wa serving as a bottom plate and two workpieces Wb and Wc serving as side plates, and the mark M is set on a torch 32 (end effector) installed at the front end of the manipulator 3.

[0063] Here, the robot control device 2 controls the position, direction, etc. of the manipulator 3 having the multi-joint arm 31 and the torch 32 in a preset robot coordinate system. The mark M serves as a reference for calibration between the robot coordinate system and a camera coordinate system described later, and the robot control device 2 needs to correctly grasp the position where the mark M is set. The mark M is preferably set correctly at a predetermined position grasped by the robot control device 2.

[0064] Figure 4 It is a diagram showing the situation of bringing the mark M close to the workpiece W. As Figure 4 shown, for example, by operating the manipulator 3, the mark M set on the torch 32 is brought close to the workpiece W. When the mark M and the workpiece W are in a close state, it is easy for the imaging unit 211 to capture an image including both the mark M and the workpiece W. In addition, by reducing the distance (relative position) between the mark M and the workpiece W, the influence of measurement error can be reduced.

[0065] Figure 5 It is a diagram showing an image capturing the workpiece W and the mark M. As Figure 5 shown, the imaging unit 211 captures an image including both the workpiece W and the mark M. For example, the imaging unit 211 appropriately captures a part of the workpiece W that is a candidate for the welding position and the mark M so that there is no missing, deformation, interference with peripheral equipment, blurring, etc. of a part of the candidate for the welding position in the workpiece W and the mark M in the image captured by the imaging unit 211.

[0066] In other words, for the mark M, it is set on the torch 32 of the manipulator 3 so that it is difficult to deviate, deform, or break, and the manipulator 3 needs to be operated to bring the mark M set on the torch 32 close to the workpiece W so that a part of the workpiece W that is a candidate for the welding position and the mark M can be appropriately captured simultaneously.

[0067] In addition, here, the marker M is set on the torch 32, but it is not limited thereto. If the robot arm 3 is moved so that it can appropriately capture simultaneously with a part of the workpiece W that is a candidate for the welding position, it may be set, for example, near the torch 32 or at other positions of the welding robot (robot arm 3). Here, the marker M is installed at the front end that moves in the same manner as the torch 32 (end effector) installed at the front end of the robot arm 3.

[0068] For example, the marker M can be set on the end effector (torch 32), can be set on the bracket for attaching the end effector to the robot arm 3, or can be set on the 6-axis drive part of the robot arm 3.

[0069] In this way, by setting the marker M at the front end that moves in the same manner as the torch 32 (end effector) installed at the front end of the robot arm 3, the positional relationship between the marker M and the torch 32 (for example, TCP: Tool Center Position) can be maintained without change. Thereby, when setting the movement path of the welding robot to appropriately weld at the welding position, the TCP can be easily determined, and the amount of calculation can be reduced. Assuming that the positional relationship between the marker M and the TCP changes corresponding to the position and posture of the robot arm 3, when determining the TCP, it is necessary to consider the position and posture of the robot arm 3, and there is a possibility that the amount of calculation increases.

[0070] Figure 6 It is a diagram showing a case where the camera coordinate system is set based on the marker M included in the captured image. As Figure 6 shown, the marker M is detected from the image captured by the imaging unit 211, the position of the marker M is set as the origin O, and a three-dimensional orthogonal coordinate system composed of an X-axis, a Y-axis, and a Z-axis orthogonal to each other at the origin O is set as the camera coordinate system.

[0071] Here, the marker M only needs to be an identifier that can make the imaging unit 211 recognize that it is properly placed in the space. As the marker, for example, an AR (Augmented Reality) marker is preferably used. By using the AR marker, when the AR marker placed in the space is recognized, it is possible to easily achieve the superimposed display of the camera coordinate system with the AR marker as the origin and the actual image.

[0072] Furthermore, as Figure 6 shown, the welding lines L1, L2, and L3 of the workpiece W are extracted. Specifically, the workpiece W is a structure composed of one workpiece Wa that serves as a bottom plate and two workpieces Wb and Wc that serve as side plates, and is shown as a welding object. The intersection lines L1, L2, and L3 of the workpieces Wa, Wb, and Wc are respectively extracted as the welding lines.

[0073] As a method for extracting the welding lines L1, L2, and L3, for example, the image captured by the imaging unit 211 can be displayed on a display screen such as a tablet terminal (e.g., the display unit 14 of the imaging terminal 1), and the extraction can be performed by user selection. Specifically, in the image displayed on the display screen, the user can trace with a finger to extract the welding lines L1, L2, and L3.

[0074] Here, in the case where a mark is set at the actual welding position, information such as the attitude of the tip of the welding torch 32 relative to the welding position, the welding speed, the welding sequence, and the detailed target position can be included in the mark. Specifically, if the mark includes indication information that the tip of the welding torch 32 contacts the welding position at 45 degrees, the attitude of the robot arm 3 can also be set based on the mark. In addition, in the case where there are multiple welding positions (welding lines), if the welding sequence is included in each mark, the movement path of the robot arm 3 can also be set.

[0075] In addition, a 3D camera can also be used to automatically extract the welding lines L1, L2, and L3. Specifically, for example, a distance measurement sensor such as a LiDAR (Light Detection and Ranging) sensor is used to obtain point cloud data corresponding to the workpiece W in the image captured by the imaging unit 211. Then, based on the point cloud data drawn in the camera coordinate system, the shape of the workpiece W can be recognized, and the part recognized as a straight line can be extracted as the welding line.

[0076] In addition, as a method for extracting the welding lines L1, L2, and L3, it is not limited to these. As long as the welding lines L1, L2, and L3 can be appropriately extracted from the image captured by the imaging unit 211, for example, the welding lines L1, L2, and L3 can also be extracted by using other image processing.

[0077] Figure 7 This is a diagram showing a case where the movement path of the welding robot is set based on the welding positions of the workpiece W included in the image in the camera coordinate system. As Figure 7 shown, the movement path of the robot arm 3 is set so as to weld the welding lines L1, L2, and L3 in sequence.

[0078] The movement path of the robot arm 3 can be set, for example, by the user selecting the welding lines L1, L2, and L3 on the display screen of a tablet terminal or the like. The user can set the welding sequence for the welding lines L1, L2, and L3, trace the welding direction with a finger, or set the welding speed.

[0079] In addition, the movement path of the robot hand 3 can be set, for example, corresponding to the distances between the welding lines L1, L2, and L3 and the welding torch 32. Specifically, it can be set to start welding from the welding line that is closer to the welding torch 32, or the movement path of the welding robot can be set so that the movement distance of the welding torch 32 becomes shorter when all of the welding lines L1, L2, and L3 are welded.

[0080] In addition, as a method for setting the movement path of the robot hand 3 for welding the welding lines L1, L2, and L3, it is not limited to these. As long as the welding lines L1, L2, and L3 can be welded appropriately, for example, AI or the like can also be used to set the movement path of the robot hand 3.

[0081] Specifically, as the movement path of the robot hand 3, it can be set to sequentially select and weld from the top, bottom, left, or right of the image among the welding positions included in the image. For example, the direction corresponding to the assembly such as whether the workpieces are connected left and right or stacked up and down is specified. Thereby, the docking error and the like caused by the thermal strain of the workpiece during welding can be reduced.

[0082] In addition, as the movement path of the robot hand 3, it can be set to sequentially select and weld in the direction from bottom to top with respect to the gravity direction among the welding positions included in the image. For example, on the basis of defining the gravity direction using the gyro sensor information included in the photographing terminal 1 or the setting information of the robot hand 3 included in the robot control device 2, the welding lines are sequentially selected in the direction from bottom to top. Thereby, the influence of the thermal strain of the workpiece during welding and the like and the dripping of the weld bead can be reduced.

[0083] In this way, the camera coordinate system is set in the image captured by the photographing unit 211, and the movement path of the robot hand 3 is set in this camera coordinate system.

[0084] Then, the program generation unit 214 transforms the movement path of the robot hand 3 set in the camera coordinate system into the robot coordinate system based on the setting position of the marker M provided on the robot hand 3, and generates an operation program for operating the robot hand 3 in this robot coordinate system. That is, the program generation unit 214 performs calibration for making the camera coordinate system and the robot coordinate system coincide, and generates an operation program based on the movement path obtained by transforming the movement path of the robot hand 3 set in the camera coordinate system into the robot coordinate system. In this calibration, as described above, the information (camera coordinate system) related to the position and orientation of the robot hand 3 included in the image captured by the photographing unit 211 and the information (robot coordinate system) related to the position and orientation of the robot hand 3 grasped by the robot control device 2 at the time of capturing this image are used.

[0085] [Robot teaching method]

[0086] Next, a robot teaching method will be specifically described in detail, in which the robot teaching system 200 uses the image captured by the camera to generate an operation program that can appropriately perform welding at the welding position.

[0087] Figure 8 It is a flowchart showing the process of the robot teaching method M100 executed by the robot teaching system 200 according to an embodiment of the present invention. As Figure 8 shown, the robot teaching method M100 includes steps S101 to S104, and each step is executed by a processor included in the robot teaching system 200.

[0088] In step S101, the robot teaching system 200 captures an image including the welding object and the mark provided on the welding robot. As a specific example, the imaging unit 211 in the robot teaching system 200 captures an image including both the workpiece W to be welded and the mark M provided on the torch 32 attached to the front end of the robot arm 3. In addition, information related to the angles of the respective axes of the robot arm 3 controlled by the robot control device 2 at the time of this imaging is stored in association with the captured image.

[0089] In step S102, the robot teaching system 200 sets the camera coordinate system based on the mark included in the image captured in step S101. As a specific example, the camera coordinate system setting unit 212 in the robot teaching system 200 sets a three-dimensional orthogonal coordinate system composed of an X-axis, a Y-axis, and a Z-axis that are orthogonal to each other at the origin O, with the position of the mark M included in the image as the origin O, as the camera coordinate system.

[0090] In step S103, the robot teaching system 200 sets the action path of the welding robot based on the welding position of the welding object included in the image in the camera coordinate system set in step S102. As a specific example, the action path setting unit 213 in the robot teaching system 200 sets the action path of the robot arm 3 in the camera coordinate system so that the torch 32 attached to the front end of the robot arm 3 moves along the welding position of the workpiece.

[0091] In step S104, the robot teaching system 200 transforms the motion path of the welding robot set in step S103 from the camera coordinate system into the robot coordinate system set in the robot control device 2 based on the set position of the mark on the welding robot, and generates an operation program for causing the welding robot to move. As a specific example, in step S103, the motion path setting unit 213 sets the motion path of the robot hand 3 in the camera coordinate system. In order to maintain the robot coordinate system based on the set position of the mark M on the robot hand 3, the program generation unit 214 transforms the motion path of the robot hand 3 in the camera coordinate system into the robot coordinate system, sets the path along which the robot hand 3 actually moves, and generates an operation program so as to perform welding appropriately at the welding position.

[0092] As described above, according to the robot teaching system 200 and the robot teaching method M100 according to an embodiment of the present invention, the imaging unit 211 images an image including the workpiece W to be welded and the mark M provided on the robot hand 3, and the camera coordinate system setting unit 212 sets the camera coordinate system based on the mark M included in the image. Then, the program generation unit 214 transforms the motion path of the robot hand 3 set in the camera coordinate system into the robot coordinate system set in the robot control device 2 based on the set position of the mark M provided on the robot hand 3, and generates an operation program for causing the robot hand 3 to move. Thereby, an operation program that can perform welding appropriately at the welding position can be generated.

[0093] As a result, even without implementing a robot teaching method that relies on the skills of an operator to generate an operation program while causing the robot hand 3 to move precisely, it is possible to reduce the dependence on the skills of the operator by using the image captured by the camera, and an operation program can be generated efficiently.

[0094] In addition, in the present embodiment, one mark M is set on the welding torch 32 of the robot hand 3, but it is not limited thereto. For example, a plurality of marks may be set.

[0095] For example, when the imaging unit 211 is to image an image including the workpiece W and the mark M, considering differences in the positional relationship among the imaging terminal 1, the workpiece W, and the mark M, sometimes an image that simultaneously includes the mark M and the workpiece W cannot be captured appropriately due to, for example, a part of the workpiece W or the mark M not being captured, or being in a shadow, or an inappropriate imaging angle. In this case, if a mark M is set on the welding torch 32 of the robot hand 3 and a mark M is also set on the opposite (back) side, the imaging unit 211 images an image so as to include the workpiece W and one of the two marks M. That is, it is possible to clearly image either the workpiece W or the plurality of marks M corresponding to the positional relationship among the imaging terminal 1, the workpiece W, and the plurality of marks M.

[0096] In addition, the plurality of markers M is not limited to two. For example, three or more markers M can also be set so that the periphery of the welding torch 32 is surrounded, and a plurality can also be set in the vertical direction among the welding torches 32.

[0097] In this way, by providing the plurality of markers M, the marker M is clearly photographed by the photographing unit 211, thereby improving the accuracy and further alleviating the restrictions caused by the posture.

[0098] In addition, the photographing unit 211 can also photograph a plurality of images. For example, when the welding positions in the workpiece W cover a wide range, after bringing the marker M closer, images including a part of the marker M and the welding position in the workpiece W are photographed in multiple segments. Then, by overlapping the images photographed in multiple segments based on the marker M contained in each image, it can be applied even when the welding position covers a wide range.

[0099] Furthermore, for example, images simultaneously including the welding position and the marker M in the workpiece W can also be photographed multiple times from different angles. And if the welding positions in the camera coordinate system are averaged by overlapping the images photographed multiple times based on the marker M contained in each image, each photographing error and measurement error can be reduced, and the position accuracy can be improved.

[0100] In addition, in the present embodiment, an example of extracting the welding lines L1, L2, and L3 from the image using a distance measurement sensor such as a LiDAR sensor is shown, but the point cloud data obtained from the LiDAR sensor can also be used to grasp the surrounding environment and the like. For example, if the shape of the workpiece W, the mounting table, and other obstacles are grasped, interference with them can be avoided, and the movement path of the robot hand 3 can be set.

[0101] The embodiments described above are for facilitating the understanding of the present invention and do not limit the interpretation of the present invention. Each element and its configuration, material, conditions, shape, size, etc. included in the embodiments are not limited to the examples and can be appropriately changed. In addition, the structures shown in different embodiments can be partially replaced or combined with each other.

Claims

1. A robot teaching system, characterized in that, a photographing unit that photographs an image including a welding object and a mark provided on an industrial robot; a camera coordinate system setting unit that sets a camera coordinate system based on the mark included in the image; a motion path setting unit that sets a motion path of the industrial robot in the camera coordinate system based on a welding position of the welding object included in the image; and a program generation unit that transforms the motion path of the industrial robot set by the motion path setting unit from the camera coordinate system into a robot coordinate system set in a robot control device based on a setting position of a mark provided on the industrial robot, and generates an operation program for operating the industrial robot.

2. The robot teaching system according to claim 1, characterized in that, the mark is provided at a front end portion of the industrial robot that moves in the same manner as an end effector mounted at a front end of a robot arm.

3. The robot teaching system according to claim 1 or 2, characterized in that, the motion path setting unit detects welding position candidates by performing image processing on the image, and sets the motion path of the industrial robot based on the welding positions extracted from the welding position candidates.

4. The robot teaching system according to claim 3, characterized in that, the motion path setting unit further sets the motion path of the industrial robot based on the set welding sequence for the welding positions.

5. The robot teaching system according to claim 4, characterized in that, the motion path setting unit selects the necessity of welding and / or sets the welding sequence corresponding to the distance between the welding position and a welding torch, and sets the motion path of the industrial robot.

6. The robot teaching system according to claim 5, characterized in that, the welding sequence is sequentially selected starting from a specific direction.

Images