JP2024006251A - Welding robot system and determination method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a welding robot system and a determination method, each enabling determination of correctness of a sensor position where the sensor is fitted to a welding robot.

SOLUTION: A welding robot system comprises a welding robot welding a steel material while moving the steel material in a prescribed direction. The welding robot system comprises: a prescribed direction side sensor which is fitted to the welding robot and is fitted to a prescribed direction side of the welding robot; an opposite side sensor which is fitted to the welding robot and is fitted to the opposite side to the prescribed direction side of the welding robot; and a determination portion which determines whether each of the prescribed direction side sensor and the opposite side sensor is fitted to the prescribed direction side or to the other side.

SELECTED DRAWING: Figure 2

COPYRIGHT: (C)2024,JPO&INPIT

Description

The present invention relates to a welding robot system and a determination method.

Automatic welding using welding robots is used to join steel materials. During automatic welding, a self-propelled welding robot is placed along the welding part and continuously welds into a groove that has been previously formed in the welding part. In a control device for a welding robot, position control based on image processing is utilized in order to appropriately position the torch of the welding robot with respect to the bevel.

Furthermore, regarding arc welding, a technique for observing the molten state of a welded region is known (see, for example, Patent Document 1). According to this technique, the welding observation device is a welding observation device for observing a molten part in arc welding, and includes a first imaging means for taking an image of a molten pool formed in the molten part; and a first detection unit that detects air bubbles generated in the molten pool from an image of the molten pool captured by the means.

Japanese Patent Application Publication No. 2021-167010

Self-propelled rail-propelled welding robots are being introduced to construction sites to improve welding quality and resolve the labor shortage at construction sites. When attempting to measure the shape of a base material to be welded using image processing using a camera using a rail self-propelled welding robot, the following points may arise.
(1) If there is only one camera for a welding robot that images the tip of the welding wire and the groove shape, there is a risk that there will be areas where images cannot be captured due to interference with jigs and incidental equipment.
(2) Due to optical reasons such as sunlight conditions, if images are taken with a single camera, the accuracy of image processing and the execution of the processing itself may not be complete.

In response to the above concerns, a case will be described in which a mechanism is adopted in which two cameras are installed at target positions with respect to the welding torch. When a welding robot is introduced at a construction site, workers must transport the robot to the welding location, assemble it, and install it. During this process, if the worker sets the two registered cameras on the robot incorrectly, it becomes impossible to properly use the two cameras.
For example, in Patent Document 1, in a welding robot, sensors such as cameras are installed on both sides of the torch in the forward and backward directions, and images obtained from both are subjected to image processing to monitor the welding status. . However, Patent Document 1 does not mention how to prevent images from being mixed up, which may occur due to incorrect installation of a sensor such as a camera.

An object of the present invention is to provide a welding robot system and a determination method that can determine whether the position of a sensor attached to a welding robot is correct or incorrect.

(1) A welding robot system according to one aspect of the present invention includes a welding robot that welds steel materials while moving the steel materials in a predetermined direction, and a sensor attached to the welding robot, a predetermined direction side sensor attached to the predetermined direction side of the welding robot; a sensor attached to the welding robot and an opposite side sensor attached to a side opposite to the predetermined direction side of the welding robot; and a determination unit that determines whether each of the predetermined direction side sensor and the opposite side sensor is attached to the predetermined direction side or the opposite side.

According to this invention, a welding robot system includes a welding robot that welds steel materials while moving the steel materials in a predetermined direction. A welding robot system is a sensor that is attached to a welding robot, and includes a predetermined direction side sensor attached to a predetermined direction side of the welding robot and an opposite side sensor attached to a side of the welding robot opposite to the predetermined direction side. Be prepared. The welding robot system includes a determination unit that determines whether each of the predetermined direction side sensor and the opposite side sensor is attached to the predetermined direction side or the opposite side. With this configuration, the welding robot system includes a determination unit that determines whether each of the predetermined direction side sensor and the opposite side sensor is attached to the predetermined direction side or the opposite side. It is possible to determine whether the position is correct or incorrect.

(2) A welding robot system according to one aspect of the present invention is the welding robot system according to (1) above, wherein the sensor includes a camera, and the welding robot system is arranged such that the predetermined direction side sensor and the opposite The side sensor further includes a control unit that performs control to image a subject installed between the predetermined direction side sensor and the opposite side sensor, and the determination unit is configured to control the predetermined direction side sensor and the opposite side sensor. It is determined whether the predetermined direction side sensor and the opposite side sensor are attached to the predetermined direction side or the opposite side, using an image outputted by capturing the subject.

In welding robot systems, the sensors include cameras. The welding robot system further includes a control unit that controls the predetermined direction sensor and the opposite sensor to image a subject installed between the predetermined direction sensor and the opposite sensor. By configuring in this way, the determination unit uses the images output by the predetermined direction side sensor and the opposite side sensor to capture and output images of the subject, and the predetermined direction side sensor and the opposite side sensor determine the predetermined direction side and the opposite side sensor. Since it can be determined where the camera is installed, it is possible to determine whether the camera is installed in the correct or incorrect position.

(3) The welding robot system according to one aspect of the present invention is the welding robot system described in (2) above, in which the subject is located in each imaging range of the predetermined direction side sensor and the opposite side sensor. Located within a predetermined range.

In the welding robot system, the subject is located within a predetermined range in the respective imaging ranges of a sensor on the predetermined direction and a sensor on the opposite side. With this configuration, the determination unit uses the images output by the predetermined direction side sensor and the opposite side sensor of a subject located within a predetermined range in their respective imaging ranges, to determine the predetermined direction side sensor. Since it can be determined whether the opposite side sensor is attached to the predetermined direction side or the opposite side, it is possible to determine whether the mounting position of the camera is correct or incorrect.

(4) A welding robot system according to one aspect of the present invention is the welding robot system described in (2) or (3) above, in which the shape of the subject is rectangular.

In the welding robot system, the shape of the object can be rectangular. With this configuration, the determination unit uses an image outputted by the predetermined direction side sensor and the opposite side sensor to capture and output a rectangular subject, and the predetermined direction side sensor and the opposite side sensor Since it is possible to determine which side the camera is attached to on the opposite side, it is possible to determine whether the camera is attached correctly or incorrectly.

(5) A welding robot system according to one aspect of the present invention is the welding robot system according to any one of (2) to (4) above, in which the shape of the subject is a rectangle, and the The angle formed by the long side of the subject and the long side of each imaging range of the sensor on the predetermined direction and the sensor on the opposite side remains unchanged.

In the welding robot system, the shape of the object is rectangular, and the angle formed by the long side of the object and the long side of each imaging range of the sensor on the predetermined direction and the sensor on the opposite side can be kept unchanged. It is only necessary that the angle formed by the long side of the subject and the long side of the imaging range remains unchanged at the timing when the predetermined direction side sensor and the opposite side sensor take images. By configuring in this way, the determination unit uses the images output by the predetermined direction side sensor and the opposite side sensor to capture and output images of a rectangular subject, so that the predetermined direction side sensor and the opposite side sensor each take a predetermined direction. Since it is possible to determine whether the camera is attached to the side or the opposite side, it is possible to determine whether the camera is attached correctly or incorrectly.

(6) The welding robot system according to one aspect of the present invention is the welding robot system according to any one of (2) to (5) above, in which the determination unit Using the coordinates of at least two vertices of the subject, it is determined whether the predetermined direction side sensor and the opposite side sensor are attached to the predetermined direction side or the opposite side.

In the welding robot system, the determination unit can use the coordinates of at least two vertices of the subject included in the image. With this configuration, the determination unit uses the coordinates of at least two vertices of the subject included in the image, and determines whether the predetermined direction side sensor and the opposite side sensor are attached to the predetermined direction side or the opposite side. Since it can be determined whether the camera is installed correctly or incorrectly.

(7) A welding robot system according to an aspect of the present invention is the welding robot system according to any one of (2) to (6) above, wherein the subject is the predetermined direction side sensor and the This is a calibration plate for associating the coordinate system of the opposite side sensor with the coordinate system of the welding robot, and is used for calibrating the predetermined direction side sensor and the opposite side sensor.

In the welding robot system, the subject is calibration for associating the coordinate systems of the sensor on the predetermined direction and the opposite side with the coordinate system of the welding robot, and is used for calibration between the sensor on the predetermined direction and the sensor on the opposite side. It can be used as a calibration plate. With this configuration, the determination unit uses images output by the predetermined direction side sensor and the opposite side sensor to capture and output images of the calibration plate, and determine whether the predetermined direction side sensor and the opposite side sensor Since it is possible to determine which side the camera is attached to, it is possible to determine whether the camera is attached in the correct or incorrect position.

(8) A welding robot system according to one aspect of the present invention is the welding robot system described in (7) above, in which the calibration plate is also used to measure the cross-sectional shape of the groove.

In the welding robot system, the calibration plate is also used to measure the cross-sectional shape of the groove. With this configuration, the determination unit uses the image outputted by the sensor on the predetermined direction and the sensor on the opposite side to capture and output the calibration plate, which is also used to measure the cross-sectional shape of the groove, and determines the side in the predetermined direction. Since it can be determined whether the sensor and the opposite side sensor are attached to the predetermined direction side or the opposite side, it is possible to determine whether the mounting position of the camera is correct or incorrect.

(9) A welding robot system according to one aspect of the present invention is the welding robot system described in (7) or (8) above, in which the calibration plate is configured to adjust the inclination of the coordinate system of the robot with respect to the world coordinate system. It is also used to find

In welding robot systems, the calibration plate is also used to determine the inclination of the robot's coordinate system with respect to the world coordinate system. With this configuration, the determination unit outputs an image that the predetermined direction side sensor and the opposite side sensor image and output of the calibration plate, which is also used to find the inclination of the robot's coordinate system with respect to the world coordinate system. Since it can be determined whether the predetermined direction side sensor and the opposite side sensor are attached to the predetermined direction side or the opposite side using , it is possible to determine whether the mounting position of the camera is correct or incorrect.

(10) A welding robot system according to one aspect of the present invention is the welding robot system according to any one of (7) to (9) above, in which the image includes the predetermined direction side sensor and the The opposite sensor is an image captured and output of the subject for the calibration.

In the welding robot system, the image may be an image output by a sensor on a predetermined direction and a sensor on the opposite side capturing and outputting a subject for calibration. With this configuration, the determination unit allows the predetermined direction side sensor and the opposite side sensor to perform the predetermined direction using the image captured and outputted from the subject for calibration. Since it is possible to determine whether the camera is attached on the opposite side or on the opposite side, it is possible to determine whether the camera is attached correctly or incorrectly.

(11) A welding robot system according to one aspect of the present invention is the welding robot system according to any one of (7) to (10) above, in which the image includes the predetermined direction side sensor and the The image is an image captured and outputted of the subject by the sensor on the predetermined direction and the sensor on the opposite side, respectively, in order to correct distortion of the image captured by the sensor on the opposite side.

In a welding robot system, an image is an image output by a sensor on a predetermined direction and a sensor on the opposite side capturing a subject, respectively, in order to correct distortion of the image captured by the sensor on the predetermined direction and the sensor on the opposite side, respectively. can do. With this configuration, the determination unit uses the image captured and output of the subject in order to correct the distortion of the image captured by the predetermined direction sensor and the opposite sensor, respectively. Since it can be determined whether the opposite side sensor is attached to the predetermined direction side or the opposite side, it is possible to determine whether the mounting position of the camera is correct or incorrect.

(12) A welding robot system according to one aspect of the present invention is the welding robot system according to any one of (1) to (11) above, in which the predetermined direction side sensor and the opposite side sensor an input unit that allows a user to input information corresponding to a position where the sensor is attached; a position to which the information inputted by the input unit corresponds; and a side opposite to the predetermined direction side sensor determined by the determination unit. and a notification unit that notifies the user when the position where the sensor is attached is different from the position where the sensor is attached.

The welding robot system includes an input unit that allows a user to input information corresponding to a position where a sensor on a predetermined direction and a sensor on the opposite side are attached. An example of information corresponding to a location is an IP address. The welding robot system notifies the user when the position corresponding to the information input by the input unit is different from the position where the predetermined direction side sensor and the opposite side sensor are attached, which is determined by the determination unit. Equipped with a notification section. With this configuration, the welding robot system causes the welding robot to weld the steel material while moving the steel material in a predetermined direction based on information corresponding to the positions where the sensor on the predetermined direction side and the sensor on the opposite side are attached. be able to. The welding robot system can notify the user if the camera is incorrectly mounted.

(13) A determination method according to an aspect of the present invention includes a welding robot that welds a steel material while moving the steel material in a predetermined direction, the welding robot being attached to a predetermined direction side of the welding robot. a step of determining whether each of a side sensor and an opposite side sensor attached to a side opposite to the predetermined direction side of the welding robot is attached to the predetermined direction side or the opposite side. .

According to this invention, the determination method is executed by a welding robot system that includes a welding robot that welds steel materials while moving the steel materials in a predetermined direction. The determination method is to determine whether the predetermined direction side sensor attached to the predetermined direction side of the welding robot and the opposite side sensor attached to the opposite side of the welding robot from the predetermined direction side are on the predetermined direction side or the opposite side. It has a step of determining whether it is attached. With this configuration, the welding robot system can determine whether the predetermined direction side sensor and the opposite side sensor are attached to the predetermined direction side or the opposite side, so it is possible to determine whether the camera is installed correctly or incorrectly. Can be judged.

According to the embodiment of the present invention, it is possible to determine whether the position of the sensor attached to the welding robot is correct or incorrect.

1 is a diagram showing an example of a welding robot system according to an embodiment of the present invention. FIG. 1 is a diagram showing an example of a welding robot system according to the present embodiment. It is a figure showing an example of operation of the welding robot system concerning this embodiment. It is a figure showing an example of operation of the welding robot system concerning this embodiment. It is a figure showing an example of operation of the welding robot system concerning this embodiment. It is a figure showing an example of operation of the welding robot system concerning this embodiment. It is a figure showing an example of operation of the welding robot system concerning this embodiment. It is a flowchart which shows an example of operation of the welding robot system concerning this embodiment. It is a flowchart which shows an example of operation of the welding robot system concerning this embodiment. It is a flowchart which shows an example of operation of the welding robot system concerning this embodiment. It is a flowchart which shows an example of operation of the welding robot system concerning this embodiment.

Next, the welding robot system and determination method of this embodiment will be explained with reference to the drawings. The embodiments described below are merely examples, and the embodiments to which the present invention is applied are not limited to the following embodiments.
In addition, in all the figures for explaining the embodiment, parts having the same functions are denoted by the same reference numerals, and repeated explanations will be omitted.
Furthermore, "based on XX" as used herein means "based on at least XX", and includes cases where it is based on another element in addition to XX. Moreover, "based on XX" is not limited to the case where XX is used directly, but also includes the case where it is based on calculations or processing performed on XX. "XX" is an arbitrary element (for example, arbitrary information).

(Embodiment)
(welding robot system)
FIG. 1 is a diagram showing an example of a welding robot system according to an embodiment of the present invention.
A welding robot system 1 according to the present embodiment automatically welds a welding object 2 using a welding robot 10. An example of the welding object 2 is steel.
The welding robot system 1 includes a welding robot 10 and a control device 9.
A groove-shaped groove 3 is formed in the welding object 2 at a pair of edges to be welded. A traveling rail 11 is installed along the groove 3 on the welding object 2, and the welding robot 10 is movable along the traveling rail 11.
In the welding robot 10, the direction intersecting the surface of the welding object 2 is the Z-axis, the extending direction of the groove 3 and the running rail 11 is the Y-axis, and the direction crossing the groove 3 (perpendicular to the Z-axis and the Y-axis, respectively) is the Y-axis. direction) is defined as the X-axis.
The welding robot 10 has a saddle 12 that moves along a traveling rail 11, and a rectangular box-shaped case 13 is supported on the saddle 12.
A moving mechanism (not shown) is installed inside the case 13, and the case 13 moves in a direction toward and away from the running rail 11 (Z-axis direction) and in a direction across the groove 3 (X-axis direction). It is possible.

A bracket 14 is installed on the side of the case 13 facing the groove 3, a holder 15 is supported at the tip of the bracket 14, and a welding torch 16 is held in the holder 15. A welding wire 161 is supported at the tip of the welding torch 16.
The holder 15 is rotatable to the bracket 14 and can be fixed at any angular position around the rotation axis S, and the aiming angle At of the welding torch 16 can be adjusted by adjusting the angle of the holder 15.
A control device 9 is connected to the welding robot 10.

The welding robot 10 is equipped with a lighting device 21, a camera 22-1, and a camera 22-2. Camera 22-1 and camera 22-2 are removable from welding robot 10. An arbitrary camera among the camera 22-1 and the camera 22-2 will be referred to as a camera 22.
An example of the illumination device 21 is a line laser irradiation device, which irradiates the measurement site 31 of the groove 3 with a laser beam that spreads in the transverse direction of the groove 3 (X-axis direction). With this configuration, the measurement site 31 can be continuously illuminated linearly in the transverse direction of the groove 3, so the cross-sectional shape 32 can be made to stand out brighter than the surrounding area.
A pair of cameras 22-1 and 22-2 are installed on both sides of the welding torch 16, and each captures an image of a measurement site 31 including a cross-sectional shape 32 illuminated linearly by an illumination device 21, and converts the images into image data. It is transmitted to the control device 9.

An example of the pair of cameras 22 each includes a solid-state imaging device such as a CCD (Charge Coupled Device), and is connected to a support installed on the side surface of the case 13 via a support panel 221 and a support arm 222. It is supported by rails 223.
Each camera 22 can adjust its orientation with respect to the support panel 221, and can also move in the X-axis direction along the support rail 223. By adjusting the position, orientation, and inclination of each camera 22, imaging The field of view, that is, the imaging area 220 on the welding object 2 including the measurement site 31 can be freely adjusted.

The welding robot system 1 includes a panel 23 supported by the welding robot 10.
The shape of the panel 23 is a rectangle such as a rectangle, and a two-dimensional gauge 230 is drawn on the surface of the panel 23 by a plurality of lines 232 and 233 arranged orthogonally.
Panel 23 may be a calibration plate. The calibration plate is used to perform calibration to associate the coordinate systems of cameras 22-1 and 22-2 with the coordinate system of welding robot 10. The coordinate system of the welding robot 10 is a coordinate system for expressing the position of the welding robot 10.
The calibration plate is used to calibrate each of the cameras 22-1 and 22-2. The calibration plate is also used to measure the cross-sectional shape of the groove 3. The calibration plate is also used to determine the tilt of the robot coordinate system with respect to the world coordinate system.
Information on the shape of the gauge 230, specifically, information on the base end position, number, length, and tip position of the plurality of lines 232 and 233 arranged orthogonally on the panel 23 is stored in advance in the control device 9. .
The panel 23 is supported by the bracket 14 via an arm 231, and is arranged so that at least the lower half thereof enters the groove 3, so that the surface of the panel 23 intersects the continuous direction of the groove 3.
The arm 231 is rotatably connected to the bracket 14, and the panel 23 can be retracted from the state of entering the groove 3 to outside the field of view of the camera 22. In order to retract the panel 23 out of the field of view of the camera 22, the arm 231 and the panel 23 may be removable from the bracket 14.
In such a welding robot system 1, prior to automatic welding work on the welding object 2, it is determined whether the camera position is correct or not, and sensing is performed on the groove 3.

FIG. 2 is a diagram showing an example of a welding robot system according to this embodiment. As shown in FIG. 2, the welding robot system 1 includes a control device 9, a traveling rail 11, a saddle 12, a welding torch 16, a lighting device 21, a camera 22-1, and a camera 22-2. .
The control device 9 includes a welding operation control section 91, a saddle movement control section 92, an input section 93, a processing section 94, a storage section 95, a camera control section 96, a determination section 97, and a notification section 98. Be prepared.
The control device 9 is configured by combining an existing computer system with a dedicated driver, and by executing a program stored in the storage section 95, determines whether the camera position is correct or incorrect, measures the groove shape, and performs the following operations on the running rail 11. It controls the operations of each part of the welding robot 10, such as running the saddle 12 and case 13 along the welding robot 10, adjusting the attitude of the welding torch 16, adjusting the voltage and current supplied to the welding torch 16, and adjusting the feed rate of the welding wire.
The control device 9 measures the overall shape of the groove 3 of the welding object 2 by measuring the cross-sectional shape 32 at a plurality of measurement sites 31, and adjusts the overall shape of the groove 3 to the obtained groove shape. The welding robot 10 is controlled based on this.

Welding operation control section 91 controls welding torch 16 . For example, the welding operation control unit 91 adjusts the attitude of the welding torch 16, adjusts the voltage and current supplied to the welding torch 16, adjusts the feed rate of the welding wire, and the like.
Saddle movement control section 92 controls saddle 12 . For example, the saddle movement control unit 92 controls the movement of the saddle 12 along the running rail 11.
The input unit 93 inputs information. As an example, the input unit 93 may include an operation unit such as a keyboard and a mouse. In this case, the input section 93 inputs information according to the operation performed on the operation section by the user. As another example, the input unit 93 may input information from an external device. The external device may be, for example, a portable storage medium.
The user inputs information corresponding to the positions at which the cameras 22-1 and 22-2 are attached to the input unit 93. An example of information corresponding to the positions where the cameras 22-1 and 22-2 are installed is the IP address of the cameras 22-1 and 22-2, etc. This is the identification information used when
Hereinafter, a case will be continued in which the IP addresses of the cameras 22-1 and 22-2 are applied as an example of information corresponding to the positions where the cameras 22-1 and 22-2 are installed.

For example, camera 22-1 and camera 22-2 are attached to welding robot 10 on a predetermined direction side and on a side opposite to the predetermined direction side. An example of the predetermined direction is the left side (minus side of the Y axis), and an example of the opposite side is the right side (plus side of the Y axis). Hereinafter, as an example, a case will be continued in which the predetermined direction side is the left side, the opposite side is the right side, the camera 22-1 is attached to the left side, and the camera 22-2 is attached to the right side.
A display section (not shown) displays a column for inputting an IP address corresponding to the left camera 22-1 and a column for inputting an IP address corresponding to the right camera 22-2. The user inputs into the input section 93 the IP address corresponding to the left camera 22-1 and the IP address corresponding to the right camera 22-2.

The processing unit 94 obtains the IP address corresponding to the left camera 22-1 and the IP address corresponding to the right camera 22-2 from the input unit 93. The processing unit 94 causes the storage unit 95 to store the obtained IP address corresponding to the left camera 22-1 and the IP address corresponding to the right camera 22-2.
Camera control section 96 controls camera 22-1 and camera 22-2. The camera control unit 96 is connected to the camera 22-1 and the camera 22-2, and obtains identification information from the camera 22-1 and the camera 22-2. An example of the identification information is an identification number unique to the camera 22, such as a MAC address (Media Access Control address). Hereinafter, a case will be continued in which a MAC address is used as an example of the identification information of the camera 22-1 and the camera 22-2.
The camera control unit 96 stores the MAC address acquired from the camera 22-1 in the storage unit 95 in association with the IP address of the camera 22-1. The camera control unit 96 stores the MAC address acquired from the camera 22-2 in the storage unit 95 in association with the IP address of the camera 22-2.

Welding robot 10 is installed on object 2 to be welded. The measurement site 31 of the groove 3 is linearly illuminated in the transverse direction by the illumination device 21 . The camera control unit 96 adjusts the imaging areas of the cameras 22-1 and 22-2 to face the groove 3. The camera 22-1 and the camera 22-2 take images of the groove 3.
The processing unit 94 acquires image data from each of the cameras 22-1 and 22-2, and processes the acquired image data. The processing unit 94 prepares a calibration function that makes the image data from the cameras 22-1 and 22-2 correspond to the world coordinate system, based on images obtained by processing the image data.
The processing unit 94 corrects distortion of the lens of the camera 22. The camera control unit 96 controls the cameras 22-1 and 22-2 to take images of a subject. An example of the subject is the panel 23 installed between the camera 22-1 and the camera 22-2 in the Y-axis direction. The camera control unit 96 controls each of the cameras 22-1 and 22-2 to place the gauge 230 drawn on the panel 23 in the imaging area and to take an image of the gauge 230.
The orientations of the cameras 22-1 and 22-2 are adjusted with respect to the reference point of the gauge 230 (for example, one of the base points where the plurality of lines 232 and lines 233 arranged orthogonally intersect), and the camera 22 -1 and camera 22-2 are fixed so that their respective optical axes are directed toward a reference point.

The respective positions of the cameras 22-1 and 22-2 supported by the welding robot 10 are normally located away from the groove 3, and from the front of the panel 23 (the Y-axis direction that is the continuous direction of the groove 3). As seen, the cameras 22-1 and 22-2 are each disposed at a displacement Dx in the X-axis direction and a displacement Dz in the Z-axis direction. Further, each of the cameras 22-1 and 22-2 has a tilt, and the tilt angle of each of the cameras 22-1 and 22-2 around the optical axis is R.
Each of the cameras 22-1 and 22-2 images the gauge 230 depicted on the panel 23. The processing unit 94 acquires image data from each of the cameras 22-1 and 22-2, and processes the acquired image data.
The processing unit 94 sets a world coordinate system to the images captured by the cameras 22-1 and 22-2, respectively, based on the image of the gauge 230 obtained by processing the image data. For example, the processing unit 94 sets the world coordinate system by determining coordinates in the world coordinate system based on coordinates on the image determined from the captured image of the gauge 230. The processing unit 94 converts the image coordinate system to the camera coordinate system based on characteristics (internal parameters) unique to the cameras 22-1 and 22-2, such as image distortion and focal length. The processing unit 94 converts the camera coordinate system to the world coordinate system based on external parameters.
In the captured image, since each of the cameras 22-1 and 22-2 is at a deviated position due to the displacement Dx in the X-axis direction, the displacement Dz in the Z-axis direction, and the tilt angle R, the gauge drawn on the panel 23 The shape of 230 (for example, the lengths and angles of the orthogonally arranged lines 232 and 233) appears deformed with respect to the original shape.

The processing unit 94 refers to the gauge 230 (for example, the lengths and angles of a plurality of lines 232 and 233 arranged orthogonally arranged) stored in the storage unit 95, and generates a gauge obtained by processing the image data. By performing a comparison calculation with the gauge 230 appearing in the image 230, the displacement Dx, the displacement Dz, and the tilt angle R of the camera 22-1 and the camera 22-2 are calculated.
The processing unit 94 performs arithmetic processing such as homography conversion on the calculation results of the displacement Dx, displacement Dz, and tilt angle R of the camera 22-1 and the camera 22-2, so that the camera 22- Information for calibrating the cross-sectional shape of the groove 3 as viewed from the front, that is, from the continuous direction of the groove 3, is acquired as an external parameter for each of the groove 1 and the camera 22-2.
The processing unit 94 causes the storage unit 95 to store the acquired external parameters of the camera 22-1 and the camera 22-2 in association with the respective IP addresses of the camera 22-1 and the camera 22-2. With this configuration, a camera coordinate system corresponding to the world coordinate system can be set on the image of the subject captured by each of the cameras 22-1 and 22-2. Note that the internal parameters of the cameras 22-1 and 22-2 are stored in the storage unit 95 in association with their respective MAC addresses.

The camera control unit 96 controls each of the cameras 22-1 and 22-2 to take images of a subject. An example of the subject is the panel 23 installed between the camera 22-1 and the camera 22-2 in the Y-axis direction. The camera 22-1 and the camera 22-2 take images of a subject.
FIG. 3 is a diagram showing an example of the operation of the welding robot system according to this embodiment. In FIG. 3, the left figure is an example of an image showing how the subject (panel 23) is imaged by the camera 22-1, and the right figure is an example of an image showing how the subject is imaged by the camera 22-2. be.
Here, the IP address of camera 22-1 is 192.168. ＊＊＊． **1, and the MAC address is LL:LL:LL:LL:LL:LL. The IP address of camera 22-2 is 192.168. ＊＊＊． **2, and the MAC address is RR:RR:RR:RR:RR:RR.
The determination unit 97 acquires image data from each of the cameras 22-1 and 22-2, and processes the acquired image data. The determining unit 97 determines whether each of the cameras 22-1 and 22-2 is attached to the left or right side of the welding robot 10, based on the image obtained by processing the image data. .

FIG. 4 is a diagram showing an example of the operation of the welding robot system according to this embodiment. In FIG. 4, the left figure is an example of an image before distortion correction (hereinafter referred to as "left side subject image") of the subject (panel 23) imaged by the camera 22-1, and the right figure is an example of the image captured by the camera 22-2. This is an example of an image (hereinafter referred to as "right-side subject image") before distortion correction of the subject (panel 23).
As shown in FIG. 4, the object (panel 23) has a rectangular shape.
According to FIG. 4, an example of the image of the subject (panel 23) captured by the camera 22-1 shows that the subject is located within a predetermined range in the imaging range of the camera 22-1, and the subject is captured by the camera 22-2. It can be seen from the example of the image (panel 23) that the subject is located within a predetermined range in the imaging range of the camera 22-2.
The determination unit 97 determines the coordinates in the image coordinate system of at least two vertices of the subject (panel 23) included in the left subject image and the image coordinate system of at least two vertices of the subject (panel 23) included in the right subject image. Get the coordinates at. For example, the determination unit 97 acquires the coordinates of opposing vertices of the subject (panel 23) included in the left subject image in the image coordinate system, and obtains the image of the opposing vertices of the subject (panel 23) included in the right subject image. Get the coordinates in the coordinate system.

FIG. 5 is a diagram showing an example of the operation of the welding robot system according to this embodiment. In FIG. 5, the left diagram is an example of a left subject image after distortion correction, and the right diagram is an example of a right subject image after distortion correction. As shown by the broken line, the angles (θL, θR) formed by the long sides of the subject and the long sides of the imaging ranges of the cameras 22-1 and 22-2 remain unchanged at least at the timing of imaging.
The determination unit 97 acquires the coordinates of opposing vertices of the two-dimensional gauge in the camera coordinate system from the subject (panel 23) included in each of the left subject image and the right subject image. For example, the determination unit 97 converts the image coordinate system to the camera coordinate system based on characteristics (internal parameters) unique to the cameras 22-1 and 22-2, such as image distortion and focal length.
The determination unit 97 obtains the coordinates of the origin (VL1) in the camera coordinate system of the two-dimensional gauge and the coordinates of the vertex (VL2) facing the origin (VL1) from the subject (panel 23) in the left subject image. . The determination unit 97 acquires the coordinates of the origin (VR1) in the camera coordinate system of the two-dimensional gauge and the coordinates of the vertex (VR2) facing the origin (VR1) from the subject (panel 23) in the right subject image.
The determination unit 97 converts the coordinates in the camera coordinate system of the opposing vertices of the two-dimensional gauge acquired from each of the left-side subject image and the right-side subject image into coordinates in the world coordinate system. For example, in the left subject image, the determination unit 97 converts the coordinates of the origin (VL1) in the camera coordinate system to coordinates (XiL(0), YiL(0)) in the world coordinate system based on external parameters. , converts the coordinates of the vertex (VL2) facing the origin in the camera coordinate system to coordinates (XiL(max), YiLR(max)) in the world coordinate system.
In the right subject image, the determination unit 97 converts the coordinates of the origin (VR1) in the camera coordinate system to coordinates (XiR(0), YiR(0)) in the world coordinate system based on the external parameters, and The coordinates of the vertex (VR2) facing the origin in the coordinate system are converted to coordinates (XiR(max), YiR(max)) in the world coordinate system.

The determination unit 97 calculates the result of converting the coordinates of the origin (VR1) in the camera coordinate system into the coordinates in the world coordinate system and the coordinates of the vertex (VL2) opposite the origin in the camera coordinate system in the left subject image. Based on the results of the conversion into coordinates in the world coordinate system, it is determined whether the camera 22-1 attached to the left side and the camera 22-2 attached to the right side are correct.
Specifically, the determination unit 97 determines that the X coordinate (XiL(max)) of the vertex (VL2) in the world coordinate system is greater than the X coordinate (XiL(0)) of the origin (VL1) in the world coordinate system. It is a large value, and the X coordinate (XiR (max)) of the vertex (VR2) in the world coordinate system is a smaller value than the X coordinate (XiR (0)) of the origin (VR1) in the world coordinate system. In this case, it is determined that the camera 22-1 and the camera 22-2 are correctly installed.
The determination unit 97 determines that the X coordinate (XiL(max)) of the vertex (VL2) in the world coordinate system is less than or equal to the X coordinate (XiL(0)) of the origin (VL1) in the world coordinate system, or If the X coordinate (XiR(max)) of the vertex (VR2) in the world coordinate system is greater than or equal to the X coordinate (XiR(0)) of the origin (VR1) in the world coordinate system, the camera 22- 1 and camera 22-2 are determined to be incorrectly installed.

The determination unit 97 determines that the X coordinate (XiL(max)) of the vertex (VL2) in the world coordinate system is less than or equal to the X coordinate (XiL(0)) of the origin (VL1) in the world coordinate system, and If the X coordinate (XiR(max)) of the vertex (VR2) in the world coordinate system is greater than or equal to the X coordinate (XiR(0)) of the origin (VR1) in the world coordinate system, the camera 22- 1 and camera 22-2 are determined to be incorrectly installed. Returning to FIG. 2, the explanation will be continued.
If the determination unit 97 determines that each of the cameras 22-1 and 22-2 is not installed correctly, it notifies the notification unit 98.
When notified by the determining unit 97, the notification unit 98 notifies the user that each of the cameras 22-1 and 22-2 is not installed at the correct position. With this configuration, the positions corresponding to the respective IP addresses of the camera 22-1 and the camera 22-2 input to the input unit 93 and the positions of the camera 22-1 and the camera 22-2 determined by the determination unit 97 can be It is possible to inform the user that the positions where each of the two parts are attached are different from each other.
The processing unit 94 sets the camera coordinate system in the images captured by the cameras 22-1 and 22-2, respectively, based on the image of the gauge 230 obtained by processing the image data.

By rotating the arm 231, the panel 23 is retracted out of the field of view of each of the cameras 22-1 and 22-2. The processing unit 94 calibrates the origin of the camera coordinate system. For example, a welding wire is brought out from the tip of the welding torch 16 of the welding robot 10.
In FIG. 1, an arbitrary position of the cross-sectional shape 32 (for example, the bending point of the groove 3 used as a preset calibration point) is selected as the torch aiming position, and the welding robot 10 is moved in the X-axis direction and the Z-axis direction. to bring the tip of the welding wire 161 extending from the welding torch 16 into contact with the torch's target position. This associates the origin of the world coordinate system with the origin of the robot coordinate system.

The camera control unit 96 controls each of the cameras 22-1 and 22-2 to take images of the welding wire including the tip of the welding wire. Each of the cameras 22-1 and 22-2 images the welding wire including the tip of the welding wire. The processing unit 94 acquires image data from each of the cameras 22-1 and 22-2, and processes the acquired image data.
The state is such that no welding wire comes out from the tip of the welding torch 16 of the welding robot 10. Camera control unit 96 controls each of camera 22-1 and camera 22-2 to take an image of the tip of welding torch 16. Each of the cameras 22-1 and 22-2 images the tip of the welding torch 16. The processing unit 94 acquires image data from each of the cameras 22-1 and 22-2, and processes the acquired image data.

The processing unit 94 acquires an image of the wire including the wire tip based on an image of the wire including the wire tip obtained by processing the image data and an image of the tip of the welding torch 16. The processing unit 94 acquires the coordinates of the welding wire tip (torch aiming position) in the robot coordinate system based on the obtained image of the wire including the wire tip.
The processing unit 94 sets the obtained coordinates of the tip of the wire in the robot coordinate system to the origin of the world coordinate system. Since the welding wire tip (torch aiming position) is detected as the current position in the robot coordinate system, the origin position in the world coordinate system can be converted to the robot coordinate system.

The saddle movement control unit 92 moves the welding robot 10 near the measurement site 31 of the groove 3. The processing unit 94 causes the illumination device 21 to linearly illuminate the measurement site 31 in the transverse direction. The processing unit 94 determines sensing points from the measurement site 31 of the groove 3. The camera control unit 96 controls each of the cameras 22-1 and 22-2 to take images of sensing points included in the measurement site 31 of the groove 3.
Each of the cameras 22-1 and 22-2 images sensing points included in the measurement site 31 of the groove 3. The processing unit 94 acquires image data from each of the cameras 22-1 and 22-2, and processes the acquired image data.
The processing unit 94 uses prepared data prepared in advance to determine the characteristics of the welding object 2 that sandwich the sensing point from an image of the sensing point included in the measurement site 31 of the groove 3 obtained by processing the image data. Based on this, it is possible to calculate the area with the left camera 22-1, whether the area can be calculated with the right camera 22-2, or whether the area can be calculated with both the left camera 22-1 and the right camera 22-2. Determine whether calculation is possible. Note that the process of step S3-1, which will be described later, is executed in an area where the processing unit 94 determines that area calculation is possible using both the left camera 22-1 and the right camera 22-2.

FIG. 6 is a diagram showing an example of the operation of the welding robot system according to this embodiment. In FIG. 6, sensing points (1) to (5) are shown at the intermediate point of the erection jig in the welding object 2.
The processing unit 94 acquires the position information of the erection jig, and based on the acquired position information of the erection jig, the left camera 22-1 at each of the sensing points (1) to (5). It is determined whether the area can be calculated, whether the area can be calculated by the right camera 22-2, or whether the area can be calculated by both the left camera 22-1 and the right camera 22-2. Here, the processing unit 94 may acquire the position information of the erection jig by sensing means, or may acquire the position information of the erection jig by inputting it from the user.
Since the sensing point (1) can be imaged by the right camera 22-2, the processing unit 94 determines that the area can be calculated by the right camera 22-2. Since sensing points (2) to (4) can be imaged by both the left camera 22-1 and the right camera 22-2, the processing unit 94 uses the left camera 22-1 and the right camera 22-2 to capture images of the sensing points (2) to (4). It is determined that the area can be calculated in both cases. Since the sensing point (5) can be imaged by the left camera 22-1, the processing unit 94 determines that the area can be calculated by the left camera 22-1.
FIG. 7 is a diagram showing an example of the operation of the welding robot system according to this embodiment. In FIG. 7, the left diagram is an example of an image captured by the left camera 22-1 at the sensing point (5). It can be seen that since the sensing point (5) can be imaged by the left camera 22-1, the area can be calculated by the left camera 22-1.
The upper right diagram is an example of an image captured by the right camera 22-2 at the sensing point (1). Since the sensing point (1) can be imaged by the right camera 22-2, it can be seen that the area can be calculated by the right camera 22-2. The lower right figure is an image obtained by inverting the left and right sides of the upper right figure. Returning to FIG. 2, the explanation will be continued.

The camera control unit 96 controls one or both of the left camera 22-1 and the right camera 22-2, which have been determined to be capable of area calculation, to image sensing points. The processing unit 94 acquires image data from each of the cameras 22-1 and 22-2, and processes the acquired image data. The processing unit 94 detects the cross-sectional shape of the groove 3 obtained by processing the acquired image data.
For example, the processing unit 94 performs inversion processing on one of the images of the measurement site 31 of the groove 3 obtained by processing the image data obtained from each of the cameras 22-1 and 22-2. The processing unit 94 calculates the length, angle, Edge detection processing is performed by calculating plate thickness, etc.
The processing unit 94 derives the shape of the groove 3 and a reference point in the robot coordinate system based on the edge detection result of the cross-sectional shape of the groove 3. The processing unit 94 determines the information specifying the shape of the groove 3 and the value of the reference point when there is no error in the derived information specifying the shape of the groove 3 and the value of the reference point. The processing unit 94 causes the storage unit 95 to store the determined shape of the groove 3 and the reference point in the robot coordinate system.
This is repeated multiple times over the entire length or a partial section of the groove 3 while changing the sensing points included in the measurement site 31 of the groove 3. With this configuration, the cross-sectional shape 32 along the continuous direction of the groove 3 can be obtained (sensing).
The welding operation control section 91, the saddle movement control section 92, the processing section 94, the camera control section 96, and the determination section 97 are configured by a computer program (for example, a hardware processor such as a CPU (Central Processing Unit) stored in the storage section 95). software).
Some or all of these functional units may be implemented using LSI (Large Scale Integration), ASIC (Application Specific Integrated Circuit), FPGA (Field-Programmable Gate Array), G Hardware (circuits) such as PU (Graphics Processing Unit) (including circuitry), or may be realized by cooperation between software and hardware.

(Operation of welding robot system)
8 to 11 are flowcharts showing an example of the operation of the welding robot system according to this embodiment. Here, a case will be described in which a calibration plate is used as an example of the panel 23.
(Step S1-1)
In the control device 9, the user inputs into the input unit 93 the IP addresses corresponding to the positions where the cameras 22-1 and 22-2 are installed. The processing unit 94 obtains the IP address corresponding to the left camera 22-1 and the IP address corresponding to the right camera 22-2 from the input unit 93. The processing unit 94 causes the storage unit 95 to store the obtained IP address corresponding to the left camera 22-1 and the IP address corresponding to the right camera 22-2.
(Step S2-1)
In the control device 9, a camera control section 96 controls each of the cameras 22-1 and 22-2. The camera control unit 96 connects to each of the cameras 22-1 and 22-2, and obtains MAC addresses from each of the cameras 22-1 and 22-2.
The camera control unit 96 stores the MAC address acquired from the camera 22-1 in the storage unit 95 in association with the IP address of the camera 22-1. The camera control unit 96 stores the MAC address acquired from the camera 22-2 in the storage unit 95 in association with the IP address of the camera 22-2.

(Step S3-1)
In the control device 9, the camera control unit 96 causes each of the cameras 22-1 and 22-2 to place the gauge 230 drawn on the calibration plate (panel 23) in the imaging area and to image the gauge 230. Take control.
Adjust the orientation of each of the cameras 22-1 and 22-2 with respect to the reference point of the gauge 230, and fix the respective optical axes of the cameras 22-1 and 22-2 toward the reference point. .
Each of the cameras 22-1 and 22-2 images the gauge 230 drawn on the calibration plate (panel 23).
(Step S4-1)
In the control device 9, the processing unit 94 acquires image data from each of the cameras 22-1 and 22-2, and processes the acquired image data. The processing unit 94 calculates characteristics (internal parameters) unique to the cameras 22-1 and 22-2, such as image distortion and focal length, by processing the image data.
The processing unit 94 acquires image data from each of the cameras 22-1 and 22-2, and processes the acquired image data. The processing unit 94 applies distortion to the image of the gauge 230 obtained by processing the image data, based on characteristics (internal parameters) unique to the cameras 22-1 and 22-2, such as image distortion and focal length. Make corrections.
The processing unit 94 sets a world coordinate system to the images captured by the cameras 22-1 and 22-2, respectively, based on the image of the gauge 230 obtained by processing the image data.
The processing unit 94 refers to the gauge 230 stored in the storage unit 95, and performs a comparison calculation between the gauge 230 obtained by processing the image data and the gauge 230 that appears in the image, so that the camera 22-1 The displacement Dx, the displacement Dz, and the tilt angle R are calculated for each of the cameras 22-2 and 22-2.
The processing unit 94 performs arithmetic processing such as homography conversion on the obtained displacement Dx, displacement Dz, and tilt angle R of the camera 22-1 and the camera 22-2, so that the camera 22-1 and the camera 22 Information for calibrating the cross-sectional shape of the groove 3 as viewed from the front, that is, from the continuous direction of the groove, is obtained as each external parameter of −2. Homography transformation refers to "transformation between two images (of the same thing)". In other words, homography transform creates an undistorted image from a distorted image using internal parameters. Calculating internal parameters may also be expressed as using homography transformation. The content of the homography transformation is matrix calculation, and if a virtual screen is assumed in the world coordinate system, the homography transformation may be performed in step S6-1, which will be described later.

(Step S5-1)
In the control device 9, the processing unit 94 stores the internal parameters of the camera 22-1 and the camera 22-2 in the storage unit 95 in association with the MAC address of the camera 22-1 and the MAC address of the camera 22-2. let
(Step S6-1)
In the control device 9, a camera control unit 96 controls each of the cameras 22-1 and 22-2 to take images of the calibration plate (panel 23). Each of the cameras 22-1 and 22-2 images the calibration plate (panel 23).
(Step S7-1)
In the control device 9, the determination unit 97 acquires image data from each of the cameras 22-1 and 22-2, and processes the acquired image data. The determining unit 97 determines whether each of the cameras 22-1 and 22-2 is attached to the left or right side of the welding robot 10, based on the image obtained by processing the image data. .
If the determining unit 97 determines that each of the cameras 22-1 and 22-2 is not correctly attached, it notifies the notifying unit 98. When notified by the determination unit 97, the notification unit 98 notifies the user that the camera 22-1 and the camera 22-2 are not installed correctly. Here, we will continue to explain the case where the determining unit 97 determines that each of the cameras 22-1 and 22-2 is correctly attached.

(Step S8-1)
In the control device 9, the processing unit 94 sets the world coordinate system in the images captured by each of the cameras 22-1 and 22-2, based on the image of the gauge 230 obtained by processing the image data. . The description will be continued with reference to FIG.
(Step S1-2)
By rotating the arm 231, the calibration plate (panel 23) is retracted out of the field of view of each of the cameras 22-1 and 22-2.
In the control device 9, the processing unit 94 calibrates the origin of the camera coordinate system. For example, a welding wire is brought out from the tip of the welding torch 16 of the welding robot 10. An arbitrary position of the cross-sectional shape 32 (for example, the bending point of the groove 3 used as a preset calibration point) is selected as the torch aiming position, and the welding robot 10 is moved in the X-axis direction and the Z-axis direction, The tip of a welding wire 161 extending from the welding torch 16 is brought into contact with the torch's target position.
The camera control unit 96 controls each of the cameras 22-1 and 22-2 to take images of the welding wire including the tip of the welding wire. Each of the cameras 22-1 and 22-2 images the welding wire including the tip of the welding wire. The processing unit 94 acquires image data from each of the cameras 22-1 and 22-2, and processes the acquired image data.

(Step S2-2)
The state is such that no welding wire comes out from the tip of the welding torch 16 of the welding robot 10.
In the control device 9, a camera control unit 96 controls each of the cameras 22-1 and 22-2 to take an image of the tip of the welding torch 16. Each of the cameras 22-1 and 22-2 images the tip of the welding torch 16. The processing unit 94 acquires image data from each of the cameras 22-1 and 22-2, and processes the acquired image data.
(Step S3-2)
In the control device 9, the processing unit 94 acquires an image of the wire including the wire tip based on an image of the wire including the wire tip obtained by processing the image data and an image of the tip of the welding torch 16. The processing unit 94 acquires the coordinates of the welding wire tip (torch aiming position) in the robot coordinate system based on the obtained image of the wire including the wire tip.
(Step S4-2)
In the control device 9, the processing unit 94 sets the acquired coordinates of the tip of the wire in the robot coordinate system to the origin of the world coordinate system. The description will be continued with reference to FIG.

(Step S1-3)
The saddle movement control unit 92 moves the welding robot 10 to the measurement site 31 of the groove 3.
In the control device 9, the processing unit 94 causes the illumination device 21 to linearly illuminate the measurement site 31 in the transverse direction. The processing unit 94 determines sensing points.
(Step S2-3)
In the control device 9, the processing unit 94 determines whether the left camera 22-1 can calculate the area or the right camera 22-2 can calculate the area based on the characteristics of the welding target sandwiching the determined sensing point. Or, it is determined whether the area can be calculated using both the left camera 22-1 and the right camera 22-2.
(Step S3-3)
In the control device 9, the camera control unit 96 controls one or both of the left camera 22-1 and the right camera 22-2, which have been determined to be capable of area calculation, to image sensing points. .
The camera control unit 96 controls each of the cameras 22-1 and 22-2 to image the measurement site 31 of the groove 3 by accessing the IP address stored in the storage unit 95. Each of the cameras 22-1 and 22-2 images the measurement site 31 of the groove 3.

(Step S4-3)
In the control device 9, the processing unit 94 acquires image data from each of the cameras 22-1 and 22-2, and processes the acquired image data. The processing unit 94 performs inversion processing on one of the images of the measurement site 31 of the groove 3 obtained by processing the image data obtained from each of the cameras 22-1 and 22-2.
(Step S5-3)
In the control device 9, the processing unit 94 determines the measurement area of the groove 3 based on the image of the measurement area 31 of the groove 3 that has undergone the reversal process and the image of the measurement area 31 of the groove 3 that has not undergone the reversal process. Edge detection processing is performed by calculating length, angle, plate thickness, etc. The description will be continued with reference to FIG.

(Step S1-4)
In the control device 9, the processing unit 94 determines whether only the sensing point on the right side is within the use area (the area can be calculated).
(Step S2-4)
In the control device 9, when it is determined that only the sensing point on the right side is within the use area (the area can be calculated), the processing unit 94 uses the sensing point on the right side to calculate the shape of the groove 3 and the robot coordinates. A reference point in the system is derived, and information specifying the derived shape of the groove 3 and the value of the reference point are output.
(Step S3-4)
In the control device 9, when it is determined that only the sensing point on the right side is not within the usage area (area calculation is possible), the processing unit 94 determines that only the sensing point on the left side is in the usage area based on the result of the edge detection process. (area calculation is possible).

(Step S4-4)
In the control device 9, when it is determined that only the left sensing point is within the use area (the area can be calculated), the processing unit 94 uses the left sensing point to determine the shape of the groove 3 and the robot coordinates. A reference point in the system is derived, and information specifying the derived shape of the groove 3 and the value of the reference point are output.
(Step S5-4)
In the control device 9, when it is determined that only the sensing point on the right side is not within the use area (the area can be calculated), the processing unit 94 determines whether or not to perform averaging processing of the setting parameters.
(Step S6-4)
In the control device 9, when it is determined that the setting parameter averaging process is to be performed, the processing unit 94 uses the right sensing point to derive the shape of the groove 3 and the reference point in the robot coordinate system, and also uses the left sensing point to derive the shape of the groove 3 and the reference point in the robot coordinate system. The shape of the groove 3 and the reference point in the robot coordinate system are derived using the sensing points.
The processing unit 94 averages the shape of the groove 3 derived using the sensing point on the right side and the shape of the groove 3 derived using the sensing point on the left side. The processing unit 94 averages the reference point in the robot coordinate system derived using the right sensing point and the reference point in the robot coordinate system derived using the left sensing point.
The processing unit 94 uses the result of averaging the shape of the groove 3 derived using the sensing point on the right side and the shape of the groove 3 derived using the sensing point on the left side, and the sensing point on the right side. The result of averaging the reference point in the robot coordinate system derived using the left sensing point and the reference point in the robot coordinate system derived using the left sensing point is output.

(Step S7-4)
In the control device 9, the processing unit 94 sets the setting parameters to be checked every time when it is determined that the setting parameters are not averaged.
(Step S8-4)
In the control device 9, the processing unit 94 determines whether there is an error in the value output in any of steps S2-4, S4-4, and S6-4.
(Step S9-4)
In the control device 9, the processing unit 94 determines that there is an error in the output value in any of steps S2-4, S4-4, and S6-4, or if the setting parameters are checked each time in step S7-4. In this case, a processing screen is displayed on a display unit (not shown).
On the processing screen, the user can select the shape of the groove 3 derived using the sensing points on the right side and the reference point in the robot coordinate system, and the shape of the groove 3 derived using the sensing points on the left side and the reference point in the robot coordinate system. You can select either the reference point at On the processing screen, the user can modify the data.
(Step S10-4)
In the control device 9, when it is determined in step S8-4 that there is no error value, the processing unit 94 determines the shape of the groove 3 and the reference point in the robot coordinate system. The processing unit 94 causes the storage unit 95 to store the determined shape of the groove 3 and the reference point in the robot coordinate system.
In step S3-1 of FIG. 8, a case has been described in which each of the cameras 22-1 and 22-2 images the gauge 230 drawn on the calibration plate (panel 23), but this is not limited to this example. do not have. For example, an off-line image of the calibration plate (panel 23) may be obtained in advance.
In FIG. 8, steps S3-1 to S5-1 may be omitted after calculating and storing the internal parameters.

In the embodiment described above, a case has been described in which the camera 22-1 and the camera 22-2 are each attached to the welding robot 10, but the present invention is not limited to this example. For example, a sensor capable of acquiring luminance information may be attached together with each of the cameras 22-1 and 22-2, or instead of the cameras 22-1 and 22-2.
In the embodiment described above, steps S1-2 to S4-2 in FIG. 9 and steps S1-3 to S5-3 in FIG. 10 may be executed sequentially or in parallel. , may be executed individually.
In the embodiment described above, a case has been described in which the two-dimensional gauge 230 is drawn on the surface of the panel 23 by a plurality of lines 232 and 233 arranged orthogonally, but the present invention is not limited to this example.
For example, two arrows arranged orthogonally may be drawn on the surface of the panel 23, or two arrows may be drawn on the surface of the panel 23, or two arrows may be drawn on the surface of the panel 23. A figure whose orientation and inclination can be detected may be drawn, or an arrangement pattern of a plurality of points having different shapes may be drawn. The gauge 230 is not limited to one drawn on the panel 23 by printing or the like, but may be one that emits light.

In the embodiment described above, the determining unit 97 determines the coordinates of the origin (VL1) in the camera coordinate system of the two-dimensional gauge from the subject (panel 23) and the vertex (VL2) opposite to the origin (VL1) in the left subject image. In the right subject image, obtain the coordinates of the origin (VR1) in the camera coordinate system of the two-dimensional gauge from the subject (panel 23) and the coordinates of the vertex (VR2) facing the origin (VR1). Although the case has been described, the present invention is not limited to this example.
For example, the determination unit 97 obtains coordinates other than the origin (VL1) in the camera coordinate system of the two-dimensional gauge from the subject (panel 23) and coordinates of a vertex opposite to the origin (VL1) in the left subject image. , in the right subject image, the coordinates other than the origin (VR1) in the camera coordinate system of the two-dimensional gauge and the coordinates of the vertex (VR2) facing other than the origin (VR1) may be obtained from the subject (panel 23). .
In the embodiment described above, the panel 23 on which the gauge 230 is displayed is retractable by the movable arm 231, but the present invention is not limited to this example. For example, the panel 23 may be detachably attached to the welding robot 10.
In the embodiment described above, a case has been described in which a line laser illumination device is used as the illumination device 21, but the present invention is not limited to this example.
For example, the illumination device 21 is not limited to a laser beam, and may be any other light source, as long as it can illuminate the groove 3 in a transverse direction in a continuous line or at multiple points lined up in a line, resulting in a cross-sectional shape 32. It is sufficient if images can be imported all at once.

The welding robot system 1 according to this embodiment includes the welding robot 10 that welds steel materials while moving the steel materials in a predetermined direction. The welding robot system 1 includes a sensor attached to the welding robot 10 and a predetermined direction side sensor attached to the welding robot 10 in a predetermined direction; It includes an opposite side sensor attached to the opposite side, and a determination unit 97 that determines whether each of the predetermined direction side sensor and the opposite side sensor is attached to the predetermined direction side or the opposite side.
With this configuration, the welding robot system 1 includes the determination unit 97 that determines whether each of the predetermined direction side sensor and the opposite side sensor is attached to the predetermined direction side or the opposite side. It is possible to determine whether the installation position is correct or incorrect.

In the welding robot system 1, the sensor includes a camera 22, and the welding robot system 1 has a sensor on a predetermined direction and a sensor on the opposite side. It further includes a control section as a camera control section 96 that controls imaging. The determination unit 97 determines whether the predetermined direction sensor and the opposite sensor are attached to the predetermined direction side or the opposite side, using the images output by the predetermined direction sensor and the opposite sensor. Determine.
With this configuration, the determining unit 97 determines whether each of the predetermined direction side sensor and the opposite side sensor is on the predetermined direction side using the image outputted by the predetermined direction side sensor and the opposite side sensor. Since it is possible to determine whether the camera 22 is attached to the opposite side, it is possible to determine whether the attachment position of the camera 22 is correct or incorrect.

In the welding robot system 1, the subject is located within a predetermined range of the respective imaging ranges of the sensor on the predetermined direction and the sensor on the opposite side.
With this configuration, the determination unit 97 uses images output by the predetermined direction side sensor and the opposite side sensor of a subject located within a predetermined range in their respective imaging ranges. Since it can be determined whether each of the sensor and the opposite side sensor is attached to the predetermined direction side or the opposite side, it is possible to determine whether the attachment position of the camera 22 is correct or incorrect.

In the welding robot system 1, the shape of the subject is rectangular. With this configuration, the determination unit 97 uses the images output by the predetermined direction sensor and the opposite sensor to capture and output images of a rectangular subject, so that the predetermined direction sensor and the opposite sensor each detect a predetermined value. Since it can be determined whether the camera 22 is attached to the direction side or the opposite side, it is possible to determine whether the attachment position of the camera 22 is correct or incorrect.
In the welding robot system 1, the object has a rectangular shape, and the angles formed by the long sides of the object and the long sides of the respective imaging ranges of the sensor on the predetermined direction and the sensor on the opposite side remain unchanged.
With this configuration, the determination unit 97 uses the image outputted by the predetermined direction sensor and the opposite sensor to capture and output a rectangular subject, and allows the predetermined direction sensor and the opposite sensor to each output a predetermined image. Since it can be determined whether the camera 22 is attached to the direction side or the opposite side, it is possible to determine whether the attachment position of the camera 22 is correct or incorrect.

In the welding robot system 1, the determining unit 97 uses the coordinates of at least two vertices of the object included in the image to determine whether the predetermined direction side sensor and the opposite side sensor are attached to the predetermined direction side or the opposite side. Determine whether the
With this configuration, the determination unit 97 uses the coordinates of at least two vertices of the subject included in the image to determine whether the predetermined direction sensor and the opposite sensor are attached to the predetermined direction side or the opposite side. Since it can be determined whether the camera 22 is installed correctly or incorrectly, it is possible to determine whether the mounting position of the camera 22 is correct or incorrect.

In the welding robot system 1, the subject is calibration for associating the coordinate systems of the sensor on the predetermined direction and the opposite side with the coordinate system of the welding robot, the calibration between the sensor on the predetermined direction and the sensor on the opposite side. This is a calibration plate used for the
With this configuration, the determination unit 97 uses images output by the predetermined direction side sensor and the opposite side sensor to image the calibration plate, so that each of the predetermined direction side sensor and the opposite side sensor can move in the predetermined direction. Since it is possible to determine whether the camera 22 is attached to the side or the opposite side, it is possible to determine whether the attachment position of the camera 22 is correct or incorrect.

In the welding robot system, the calibration plate is also used to measure the cross-sectional shape of the groove.
With this configuration, the determination unit 97 uses the image outputted by the sensor on the predetermined direction and the sensor on the opposite side to take an image of the calibration plate which is also used to measure the cross-sectional shape of the groove. Since it can be determined whether the side sensor and the opposite side sensor are attached to the predetermined direction side or the opposite side, it is possible to determine whether the mounting position of the camera 22 is correct or incorrect.

In a welding robot system, the calibration plate is also used to determine the inclination of the robot's coordinate system with respect to the world coordinate system.
With this configuration, the determination unit 97 outputs an image obtained by capturing and outputting the calibration plate, which is also used for determining the inclination of the robot's coordinate system with respect to the world coordinate system, by the sensor on the predetermined direction and the sensor on the opposite side. Since it can be determined whether the predetermined direction side sensor and the opposite side sensor are attached to the predetermined direction side or the opposite side using , it is possible to determine whether the mounting position of the camera 22 is correct or incorrect.

In the welding robot system, the image is an image output by a sensor on a predetermined direction and a sensor on the opposite side capturing and outputting a subject for calibration. With this configuration, the determination unit 97 uses the images outputted by the predetermined direction sensor and the opposite sensor for calibration, respectively. Since it can be determined whether the camera is attached to the predetermined direction side or the opposite side, it is possible to determine whether the camera is attached to the correct or incorrect position.

In the welding robot system 1, an image is output by each of the sensor on the predetermined direction and the sensor on the opposite side capturing and outputting an image of a subject in order to correct the distortion of the image captured by the sensor on the predetermined direction and the sensor on the opposite side, respectively. This is an image.
With this configuration, the determination unit 97 determines whether the predetermined direction sensor and the opposite sensor each image a subject in order to correct the distortion of the image captured by the predetermined direction sensor and the opposite sensor. Since it is possible to determine whether the predetermined direction side sensor and the opposite side sensor are attached to the predetermined direction side or the opposite side using the output images, it is possible to determine whether the mounting position of the camera is correct or incorrect.

In the welding robot system 1, there is an input unit 93 that allows a user to input information corresponding to a position where a predetermined direction side sensor and an opposite side sensor are attached, a position to which the information input by the input unit 93 corresponds, and a determination. A notification section 98 is provided to notify the user when the positions where the predetermined direction side sensor and the opposite side sensor are attached, which is determined by the section 97, are different.
With this configuration, the welding robot system 1 allows the welding robot 10 to move the steel material in a predetermined direction based on information corresponding to the positions where the predetermined direction side sensor and the opposite side sensor are attached. Can be welded. Welding robot system 1 can notify the user if the mounting position of camera 22 is incorrect.

Although the embodiments have been described above, these embodiments are presented as examples and are not intended to limit the scope of the invention. These embodiments can be implemented in various other forms, and various omissions, substitutions, changes, and combinations can be made without departing from the gist of the invention. These embodiments are included within the scope and gist of the invention, and at the same time are included within the scope of the invention described in the claims and its equivalents.
Note that the above-described control device 9 may be realized by a computer. In that case, a program for realizing the functions of each functional block is recorded on a computer-readable recording medium. The program recorded on this recording medium may be read into a computer system and executed by a CPU. The "computer system" herein includes hardware such as an OS (Operating System) and peripheral devices.
Furthermore, the term "computer-readable recording medium" refers to portable media such as flexible disks, magneto-optical disks, ROMs, and CD-ROMs. Furthermore, a "computer-readable recording medium" includes a storage device such as a hard disk built into a computer system.

Furthermore, a "computer-readable recording medium" may include one that dynamically stores a program for a short period of time. An example of a device that dynamically stores a program for a short period of time is a communication line used to transmit a program via a network such as the Internet or a communication line such as a telephone line.
Further, the "computer-readable recording medium" may also include a medium that retains a program for a certain period of time, such as a volatile memory inside a computer system that is a server or a client. Further, the above program may be for realizing some of the functions described above. Moreover, the above program may be one that can realize the above-described functions in combination with a program already recorded in the computer system. Moreover, the above program may be realized using a programmable logic device. The programmable logic device is, for example, an FPGA.

Note that the above-mentioned control device 9 has a computer inside. Each process of the control device 9 described above is stored in a computer-readable recording medium in the form of a program, and the above-mentioned processes are performed by the computer reading and executing this program.
Here, the computer-readable recording medium refers to a magnetic disk, a magneto-optical disk, a CD-ROM, a DVD-ROM, a semiconductor memory, and the like. Alternatively, this computer program may be distributed to a computer via a communication line, and the computer receiving the distribution may execute the program.
Moreover, the above-mentioned program may be for realizing a part of the above-mentioned functions.
Furthermore, it may be a so-called difference file (difference program) that can realize the above-described functions in combination with a program already recorded in the computer system.

1 Welding robot system 10 Welding robot 11 Traveling rail 12 Saddle 13 Case 14 Bracket 15 Holder 16 Welding torch 161 Welding wire 2 Welding object 21 Lighting device 22, 22-1, 22-2 Camera 220 Imaging area 221 Support panel 222 Support arm 223 Support rail 23 Panel 230 Gauge 231 Arm 232, 233 Line 3 Bevel 31 Measurement site 32 Cross-sectional shape 9 Control device 91 Welding operation control section 92 Saddle movement control section 93 Input section 94 Processing section 95 Storage section 96 Camera control section 97 Judgment Section 98 Notification Section

Claims (13)

A welding robot system comprising a welding robot that welds steel materials while moving the steel materials in a predetermined direction,
a sensor attached to the welding robot, a predetermined direction side sensor attached to the predetermined direction side of the welding robot;
a sensor attached to the welding robot, an opposite side sensor attached to a side opposite to the predetermined direction side of the welding robot;
a determination unit that determines whether each of the predetermined direction side sensor and the opposite side sensor is attached to the predetermined direction side or the opposite side;
A welding robot system equipped with The sensor includes a camera;
The welding robot system further includes a control unit that controls the predetermined direction side sensor and the opposite side sensor to image a subject installed between the predetermined direction side sensor and the opposite side sensor,
The determination unit is configured to determine whether the predetermined direction side sensor and the opposite side sensor are on the predetermined direction side and the opposite side using images outputted by the predetermined direction side sensor and the opposite side sensor. The welding robot system according to claim 1, wherein the welding robot system determines where it is attached. The welding robot system according to claim 2, wherein the subject is located within a predetermined range of imaging ranges of the predetermined direction side sensor and the opposite side sensor. The welding robot system according to claim 3, wherein the object has a rectangular shape. The shape of the subject is a rectangle,
An angle formed by a long side of the subject and a long side of each imaging range of the sensor on the predetermined direction and the sensor on the opposite side is unchanged;
The welding robot system according to claim 4. The determination unit uses coordinates of at least two vertices of the subject included in the image, and determines whether the predetermined direction side sensor and the opposite side sensor are attached to either the predetermined direction side or the opposite side. The welding robot system according to claim 5, wherein the welding robot system determines whether the The subject is calibration for associating the coordinate systems of the predetermined direction side sensor and the opposite side sensor with the coordinate system of the welding robot, and the subject is calibration for associating the coordinate systems of the predetermined direction side sensor and the opposite side sensor with the coordinate system of the welding robot, and the calibration of the predetermined direction side sensor and the opposite side sensor. The welding robot system according to claim 6, which is a calibration plate used. The welding robot system according to claim 7, wherein the calibration plate is also used to measure the cross-sectional shape of the groove. The welding robot system according to claim 8, wherein the calibration plate is also used to determine the inclination of the robot's coordinate system with respect to the world coordinate system. 10. The welding robot system according to claim 9, wherein the image is an image output by the predetermined direction side sensor and the opposite side sensor capturing and outputting images of the subject for the calibration. The image is an image output by each of the predetermined direction side sensor and the opposite side sensor capturing and outputting an image of the subject in order to correct distortion of the image captured by each of the predetermined direction side sensor and the opposite side sensor. The welding robot system according to claim 9. an input unit that allows a user to input information corresponding to a position where the predetermined direction side sensor and the opposite side sensor are attached;
Notifying the user when a position corresponding to the information input by the input unit is different from a position where the predetermined direction side sensor and the opposite side sensor are installed, which is determined by the determination unit. A notification section to
The welding robot system according to any one of claims 1 to 11, comprising: A determination method performed by a welding robot system including a welding robot that welds steel materials while moving the steel materials in a predetermined direction, the method comprising:
A predetermined direction side sensor attached to the predetermined direction side of the welding robot and an opposite side sensor attached to the opposite side of the welding robot to the predetermined direction side are each attached to either the predetermined direction side or the opposite side. A determination method comprising the step of determining whether or not the vehicle is attached to the vehicle.

Images