JP5251440B2 - Work posture recognition method, work posture recognition device, and robot - Google Patents

Description

  The present invention relates to a workpiece posture recognition method and a workpiece posture recognition device in a robot that performs work on a workpiece supplied in a random posture.

  In various production sites, robots are frequently used to appeal for speeding up and efficiency of work. When supplying a work, which is a work object, to a robot, it is common to align or supply the work. However, in recent years, in order to improve production efficiency, workpiece alignment and positioning processes can be omitted, workpieces can be supplied in a random posture, and the robot can recognize the position and posture of the workpiece and perform work on necessary parts. It has been demanded.

  As a method for recognizing the position and orientation of a workpiece, for example, a method is known in which the contour of a target object (work) is regarded as a contour function and contour matching is performed with a contour function database. In this method, a target object (work) given three-dimensional numerical data is regarded as a plurality of postures by a camera, and a contour function is calculated from contour points of the target object (work) to create a contour function database. Then, a target object (work) in real space is imaged with a camera, and a contour function is extracted from the camera image. For the correlation between the extracted contour function and the contour function stored in the database, a correlation coefficient is calculated using Fourier transform, and a method for estimating the position and orientation of the target object from the result has been proposed (for example, , See Patent Document 1).

JP 2004-326314 A

  However, in the above method, when obtaining a contour function from the camera image of the target object, or when obtaining a correlation between the obtained contour function and the contour function database, the amount of data is increased or complicated calculation processing is performed. There is a problem that a lot of calculation time is required.

  SUMMARY An advantage of some aspects of the invention is to solve at least a part of the problems described above, and the invention can be implemented as the following forms or application examples.

  (Application example 1) A workpiece posture recognition method for recognizing the posture of the workpiece in a robot that performs a work on a workpiece supplied in a random posture, the workpiece having a plurality of outer surfaces, and each outer surface The robot has a directionality and is provided with different types of marks, and the robot captures images of at least the marks of the workpiece and images of the plurality of types of marks by the imaging units. Master image storage means for storing a master image in advance, an image input step for capturing a mark image captured by the imaging means, and the captured mark image and the master image stored in the master image storage means An image comparison step of comparing an image and detecting a degree of coincidence or difference between the mark image and the master image, and the image comparison step Work posture recognition method characterized in that the comparison results obtained; and a posture determination step of determining posture of the workpiece.

  (Application Example 2) In the image comparison step, the mark image and the master image are sequentially compared, the master image that matches the mark image at the maximum is detected, and the type of the mark is recognized. A difference in direction or angle between the mark image and the master image is detected, and in the posture determination step, the surface of the workpiece facing the imaging unit is recognized from the type of the mark, and the direction or angle of the mark image is determined. The work posture recognition method described above, wherein the direction and angle from the posture of the workpiece when the master image is acquired are recognized from the difference.

  According to these methods, different types of marks are given to the work for each outer surface. Therefore, by comparing the mark image picked up by the image pickup means with the master image and recognizing the type of the mark, it is easy to determine which side of the workpiece faces the direction in which the image pickup means is provided. be able to. That is, the direction of the workpiece can be determined. Further, by comparing the degree of coincidence or difference with the front master image, it is possible to determine which direction the mark having directionality indicates or how much it is inclined. As a result, it is possible to easily determine the direction, direction, inclination, and angle of the workpiece provided with the mark. Accordingly, the amount of data can be reduced, and the posture of the workpiece can be recognized in a short time without performing complicated arithmetic processing.

  (Application Example 3) The work posture recognition method described above, wherein the mark is formed in an asymmetric shape.

  According to this method, the mark is directional and has an asymmetric shape. Therefore, when the mark image and the master image are compared, the degree of coincidence or the difference can be easily recognized. Further, it is possible to easily determine the direction of the mark, the vertical / horizontal relationship, the inclination, and the like.

  (Application example 4) The work posture recognition method described above, wherein the mark is provided in a different color for each outer surface of the work.

  According to this method, by identifying the color of the mark, it is possible to easily determine which surface faces in the direction in which the imaging unit is provided. Therefore, the shape of the mark given to one work can be made the same. As a result, the type (data amount) of the master image can be reduced, and the time for comparing the mark image and the master image in the image comparison process can be reduced.

  (Application example 5) The work posture recognition method described above, wherein the mark can be detected by ultraviolet rays or infrared rays.

  According to this method, the mark can be identified by a multi-CCD camera or the like and is not visible to human eyes. Therefore, it is possible to prevent the appearance characteristics of the finished product from being reduced.

  (Application example 6) A workpiece posture recognition device for recognizing the posture of the workpiece in a robot that performs work on a workpiece supplied in a random posture, the workpiece having a plurality of outer surfaces, and each outer surface A mark having a direction and a different type of mark is provided, and an imaging unit that images the mark of the workpiece and a master image captured by the imaging unit for a plurality of types of the mark are stored in advance. A master image storage unit, an image input unit that captures a mark image captured by the imaging unit, the captured mark image and the master image stored in the master image storage unit are compared, and the mark image An image comparison unit that detects a degree of coincidence or difference with the master image, and a posture of the workpiece is determined from a comparison result obtained by the image comparison unit. Work posture recognition apparatus characterized by comprising: a posture determination processing unit.

  (Application Example 7) In the image comparison unit, the mark image and the master image are sequentially compared to detect the master image that matches the mark image at the maximum to recognize the type of the mark, and A difference in direction or angle between the mark image and the master image is detected, and the posture determination processing unit recognizes the surface of the workpiece facing the imaging unit from the type of the mark, and the direction or angle of the mark image The workpiece posture recognition apparatus according to claim 1, wherein a direction and an angle from the posture of the workpiece when the master image is acquired are recognized.

  According to these apparatuses, different types of marks are given to the work for each outer surface. Therefore, by comparing the mark image picked up by the image pickup means with the master image and recognizing the type of the mark, it is easy to determine which side of the workpiece faces the direction in which the image pickup means is provided. be able to. That is, the direction of the workpiece can be determined. Further, by comparing the degree of coincidence or difference with the front master image, it is possible to determine which direction the mark having directionality indicates or how much it is inclined. As a result, it is possible to easily determine the direction, direction, inclination, and angle of the workpiece provided with the mark. Accordingly, the amount of data can be reduced, and the posture of the workpiece can be recognized in a short time without performing complicated arithmetic processing.

  (Application example 8) The workpiece posture recognition apparatus, wherein the mark is formed in an asymmetric shape.

  According to this apparatus, the mark is directional and has an asymmetric shape. Therefore, when the mark image and the master image are compared, the degree of coincidence or the difference can be easily recognized. Further, it is possible to easily determine the direction of the mark, the vertical / horizontal relationship, the inclination, and the like.

  (Application example 9) The workpiece posture recognition apparatus, wherein the mark is provided in a different color for each outer surface of the workpiece.

  According to this apparatus, by identifying the color of the mark, it is possible to easily determine which surface faces in the direction in which the imaging unit is provided. Therefore, the shape of the mark given to one work can be made the same. As a result, the type (data amount) of the master image can be reduced, and the time for comparing the mark image with the master image in the image comparison unit can be reduced.

  (Application example 10) The workpiece posture recognition apparatus described above, wherein the mark can be detected by ultraviolet rays or infrared rays.

  According to this apparatus, the mark can be identified by a 2CCD camera or the like and is not visible to human eyes. Therefore, it is possible to prevent the appearance characteristics of the finished product from being reduced.

(About work posture recognition device)
A workpiece posture recognition apparatus to which the workpiece posture recognition method of the present invention is applied will be described with reference to FIG. FIG. 1 is a diagram illustrating a configuration example of a workpiece posture recognition apparatus.

  As shown in FIG. 1, the workpiece posture recognition device 1 includes a stage 5, a robot 10, and a control unit 20 that controls the robot 10. The stage 5 holds a work W that is a work target to which a mark to be described later is given. The workpiece W is conveyed by a belt conveyor (not shown), carried into the stage 5, and after the work by the robot 10 is carried out, it is carried out to the next stage 5 or the next process. At this time, the workpiece W is carried in a random posture. That is, the work W alignment process and positioning process are not provided in order to improve production efficiency and simplify equipment.

  The robot 10 includes a camera 12 as an imaging unit, a robot hand 14, robot arms 16 and 17, and a joint portion 18. The robot 10 is a so-called articulated robot, and the robot arms 16 and 17 are movable with the joint portion 18 as a fulcrum. Then, work is performed on the workpiece W by the robot hand 14. The camera 12 functions as an eye of the robot 10, and recognizes the position, posture, work site, and the like of the workpiece W.

  The control unit 20 includes at least an image processing device 30, a storage device 40, and a computer 50. The image processing device 30 includes at least an image input unit 32, an image comparison processing unit 34, and a camera position control unit 36. The storage device 40 includes at least a master image storage unit 42 and a recognition result storage unit 44. The computer 50 functions as a central processing unit, and controls the robot 10, the image processing device 30, the storage device 40, and the like as a whole. The operation of the control unit 20 will be described later.

(About the mark)
Next, marks to be given to the workpiece will be described with reference to FIGS. FIG. 2 is a diagram illustrating an example of a workpiece to which a mark is given, and FIG. 3 is a diagram illustrating the mark.

  As shown in FIG. 2, the workpiece W in the present embodiment is, for example, a hexahedron in which rectangular surfaces face each other in parallel, that is, a brick shape, and part of four side surfaces are at different angles from the top surface side. It is formed in the shape cut off diagonally. That is, this work W has directionality in the vertical direction, the front-rear direction, and the horizontal direction. Hereinafter, with respect to the surface F of the workpiece W, a front view of the surface F3 is a front view, the top surface is F1, the bottom surface is F2, the front surface is F3, the rear surface is F4, the right surface is F5, and the left surface is F6. Called.

  A mark C is given to each surface F of the workpiece W. In this embodiment, the marks C are printed on each surface F in a small manner. However, in the drawings, the mark C is enlarged and emphasized for easy understanding. As shown in FIG. 3, the mark C has a deformed arrow shape, for example. That is, in the arrow A, the part corresponding to the arrow of the arrow is formed only on one side of the arrow bamboo. That is, the arrow A as the mark C is formed asymmetrically. In this case, the up and down directions in FIG. 3 are represented by the direction of the arrow a of the arrow A, and the left and right directions in FIG.

  The workpiece W shown in FIG. 2 can be discriminated slightly from the top F1, bottom F2, front F3, rear F4, right F5, and left F6 based on the arrow A1 shown in FIG. Arrow A is given. The arrow A is identified by, for example, the number of arrow feathers b that are given. That is, arrow A1 has one arrow blade b, arrow A2 has two arrow blades b, arrow A3 has three arrow blades b, arrow A4 has four arrow blades b, and arrow A5 has five arrow blades b. The arrow A6 is provided with six arrow feathers b and is identified. In the present embodiment, the arrow A1 is on the top surface F1 of the workpiece W, the arrow A2 is on the bottom surface F2, the arrow A3 is on the front surface F3, the arrow A4 is on the rear surface F4, the arrow A5 is on the right surface F5, and the left surface. An arrow A6 is given to F6.

  At this time, on the top surface F1 and the bottom surface F2, the front surface F3, the rear surface F4, the right surface F5, and the left surface F6 are arranged with the arrow a of the arrow A so that the direction of the arrow a of the arrow A is from the left surface F6 to the right surface F5. It is given so that the direction is from the bottom surface F2 to the top surface F1. The top surface F1 and the bottom surface F2 have an arrow A arrow b in the rear surface F4 direction, and the front surface F3 and the rear surface F4 have an arrow A arrow blade b in the left surface F6 direction. The left surface F6 is provided so as to be in the direction of the front surface F3. That is, by knowing the type of arrow A given to the surface F, the direction of the arrow a, and the direction of the arrow blade b, the type, direction, and direction of the surface F can be known.

(About the master image)
Here, the master image stored in the master image storage unit will be described with reference to FIG. FIG. 4 is a diagram illustrating an example of a master image.
Using the camera 12 shown in FIG. 1, a master image is prepared in advance when each mark C given to the workpiece W is observed from the front. For example, using the camera 12 of the robot 10 of the workpiece posture recognition apparatus 1 shown in FIG. 1, the mark C given to each surface of the workpiece W is imaged from the front so that the arrow a of the arrow A points upward. The master image. Specifically, the position of the camera 12 is controlled by the camera position control unit 36 of the image processing apparatus 30 of the control unit 20, and the camera 12 is positioned in front of each surface of the workpiece W placed on the stage 5 to capture each image. To do.

  As a result, a master image M as shown in FIG. 4 is obtained. The master image M1 is an image of the arrow A1 on the top surface F1, the master image M2 is an image of the arrow A2 on the bottom surface F2, and the master image M3 is an image of the arrow A3 on the front surface F3. Similarly, the master image M4 is an image obtained by capturing an arrow A4 on the rear surface F4, the master image M5 is an image captured by the arrow A5 on the right surface F5, and the master image M6 is an image obtained by capturing the arrow A6 on the left surface F6. In this case, the master images M1, M3, M5 and the master images M2, M4, M6 are different from each other in the direction of the arrow blade b of the arrow A in FIG. In any master image M, the arrow a points upward. The master image M is stored in the master image storage unit 42 of the storage device 40 of the control unit 20 shown in FIG.

(About work posture recognition method)
(First embodiment)
Next, the workpiece posture recognition method of the present invention will be described with reference to FIGS. FIG. 5 is a flowchart showing a flow of the workpiece posture recognition method, FIG. 6 is a diagram for explaining the workpiece posture recognition method, and FIG. 7 is a diagram showing an example of a mark image. FIG. 8 is a diagram illustrating a comparison process between a mark image and a master image. Note that the X axis, the Y axis, and the Z axis shown in FIG. That is, in the movement control of the robot hand 14 of the robot 10, it is a coordinate axis serving as a basis for coordinates indicating positions such as a movement start point and a movement end point. In the present embodiment, the robot 10 is set at a position facing the XZ plane and facing the Y direction.

  In this work posture recognition method, in order to improve production efficiency and simplify equipment, the posture of the work W carried in a random posture on a production line or the like not provided with the work W alignment process or positioning process is described above. The workpiece posture recognition device 1 is used for recognition. As shown in FIG. 5, the workpiece posture recognition method includes a workpiece carry-in step S1, a mark imaging step S2, a mark image input step S3, an image comparison step S4, and a posture determination step S5.

  In the workpiece carrying-in process in step S1, the workpiece W to which the above-mentioned mark C is given is conveyed by a belt conveyor (not shown) or the like and carried into the stage 5 in the workpiece posture recognition apparatus 1 shown in FIG. At this time, the workpiece W is carried in a random posture. Therefore, for example, as shown in FIG. 6 (a), the loaded work W overlaps with and interferes with which surface F faces in which direction, or other work W (not shown). I don't know how many angles are arranged with respect to the X, Y, and Z axes. Therefore, the process proceeds to step S2 shown in FIG.

  In the mark imaging process of step S2 shown in FIG. 5, the mark C given to the carried workpiece W is imaged using the camera 12 shown in FIG. First, the camera 12 of the robot 10 shown in FIG. 1 is directly opposed to the XY plane in FIG. 6A by the camera position control unit 36 of the image processing apparatus 30, and the mark C of the workpiece W is viewed from the Z (+) direction. Image. In this case, since the mark Ca is given in the Z (+) direction, the mark Ca is photographed to obtain the mark image P1 shown in FIG. Next, the camera 12 faces the XZ plane in FIG. 6A and images the mark C of the workpiece W from the Y (−) direction. In this case, since the mark Cb is given in the Y (−) direction, the mark Cb is photographed to obtain a mark image P3 shown in FIG. Next, the camera 12 faces the YZ plane in FIG. 6A and images the mark C of the workpiece W from the X (+) direction. In this case, since the mark Cc is given in the X (+) direction, the mark Cc is photographed to obtain a mark image P5 shown in FIG. That is, the mark C which opposes from the X-axis direction, the Y-axis direction, and the Z-axis direction as the absolute coordinate axes in FIG.

  In the mark image input process of step S3, the mark images P1, P3, and P5 captured by the camera 12 are taken into the image input unit 32 of the image processing device 30 of the control unit 20 shown in FIG.

  Then, in the image comparison step in step S4 and the posture determination step in step S5, a comparison process and posture determination between the captured mark image P and the master image M stored in the master image storage unit 42 are performed. This comparison process and posture determination are performed by the command and control of the computer 50 in the image comparison processing unit 34 of the control unit 20 shown in FIG.

  First, in the image comparison process in step S4, the verification is performed on the mark image P1 obtained in step S2. As shown in FIG. 8A, when the mark Ca in the mark image P1 is observed, the mark Ca is an arrow Aa, and the arrow Aa has one arrow blade b. Therefore, it can be seen that the arrow Aa is the arrow A1 given to the top surface F1 of the workpiece W. Therefore, the master image M1 obtained by capturing the arrow A1 stored in the master image storage unit 42 is taken into the image comparison processing unit 34, and the mark image P1 and the master image M1 are compared. Then, it can be seen that the direction of the arrow aa in the direction of the arrow a is the range of the X (+) direction in the same figure, but the inclination is different by α degrees compared to the arrow A1 of the master image M1. Also, it can be seen that the arrow blade b of the arrow Aa is oriented in the Y (+) direction.

  Next, the mark image P3 is compared and verified. As shown in FIG. 8B, when the mark Cb in the mark image P3 is observed, the mark Cb is an arrow Ab, and the arrow Ab has three arrow blades b. Therefore, it can be seen that the arrow Ab is an arrow A3 given to the front surface F3 of the workpiece W. Therefore, the master image M3 obtained by capturing the arrow A3 stored in the master image storage unit 42 is taken into the image comparison processing unit 34, and the mark image P3 and the master image M3 are compared. Then, it can be seen that the direction of the arrow Ab of the arrow Ab is the same as the Z (+) direction in the figure, and the inclination and the like are the same. Also, it can be seen that the arrow blade b of the arrow Ab is directed in the X (−) direction.

  Next, the mark image P5 is compared and verified. As shown in FIG. 8C, when the mark Cc in the mark image P5 is observed, the mark Cc is an arrow Ac, and the arrow Ac has five arrow blades b. Therefore, it can be seen that the arrow Ac is an arrow A5 given to the right surface F5 of the workpiece W. Therefore, the master image M5 obtained by capturing the arrow A5 stored in the master image storage unit 42 is taken into the image comparison processing unit 34, and the mark image P5 and the master image M5 are compared. Then, it can be seen that the direction of the arrow Ac in the direction of the arrow Ac is substantially the same Z (+) range, but the inclination is different by β degrees compared to the arrow A5 of the master image M5. Further, it can be seen that the arrow blade b of the arrow Ac is oriented in the Y (−) direction.

  In the posture determination process of step S5, as shown in FIG. 6B, the mark Ca is given as a result of the comparison verification result between the mark image P and the master image M obtained in the image comparison process of step S4. It can be determined that the surface F is the top surface F1, the surface F to which the mark Cb is attached is the front surface F3, and the surface F to which the mark Cc is attached is the right surface F5. This can be determined by using any combination of the type of arrow A, the direction of arrow a, and the direction of arrow blade b, or all of them. Also, the arrow A1 (Aa) on the top surface F1 is inclined by α degrees with respect to the X axis, the arrow A3 (Ab) on the front surface F3 is not inclined with respect to the Z axis, and the arrow A5 (Ac on the right surface F5) ) Is inclined by β degrees with respect to the Z axis, the inclination of the workpiece W with respect to the X axis (Y axis) and the Z axis can be known.

  That is, as shown in FIG. 6C, the workpiece W is arranged with the top surface F1 in the Z (+) direction, the front surface F3 in the Y (−) direction, and the right surface F5 in the X (+) direction. Yes. Further, it can be seen that the workpiece W is inclined by α degrees with respect to the X axis in the XY plane and is inclined by β degrees from the Z axis in the YZ plane. The verification result is stored in the recognition result storage unit 44 of the storage device 40 of the control unit 20 shown in FIG. 1 and becomes a basic instruction command for the work of the robot 10 on the workpiece W.

  Next, the process proceeds to step S6, in which it is determined whether there is a workpiece W whose posture is to be determined next. Next, when there is a workpiece W for which the posture is determined (YES), the process proceeds to the above-described workpiece carry-in process of step S1, and the above-described operation is repeated. Next, when there is no workpiece W for determining the posture (NO), this posture recognition work is ended.

The effects of this example will be described below.
(1) According to the workpiece posture recognition method using the above-described workpiece posture recognition apparatus, the workpiece W is provided with an asymmetric arrow A that can indicate directionality as a mark C that can be identified for each surface F. Has been. Then, for the workpiece W supplied in a random posture, the arrow A is captured by the camera 12 to obtain a mark image P, and the mark image P is compared with a master image M of the arrow A prepared in advance. can do.

  Therefore, which surface F of the workpiece W is directed to which direction depending on the type of the arrow A, which direction the workpiece W is directed to according to the direction indicated by the arrow a of the arrow A, the arrow A of the mark image P and the master image M It can be determined in what direction and how much the workpiece W is tilted by the difference in tilt from the arrow A. That is, the posture of the workpiece W can be recognized by a simple operation of comparing the mark image P and the master image M. As a result, the posture of the workpiece W can be recognized with a small amount of data without performing complicated arithmetic processing using CAD / CAM data, contour functions, or the like. Accordingly, it is possible to shorten the calculation time for posture recognition of the workpiece W, and to contribute to the efficiency of posture recognition work.

(Second embodiment)
Here, the workpiece posture recognition method of the second embodiment will be described. The second embodiment is an example in which the state of the mark applied to each surface of the workpiece W is different from the first embodiment. Further, the same configurations and contents as those of the first embodiment are denoted by the same reference numerals and description thereof is omitted.

(About the mark)
The marks in the second embodiment will be described with reference to FIG. FIG. 9 is a diagram for explaining the workpiece and the mark in the second embodiment.
As shown in FIG. 9, the workpiece W in the second embodiment has the same shape as the workpiece W of the first embodiment. A mark D is given to each surface F of the workpiece W. The mark D has an arrow shape modified in the same manner as in the first embodiment. In the arrow E of the mark D, the part corresponding to the arrow feathers is formed only on one side of the arrow bamboo. That is, the arrow E as the mark D is formed asymmetrically.

  The workpiece W shown in FIG. 9 can be identified by being colored in different colors based on the arrow A1 shown in FIG. 3 with respect to the top surface F1, the bottom surface F2, the front surface F3, the rear surface F4, the right surface F5, and the left surface F6. The arrow E is given. For example, the arrow E1 is colored red, the arrow E2 is blue, the arrow E3 is green, the arrow E4 is yellow, the arrow E5 is black, and the arrow E6 is white. In this embodiment, the arrow E1 is on the top surface F1 of the workpiece W, the arrow E2 is on the bottom surface F2, the arrow E3 is on the front surface F3, the arrow E4 is on the rear surface F4, the arrow E5 is on the right surface F5, and the left surface. An arrow E6 is given to F6.

  At this time, on the top surface F1 and the bottom surface F2, the front surface F3, the rear surface F4, the right surface F5, and the left surface F6 have the arrow a of the arrow E directed from the left surface F6 to the right surface F5. It is given so that the direction is from the bottom surface F2 to the top surface F1. The top surface F1, the bottom surface F2, the right surface F5, so that the arrow blade b of the arrow E is in the rear surface F4 direction, and the front surface F3, the rear surface F4, the arrow blade b of the arrow E is in the left surface F6 direction, The left surface F6 is provided so as to be in the direction of the front surface F3. That is, by knowing the type of arrow E given to the surface F, that is, the colored color, the direction of the arrow a, and the direction of the arrow blade b, the type, direction, and direction of the surface F can be known.

  Thereafter, the posture of the workpiece W to which the mark D is given is recognized by applying the acquisition of the master image M and the workpiece posture recognition method described in the first embodiment. That is, the second embodiment is that the arrows E1 to 6 as the mark D are not identified by the difference in the number of the arrow blades b but by the difference in the colored colors.

The effects of the second embodiment will be described below.
(1) According to the workpiece posture recognition method described above, the workpiece W is provided with an asymmetrical and different-colored arrow E that can indicate the direction as the mark D that can be identified for each surface F. Therefore, by identifying the color of the arrow E, it is possible to easily determine which surface F of the workpiece W is directed in which direction. Therefore, the shape of the mark D given to one work can be made the same, and the type (data amount) of the master image M can be reduced. Therefore, the posture of the workpiece W can be recognized in a shorter time.

(Third embodiment)
Here, the workpiece posture recognition method of the third embodiment will be described. The third embodiment is an example in which the state of the mark applied to each surface of the workpiece W is different from the first and second embodiments. Further, the same configurations and contents as those of the first and second embodiments are denoted by the same reference numerals and description thereof is omitted.

  The workpiece W in the third embodiment has the same shape as the workpiece W in the first and second embodiments. A mark G is given to each surface F of the workpiece W. The mark G has an arrow shape modified in the same manner as in the first embodiment shown in FIG. The arrow H of the mark G is printed on each surface F of the workpiece W with ink having a function that can be recognized by irradiating ultraviolet rays or infrared rays, for example. The arrow H printed with this ink can be observed with an ultraviolet lamp or an infrared lamp.

Examples of this type of ink include inks that change color when irradiated with ultraviolet rays or infrared rays (photochromic inks) and inks that contain light emitting materials that emit light in a wavelength range that can be recognized by the camera 12 when irradiated with ultraviolet rays or infrared rays. Etc. can be applied.
Thereafter, the above-described acquisition of the master image M and the mark image P and the above-described workpiece posture recognition method are applied while irradiating an ultraviolet lamp or an infrared lamp, and the posture of the workpiece W to which the mark G is given is recognized.

Hereinafter, effects of the third embodiment will be described.
(1) According to the above-described workpiece posture recognition method, the workpiece W is provided with the mark G that can be recognized by irradiating each surface F with an ultraviolet lamp, an infrared lamp, or the like. Therefore, the mark G can be identified by a 2CCD camera or the like during posture recognition work, and cannot be visually recognized in a normal state. Therefore, it is possible to prevent the appearance characteristics of the finished product from being reduced.

  As mentioned above, although embodiment of this invention was described, various deformation | transformation can be added with respect to the said embodiment in the range which does not deviate from the meaning of this invention. For example, modifications other than the above embodiment are as follows.

  (First Modification) In the above-described embodiment, the case where the mark image P is acquired for each surface F of the workpiece W in the mark imaging process of step S2 shown in FIG. 5 is described as an example, but the present invention is not limited to this. As shown in FIG. 10, which is a diagram illustrating a first modification, the mark image P may be acquired by looking down over the supplied workpiece W as it is. The mark image P0 shown in FIG. 10 is acquired with the camera 12 shown in FIG. 1 facing the upper part Q of the ridgeline between the front surface F3 and the right surface F5. In this way, the arrow A1 given to the top surface F1, the arrow A3 given to the front surface F3, and the arrow A5 given to the right surface F5 are recorded in one mark image P0.

  Further, in creating the master image M, a plurality of master images M are created by imaging a plurality of marks C given to the workpiece W at different angles using the camera 12 shown in FIG. Then, in the image comparison process of step S4 shown in FIG. 5, the captured mark image P0 is compared with the plurality of master images M stored in the master image storage unit 42, and the closest (highest matching) master is obtained. An image M is extracted. Then, the difference between the mark image P0 and the extracted master image M is compared and verified. In the posture determination step in step S5, the posture of the workpiece W is determined based on the above-described comparison verification result between the mark image P and the master image M obtained in the image comparison step in step S4. According to this method, the work of capturing the mark image P0 in the mark imaging step S2 can be simplified, and the time for determining the posture of the workpiece W can be shortened.

  (Second Modification) In the above-described embodiment, the case where the arrows A, E, H with the arrow blades b having different positions and numbers are used as the marks C, D, G has been described as an example, but the present invention is not limited to this. . Arrows A, E, and H are examples, and various modifications and applications are possible. For example, arrows J, K, L, etc. as shown in FIG. In other words, the marks need only be directional and formed in an asymmetric shape, and can be identified by applying a slight deformation. The arrows J, K, and L are identified by the number of line segments to be assigned. Further, the mark is not limited to an arrow. Even in these cases, the same effect as the above-described embodiment can be obtained.

  (Third Modification) In the above embodiment, the case where the workpiece W is carried into the stage 5 by a belt conveyor or the like has been described as an example, but the present invention is not limited to this. For example, the workpieces W may be stacked on a tray or the like. Even in this case, the same effect as the above-described embodiment can be obtained.

  (Fourth Modification) In the above-described embodiment, the case where the arrows A, E, and H as the marks C, D, and G are printed and provided on each surface of the workpiece W has been described as an example, but the present invention is not limited thereto. Not. Arrows A, E, and H may be printed on a label and attached to each surface F. Moreover, it may be imprinted on each surface. It is only necessary that a mark having directionality and an asymmetric shape is formed by some method so that each mark can be identified by applying a slight deformation. In the above-described embodiment, the case where the camera 12 as the imaging unit is provided as an integral part of the robot 10 has been described as an example, but the present invention is not limited to this. You may provide in the position which looks down at the robot 10 and the workpiece | work W in a production line. Even in these cases, the same effect as the above-described embodiment can be obtained.

The figure which shows the structural example of a workpiece | work attitude | position recognition apparatus. The figure which shows the example of the workpiece | work provided with the mark. The figure explaining a mark. The figure which shows the example of a master image. The flowchart which shows the flow of the workpiece | work attitude | position recognition method. The figure explaining the workpiece posture recognition method. The figure which shows the example of a mark image. The figure explaining the comparison process of a mark image and a master image. The figure explaining the workpiece | work and the mark in 2nd Example. The figure explaining a 1st modification. The figure which shows the modification of an arrow.

Explanation of symbols

  DESCRIPTION OF SYMBOLS 1 ... Work posture recognition apparatus, 5 ... Stage, 10 ... Robot, 12 ... Camera as an imaging means, 20 ... Control part, 30 ... Image processing apparatus, 32 ... Image input part, 34 ... Image comparison processing part, 40 ... Memory | storage Device, 42 ... Master image storage unit, A, E, H, J, K, L ... Arrow, C, D, G ... Mark, F ... Surface, M ... Master image, P ... Mark image, S3 ... Image input process , S4: Image comparison step, S5: Posture determination step, W: Workpiece, a ... Arrow, b ... Arrow feather.

Claims (9)

A workpiece posture recognition method for recognizing the posture of the workpiece in a robot that performs work on a workpiece supplied in a random posture,
The workpiece has a plurality of outer surfaces, it marks one by one are assigned to each said outer surface,
Each of the marks is a different type and has an asymmetric shape having directionality for each outer surface ,
The robot includes imaging means for imaging the mark, the master image storing means for storing each master image captured by the imaging means with respect to each said mark in advance, a,
An image input step of capturing a mark image picked up by the image pickup means;
The captured mark image is sequentially compared with the plurality of master images stored in the master image storage means, and the master image that matches the mark image at the maximum is detected to recognize the type of the mark. And an image comparison step for detecting a difference in direction or angle between the mark of the mark image and the mark of the master image,
The outer surface of the workpiece facing the imaging unit is recognized from the type of the mark, and the direction and angle from the posture of the workpiece when the master image is acquired is recognized from the difference in direction or angle of the mark image. And a posture determination step of determining the posture of the workpiece. The work posture recognition method according to claim 1, wherein the mark is provided in a different color for each outer surface of the work. The workpiece posture recognition method according to claim 1, wherein the mark is detectable by ultraviolet rays or infrared rays. A workpiece posture recognition device for recognizing the posture of the workpiece in a robot that performs work on a workpiece supplied in a random posture,
The workpiece has a plurality of outer surfaces, it marks one by one are assigned to each said outer surface,
Each of the marks is a different type and has an asymmetric shape having directionality for each outer surface ,
Imaging means for imaging the previous Symbol mark,
A master image storage unit that stores in advance a master image captured by the imaging unit for each of the marks;
An image input unit that captures a mark image captured by the imaging unit;
The captured mark image is sequentially compared with the plurality of master images stored in the master image storage means, and the master image that matches the mark image at the maximum is detected to recognize the type of the mark. And an image comparison step for detecting a difference in direction or angle between the mark of the mark image and the mark of the master image,
The outer surface of the workpiece facing the imaging unit is recognized from the type of the mark, and the direction and angle from the posture of the workpiece when the master image is acquired is recognized from the difference in direction or angle of the mark image. And a posture determination step of determining the posture of the workpiece. The workpiece posture recognition device according to claim 4 , wherein the mark is formed in a different color for each outer surface of the workpiece. The workpiece posture recognition apparatus according to claim 4 , wherein the mark is detectable by ultraviolet rays or infrared rays. A robot that performs work on a workpiece supplied in a random posture,
The workpiece has a plurality of outer surfaces, and one mark is given to each outer surface,
Each of the marks is a different type and has an asymmetric shape having directionality for each outer surface,
Imaging means for imaging the mark;
A master image storage unit that stores in advance a master image captured by the imaging unit for each of the marks;
An image input unit that captures a mark image captured by the imaging unit;
The captured mark image is sequentially compared with the plurality of master images stored in the master image storage means, and the master image that matches the mark image at the maximum is detected to recognize the type of the mark. And an image comparison step for detecting a difference in direction or angle between the mark of the mark image and the mark of the master image,
The outer surface of the workpiece facing the imaging unit is recognized from the type of the mark, and the direction and angle from the posture of the workpiece when the master image is acquired is recognized from the difference in direction or angle of the mark image. And a posture determination step of determining the posture of the workpiece.   The robot according to claim 7, wherein the mark is formed in a different color for each outer surface of the workpiece.   The robot according to claim 7, wherein the mark is detectable by ultraviolet rays or infrared rays.

Images