JPS5993293A - Visual device for robot - Google Patents

Abstract

(57) [Summary] This bulletin contains application data before electronic filing, so abstract data is not recorded.

Description

[Detailed Description of the Invention] [Original Field of the Invention] The present invention relates to a robot vision device, and more particularly to a robot/soto vision device that detects the position and orientation of a workpiece during assembly work by a robot. In particular, the present invention relates to a robot visual device suitable for being attached to the hand of a robot.

[Prior art]

Conventionally, as a means of detecting the position of an object, the entire object is illuminated uniformly, this optical image is converted into an electrical signal using an imaging device such as a TV right camera, and this electrical signal is converted into a certain reference signal. There is a system that converts the image signal into 21[ and processes this binarized image signal. However, with this device, the color or brightness of the surface of the object is significantly different from the background, and it is necessary to separate and extract only the object on the image through binarization. Also,
This device cannot detect the position in the depth direction, so when the object is grasped, such as during assembly work by robot VL,
If parts must be attached to an object, this object must be at a certain distance from the detector. Therefore, the above-mentioned apparatus using binary images has the disadvantage that the objects to be worked on are limited.

In addition, “A Visu” is used for manual welding by robots.
alSensor for Arc-WeldingR
robots"Bamba+T,, etal, +11 t
h Int, S7mp-On Industrial
RObOtS+ PP151-15B (1981)
There is a device disclosed in 2006, which attaches an optical cutting detection head to the tip of a robot, performs arithmetic processing on the detected original cutting shape, and visually detects the welding position. However, this device has the disadvantage that it cannot be used for assembly work because it is limited to working with fully grooved objects.

Furthermore, an attempt was made to apply the above device to assembly work by the NBS device (VanderBrug + G, J
, + etaL “Eight Vision System
for Real Time Control
of Robots” 9th Int, Symp
, on Ind-ustrial Robots, pp.
213-230.1979). In order to completely detect the position and orientation of an object three-dimensionally using this device, it is necessary to move the robot arm carrying the detector and view the object from several different angles. The drawback was that it took time.

Furthermore, as a device for detecting the position and orientation of an object without being affected by its color, there is a device that fully applies the light cutting method. This uses a detector consisting of a slit light source 1 and an imaging device 2, as shown in FIG.

The line of intersection between the light ray 3 on the flat plate projected from the slit light source 1 (hereinafter referred to as slit 9) and the surface of the object, that is, the light cutting line 4, is at a certain angle with the original axis of this slit X3. When the image is captured by the imaging device 2 from the diagonal direction,
For example, as shown in Figure 2, the cross-sectional shape of the object can be obtained.
Ru. Point 11, which is far away from the detector, is located above on the image, so extract this light cutting waveform and select point a on Figure 2.
By detecting and processing the position of +a' on the image, the distance to the object and the position in the left and right direction can be detected.

Also, by detecting the angle θ, the slit tube e3
The angle of rotation of the surface of the object 5 perpendicular to the plane formed by the image can be detected.

As shown in FIG. 5, two slit light sources 1a and Ib are combined to form a cross-shaped slit 93a that intersects with each other.

Make 3b, each slit 9 3a + 3b
For this, two imaging devices 2a and 2b are fully arranged to capture images of two sets of optical cutting lines. With this configuration, it is possible to detect the rotation angle of the object surface on two axes perpendicular to the two non-parallel planes, so the attitude of the object can be determined without moving the detector. can be detected three-dimensionally. Also,
In addition to the distance at object 1, the size of the object in two directions
Position can also be detected.

However, in such a configuration, two slit light sources and two
Since multiple imaging devices are required, there is a drawback that the detector becomes large. For this reason, the relative positional relationship between the workpiece and the robot hand can be detected by using a detector attached to the robot hand.
The disadvantage is that it is difficult to use a detector with the above configuration in cases where it is required to obtain a high degree of accuracy.

[Objective of the Invention J] The present invention addresses the above-mentioned shortcomings of the prior art, and the present invention is a small and compact device that detects the three-dimensional position and orientation of an object at high speed without being affected by the object's color or brightness. Lightweight Robo V
) is intended to provide a visual device.

[Summary of the invention]

As shown in FIG.
Two imaging devices are provided, and two sources 17, , ) source 1a are provided.
, 1bi rotate the slit lights 5a, 5b in the same direction around the intersection line of the slit lights 5a, 5b, and rotate the slit lights 3a, 3b.
The optical cutting line of the image is detected by one imaging device. During detection, two sets of optical cutting lines are extracted completely independently.
The slit light sources 1a and 1b are alternately switched to emit light one by one. Further, in the present invention, the cross-shaped slit lights 3a and 3b shown in FIG. 4 may be obtained by slit light sources 1a and 1b arranged in an inverted shape as shown in FIG. That is, in FIG. 4, S! 7 +7 original 3
The slit light sources 1a and 1b forming a + 5 b are
Slit light 3a.

As long as the reed is on the plane of 6b and the angle between the slit light source 18ib and the original axis 8 of the imaging device is smaller than 90', it can be moved and placed anywhere.

[Embodiment of the Invention] An embodiment of detecting the position and posture of an object using the robot vision device of the present invention will be described below.

Here, in order to make the explanation easier to understand, the apparatus configuration shown in FIG. 4 will be explained as an example. In addition, the following explanation is
1 can be applied in exactly the same manner to the device configuration shown in FIG.

In FIG. 4, when the two slit light sources 1a and 1b each emit one light, the correspondence between the light cutting line detected by the imaging device 2 and the actual position of the object is as shown in FIG. al (as shown in bl, it becomes a diagonal lattice shape.

This correspondence is determined in advance using an object with dimensions a while changing its position from the detector, and is stored in a storage device.
put. Then, when detecting the position and orientation of the object, by comparing this pre-stored correspondence with the position on the t''L original cutting line image detected by the imaging device R2, the position and orientation of the object are compared. The actual position and inclination can also be determined.In the present invention, the two slit beams 3a+3b are switched and projected, and the distance, position, and inclination to the object on two planes that are not parallel to each other are determined.
The three-dimensional position and orientation of a rainbow object can be uniquely determined.

In addition, in the present invention, the intersection line 6 of the two slit lights 3a and 3b
It is assumed that the detector or the target object is roughly aligned in advance so that It shall be detected precisely.

Next, a method for determining the correspondence between the position of the detected light section line on the image and the actual position of the object will be explained using FIG. Here, only the case of the slit light source 1a shown in FIG. 4 will be explained, or the slit light source 1b shown in FIG. 4 and the slit light source 1a shown in FIG.
The same applies to case 11). As shown in FIG. 7, the intersection line 5 of the two slit lights coincides with the b-axis, and the slit light source 1
Assume a coordinate thread xyz such that the slid "jQ 5 A" by alC coincides with the xz"F plane. As shown in FIG. 7, a plane 6 that is perpendicular to the two axes and wider than the field of view of the imaging device 2 is placed on a scaled rail 7 so that it can be moved in parallel in the z-axis direction. If the position 'fc of the light cutting line on the detected image is determined while moving the plane 6 away from the detector by, for example, 1σ increments, an equidistant line diagram as shown in FIG. 8 will be obtained. Next, the plane 6 is made into a rectangle with a constant width, and such rectangles are prepared in several widths, and the rectangular surface is erected perpendicular to the z-axis and moved in two axial directions.

For example, the width of the plane 6 in the X-axis direction is set to 201@, and when each plane 6 is moved in the two-axis direction, the locus of the end point of the light cutting line detected is determined as shown in Fig. 9. You can obtain a monospaced line diagram (with the X coordinate set to 4) like this. In the equidistant line diagram shown in Figure 8 and the equispaced line diagram shown in Figure 9, 1
, the distance along a certain horizontal line hh' on the diagram and the change in position in the X direction are as shown in Figures 10 and 11, respectively. If these are expressed as a distance function 2 at the vertical coordinate j on the diagram and a function X of the position in the X direction, and the horizontal coordinate i on the diagram is expressed as a variable, then Zr('(il=aj'g+aj+i+aj212+a
j515+-(1nx"=g(1)=bjo+bj1i
It can be approximated as +bj 212+bjsi5+-(2). The degree of approximation is determined by the required detection accuracy. For every j on the diagram (for example, j−1
~256), a j n + b 3 , , (
If n = Q + I + 2+ ...,) is calculated in advance using the above method, the position in the two directions and in the In addition, when determining the inclination of a plane constituting the object to be detected, the actual coordinates (x, z) (X'+Z
') Yoshi, z' −z θ,! tan-”Xt-x・・・・・・・・・
...(3) Using sound, you can find the angle between that plane and the X-axis.

Next, the means for extracting all the edge cutting lines from the detected image will be specifically explained. In this case, the case of the one-sided slit light 3a shown in FIG. 4 will be explained. The light cutting line imaged by the imaging device 2 generally has a certain width, depending on the width of the slit light and the blurring of the 9th grade thread. Therefore, the horizontal scanning direction of the imaging device 2 is shown in FIGS. 8 and 9. Place it in line with the direction of @hh' (horizontal direction),
The peak position (that is, the brightest point) of each horizontal set meal signal is assumed to be the position 1 of the optical cutting line at the coordinate i of the entire image j (see FIG. 12). In this way, the coordinates of the position of the optical cutting line for subtracting equations (1) and (2) are extracted.

Next, what is the process of detecting the three-dimensional position and orientation of an object using the robot vision device of the present invention? : Cylindrical object 9 shown in Fig. 16 and circular hole 1 on a plane shown in Fig. 14
This will be explained using the detection of 0 as an example.

First, a method for detecting the position and orientation of the cylindrical object 9 will be explained. For example, suppose that the imaging device 2 detects a light cut image as shown by the solid line in FIG. 15 when the entire slab light 3a shown in FIG. 5 is projected. In FIG. 16, the position of the brightest point in the horizontal direction is detected as described above, and the shape of the light section line is extracted, as shown in FIG. 16. The waveform shown in Fig. 16 is approximated by a broken line, and the coordinates (i, j) of the end points of each line segment are
Equations (1) and (2) that were calculated in advance are '! Using ir, the actual coordinates (x+z) [When converted, the child shown in FIG. 17 is obtained. In this figure, line segment A has the smallest two coordinates.

That is, the approximate middle IL in the X direction of the top surface of the cylindrical object 9 from the midpoint of the line segment closest to the detector? location is required. Furthermore, the inclination of the object 9 in the xz plane is determined using equation (3). Next, switch the source of the slit) and the fifth
By performing exactly the same detection on the optical section image (indicated by broken line B in FIG. 15) obtained for another 10,000 slit beams 3b shown in the figure, the y Find the center position from the direction A and the inclination 'l of the object 9 in the yz plane. Furthermore, based on the above detection results, the distance 2 from the detector force 1 to the center position of the top surface of the object 9 is zl! If it is approximately perpendicular to ffI, then z
1+z2 zAZ5 , '/++12
,,, (4) z= -+ 2 y2-yl 2 or Z3+zA Z2-Zl, X1+X2,
+ (5)"" 2 X2-x, 2. Here, Xj + Zj 1Z21Z5!Z4 are the y coordinates of the end points of B) shown in Figure 15, and Zj 1Z21Z5!Z4 are the 2 of the four end points, respectively.
Represents coordinates. Based on the above detection results, if the inclination of the upper surface of the cylindrical object 9 in the xz plane and the yz plane is significantly different from 90°, the method of determining the center position from the midpoint of the light section line and the method using equation (4) or (5) If it is determined that the error in the distance calculation cannot be ignored, move the robot arm according to the inclination detection result so that the two axes, that is, the intersection line of the slit beams 5a and 5b are almost perpendicular to the plane, and try again. Detects center position and distance.

Next, a method for detecting the center position and direction of the circular hole 10 perpendicular to the plane shown in FIG. 14 will be explained. FIG. 18 is a diagram showing an example of a light section line obtained when the hole 10 shown in FIG. 14 is imaged by an imaging device. In this case, as in the previous example, X (plane and yz
Two sets of original cut images in a plane are detected independently by switching the full slab light source. The solid line and broken line in FIG. 18 indicate two sets of optically sectioned images obtained in this manner. In the figure, by processing the line segment connecting points a1+82k and the line segment connecting point b++b2 to correspond to the line segments A and B in FIG. 15 of the previous example,
The position of the hole 10 and the direction in which the hole is located can be detected in exactly the same way.

Below, specific embodiments of the robot viewing device of the present invention will be described. First, the overall structure and operation of the apparatus will be explained, and then the specific structure of each part of the detector will be described.

FIG. 19 is a diagram showing an embodiment of the overall configuration of the robot visual device of the present invention. The detector is composed of an imaging device 2 and slit light sources 1a, 1i), and is arranged and configured as follows. That is, (1) two slits fQ
The intersection line 5 of the planes formed by 3a and 3b is made to coincide with the daily rotation axis of the gripper of the robot.

(2) Light from slit light sources 1a and 1b @ 8 a, 8
The original axes 8c of b and photograph 1 house decoration + fi 12 intersect at approximately one point on the X-ray 5 of the slit sources 3a, 31).

(3) Source of slit light source 1a, 11) @ 8 a +
8b and the original axis 8C of the device 2 are on the same plane.

(4) The angle between the original axis 8a of the slit light source 1a and the intersection line 5 of the slit source is equal to the angle between the original axis 8b of the slit source 1b and the intersection #J5 of the slit source.

(5) The original axis 8a of the Thrivet original source 1a and the original @ of the imaging device 2
8c is equal to the angle formed by the original axis 8b of the Slivt light source 1b and the original female 8c of the imaging device 12.

A detector is configured on the robot arm 11 with the arrangement as described above. As another modification of the detector configuration method, the above (
There are 1 to 4 logically possible combinations among 1) to (5). Further, in FIG. 19, the detector is fixed to a portion of the robot that rotates the gripper 18, but it may be fixed on the gripper 18 and rotated together with the gripper 18.

The entire RoboSoto visual system is controlled by a microcomputer (or minicomputer) 15 shown in FIG. That is, the slit source switching device 13 is controlled to switch the slit sources 1 a + 1 b to 4t3 elements one by one, and each light section image is detected by imaging@position 2vc. The detected image signal is input to the optical cutting line extraction circuit 14, and the -M, 9J cutting waveform is input to the microcomputer 15. The yc cutting line extraction circuit 14 compresses two-dimensional image data into one-dimensional waveform data according to the method described above, and is disclosed in Japanese Patent Application No. 57-14754.
The device disclosed in No. 27 may also be used. The two sets of optical section line waveform data thus obtained are processed in the microcomputer 15 according to the procedure described above.

That is, after the polygonal line approximation of the waveform data, equations (1) to (5)
The three-dimensional position and orientation of the object are calculated, and the data is output to the control device of the entire robot arm mechanism. Coefficient cl necessary to calculate equations (1) and (2)
jn+bjn(j=0+1+213...+n=0.
1.2.3-.-) are obtained in advance by the method described above, stored in the storage device t16, and read out and used as needed.

Next, the operation of the robot visual system of this embodiment will be explained in detail.

Detection of the object All lines 9Before, as already explained, the formula (υ
It is necessary to store the coefficient ajn+bjn (and the coefficient of nyj obtained in the same manner) shown in (2) in the storage device 11HC. Using the device shown in FIG. 7, the robot is operated and fixed so that the intersection line 5 of the slit source is parallel to the rail 7, and the equidistant line diagram shown in FIG. 8 and the equidistant line diagram shown in FIG. Obtain the manufacturing width diagram shown in . This work is switched by the slit switching device 13, and the two slits) ft, 3a
, 3b respectively. Next, based on these data, polynomial approximation is performed by the microcomputer 15 to obtain the coefficient ajn+bjn'j of equation (1) (2n) for each jVc and store it in the storage device 16.

In the process of detecting the target object, as already explained using FIGS. 16 and 14 as examples, the microcomputer 15 controls the slit source switching device 13, and switches the two sets of slit light sources 1a and 1b from one to the other. A light cutting waveform based on a light cutting image in the case of hollowing is obtained by the original cutting extraction circuit 14, and after being subjected to polygonal approximation by the microcomputer 15, the actual position coordinates of each n line segment are stored in the storage device 16. Formulas (1) and (2) are based on the stored coefficients ajn and Jn.
(and the formula for calculating the similar yj). The microcomputer 15 has two sets of light sources 1a.

Among the line segments when each of 1b is emitted, select one line segment on the target object using distance 2 as a criterion.Usually, the line segment closest to the detector and near the center of the field of view) , from each of the four end points, equations (3) to (5)
The position and orientation of the target object are detected by calculating the midpoint of the line segment and outputting the detected position and orientation to the control device of the robot arm mechanism.

Next, the specific configuration of each part of the detector will be explained.

The imager 2tC uses a TV camera and can detect the optical cutting line at high speed by scanning the image in the direction 1 shown in FIG. 12 and the horizontal scanning direction.

Of course, a two-dimensional image detector outside the TV left camera, such as a combination of a one-dimensional seven-otodiode array and a galvanometer mirror, may also be used. Among TV cameras, those that use two-dimensional solid-state image sensors in particular have (a) earthquake resistance and impact resistance;
B) lifespan, 01 image distortion, b) small size, light weight, bite, (Yamajaku gunto), it is superior to the one using 1k electrons.
ing. Figure 20 shows an image taken using all 19 two-dimensional solid-state image sensors. It is a figure which shows one specific put of an apparatus. In this specific example, the part mounted on the robot soto arm is the 21st
As shown in the figure, 2 units excluding the TV camera control unit 22
Dimensional solid-state image sensor 19 and front image signal amplifier 20
h') with only the synchronous drive signal waveform shaping circuit 21, further reducing the size and weight. In Figure 20, the front R
The image signal amplifier 20 is mounted on the substrate 23a, and is connected to the two-dimensional solid-state image sensor 19 and the synchronous drive signal waveform shaping circuit 2.
1 is mounted on a substrate 25b and fixed on a back cover 25 with a support 24. A connector 26 is attached to the back cover 25, and the -off signal and power are supplied through this connector 26. Further, the back cover 25 and the outer frame 27 are made of a non-metallic material such as plastic, which has a copper foil (or metal plating) for electrostatic shielding on the inner surface. Furthermore, it is also possible to make the imaging lens 28 out of plastic. As described above, the use of the imaging device according to this embodiment has the advantage of being earthquake resistant and impact resistant, long life, low image distortion, and power saving, and has the effect of making the detector extremely compact and quantifiable.

Next, a specific configuration of the slit light sources 1 a + 1 b will be described. As a light source, you can use a 710 gen lamp, a radiation tube, an axial diode, etc.
Light-emitting diodes are the best in six points: (1) Earthquake resistance, (1) Impact resistance, (2) Life expectancy, and (1) Compactness and light weight. 22nd
The figure shows a specific example of a slit light source using an axial diode. The light emitting diode 29 is of a high-blade type that emits infrared light. Since the maximum sensitivity wavelength of a two-dimensional solid-state image sensor is usually around 800 nm, detection sensitivity can be maximized by using an axial diode with this wavelength. As shown in FIG. 22, a plurality of light emitting diodes 29 are arranged in parallel along the longitudinal direction of the cylindrical lens 30, for example. In the plan view shown in 22nd [2(al), the axial diode 29 and the slit 61 are in an image forming relationship with respect to the cylindrical lens 30.

The position of the imaging plane 32 is set to the approximate target position,
The imaging surface 62 and the slit 31 are 1 with respect to the imaging lens 33.
It is related to image formation. I really appreciate the above configuration.
Since the light emitted from the light source diode 29 can be efficiently concentrated to form a slit light, a bright slit light source can be realized in addition to the above three characteristics. Furthermore, by using a lens-based light emitting diode 29 with strong directivity, an even more powerful slit light source can be realized.

FIG. 23 is a diagram showing another specific example of a slit light source using a light emitting diode. As shown in FIG. 23, a plurality of light emitting diodes 29 are arranged along the slit 31, and the slit '51 and the imaging surface 62 are in an imaging relationship with respect to the imaging lens 33. In addition, the cylindrical lens 30id is inserted between the imaging lens 33 and the slit 31 so that there is no unevenness on the imaging surface 32 at the slit source. In this specific example, if the relationship between the images on the image forming surface 32 is out of order, there is a drawback that unevenness occurs at the slit source, but this can be ignored in the present invention, which detects the position of the light cutting line. According to this specific example, as is clear from a comparison with FIG. 22, the length in the original axis direction can be shortened, and in addition to the characteristics of the light emitting diode 29, the slit light source can be made significantly smaller. There is.

Further, like the imaging device, if the outer frame is made of non-metallic material such as Blastivuk, the detector can be made significantly smaller and lighter.

Note that in the specific examples of the slit light sources shown in FIGS. 22 and 23, the slit source does not have a perfect flat plate shape. This problem can be avoided by not making the diameter of the imaging lens 33 larger than necessary.

〔Effect of the invention〕

According to the present invention, the position and orientation of the target object in two non-parallel planes can be determined by arranging the slit light source so that the two slit sources cross each other and analyzing the light cutting line of each IT. Since detection can be performed without moving the detector or the target object, there is an effect that the three-dimensional position and orientation of the object can be detected at high speed.

In addition, since the cross-shaped slit source is obtained from two sets of slit light sources arranged in an inverted shape, the imaging device and the slit light source can be integrated, making it possible to achieve compactness and quantity. This has the effect of making it possible to detect objects that are not affected by the object being grabbed. Furthermore, since the original cutting lines in two non-parallel planes are detected using only one imaging device, there is an effect that the entire detector can be made smaller and lighter.

Furthermore, the effect of the light sectioning method, which is the basis of the present invention, has the effect of making it possible to detect the position and orientation of the object without being affected by the color or surface condition of the object.

[Brief explanation of drawings]

Figure 1 is a perspective view showing the detector of the Robo-Soto visual device using the optical sectioning method, Figure 2 is a diagram showing example 1 of the detected image of the detector shown in Figure 1, and Figure 3 is using the optical sectioning method. FIG. 4 is a perspective view of the detector according to the principle of the present invention; FIG. 5 is a perspective view showing the entire basic structure of the detector according to the present invention; FIG. The figure shows equidistant lines and flute width lines obtained by the detector shown in Figure 4, Figure 7 is a perspective view of the detector that obtains equidistant lines and equidistant lines, and Figure 8 shows equidistant lines 11-j. Figure 9 is a diagram showing an example of the equal f@ line, Figure 10 is a diagram showing changes in the equidistant line shown in Figure 8, Figure 11 is a diagram showing the equidistant line shown in Figure 9. Diagram showing changes in lines, 1st
Figure 2 shows the complete method for extracting optical cutting lines, Figure 13 and Figure 1.
Figure 4 shows an example of the object to be detected, Figures 15 and 16
17 and 17 are diagrams showing the detection processing process of the object to be detected shown in FIG. 13, FIG. 18 is a diagram showing the detected image of the object to be detected shown in FIG. FIG. 20 is a diagram showing a specific example of the imaging device used in the robot vision device of the present invention, and FIG. 21 is a diagram showing an example of the overall configuration of the device. FIG. Figures 22 (1a) and 23 (al are plan views showing specific examples of the slit light source used in the detector of the robot vision device of the present invention, Figures 22 (bl and 23 (bl) are the plan views of the present invention). This is a front view showing a specific example of the light source used in the detector of the robot vision device.1...Slit light source, 2...Imaging device, 5a, 3b
...Slit source, 4...Optical cutting line, 5...Intersection line of slit source, 6...Right, 7...Rail with scale, 8a+8b+80...Original axis, 9.10 ...Target object, 11...Robot arm, 12...Gree/de (rotation axis, 13°°° slide source switching device, 14...
・Disconnection extraction circuit, 15...Microcomputer, 16...Storage device, 17...Detected data, 1.
・Gritzpa, 19...2-dimensional solid-state image sensor, 2
0... Front ITII image signal amplifier, 21... Synchronization signal waveform shaping circuit, 22... TV right camera control unit, 2! +a, 2! +t)... Board, 24... Support, 25... Back cover, 26... Connector, 27...
Outer frame, 28. 35... Imaging lens, 29... Light emitting diode, 30... Cylindrical lens, 31...
- Thrivet, 32...imaging surface. ;4'l Fig. 5 Fig. 2 Fig. 3 b Fang 40 Fig. 5 O 6 Fig. Fig. 12 Fig. 13 Fig. 14 Fig. 15 Fig. 16 Fig. 17 Fig. 8 Fig. tq Fig. Fang Fig. 20 - + Fig. 21 Procedural amendment (method) Indication of the case 1982 Patent Application No. 201931, Name of the invention Name of the person who corrects the robot vision device 1!,, 4510) Co., Ltd. 11.
Hitachi Manufacturing Representative Name III
Contents of Katsu Rakujo Ri Person Correction As shown in the attached page Kaya 6 Garden

Claims (1)

[Claims] (1) A robot that detects an optical image of a target object, analyzes it to fully detect the position and orientation of the target object, and controls the entire arm mechanism of the robot based on the detection results. In a visual device, there is a slit light source that generates two flat slit lights that are not parallel, and a slit light source that is arranged so as not to be on a plane formed by the two slit lights, and that connects the two slit lights with the surface of a target object. An imaging device that converts an optical image of intersection lines into an electrical signal, and - two slit light sources in one
A slit source switching device that cuts the tubes one by one to emit light, a light cutting line extraction device that separates and beats bright lines on the image obtained from the imaging device, and a device that separates and separates the bright lines on the image obtained from the imaging device, and compares the positions of the lines to be separated and extracted on the image with their actual positions. What is claimed is: 1. A robot vision device comprising: a storage device for storing correspondence relationships; and calculation means for analyzing the position and orientation of a target object from the separated and extracted lines and the stored correspondence relationships. (2) The slit light source is configured using a plurality of light emitting diodes.
The robot visual device described in section 1). (4) The above imaging device is characterized in that it is divided into a detection section consisting of a two-dimensional solid-state image sensor and a front image signal amplifier, and a control section, and the detection section is provided on the arm of the robot. A robot visual device according to claim (3). (5) The robot visual device according to claim (1), wherein the outer frame of the imaging device is made of non-metal. (6) The robot visual device according to claim (1), wherein the outer frame of the slit light source is made of a non-metallic material.