JP2003211382A - Robot control device - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To improve robustness related to visual recognition in controlling a robot arm by a visual servo. <P>SOLUTION: This robot control device 2 is composed of a CCD camera 12 mounted to the robot arm 1; a visual recognition device 13 for processing the photographed image data; a robot controller 11 for controlling the position attitude of the robot arm 1 on the basis of the position correction quantity from the visual recognition device 13; and a camera control device 14 for controlling a diaphragm adjusting mechanism, a focal distance fluctuating mechanism and a focus adjusting mechanism of the CCD camera 12. In photographing a work W by the visual service, the camera control device 14 controls the diaphragm adjusting mechanism to have the exposure conditions equivalent to those in storing target data, controls the focal distance fluctuating mechanism to settle the whole image of the work W within the visual field and controls the focus adjusting mechanism to photograph the work W in the focus equivalent to that in storing the target data. <P>COPYRIGHT: (C)2003,JPO

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a robot controller for performing visual feedback control (so-called visual servo) of the position and orientation of a robot arm based on image data taken by a camera.

[0002]

For example, in an assembly robot or the like, when a work is gripped by a robot arm, the robot arm is controlled by using a visual device. This control is generally performed by taking a picture of the work with a camera attached to the tip of the robot arm at a predetermined position relatively far from the work, detecting the absolute position of the work from the taken image data, and detecting that position. The robot arm was moved to the position and the work was gripped by the hand.

However, in such a control method, alignment accuracy is relatively low, and calibration between devices such as conversion of a camera coordinate system to a robot coordinate system is required, so that preparation is very troublesome. Work (parameter setting) etc. is required, and further, when the work moves after the shooting (or when the work moves relatively)
Has a problem that it cannot be applied.

Therefore, in recent years, visual feedback control called visual servo has attracted attention.
In this method, for example, the robot arm is moved to a position immediately before gripping the work during teaching, the work is photographed by a CCD camera attached to the robot arm, and the feature amount of the work image is stored as target data. I'll do it. During actual work, the robot arm is used so that the work is always photographed by the CCD camera and the current data is compared with the target data to make the error zero, that is, the appearance is the same as at the time of teaching. The control of the position and orientation of (1) is repeated (feedback control), and when the error converges to 0, the gripping operation by the hand is executed.

In this case, the feature amount is obtained by extracting a plurality of (for example, eight) feature points (specific edges or holes, affixed markers, etc.) set on the work, and the positions and orientations thereof. The position and orientation of the work in the three-dimensional space are recognized by the camera coordinates.

Unlike the conventional method of "moving after seeing", the control by such a visual servo is "moving while seeing", so that quick and accurate position / orientation control of the robot arm can be performed. At the same time, since the position of the robot is controlled relative to the work, the conversion to the absolute coordinates of the robot (calibration) is unnecessary, teaching work (preparation work) is simplified, and, for example, on a conveyor. Gripping the moving workpiece,
For example, gripping a workpiece while moving with a mobile robot.
There is an advantage that it can be applied even when the object moves relatively.

However, in the conventional control by the visual servo, there is still room for improvement in terms of robustness regarding visual recognition (recognition of an object with respect to environmental changes). That is, in the past, the optical conditions at the time of photographing with the CCD camera, that is, the size of the field of view (focal length), the focus of the lens, the diaphragm (exposure condition), etc., were fixed, so that, for example, the work piece with respect to the robot arm was fixed. When relatively moving, especially when the camera is relatively close to the work, part or all of the work image may be out of the field of view of the camera, making it impossible to obtain accurate current data. The camera could lose sight of the work.

It is also conceivable that the image of the workpiece photographed by the camera will be out of focus and will be blurred, and if such image blurring occurs, the detection accuracy of the characteristic amount will be reduced. . Furthermore, if there is a change in the amount of ambient light such as when the environment becomes darker than when teaching (when target data is stored), the feature quantity detection accuracy may also decrease.

The present invention has been made in view of the above circumstances, and an object thereof is to control a robot arm by a so-called visual servo, and to provide a robot control device capable of improving robustness regarding visual recognition. To provide.

[0010]

In the conventional visual servo, the optical condition at the time of photographing by the camera, that is, the size of the visual field (focal length), the focus of the lens, the aperture (exposure condition), etc. are fixed. It was On the other hand, the present inventor utilizes the adjustment function of the optical system provided in the camera,
The present invention has been accomplished with a focus on incorporating the adjusting function into a feedback system of a visual servo and performing feedback control of the adjustment of the optical system of the camera by a signal from the outside.

That is, the present invention is for controlling a robot arm by a so-called visual servo, and based on photographed image data obtained by photographing an object by a camera,
It is characterized in that a camera control means for controlling the optical system adjusting means provided in the camera is provided (the invention of claim 1). According to this, even when the optical conditions (environment) of the surroundings are changed, the camera control means can deal with it by controlling the optical system adjusting means. As a result,
It is possible to improve the robustness of visual recognition, that is, the recognizability of an object with respect to environmental changes, and to realize stable visual servo.

In this case, when the optical conditions differ between the teaching and the actual work, it may be possible to make a software correction in the image processing. However, there is a disadvantage that the response of the visual servo is deteriorated. In addition, some cameras have an automatic focus adjustment function that automatically adjusts the optical system of the camera, for example, an automatic focus function that automatically adjusts the focus of the lens and a function that automatically adjusts the aperture amount based on the detection of ambient light. However, in such a camera that adjusts the optical system based on its own judgment, the optical system of the camera is controlled independently of the control of the robot arm by the visual servo,
It is hard to say that it is compatible with the visual servo, and it is insufficient in terms of stable control by the visual servo.

More specifically, the following modes are conceivable as control modes of the camera control means. That is, in the optical system adjusting means having the focal length changing mechanism, the focal length can be changed so that the entire image of the object is within the visual field of the camera. ). As a result, for example, when part or all of the image of the work is out of the field of view of the camera,
Since it is possible to take measures such as widening the field of view to widen the field of view, it is possible to prevent the camera from losing sight of the object and to obtain accurate current data.

At this time, a plurality of target data whose focal length has been changed in a plurality of steps by the focal length changing mechanism is stored in the storage means in advance, and the image processing means sets the focal length controlled by the camera control means. It is possible to calculate the error of the current data by using the corresponding target data (the invention of claim 3), and thereby, the error from the current data is calculated by using the desired target data as it is from a plurality of pieces. Therefore, the process of correcting the target data or the current data according to the focal length is not necessary, and the error can be accurately calculated in a short time to control the robot arm.

Further, in the case where the optical system adjusting means is provided with the focus adjusting mechanism, the focus can be adjusted so that the object is photographed with the same focus as when the target data is stored. Invention of 4). This makes it possible to prevent the image of the object captured by the camera from becoming out of focus and blurring, and it becomes possible to capture a clear image. The robot arm can be controlled.

Further, the optical system adjusting means provided with a diaphragm adjusting mechanism may be structured so that the diaphragm is adjusted so that the exposure condition is equivalent to that when the target data is stored (claim 5). invention). Alternatively, the optical system adjusting means having an AD gain adjusting means for adjusting the AD gain of the captured image data of the camera has a configuration in which the AD gain is adjusted so that the exposure condition becomes equivalent to that when the target data is stored. It is possible (the invention of claim 6).
According to these, it is possible to obtain the current data and thus the error under the same exposure condition as when storing the target data.
The accuracy and reliability of control of the robot arm can be improved.

[0017]

BEST MODE FOR CARRYING OUT THE INVENTION An embodiment in which the present invention is applied to, for example, a multi-joint (6-axis) type robot for assembly (claim 1
(Corresponding to 5) will be described with reference to the drawings.
FIG. 1 schematically shows the configuration of a robot system according to this embodiment.
An axis type robot arm (robot body) 1 and a robot control device 2 for controlling the robot arm 1 are provided.

In this system, in this case, the work W which is an object supplied (or conveyed by a conveyor or the like) onto the workbench at an arbitrary position and posture by the robot arm 1 fixedly installed in the equipment. Hold
It is designed to be assembled and transported to a predetermined position.
A plurality of (for example, eight) feature points (specific edges, holes, affixed markers, etc.) are set on the work W for visual recognition described later.

The robot arm 1 is provided with a first arm 4 which is rotatable (swirlable) about a vertical axis on a base 3 which is fixedly installed in a facility, and a first arm 4 has a first arm 4 at the tip thereof. The two arms 5 are provided so as to be rotatable about a horizontal axis, and the third arm 6 is provided at the tip of the second arm 5 so as to be rotatable about the horizontal axis. Furthermore, the third
A fourth arm 7 is coaxially rotatably provided on the tip end surface of the arm 6, a fifth arm 8 is rotatably provided on the tip end of the fourth arm 7, and a sixth arm 7 is provided on the tip end surface of the fifth arm 8. 9 is provided so as to be coaxially rotatable. A hand 10 is detachably (replaceable) attached to the tip end surface of the sixth arm 9.

Further, each of the arms 4 to 9 of the robot arm 1 is adapted to be driven by a servomotor (not shown) with an encoder, and each of these servomotors (and the hand 10) is It is controlled by a robot controller 11 which is provided externally and is mainly composed of a microcomputer, so that the work of gripping the work W or the like is automatically executed.

At this time, the robot controller 11
The robot controller 2 constitutes a part of the robot controller 2, and the robot controller 2 determines the position and orientation of the robot arm 1 based on the information of the camera (visual sensor) by the software configuration (execution of the program) of, for example, the work. Dynamic visual feedback control called visual servo, which performs feedback control to the gripping position of W, is executed as follows.

In order to realize the position / orientation control by the visual servo, a CCD camera 12, which is a camera for taking an image of the work W, is attached to a hand portion of the robot arm 1, for example, a side surface portion of the fifth arm 8. There is. Along with this, a visual recognition device 13 which mainly comprises a microcomputer and which takes in and processes captured image data from the CCD camera 12 is provided. This visual recognition device 13
Is a control operation signal (position correction amount) based on image processing.
Is provided to the robot controller 11, and together with the CCD camera 12 constitutes a part of the robot controller 2. The visual recognition device 13 may be built in the robot controller 11.

At this time, the visual recognition device 13 is provided with a storage unit (not shown) for storing target data obtained by the teaching operation executed in advance. In the teaching operation, for example, a manual operation using a teaching pendant causes the robot arm 1 to move to a teaching target position with respect to the work W (the work W by the hand 10).
Is moved to a position and orientation immediately before gripping the workpiece W, and the work W is photographed by the CCD camera 12 at that position, and a feature amount (for example, the work W Positions of multiple feature points on the image,
The size (length, area), inclination angle, etc.) is stored as target data (setting value).

In order to control the camera, which will be described later, the storage unit stores a plurality of pieces of target data whose focal lengths are changed in a plurality of steps, and also the brightness of the image during teaching ( Brightness information, focus information (image differential intensity information), and the like are also stored.

Then, at the time of actual work, the robot control device 2 moves the robot arm 1 at an arbitrary position and posture.
The work W is photographed by the CCD camera 12, the photographed image data is processed by the visual recognition device 13, and the feature amount (position and posture of the work W) on the current image is similarly obtained as current data (feedback signal). , The current data is compared with the target data, and the error (deviation) is reduced (set to 0), that is, the position correction amount (control) is adjusted so that the image by the CCD camera 12 looks the same as at the time of teaching. The amount) is calculated and output to the robot controller 11 as a control operation signal.

In this case, the visual recognition device 13 of the work W is based on, for example, a three-dimensional orthogonal coordinate system in which the photographing optical axis direction of the CCD camera 12 is the Z axis and the photographing screen (projection surface) is the XY plane. Differences between the feature amount of the captured image and the target data, x (position in the X-axis direction), y (position in the Y-axis direction), z (position in the Z-axis direction), Rx (posture about the X-axis (rotation angle) )), Ry (posture around Y axis (rotation angle)), R
The six components of z (posture (rotation angle) around the Z axis) are obtained, and these are output to the robot controller 11 as position correction amounts.

The robot controller 11 repeatedly controls (feedback control) the position and orientation of the robot arm 1 based on the position correction amount, and the error converges to a value below the threshold value (0) by this control, that is, the robot. When the position and orientation of the arm 1 with respect to the work W coincide with the teaching target position, the gripping operation of the work W by the hand 10 is executed. Therefore, the visual recognition device 13
The robot controller 11 functions as the storage unit and the image processing unit according to the present invention, and the robot controller 11 functions as the control unit according to the present invention.

Although not shown, the CCD camera 12 is provided with an optical system adjusting means for adjusting the optical conditions at the time of photographing. Although detailed description is omitted, in this embodiment, as the optical system adjusting means,
Adjusts the focal length variation mechanism (zoom mechanism) that changes the focal length (in other words, enlarges or reduces the field of view of the camera), the focus adjustment mechanism (autofocus mechanism) that focuses the lens, and the aperture amount (exposure condition) at the time of shooting. A diaphragm adjustment mechanism is provided.

In the robot controller 2 of this embodiment, the focus of the work W is picked up by the CCD camera 12 during the actual work (when the control of the robot arm 1 is executed by the visual servo). Controls the distance variation mechanism, the focus adjustment mechanism, and the aperture adjustment mechanism (outputs a camera control signal to the CCD camera 12)
A camera control device 14 is provided as a camera control means for the purpose.

At this time, as will be described later in the description of the operation, the camera control device 14 controls the brightness information of the current captured image data of the CCD camera 12 and the visual recognition device 13 when the work W is photographed by the visual servo. The brightness information at the time of teaching stored in the storage unit is compared, and the aperture adjustment mechanism of the CCD camera 12 is controlled so that the exposure conditions are equivalent to those at the time of storing the target data.

Further, the camera control device 14 determines whether or not the entire image of the work W is within the field of view of the CCD camera 12 based on the current image data of the CCD camera 12 when the work W is photographed by the visual servo. If a part or all of the image of the work W is out of the field of view of the CCD camera 12, the focal length variation mechanism of the CCD camera 12 is controlled so that the entire image of the work W falls within the field of view ( The focal length is shortened to a wide angle).

In this case, in the visual servo,
Since the visual recognition device 13 obtains the feature amount (current data) according to the focal length, target data corresponding to the focal length is also necessary for error detection. Therefore, at the time of teaching, a plurality of target data whose focal lengths are changed in a plurality of steps are obtained by the focal length changing mechanism of the CCD camera 12, and these are stored in the storage unit of the visual recognition device 13. ing.

Further, the camera control device 14 evaluates, for example, a differential intensity value from the current image data of the CCD camera 12 when the work W is imaged by the visual servo, so that the image of the work W is as taught. Compare to determine whether it is not blurred, and if it is blurred,
The focus adjustment mechanism is controlled so that the work W is photographed with the same focus as when the target data is stored.

Next, the operation of the above structure will be described with reference to FIGS. First, the flowchart of FIG. 2 schematically shows the procedure of the target data storage processing executed by the robot controller 2 during teaching. In this teaching, first, step S1
At this point, the hand portion of the robot arm 1 is moved to a target position with respect to the work W (for example, the position and posture immediately before gripping the work W with the hand 10) by a manual operation using a teaching pendant, for example.

In the next step S2, the variable i is set to 1, and in step S3, the work W is photographed by the CCD camera 11 with the focal length of the lens of the CCD camera 12 being fi. . Then, in step S4, image processing is performed by the visual recognition device 13 from the obtained image data, and a feature amount indicating a three-dimensional position or orientation of the work W on the image (for example, a plurality of features of the work W). The position, size (length, area), inclination angle, etc. of the point on the image are stored in the storage unit together with the focal length fi as the target data Id (fi).

Here, fi which is a parameter of the focal length
(1 ≦ i ≦ n) is f1>f2>f3>...> fn (mm)
Will be satisfied. At this time, the focal length depends on the specifications of the lens to be used. For example, f1 is in a state in which all the feature quantities (target data) Id observed from the object are obtained and the object can be observed in the most magnified manner. F is the focal length
n is a feature amount (target data) Id observed from the object.
Is obtained, and the focal length is such that the object can be observed in the widest angle. Further, fi is a value obtained by appropriately defining an integer n (> 1) and dividing fn to f1 into n, that is, fi.
= F1- (f1-fn) / (n-1) * (i-1).

In the next step S5, it is determined whether or not the variable i is an integer n or more. If it is less than n (No), the value of the variable i is incremented by 1 in step S6, The processes of steps S3 to S6 are repeated until the value of i becomes n (Yes in step S5). As a result, the storage unit of the visual recognition device 13 stores a plurality (n pieces) of target data Id (fi) in which the focal length is changed in a plurality of steps (n steps from f1 to fn). . Although not shown in FIG. 2, at the time of this teaching, the focus of the lens of the CCD camera 12 is automatically adjusted by a focus adjusting mechanism (autofocus), and the brightness information of the image and the focus are obtained. The information of (differential intensity of image) is also stored in the storage unit together with the target data.

Next, the flow chart of FIG. 3 schematically shows the procedure of the position and orientation control of the robot arm 1 by the visual servo executed by the robot controller 2 during the actual work. That is, when the work is started, step S
At 11, the work W at the current position is observed by the CCD camera 12, and at next step S12, first, whether or not appropriate brightness is obtained from the luminance information of the observed image, that is, By comparing with the brightness information stored in the storage unit, it is determined whether the brightness is similar to the brightness at the time of teaching.

Here, as shown conceptually in FIG. 4A, when the surrounding environment is dark and the entire image is too dark (or too bright) (step S1).
2), and in step S13, the camera control device 1
4 outputs a control signal to the CCD camera 12 so that the exposure conditions are the same as when teaching, and the CCD camera 12
The diaphragm adjustment mechanism adjusts the diaphragm. As a result, the brightness of the entire image becomes appropriate, as shown in FIG.

If the appropriate brightness of the image is obtained (Yes in step S12), in the next step S14,
It is determined whether the entire image of the work W is within the field of view of the CCD camera 12. Here, as illustrated in FIG. 5A, when part (or all) of the image of the work W is out of the field of view (No in step S14), the camera control device is operated in step S15. 14 outputs a control signal to the CCD camera 12 so as to change (shorten) the focal length, and the CCD camera 1
The focal length is adjusted by the focal length changing mechanism 2.

In this case, for example, the focal length is initially set to f1, and the focal length fi is increased by one step (shortened, for example) until all the images of the work W are within the field of view of the CCD camera 12. ) Going is done. Thus, as shown in FIG. 5B, the entire image of the work W is C
It comes to fit within the field of view of the CD camera 12. Work W
If the entire image of the image is within the field of view of the CCD camera 12 (Yes in step S14), the next step S16
At, it is determined whether the image of the work W is out of focus (whether the image is out of focus).

Here, when the focal length is changed in step S15, for example, there is a possibility that the focus may not be achieved as illustrated in FIG. 6 (a). Such image blurring is detected by, for example, the differential intensity value of the image. When the image is blurred, the differential intensity of the image is reduced, and therefore it is possible to judge that the image is blurred by evaluating this differential intensity value (comparing with the differential intensity at the time of teaching).
If the image is blurred (Yes in step S16)
s), in step S17, from the camera control device 14 to C
A control signal is output to the CD camera 12 to perform focus adjustment, and the focus adjustment mechanism performs focus adjustment.

As a result, an image in focus is obtained, as shown in FIG. 6 (b). If the focus is appropriate (Yes in step S16), in the next step S18, the captured image data at that time is taken into the visual recognition device 13 and image processed (feature amount extraction). Then, the current data I (t, fi) is obtained. Then, in step S19, the current data I (t, f
i) and the target data I corresponding to the corresponding focal length fi
d (fi) is compared, and the error (position correction amount) ΔI
(T) is calculated.

In the next step S20, it is judged whether or not the absolute value of the obtained error ΔI (t) is less than or equal to the threshold value. If the absolute value exceeds the threshold value, that is, the error is still large and the robot arm 1 is the teaching target. If the position has not been reached (No), in step S21, the control amount R (t) of the robot arm 1 is calculated from the error ΔI (t) and output to the robot controller 11, and in step S22, The position and orientation of the robot arm 1 is controlled (moved). Then, the processing from step S11 is repeated.

By the control as described above, the hand of the robot arm 1 gradually approaches the work W from a position relatively distant from the work W, and finally the error ΔI (t) becomes less than or equal to the threshold value ( 0), that is, the position and orientation of the robot arm 1 with respect to the work W coincides with the teaching target position (Yes in step S20). At this point, the control by the visual servo ends, and the work W of the hand 10 moves. That is, the process proceeds to the gripping work (step S23).

Here, when the surrounding optical conditions (environment) and the like change between the time of teaching and the time of actual work, C as in the conventional case is used.
Under the optical conditions at the time of shooting with a CD camera, that is, when the focal length, the focus of the lens, the diaphragm, etc. are fixed, the camera may lose sight of the work, or the accuracy of detecting the feature amount may be reduced. there were.

On the other hand, in the present embodiment, the camera controller 14 controls the aperture adjusting mechanism, the focal length changing mechanism and the focus adjusting mechanism of the CCD camera 12, so that the exposure conditions equivalent to those at the time of teaching are provided. The current image data can be taken in (steps S12 and S13), and the CCD is adjusted so that the entire image of the work W fits within the field of view.
The focal length of the camera 12 can be controlled (steps S14 and S15), and the work W can be photographed with the same focus as when teaching (steps S16 and S1).
7).

As a result, according to the present embodiment, the adjustment of the optical system of the CCD camera 12 is incorporated in the feedback system of the visual servo, and the feedback control is performed by the signal from the outside. )
It is possible to easily and swiftly respond to changes in the above. As a result, it is possible to improve the robustness of the visual recognition, that is, to improve the recognizability of the work W with respect to the environmental change, and to obtain the excellent effect that the stable visual servo can be realized. .

Although the CCD camera 12 is provided with the diaphragm adjusting mechanism to adjust the diaphragm in the above embodiment, the CCD is adjusted so that the exposure condition is the same as that when the target data is stored.
The AD gain of the image data captured by the camera 12 may be adjusted (the invention of claim 6).
Similarly, since the current data and thus the error can be obtained under the same exposure condition as when the target data is stored, the accuracy and reliability of the control of the robot arm 1 can be improved.

In the above embodiment, the CCD camera 1
In FIG. 2, three kinds of optical system adjusting means of an aperture adjusting mechanism, a focal length changing mechanism, and a focus adjusting mechanism are provided, and the exposure condition, the focal length, and the focus of the lens are all controlled by the camera control device 14. Either one or two
It goes without saying that even a configuration for controlling one of them is included in the technical scope of the present invention. In the above embodiment, the focal length is set to f1 first, and when the image of the work W is out of the visual field, the focal length fi is sequentially changed. It is also possible to adopt a configuration in which the focal length is predicted, shooting is performed at that focal length, and then the focal length is adjusted as necessary. The focus adjustment (focus) can also be predicted and controlled.

Besides, the present invention is not limited to the above-mentioned embodiments, but the present invention can be applied to, for example, a mobile robot, and the work W being moved by a conveyor or the like can be grasped. The present invention can be applied to work, and can be applied to various works other than work for gripping and carrying work, and various modifications can be made to the hardware configuration of the robot arm, the contents of work (control), and the like. It is possible. The present invention can be appropriately modified and implemented without departing from the scope of the invention, such as various modifications of the configuration and mounting position of the camera.

[Brief description of drawings]

FIG. 1 is a diagram schematically showing the configuration of a robot system according to an embodiment of the present invention.

FIG. 2 is a flowchart showing a processing procedure at the time of teaching.

FIG. 3 is a flowchart showing a processing procedure during actual work.

FIG. 4 is a diagram schematically showing a state of an image when a surrounding environment is dark (a) and when an aperture is adjusted (b).

FIG. 5 is a diagram schematically showing a state of an image when a part of the image of the work is out of the field of view (a) and when the focal length is changed (b).

FIG. 6 is a diagram schematically showing a state of an image when a work image is blurred (a) and when a focus is adjusted (b).

[Explanation of symbols]

In the drawings, 1 is a robot arm, 2 is a robot controller,
10 is a hand, 11 is a robot controller (control means), 12 is a CCD camera (camera), 13 is a visual recognition device (storage means, image processing means), 14 is a camera control device (camera control means), and W is a work ( Object).

   ─────────────────────────────────────────────────── ─── Continued front page    (72) Inventor Takashi Naito             Aichi Prefecture Nagachite Town Aichi District             Ground 1 Toyota Central Research Institute Co., Ltd. F term (reference) 3C007 AS06 BS12 HS27 KS21 KT00                       KT01 KT06 KT11 KV01 MT04                 5B047 AA13 BB04 BC05 BC14 CA17                       CB23 DC06                 5B057 AA05 BA02 BA17 DA07 DB03                       DC03 DC04 DC05 DC08 DC33                       DC36 DC39                 5C022 AB01 AB12 AB21 AC42 AC51                       AC69 AC74 AC78

Claims (6)

[Claims] 1. A camera attached to a robot arm, and a feature amount on an image when the object is photographed by the camera in a state where the robot arm is preliminarily positioned at a teaching target position for the object such as a work. Image processing for processing the photographed image data of the object photographed by the camera to obtain the feature amount on the current image as the current data, and calculating an error from the target data. A robot controller comprising: a means for controlling the position and orientation of the robot arm so as to reduce the error based on the error obtained by the image processing means. The camera is configured to include an optical system adjusting unit that adjusts the optical condition at the time of shooting, and the camera allows the pair to be adjusted. Robot control apparatus characterized by comprising a camera control means for controlling the optical system adjusting means of the camera based on the captured image data obtained by photographing the object. 2. The optical system adjusting means includes a focal length changing mechanism, and the camera controlling means controls the focal length changing mechanism so that the entire image of the object falls within the field of view of the camera. The robot controller according to claim 1, characterized in that: 3. The storage means stores a plurality of target data whose focal length is changed in a plurality of steps by the focal length changing mechanism, and the image processing means is controlled by the camera control means. The robot controller according to claim 2, wherein an error of the current data is calculated using the target data corresponding to the focal length. 4. The optical system adjusting means includes a focus adjusting mechanism, and the camera controlling means controls the focus adjusting mechanism so as to photograph an object with the same focus as when the target data is stored. The robot controller according to any one of claims 1 to 3, characterized in that: 5. The optical system adjusting means includes an aperture adjusting mechanism, and the camera control means controls the aperture adjusting mechanism so that an exposure condition equivalent to that when the target data is stored is obtained. The robot controller according to any one of claims 1 to 4. 6. The optical system adjusting means includes AD gain adjusting means for adjusting the AD gain of the image data of the camera, and the camera controlling means has an exposure condition equivalent to that when the target data is stored. 5. The robot controller according to claim 1, wherein the AD gain adjusting means is controlled as described above.