JPH0970786A - Holding hand - Google Patents

Abstract

PROBLEM TO BE SOLVED: To realize the positioning of high precision by providing on a holding hand a plurality of holding members to hold a work and a photographing means whose photographing direction is same as the holding direction which is provided between a plurality of holding members to directly reflect the positioning by the image recognition in the positioning of the holding hand. SOLUTION: In order to hold a work W to realize the automatic assembly using a holding hand 2, a robot arm 1 is moved to the holding position, the work is photographed by a CCD camera 6 provided on the holding hand 2, the photographed image is incorporated in an image processing device 7, the characteristic quantity and points of the work are detected based on the information on the incorporated image in the image processing device 7, and the image recognition is achieved to recognize the location, shape and position of the work W. A robot controller 8 moves the position of the holding hand 2 through the rotation, parallel displacement, etc., of the robot arm 1 according to the information on the obtained location, shape and position of the work.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a gripping hand, and more particularly to a gripping hand that is provided at the tip of a robot arm and grips an object to be gripped.

[0002]

2. Description of the Related Art In automatic assembly work using a robot, it is necessary to perform relative positioning between a hand and an object with high precision. Therefore, there are cases where it is difficult to deal with changes in positioning accuracy over time, variations in parts, and the like.

Therefore, as described in Japanese Utility Model Laid-Open No. 61-105594, a first distance sensor that operates when the robot hand approaches a predetermined distance from the work in the main body of the robot hand, and the hand. Is provided with a second distance sensor that operates when the gripping member of the robot approaches a predetermined distance with respect to the workpiece, and moves the robot hand at high speed until the hand approaches the workpiece, and at low speed after approaching the predetermined distance. There are things I tried to get closer.

Further, as described in Japanese Utility Model Laid-Open No. 5-2894, a camera is attached on the end effector at the tip of the robot arm to detect a photographing pattern attached to an assembly object, and the area and center of gravity of the pattern are detected. There is a method in which the movement path of the arm is determined by calculating the distance and direction of the arm tip with respect to the assembly object by measuring.

[0005]

However, the above-mentioned robot hand provided with the distance sensor is provided with other detecting means for performing presence / absence and characteristics of the object to be grasped and positioning in the horizontal plane. It is necessary to perform high-precision positioning. Further, in the case where the imaging device is attached to the tip of the robot arm, it is impossible to perform the positioning and the recognition at the same time, and in order to perform the positioning and the recognition at the same time, the imaging device is placed toward the gripping member of the hand. I have to incline only at an angle,
In this case, the gripping direction (generally the z direction)
It becomes impossible to deal with the change of.

[0006]

In order to solve the above-mentioned problems, the gripping hand according to claim 1 is provided at the tip of a robot arm and grips an object to be gripped.
The gripping hand is configured to have a plurality of gripping members that grip the gripping target object, and an image capturing unit that is provided between the plurality of gripping members and has an imaging direction that is the same as the gripping direction.

A gripping hand according to a second aspect is the gripping hand according to the first aspect, wherein the plurality of gripping means are members that sandwich the gripping object from both sides, and the image pickup means is located at the center between the plurality of gripping members. Prepared for the configuration.

According to a third aspect of the present invention, there is provided a grasping hand according to the first or second aspect, in which at least one of the plurality of grasping members is fixed.

According to a fourth aspect of the present invention, there is provided a gripping hand according to the first or second aspect, which has the plurality of gripping members having different functions.

The gripping hand of claim 5 is the gripping hand of claim 1 or 2, wherein the plurality of gripping members are slidably provided.

According to a sixth aspect of the present invention, there is provided a grasping hand according to the third aspect, wherein a grasping member other than the fixed grasping member of the plurality of grasping members is slidably provided.

According to a seventh aspect of the present invention, there is provided a grasping hand according to any one of the first to sixth aspects, wherein the tip end portion of the grasping member is provided with an illuminating means for illuminating the grasped object.

The gripping hand of claim 8 is the gripping hand of claim 7, further comprising means for changing the position and / or the posture of the gripping member in accordance with the imaging result of the imaging means.

According to a ninth aspect of the present invention, there is provided a gripping hand according to any one of the first to eighth aspects, further comprising illumination means for illuminating the object to be gripped around the image pickup means.

According to a tenth aspect of the present invention, there is provided a gripping hand according to the first aspect.
In any one of the gripping hands, the image pickup unit has an image forming unit having a fixed focus, and the image forming unit has an image pickup surface when the gripping member is at the height of the gripping target portion of the gripping target. It is configured to have a focal length that forms an image at.

The gripping hand of claim 11 is the same as that of claim 1 described above.
In the gripping hand of 0, the image pickup means is provided so as to be able to move forward and backward, and the driving means for moving the image pickup means forward and backward is provided.

A gripping hand according to a twelfth aspect is the above-mentioned first aspect.
In any one of the gripping hands of Nos. 9 to 9, the image pickup unit has an autofocus image forming unit.

A gripping hand according to a thirteenth aspect is the above-mentioned first aspect.
In each of the gripping hands of any one of 1 to 12, the plurality of gripping members are formed with an escape portion for avoiding contact with the image pickup means in the closest state.

A gripping hand according to a fourteenth aspect is the above-mentioned one.
In any one of the gripping hands, a storage unit for storing the image pickup unit is provided, and the image pickup unit can be moved back and forth between an image pickup position for picking up the gripping target and a position stored in the storage unit. A drive means for moving the image pickup means forward and backward is provided.

[0020]

BEST MODE FOR CARRYING OUT THE INVENTION Embodiments of the present invention will be described below with reference to the accompanying drawings. FIG. 1 is an explanatory view showing a first embodiment of the present invention. A gripping hand 2 is attached to the tip of the robot arm 1. In this gripping hand 2, two gripping members 4 and 5 are attached to a hand main body 3 so as to be swingable in the directions indicated by the arrows, and claw portions 4a and 5a are formed at the tips of these gripping members 4 and 5, A gripping unit that grips and grips the gripping target W from both sides is configured. Although not shown, a hand driving device using an electromagnetic valve, a motor or the like for opening and closing the holding members 4 and 5 is provided.

Further, the gripping hand 2 is provided with a CCD camera 6 as an image pickup means in which the image pickup direction is the same as the gripping direction (here, the z direction) between the two gripping members 4 and 5. . An image processing device 7 that takes in the image pickup information of the CCD camera 6 and performs processing such as image recognition,
Based on the processing result of the image processing apparatus 7, the robot arm 1 is rotated and moved in parallel to position the gripping hand 2, and the other robot arm 1 and the gripping hand 2 are positioned.
The robot controller 8 performs control necessary for general gripping operations such as opening and closing of the robot.

In order to grip the object W to be gripped for performing automatic assembly or the like using the gripping hand 2 configured as described above, after moving the robot arm 1 to the gripping position as shown in FIG. Alternatively, the CCD camera 6 provided in the gripping hand 2 while moving the robot arm 1 to the gripping position.
The gripping target W is imaged by, the captured image is captured in the image processing device 7, and the image processing device 7 detects the feature amount, the feature point, and the like of the gripping target W based on the captured image information, Image recognition processing for recognizing the position, shape, posture, etc. of the grasped object W is performed.

Then, the robot controller 8 rotates or moves the robot arm 1 in parallel according to the information such as the position, shape, and orientation of the grasped object W obtained by the image recognition processing by the image processing device 7. , A hand position correction process of moving the position of the gripping hand 2 according to the position, shape, posture, etc. of the gripping target W is performed.

In this manner, the gripping hand 2 is grasped by repeating the process of correcting the position of the grasping hand 2 in real time while recognizing the grasping object W based on the captured image obtained from the CCD camera 6. The gripping members 4 and 5 of the gripping hand 2 are driven by positioning the gripping members 4 and 5 at an optimum gripping position with respect to W, and claw portions 4a and 5a thereof are driven.
The object W to be gripped is sandwiched and gripped from both sides.

In this case, the CCD camera 6 holds the object W to be grasped.
Is imaged and the gripping hand 2 is positioned based on the imaging result, so that the gripping hand 2 can be positioned with high accuracy, and the influence of variations in the gripping target W, positioning error of the gripping target W, and the like. The gripping target W can be gripped without receiving the grip.

Further, since the CCD camera 6 as the image pickup means is provided between the gripping members 4 and 5 of the gripping hand 2, the gripping target object W is still present in the screen of the image pickup means. The gripping hand 2 can be positioned in real time while detecting the characteristic amount and the characteristic point of W and performing positioning by image recognition, and the positioning completion position (recognition / correction completion position) by image processing is gripped by the gripping hand 2. It becomes possible to match the operation start position, the positioning by image recognition can be directly reflected in the positioning of the gripping hand 2, and the relative positioning accuracy between the gripping target W and the gripping hand 2 can be improved. I can. Furthermore, it becomes possible to detect in advance the direction in which the gripping target W should not come into contact with the gripping hand 2,
The precision and quality of gripping can be improved.

In this way, the gripping members 4 of the gripping hand 2 are
By arranging the image pickup means (CCD camera 6) between the five so that the gripping direction and the image pickup direction are the same and reducing the offset amount between the gripping hand and the image pickup means, the gripping target W
Can be recognized and positioned at the same time, the positioning accuracy of the gripping hand 2 can be improved and gripping errors can be reduced, and the gripping members 4, 5 in the imaging direction can be improved.
It is possible to cope with the position change of the (holding hand 2).

FIG. 3 is an explanatory view showing the second embodiment of the present invention. In this embodiment, the CCD camera 6 of the first embodiment is attached to the center of the two gripping members 4 and 5 of the gripping hand 2.

In this way, by mounting the CCD camera 6 in the center between the two gripping members 4 and 5 of the gripping hand 2, when gripping the gripping target W by the same operation as in the first embodiment, the image At the time of positioning by recognition, it is possible to perform the positioning without causing the distortion of the peripheral image by the image forming means attached to the CCD camera 6 to the respective gripping members 4 and 5.

That is, when the object W to be grasped is sandwiched and grasped from both sides by the grasping members 4 and 5,
For example, as shown by a virtual line in FIG.
When the camera 6'is provided at a position other than the center between the gripping members 4 and 5, when the gripping target W is located in the center between the gripping members 4 and 5, the CCD camera 6'takes an image with a broken line in FIG. Although it is performed in the image pickup area as shown, in this case, the influence of the distortion of the peripheral portion of the image plane by the image forming means attached to the CCD camera cannot be ignored. Further, when the object to be grasped is directly below the image pickup means, the influence of the distortion of the image is reduced, but in order to accurately grasp the object to be grasped, the grasping hand (or the grasping member) must be moved by a certain distance. There is a risk that the positioning accuracy will be reduced.

On the other hand, the image pickup means is used as the gripping members 4, 5
When the gripping target W is sandwiched and gripped by sandwiching the gripping target W from both sides by disposing it in the center of the space, the distortion of the peripheral portion of the image by the image forming means attached to the image pickup means is offset to both gripping members 4 and 5. The positioning accuracy of both gripping members 4, 5
Can be secured evenly.

FIG. 4 is an explanatory view showing the third embodiment of the present invention. In this embodiment, one of the two gripping members 4, 5 of the gripping hand 2 of the first embodiment is integrally formed with the hand main body 3 to form a fixed gripping member, and this gripping member 5 is fixed. A CCD camera 6 as an image pickup means is attached to the hand main body 3 with a certain offset amount based on the grip member 5.

In the gripping hand 2 thus configured, the image picked up by the CCD camera 6 is captured and the gripping hand 2 is positioned by image recognition with the fixed gripping member 5 as a reference. When the object to be grasped is grasped, the object to be grasped is abutted against the stationary grasping member 5 by the movable grasping member 4, and the object is repositioned and grasped.

As described above, by using at least one gripping member 5 of the plurality of gripping members 4 and 5 of the gripping hand 2 as a fixed gripping member, the relative positioning accuracy between the gripping hand 2 and the image pickup means is fixed. It can be improved by using the member as a reference, and the offset amount can be clarified,
Since the position of the object to be grasped also depends on the positioning of the mechanical abutting, compared to the case where the grasping member rotates from both sides to sandwich and grasp the object to be grasped, the mechanical force at the time of grasping is increased. The occurrence of backlash is suppressed, the difference between the position of the gripping target detected by image processing and the position of the gripping target after gripping is reduced, and the repeatability of gripping can be improved.

5, 6 and 7 are an explanatory view showing a fourth embodiment of the present invention and a side view thereof. In this embodiment, the hand body 3 of the gripping hand 2 includes two sets of gripping members 14 and 15 and gripping members 16 and 17 having different functions.

In the gripping hand 2 configured as described above, the image picked up by the CCD camera 6 is captured, the size of the gripping target is recognized and discriminated by image recognition, and the gripping member to be used is selected according to the recognition result. For example, as shown in FIG. 5, when the object to be gripped is WA, the gripping members 14, 1
5 is used for gripping, and when the object is a gripping target WB, gripping members 16, 17 are used for gripping.

By thus providing one gripping hand with a plurality of gripping members having different functions, the features such as the position, shape, size and direction of the gripping target are recognized and distinguished from the image picked up by the image pickup means, The gripping member corresponding to the gripping target can be selected and gripped, and one gripping hand can appropriately grip a plurality of types of gripping target. Further, as a result, for example, a gripping member that grips a small gripping target may damage a large gripping target, or a gripping member that grips a large gripping target may grip a small gripping target. It is possible to avoid a situation such as an attempt to drop it.

FIG. 8 is an explanatory view showing the fifth embodiment of the present invention. In this embodiment, the hand body 3 of the gripping hand 2
Attach slide members 18 and 19 slidably to
By attaching the gripping members 4 and 5 to the slide members 18 and 19, the gripping members 4 and 5 are slidable, and a driving unit 21 including a pulse motor or the like for sliding the slide members 18 and 19 on the hand body 3 is provided. , 22 are provided.

In the gripping hand 2 configured as described above, the gripping target W is imaged by the CCD camera 6, and the size and position of the gripping target are detected by image recognition.
The grippers 4 and 5 are moved by a distance corresponding to the gripping target W by driving the driving units 21 and 22 to grip the gripping target W.

In this way, the gripping members 4, 5 of the gripping hand 2 are
By making the slide type, the position and size of the grasped object are detected by using image recognition, the position of the grasping hand 2 is adjusted from the detected position of the grasped object, and the detected size of the grasped object. By adjusting the opening and closing of the gripping members 4 and 5, it is possible to grip a plurality of types of gripping target objects having different sizes by one set of gripping members 4 and 5. Further, since the size of the object to be grasped can be recognized, the grasping members 4, 5
By adjusting the movement distance of the gripping object, the gripping target can be gripped without applying an extra force, and the gripping members 4, 5,
It is possible to prevent the object to be gripped and the gripping hand 2 from being damaged.

FIG. 9 is an explanatory view showing a sixth embodiment of the present invention. In this embodiment, the two gripping members 4, 5 of the gripping hand 2 are combined by combining the third embodiment and the fifth embodiment.
One of the gripping members 5 is integrally formed with the hand main body 3 to form a fixed gripping member, and the fixed gripping member 5 is used as a reference with a certain offset amount, and the CCD camera 6 serving as an imaging unit. Attach to the hand body 3,
Further, the other gripping member 4 is attached to a slide member 18 slidably attached to the hand body 3 to make it a slide type, and the hand body 3 is provided with a drive unit 21 such as a pulse motor for sliding the slide member 18. .

In the gripping hand 2 configured as described above, the image picked up by the CCD camera 6 is captured, and the size and position of the gripping target W is detected based on the fixed gripping member 5 by image recognition, and the driving unit 21 is operated. Is driven to move the gripping member 4 by a distance corresponding to the gripping target W to grip the gripping target W.

As described above, by using one of the plurality of gripping members 4 and 5 of the gripping hand 2 as a fixed gripping member and the other as a sliding type gripping member, the third embodiment and the fifth embodiment described above.
The effect of the embodiment is obtained, and a plurality of types of gripping objects having different sizes can be gripped with an appropriate gripping force after positioning, and gripping with different sizes by gripping with a fixed gripping member as a reference. It is possible to unify the positioning reference points for the object, reduce errors such as mechanical rattling at the time of gripping, directly reflect the positioning by image recognition to the grip, and perform highly accurate positioning. Can be gripped.

FIG. 10 is an explanatory view showing the seventh embodiment of the present invention. In this embodiment, the gripping members 24 and 25 are attached to the hand body 3 of the gripping hand 2, and the gripping members 2
Multiple LEDs that irradiate the object to be grasped at the tip of 4, 25
Illumination means consisting of 26 is provided.

In the gripping hand 2 configured as described above, the gripping object is imaged by the CCD camera 6 while illuminating the gripping object by the plurality of LEDs 26, and the gripping hand 2 is positioned by the image recognition based on the imaging result. The gripping members 24 and 25 grip the gripping target member.

In this way, the gripping member 24 of the gripping hand 2,
By providing an illumination means at the tip of 25, it is possible to prevent the shadow of the gripping members 24, 25, etc. from being formed on the gripping target object by the environmental illumination, and reduce the influence of this shadow on imaging, image recognition, and positioning. As a result, highly accurate positioning can be performed. In addition, the gripping member 24,
By providing the illuminating means at the tip of 25, the illuminating means moves together with the gripping members 24 and 25, so that one illuminating means can illuminate a plurality of places.

In this case, the robot controller 8 opens and closes the gripping members 24 and 25 according to the image recognition result obtained from the image pickup result of the CCD camera 6 to change the position and the posture of the gripping member. 24, 2
The irradiation direction from the illumination means provided at the tip of 5 changes, and a clearer image of the grasped object can be obtained. By doing so, image recognition and positioning accuracy are further improved.

FIG. 11 is an explanatory view showing the eighth embodiment of the present invention. In this embodiment, the gripping members 24 and 25 are attached to the hand body 3 of the gripping hand 2, and the gripping members 2
Multiple LEDs that irradiate the object to be grasped at the tip of 4, 25
In addition to providing the illuminating means consisting of 26, the illuminating means comprising a plurality of LEDs 27 arranged around the CCD camera 6 of the hand body 3.

In the gripping hand 2 thus configured, the gripping target 2 is imaged by the CCD camera 6 while illuminating the gripping target by the plurality of LEDs 26 and LEDs 27, and the gripping hand 2 is positioned by the image recognition based on the imaging result. Then, the object to be grasped is grasped by the grasping members 24 and 25.

By thus providing the illuminating means around the image pickup means, when a short focus lens is used for the image pickup means in the image forming system, or an automatic focus image pickup system (image forming system) is used. In this case, since it is necessary to perform positioning after the gripping object comes close to the space between the gripping members, the lighting effect is weak only with the environmental lighting or the lighting means at the tip of the gripping member, and the gripping member is surrounded by the gripping members. Although a clear image of the grasped object cannot be obtained in a dark environment, even in such a case, the grasped object can be illuminated by the illumination means between the grasping members, and a clear image of the grasped object can be obtained. It is possible,
Image recognition and positioning accuracy can be maintained and improved.

FIG. 12 is an explanatory view showing the ninth embodiment of the present invention. In this embodiment, the CCD camera 30 in which the fixed focus lens 30a is attached to the hand body 3 of the gripping hand 2
It has. Then, the focal length x of the fixed focus lens of the CCD camera 30 is set to the holding member 4 of the holding hand 2.
The gripping target portion W of the gripping target object W
The distance is set to form an image on the image pickup surface when the height is a or wb.

In the gripping hand 2 configured as described above, when the gripping hand 2 approaches the gripping target W, C
When the image captured by the CD camera 30 is processed by the image processing device 7, the image is subjected to Laplacian filter processing to obtain the difference between the highest pixel value and the lowest pixel value of the image as the sharpness of the edge portion, and the peak Is detected and the robot controller 1 drives and controls the robot arm 1 so that the imaging distance matches the focal length x, and when the imaging distance matches the focal length x, the gripping members 4 and 5 are driven to grasp the gripping target W. By gripping, the gripping members 4 and 5 accurately grip the gripping target portions Wa and Wb of the gripping target object W.

As described above, the image pickup means has an image forming means having a fixed focus, and the image forming means indicates the focal length which forms an image on the image pickup surface when the gripping member is at the height of the gripping target portion of the gripping target. By having such a structure, it is possible to avoid occurrence of variations in height of the gripping target, gripping errors due to mechanical operation errors, collision / damage between the gripping hand and the gripping target, and incomplete gripping. As a result, the positioning accuracy of the gripping hand can be improved not only in the horizontal plane but also in the height direction (the direction on the line connecting the gripping hand and the gripping target).

FIG. 13 is an explanatory view showing the tenth embodiment of the present invention. In this embodiment, the gripping hand 2 is provided with the CCD camera 30 of the ninth embodiment so as to be able to move up and down, and a drive motor 3 for driving the CCD camera 30 up and down.
1 and so on.

In the gripping hand 2 configured as described above, three types of gripping target objects WC, WC, in which the heights of the gripping target portions Wa, Wb are different according to the height of the gripping target object, for example, as shown in FIG. When gripping a CD or CE, the gripping member 4,
The drive motor 31 causes the CCD camera 30 to form an image at the focal length x when the claw portions 4a and 5a of the reference numeral 5 match the gripping target portions Wa and Wb of the gripping target objects WC, CD, and CE.
Up and down.

Then, as described in the ninth embodiment, when the gripping hand 2 approaches the gripping target W, C
When the image processing device 7 performs image processing on the captured image from the CD camera 30, the robot arm 1 is drive-controlled so that the captured distance matches the focal length x.
When the gripping objects 4 and 5 are matched, the gripping target W is driven.
By gripping the object to be gripped by the gripping members 4 and 5,
The gripping target portions Wa and Wb of WD and WE are accurately gripped.

As described above, the image pickup means has an image forming means having a fixed focus, and the image forming means indicates the focal length for forming an image on the image pickup surface when the gripping member is at the height of the gripping target portion of the gripping target. Further, by providing the image pickup means so as to be able to move forward and backward, and by providing the driving means for moving the image pickup means forward and backward, from the upper surface of the gripping target object when the gripping members 4 and 5 are at a portion for gripping the gripping target object. By adjusting the position of the image pickup means so that the distance to the image pickup means becomes the image formation position (focusing position) of the image formation means, accurate positioning is performed for a plurality of types of gripping objects having different heights. Therefore, it is possible to surely grip.

FIG. 14 is an explanatory view showing the eleventh embodiment of the present invention. In this embodiment, the hand body 3 of the gripping hand 2 is provided with the gripping members 34 and 35, and the autofocus lens 32a is mounted between the gripping members 34 and 35.
A CD camera 32 is provided.

In the gripping hand 2 configured as described above, image recognition is performed from the image picked up by the CCD camera 32 to position the gripping hand 2 as in the above-described embodiments, and the gripping members 34 and 35 are closed and gripped. The object is gripped, but at this time, even if the gripping hand 2 is moved in the imaging direction after the gripping hand 2 is positioned in a plane perpendicular to the imaging direction, the automatic focusing mechanism of the CCD camera 32 sequentially Since the image is in focus, a clear image of the object to be grasped can be obtained, and image recognition based on this clear image and positioning of the grasping hand 2 can be performed.

Further, when the parts are assembled using the gripping hand 2, for example, the ring-shaped member WF held by the gripping members 34 and 35 by moving the gripping hand 2 in the z direction is a shaft member WG. In the case of mounting on, the gripping hand 2 is moved linearly in the axial direction, so that the focal length of the CCD camera 32 changes with the movement, and the center coordinates of the shaft member WG is detected by the image processing device 7, and The ring-shaped member WF can be accurately attached to the shaft member WG by moving the gripping hand 2 while correcting the position of the gripping hand 2 so as not to cause a positional deviation.

As described above, by providing the autofocus image forming means as the image pickup means, a clear image of the gripping target object can be obtained even when the gripping hand 2 is moved in the image pickup direction, and the gripping target object and the gripping target object are grasped. The gripping hand 2 can be moved while maintaining an optimum relative position with the hand 2.
It is possible to improve the linear accuracy of movement in the image pickup direction.

FIG. 15 is an explanatory diagram showing a twelfth embodiment of the present invention. In this embodiment, when the gripping members 34, 35 are closest to the inside of the gripping members 34, 35 of the gripping hand 2, the escape groove 34a, which is an escape portion, prevents the gripping members 34, 35 from coming into contact with the CCD camera 32. , 35a are formed. The configuration of this embodiment can be applied to each of the above embodiments.

In the gripping hand 2 configured as described above, for example, when the gripping members 34 and 35 fail to grip an object to be gripped and the gripping members 34 and 35 come closest to each other, or the external shape is smaller than that of the CCD camera 32. When grasping the object to be grasped, the CCD camera 32 is sandwiched between the grasping members 34 and 35, and the CCD camera 32 and the grasping members 34 and 3 are inserted.
5. The gripping hand 2 is prevented from being damaged.

FIG. 16 is an explanatory diagram showing a thirteenth embodiment of the present invention. In this embodiment, a camera housing 36 for housing the CCD camera 32 is provided in the gripping hand 2 and the robot arm 1, and the CCD camera 32 is provided so as to be able to move up and down (advance and retreat). A drive motor 37, which is a drive means for moving forward and backward (up and down) with respect to the storage position, is provided. The configuration of this embodiment can be applied to each of the above embodiments.

In the gripping hand 2 constructed as described above, the CCD camera 32 is retracted and retracted by the drive motor 37 into the camera housing 34 before the gripping members 34 and 35 grip the object to be gripped. . As a result, the gripping members 4, 5 fail to grip the gripping target, and the gripping members 34,
When 35 is closest, or CCD camera 3
When gripping a gripping object having an outer shape smaller than 2, C
C by sandwiching the CD camera 32 between the gripping members 34 and 35
The CD camera 32, the gripping members 34 and 35, and the gripping hand 2 are prevented from being damaged, and generally, the shape of the gripping member is not limited, and the interference between the imaging unit and the gripping member can be avoided.

[0066]

As described above, according to the gripping hand of claim 1, a plurality of gripping members for gripping a gripping target object, and an imaging direction provided between the gripping members are the same as the gripping direction. Since it has means, it is possible to grip without being affected by variations in gripping objects, position errors, and the like, and it is possible to match the positioning completion position of the gripping hand by image processing with the gripping start position. The positioning by recognition can be directly reflected in the positioning of the gripping hand, and highly accurate positioning can be performed.

According to the gripping hand of claim 2, in the gripping hand of claim 1, the plurality of gripping means are members for sandwiching the object to be gripped from both sides, and the image pickup means is provided in the center between the plurality of gripping members. Therefore, the distortion of the peripheral portion of the image of the image forming means attached to the image pickup means is not biased to any one of the plurality of gripping members, and any of the plurality of gripping members can be positioned with high accuracy. .

According to the gripping hand of claim 3, in the gripping hand of claim 1 or 2, since at least one gripping member of the plurality of gripping members is fixed, positioning is performed with the fixed gripping member as a reference. Can be done,
It is possible to reduce the change in the relative position between the gripping member and the image pickup means due to mechanical backlash over time, and it is possible to perform stable and highly accurate positioning and improve the positioning accuracy.

According to the gripping hand of claim 4, in the gripping hand of claim 1 or 2, since the gripping hand has a plurality of gripping members having different functions, gripping according to the gripping target object by image recognition using the image pickup means. A member can be selected, and a plurality of types of gripping objects with different characteristics such as size, shape, direction, and position can be gripped with one gripping hand, and a gripping error or damage to the gripping object due to it The situation can be prevented.

According to the gripping hand of claim 5, in the gripping hand of claim 1 or 2, since a plurality of gripping members are provided slidably, a plurality of types of gripping members having different sizes are formed by one set of gripping members. The object can be grasped, and an appropriate grasping force for the grasped object can be set, so that the grasping member, the grasped object, the grasping hand, and the like can be prevented from being damaged.

According to the gripping hand of claim 6, in the gripping hand of claim 3, a gripping member other than the fixed gripping member of the plurality of gripping members is slidably provided. The object to be grasped can be grasped by one grasping hand, and it is possible to prevent a situation such as a grasping error and a damage to the object to be grasped due to the mistake.
It is possible to set an appropriate gripping force for the object to be gripped and prevent damage to the gripping member, the object to be gripped, the gripping hand, and the like.

According to the gripping hand of claim 7, in the gripping hand of any one of claims 1 to 6, the tip end portion of the gripping member is provided with an illuminating means for illuminating the gripping object, so that the gripping hand depends on the environmental lighting. Without doing so, it is possible to illuminate a plurality of places with the illumination means that moves with the hand, the captured image of the grasped object becomes clear, and the image recognition and the hand positioning accuracy therewith are improved.

According to the gripping hand of claim 8, the gripping hand of claim 7 is provided with means for changing the position and / or the posture of the gripping member in accordance with the image pickup result of the image pickup means. Can be obtained, the captured image of the grasped object becomes clear, and the image recognition and the positioning accuracy of the hand thereby are improved.

According to the gripping hand of claim 9, the gripping hand according to any one of claims 1 to 8 is provided with an illuminating means for illuminating the gripping object around the image pickup means. Even when the object is present between the gripping members, the object to be gripped can be illuminated, the captured image of the object to be grasped becomes clear, and image recognition and hand positioning accuracy thereby are improved.

According to the gripping hand of claim 10, in the gripping hand according to any one of claims 1 to 9, the image pickup means has an image forming means having a fixed focus, and the image forming means has a grasping member to be grasped. Since it has a focal length that forms an image on the imaging surface when it is at the height of the object to be grasped, it avoids a grasping error or a collision between the grasping hand and the grasping object due to variations in the height direction of the grasping object. Thus, the positioning accuracy of the gripping member can be improved not only in the horizontal plane but also in the height direction.

According to the gripping hand of claim 11, in the gripping hand of claim 10, the image pickup means is provided so as to be movable back and forth, and the driving means for moving the image pickup means forward and backward is provided. It becomes possible to adjust the position of the image pickup device so that the distance from the upper surface of the object to be grasped to the image pickup device when it is in a region for holding an object becomes a focal point distance. The object can be grasped accurately.

According to the gripping hand of claim 12, in the gripping hand of any one of claims 1 to 9, the image pickup means has an image forming means for autofocusing. Therefore, even when the gripping hand is moved in the image pickup direction. A clear image of the gripping target can be obtained, the gripping hand can be moved while maintaining the optimum relative position between the gripping target and the gripping hand, and the movement accuracy of the gripping hand in the imaging direction can be improved. .

According to the gripping hand of claim 13, in the gripping hand of any one of claims 1 to 12, a plurality of gripping members are provided with relief portions for avoiding contact with the image pickup means in the closest state. Therefore, even when the grasped object fails to be grasped or the outer shape of the grasped object is smaller than the image capturing means, it is possible to prevent the grasping member, the image capturing means and the like from being damaged by sandwiching the image capturing means between the grasping members.

According to the gripping hand of claim 14, in the gripping hand of any one of claims 1 to 12, a storage portion for accommodating the image pickup means is provided, and the image pickup means and the image pickup position for picking up an image of the object to be grasped. Since the drive means is provided so as to be able to move forward and backward with respect to the position stored in the storage section and to move the image pickup means forward and backward, the image pickup means is retracted into the storage section immediately before the gripping member grips the object to be gripped. Therefore, it is possible to prevent the interference between the gripping member and the imaging means regardless of the shape of the gripping member or the size of the gripping target.

[Brief description of drawings]

FIG. 1 is an explanatory diagram showing a first embodiment of the present invention.

FIG. 2 is an operation flow chart for explaining the operation of the first embodiment.

FIG. 3 is an explanatory diagram showing a second embodiment of the present invention.

FIG. 4 is an explanatory diagram showing a third embodiment of the present invention.

FIG. 5 is an explanatory diagram showing a fourth embodiment of the present invention.

6 is an explanatory side view of FIG.

FIG. 7 is a bottom view of FIG.

FIG. 8 is an explanatory diagram showing a fifth embodiment of the present invention.

FIG. 9 is an explanatory diagram showing a sixth embodiment of the present invention.

FIG. 10 is an explanatory diagram showing a seventh embodiment of the present invention.

FIG. 11 is an explanatory diagram showing an eighth embodiment of the present invention.

FIG. 12 is an explanatory diagram showing a ninth embodiment of the present invention.

FIG. 13 is an explanatory view showing a tenth embodiment of the present invention.

FIG. 14 is an explanatory diagram showing an eleventh embodiment of the present invention.

FIG. 15 is an explanatory diagram showing a twelfth embodiment of the present invention.

FIG. 16 is an explanatory diagram showing a thirteenth embodiment of the present invention.

[Explanation of symbols]

1 ... Robot arm, 2 ... Grip hand, 3 ... Hand body, 4, 5, 14, 15, 16, 17, 24, 25, 3
4, 35 ... Gripping member, 6, 30, 32 ... CCD camera,
7 ... Image processing device, 8 ... Robot controller, 18,
19 ... Sliding member 21, 22 ... Driving unit, 26, 27
... LED, 30a ... Fixed focus lens, 32a ... Auto focus lens.

Claims (14)

[Claims] 1. A gripping hand, which is provided at a tip of a robot arm and grips an object to be gripped, the gripping hand includes a plurality of gripping members for gripping the object to be gripped, and imaging provided between the gripping members. A gripping hand having an image pickup means whose direction is the same as the gripping direction. 2. The gripping hand according to claim 1,
A gripping hand, characterized in that the plurality of gripping means comprises members for sandwiching the gripping target from both sides, and the image pickup means is provided at the center between the plurality of gripping members. 3. The gripping hand according to claim 1, wherein at least one gripping member of the plurality of gripping members is fixed. 4. The gripping hand according to claim 1, wherein the gripping hand has the plurality of gripping members having different functions. 5. The gripping hand according to claim 1, wherein the plurality of gripping members are slidably provided. 6. The gripping hand according to claim 3,
A gripping hand, wherein a gripping member other than the fixed gripping member of the plurality of gripping members is provided slidably. 7. The gripping hand according to claim 1, further comprising illumination means for illuminating the gripping target object at a tip portion of the gripping member. 8. The gripping hand according to claim 7,
A gripping hand comprising means for changing the position and / or the posture of the gripping member according to the imaging result of the imaging means. 9. The gripping hand according to claim 1, further comprising illumination means around the image pickup means for illuminating the gripping target. 10. The gripping hand according to claim 1, wherein the image pickup unit has an image forming unit having a fixed focus, and the image forming unit includes a gripping member for gripping an object to be gripped. A gripping hand having a focal length that forms an image on an imaging surface when at a height of a part. 11. The gripping hand according to claim 10, wherein the image pickup means is provided so as to be able to move forward and backward, and a drive means for moving the image pickup means forward and backward is provided. 12. The gripping hand according to any one of claims 1 to 9, wherein the imaging unit has an image forming unit for autofocus. 13. The gripping hand according to any one of claims 1 to 12, wherein the plurality of gripping members are formed with an escape portion for avoiding contact with the imaging means in the closest state. A gripping hand. 14. The gripping hand according to claim 1, further comprising a storage section for storing the image pickup means, and storing the image pickup means in an image pickup position for picking up an image of the gripping target and the storage section. The gripping hand is provided so as to be able to advance and retreat to and from the position where the image pickup means is moved.