JP6776385B2 - Control method, control device and control system for robot arm with robot hand - Google Patents

Description

The present invention relates to a method, an apparatus and a system for controlling a robot arm with a robot hand based on information on characteristic values of a bundle of paper sheets (for example, a state such as thickness and damage).

In the past, "a banknote processing device using a robot arm with a robot hand" has been proposed (for example, Japanese Patent Application Laid-Open No. 62-92095). In such a bill processing device, after the bill bundle is taken out from the bill storage box by the robot arm with a robot hand, it is conveyed to the bill counting bill confirmation unit, and the bill counting bill confirmation unit sorts the bill bundle by denomination. The number of sheets for each denomination is counted. Then, the banknote bundles sorted by denomination are transported to a predetermined position by a robot arm with a robot hand, which is different for each denomination.

Japanese Unexamined Patent Publication No. 62-92095

By the way, conventionally, a robot hand is made to grab a bundle of paper leaves stored in a box that stores a bundle of paper leaves such as a bundle of banknotes (hereinafter referred to as a "paper leaf bundle storage box"), and the robot hand is held by a robot arm. When the paper leaf bundle was pulled out from the paper leaf bundle storage box by retreating, the paper leaf bundle may collapse or a part of the paper leaf bundle may fall off from the robot hand.

An object of the present invention is that when a paper leaf bundle is pulled out from a paper leaf bundle storage box by a robot arm with a robot hand, the paper leaf bundle may collapse or a part of the paper leaf bundle may fall off from the robot hand. The purpose is to reduce the risk of

The robot arm control system with a robot hand according to the first aspect of the present invention includes a robot arm with a robot hand, an imaging device, and a control device. The control device has a storage unit, an acquisition unit, a derivation unit, and a control unit. The image information of the paper leaf bundle is stored in the storage unit in association with the information of the damage state index value indicating the damaged state of the paper leaf bundle. The acquisition unit acquires image information of a bundle of paper sheets from the image pickup apparatus. The derivation unit collates the image information of the paper leaf bundle acquired in the acquisition unit with the image information of the paper leaf bundle stored in the storage unit, and derives the damage state index value information. The control unit controls the operation of the robot arm with the robot hand based on the information of the damage state index value derived by the derivation unit.

By the way, in general, the smaller the damaged state of the paper leaf bundle, the better the slip between the paper leaves, and as a result, the paper leaf bundle may collapse or a part of the paper leaf bundle may fall off. Is high. On the other hand, in this system, the movements of the robot hand and the robot arm can be controlled according to the damaged state of the bundle of paper sheets. Then, in this system, for example, if the gripping pressure and the gripping allowance of the robot hand are increased as the damaged state of the paper leaf bundle is smaller, the paper leaf bundle is taken out from the paper leaf bundle storage box. It is possible to reduce the risk that a part of the paper leaf bundle will fall off from the robot hand.

The robot arm control system with a robot hand according to the second aspect of the present invention is the robot arm control system with a robot hand according to the first aspect, and the robot hands have a pair of fingers facing each other. Then, the control unit shortens the distance between the fingers when the robot hand grips the bundle of paper leaves as the damage state index value approaches a value indicating that the damage state is small.

The robot arm control system with a robot hand according to the third aspect of the present invention is the robot arm control system with a robot hand according to the first aspect, and the robot hands have a pair of fingers facing each other. Further, in this robot arm control system, a pressure sensor is provided on at least one finger of the pair of fingers. Then, the control unit controls the finger so that the value indicated by the pressure sensor becomes larger as the damage state index value approaches the value indicating that the damage state is smaller.

The robot arm control system with a robot hand according to the fourth aspect of the present invention is a robot arm control system with a robot hand according to any one of the first to third phases, and the control unit is a damage state index. As the value approaches the value indicating that the damaged state is large, at least one of the moving speed and the moving acceleration of the robot hand when grasping the bundle of paper leaves is lowered.

The robot arm control system with a robot hand according to the fifth aspect of the present invention is the robot arm control system with a robot hand according to the fourth aspect, and the moving speed is the backward speed and the moving acceleration is the backward acceleration.

The robot arm control system with a robot hand according to the sixth aspect of the present invention is a robot arm control system with a robot hand according to any one of the first to fifth aspects, and the control unit is a paper leaf. After the robot hand grips the bundle of paper leaves contained in the bundle storage box, the robot hand is retracted by a certain distance, the bundle of paper leaves is pulled out by a certain length, and then the bundle of paper leaves is released. When controlling the robot hand to grip the pulled-out paper bundle bundle again, the closer the damage state index value is to the value indicating that the damaged state is large, the more the paper leaf bundle is pulled out. Increase at least one of the allowance and the gripping allowance at the time of re-grasping.

The robot arm control device with a robot hand according to the seventh aspect of the present invention includes a storage unit, an acquisition unit, a derivation unit, and a control unit. The image information of the paper leaf bundle is stored in the storage unit in association with the information of the damage state index value indicating the damaged state of the paper leaf bundle. The acquisition unit acquires image information of a bundle of paper leaves. The derivation unit collates the image information of the paper leaf bundle acquired in the acquisition unit with the image information of the paper leaf bundle stored in the storage unit, and derives the damage state index value information. The control unit controls the operation of the robot arm with the robot hand based on the information of the damage state index value derived by the derivation unit.

Therefore, this robot arm control device with a robot hand can cause the robot hand and the robot arm to perform an operation in consideration of a damaged state of a bundle of paper sheets. Therefore, in this robot arm control device with a robot hand, a part of the paper leaf bundle falls off from the robot hand when the robot arm with the robot hand is made to pull out the paper leaf bundle from the paper leaf bundle storage box. It is possible to reduce the risk of spilling.

The robot arm control method with a robot hand according to the eighth aspect of the present invention includes an acquisition step, a derivation step, and a control step. In the acquisition step, the image information of the paper leaf bundle is acquired. In the derivation step, (a) the image information of the paper leaf bundle is stored in the storage unit in association with the information of the damage state index value indicating the damaged state of the paper leaf bundle. And (b) the image information of the paper leaf bundle acquired in the acquisition step is collated, and the information of the damage state index value is derived. In the control step , the operation of the robot arm with the robot hand is controlled based on the information of the damage state index value derived in the derivation step .

By the way, in general, the smaller the damaged state of the paper leaf bundle, the better the slip between the paper leaves, and as a result, the paper leaf bundle may collapse or a part of the paper leaf bundle may fall off. Is high. On the other hand , in this robot arm control method with a robot hand, the robot hand and the robot arm can be made to perform an operation in consideration of a damaged state of a bundle of paper sheets. Therefore, by implementing this robot arm control method with a robot hand, a part of the paper leaf bundle falls off from the robot hand when the paper leaf bundle is pulled out from the paper leaf bundle storage box by the robot arm with the robot hand. It is possible to reduce the risk of spilling.

It is a schematic block diagram of the robot arm control system with a robot hand which concerns on embodiment of this invention. It is a perspective view of the robot hand which concerns on embodiment of this invention. It is a right side view of the pressing part standby state of the robot hand which concerns on embodiment of this invention. It is a right side view of the push portion protruding state of the robot hand which concerns on embodiment of this invention. It is an image diagram of the control table stored in the storage part of the control device which concerns on embodiment of this invention. It is a perspective view of the paper leaf bundle storage box which stores the banknote bundle extracted by the robot hand which concerns on embodiment of this invention. It is sectional drawing which shows the state when the banknote bundle is placed on the place tray of the banknote organizer by the robot hand which concerns on embodiment of this invention. It is a perspective view which shows the state of the slide receiving part when the finger part of the robot hand is inserted into the paper leaf bundle storage box in embodiment of this invention. It is a perspective view which shows the state of the slide receiving part at the time of pulling out the finger part of the robot hand from the paper leaf bundle storage box in embodiment of this invention. It is a schematic block diagram of the image data forming apparatus for character determination of the paper leaf bundle which concerns on embodiment of this invention. It is an image diagram of the program and the database stored in the storage of the image data forming apparatus for character determination of the paper leaf bundle which concerns on embodiment of this invention. It is a figure explaining the operation of the image data forming apparatus for character determination of the paper leaf bundle which concerns on embodiment of this invention. It is an image diagram of the main table stored in the storage of the image data forming apparatus for character determination of the paper leaf bundle which concerns on embodiment of this invention. It is an image diagram of the image processing data table stored in the storage of the image data forming apparatus for character determination of the paper leaf bundle which concerns on embodiment of this invention. It is the schematic for demonstrating the function of the thickness derivation module of the image data forming apparatus for character determination of the paper leaf bundle which concerns on embodiment of this invention. In this figure, the figure on the side (a) shows the original actual image data, and the figure on the side (b) shows the processed image data. It is a schematic diagram for demonstrating the function of the 1st state index value derivation module of the image data forming apparatus for character determination of the paper leaf bundle which concerns on embodiment of this invention. In this figure, the figure on the (c) side shows the actual image data, and the figure on the (d) side shows the processed image data.

As shown in FIG. 1, the robot arm control system 500 with a robot hand according to the embodiment of the present invention is mainly composed of a robot hand 100, a robot arm RA, an image pickup device DC, and a control device 400. In the embodiment of the present invention, the robot hand 100 is fixed to the tip of the robot arm RA, and hereinafter, this may be referred to as a "robot arm with a robot hand". Further, in the embodiment of the present invention, the imaging device DC is arranged on the robot hand 100. Hereinafter, the components of the robot arm control system 500 with a robot hand will be described in detail.

(1) Robot Arm with Robot Hand The robot arm with a robot hand according to the embodiment of the present invention is mainly composed of a robot hand 100 and a robot arm RA, as shown in FIGS. 2 to 4.
Hereinafter, these components will be described in detail.

(1-1) Robot Hand As shown in FIG. 2, the robot hand 100 according to the embodiment of the present invention is a two-finger type robot hand, which is fixed to the tip of the robot arm RA. Then, as shown in FIG. 2, the robot hand 100 mainly includes a movable finger 110, a fixed finger 120, a movable finger reciprocating mechanism 130, a pressing portion 140, a pressing portion reciprocating mechanism 150, and a slide receiving portion. It is composed of 160, a slide receiving portion urging member 170, and a connecting portion 180. Hereinafter, these components will be described in detail.

(1-1-1) Movable Finger The movable finger 110 is formed from a base 111 and a claw 112 as shown in FIG. The base portion 111 is a substantially trapezoidal thick plate portion. The claw portion 112 is an elongated rectangular thick plate portion, and extends forward from the side surface on the short side side of the base portion 111. The movable finger 110 is fixed to the elevating plate 132 (described later) on the long side side of the base 111 of the movable finger reciprocating mechanism 130.

(1-1-2) Fixed Finger The fixed finger 120 is formed from a base portion 121 and a claw portion 122 as shown in FIG. The base 121 is a rectangular plank portion. The claw portion 122 is an elongated rectangular plank portion, and extends forward from the front central side surface of the base portion 121. That is, the fixed finger 120 is a thick plate member that exhibits a convex shape in a plan view. The fixed finger 120 is fixed to the support plate 131 (described later) of the movable finger reciprocating mechanism 130. Then, as shown in FIG. 2, the fixed finger 120 faces the movable finger 110 in the reciprocating direction of the movable finger 110.

(1-1-3) Movable finger reciprocating mechanism The movable finger reciprocating mechanism 130 mainly includes a support plate 131, an elevating plate 132, an air cylinder mechanism 133, and an elevating table 134, as shown in FIGS. It is composed of. The support plate 131 supports the air cylinder mechanism 133. The air cylinder mechanism 133 is a double-acting type and is a drive source for raising and lowering the elevating table 134. The air cylinder mechanism 133 is attached to the support plate 131 as described above. An elevating plate 132 is attached to the elevating table 134. That is, the air cylinder mechanism 133 raises and lowers the elevating plate 132 by raising and lowering the elevating table 134. Further, the air cylinder mechanism 133 is provided with air supply / exhaust ports 135 and 136 as shown in FIGS. 3 and 4. An air air supply / exhaust pipe (not shown) is connected to the air air supply / exhaust ports 135 and 136.

(1-1-4) Pressing portion As shown in FIGS. 2 to 4, the pressing portion 140 is a substantially concave plate-shaped member, and the standing portions RU on both sides extend toward the movable finger side. As described above, it is attached to the connecting piece 152b (described later) of the piston 152 (described later) of the pressing portion reciprocating mechanism 150. Then, the pressing portion 140 can be reciprocated along the front-rear direction by the pressing portion reciprocating mechanism 150.

(1-1-5) Pushing portion reciprocating mechanism The pressing portion reciprocating mechanism 150 is a double-acting air cylinder mechanism for reciprocating the pressing portion 140 along the front-rear direction, and is shown in FIG. As shown in FIG. 4, it is mainly composed of a cylinder block 151, a piston 152, an air supply / exhaust port 153, and a knob 154. The cylinder block 151 is a substantially rectangular parallelepiped member, and is joined to the side opposite to the movable finger of the fixed finger 120 as shown in FIG. Two rows of cylinder holes (not shown) are formed inside the cylinder block 151 along the longitudinal direction. The piston 152 is formed of a pair of pistons 152a and a connecting piece 152b. The pair of pistons 152a extend in parallel from one surface of the connecting piece 152b in the same direction. The pair of pistons 152a are inserted into the two rows of cylinder holes, respectively. The above-mentioned pressing portion 140 is joined to the side of the connecting piece 152b opposite to the piston extending side. One air supply / exhaust port 153 is provided on each side. An air supply / exhaust pipe (not shown) is connected to each of these air supply / exhaust ports 153. The knob 154 is attached to each air air supply / exhaust port 153. The knob 154 is a member for adjusting the air supply amount or the exhaust amount, and can adjust the elevating speed of the elevating table 134, that is, the elevating speed of the elevating plate 132. It is preferable that the knob 154 adjusts the displacement from the viewpoint of ease of speed adjustment (difficulty of occurrence of speed unevenness).

By configuring the pressing portion reciprocating mechanism 150 as described above, the pressing portion 140 can be reciprocated along the front-rear direction by introducing and exhausting air. As a result, the robot hand 100 can be switched between the pressing portion standby state shown in FIG. 3 and the pressing portion protruding state shown in FIG.

(1-1-6) Slide receiving portion The slide receiving portion 160 is a pair of long and thin rectangular thick plate members arranged on both sides of the claw portion 122 of the fixed finger 120 as shown in FIG. , Is urged forward by the slide receiving portion urging member 170 described later. Further, the upper surface of the tip of the slide receiving portion 160 exists on the surface including the upper surface of the tip of the claw portion 122 of the fixed finger 120 (the surface on the side facing the movable finger 110). Here, the upper surface of the tip of the slide receiving portion 160 may be located slightly below the upper surface of the tip of the claw portion 122 of the fixed finger 120.

(1-1-7) Slide receiving portion urging mechanism The slide receiving portion urging member 170 is a tension coil spring, and is on both sides of the claw portion 122 of the fixed finger 120 as shown in FIG. It is arranged on the rear side of the slide receiving portion 160 and urges the slide receiving portion 160 toward the front. That is, if the slide receiving portion 160 is pushed backward and then the slide receiving portion 160 is released, the slide receiving portion 160 is pushed back to the initial position by the slide receiving portion urging member 170.

(1-1-8) Connecting portion The connecting portion 180 is a portion for connecting the robot hand 100 to the robot arm RA, for example, a flange or the like.

(1-2) Robot Arm The robot arm RA is, for example, an existing multi-axis robot arm.

(2) Imaging device The imaging device DC is, for example, a digital camera such as a CCD camera, and is a support extending from a support plate 131 of a movable finger reciprocating mechanism 130 of the robot hand 100 as shown in FIGS. It is fixed to the right side of the movable finger reciprocating mechanism 130 by the arm SA. The image pickup device DC transmits electronic data of an image taken while intermittently taking a picture to the control device 400.

(3) Control device As shown in FIG. 1, the control device 400 is mainly composed of a control unit 410, a lead-out unit 430, a storage unit 420, and an acquisition unit 440. Hereinafter, these components will be described in detail.

(3-1) Control unit The control unit 410 is, for example, a control device of a central processing calculation device of a computer, and is communicated and connected to a robot arm RA, a robot hand 100, and an imaging device DC as shown in FIG. By transmitting various control signals to the robot arm RA, the robot hand 100, and the imaging device DC, the operation of the robot arm RA and the robot hand 100 and the imaging process of the imaging device DC are controlled. As shown in FIG. 1, the control unit 410 transmits a control signal to the robot arm RA, the robot hand 100, and the image pickup device DC according to a command described in the control program stored in the storage unit 420. Data necessary for generating a control signal is read from at least one of the storage unit 420 and the derivation unit 430, and a control signal is generated from the data and transmitted to the robot arm RA, the robot hand 100, and the imaging device DC.

(3-2) Derivation unit The derivation unit 430 is, for example, an arithmetic unit of a central processing arithmetic unit of a computer, and as shown in FIG. 1, data stored in the storage unit 420 and an acquisition unit 440. It is responsible for generating data necessary for generating a control signal from the data transmitted from the computer and supplying the data to the control unit 410. For example, the derivation unit 430 receives the image data sent from the image pickup apparatus DC via the acquisition unit 440, collates the image data with the image data Dt2 in the control table (described later) To0, and collates the image. The thickness data Dt4 and the state index value data Dt5 corresponding to the image data Dt2 that most closely matches the data Dt2 are derived, and the data Dt4 and Dt5 are transmitted to the control unit 410. When deriving the state index value data Dt5, the state index value may be derived from the image data Dt2 by using machine learning or the like represented by deep learning.

(3-3) Storage unit The storage unit 420 stores a control program, control parameters, a control table, and the like. The control table includes the control table To0 shown in FIG. The control table To0 is created, for example, by the image data forming device 1 for determining the characteristics of the bundle of paper sheets, which will be described later. Here, the bundle of paper leaves is, for example, a bundle of banknotes (bundle of bills) or the like. As shown in FIG. 5, the control table To0 is mainly provided with an ID field Fo1, an image field Fo2, a thickness field Fo3, and a state index value field Fo4. Unique numerical data (hereinafter referred to as ID data) Dt1 attached to each record is stored in the ID field Fo1. In the image field Fo2, a plurality of front image data (hereinafter, referred to as image data) Dt2 of 200 paper leaf bundle storage boxes (described later) 200 for storing paper leaf bundles having various thicknesses and states are stored. In this image, the front door (described later) 220 of the paper leaf bundle storage box 200 is opened, and one side of the paper leaf bundle having various thicknesses and states can be visually recognized. .. Further, in the front image of the paper leaf bundle storage box 200, in addition to the paper leaf bundle, the front frame of the housing (described later) 210 of the paper leaf bundle storage box 200, the upper support plate (described later) 230, and the lower side. A side support plate (described later) 240 and the like are included. In the thickness field Fo3, data (hereinafter, referred to as thickness data) Dt4 of the thickness of the bundle of paper sheets corresponding to the image data Dt2 is stored. In the state index value field Fo4, the state index value data (hereinafter referred to as the state index value data) Dt5 of the bundle of paper sheets corresponding to the image data Dt2 is stored. It should be noted that this state index value is an index value of 0 to 1 indicating damage such as wrinkles and scratches on the bundle of paper leaves, and the less the damage is, the more there is no gap between the paper leaves. It becomes close to 1. Then, the data Dt1, Dt2, Dt4, Dt5 input to the above-mentioned fields Fo1 to Fo4 are associated with each record (for each row of the main table To0 in FIG. 5), and constitute a data set. There is.

(3-4) Acquisition unit The acquisition unit 440 is, for example, a communication interface of a computer or the like, and has a role of sending the image data obtained by the image pickup apparatus DC to the derivation unit 430 as shown in FIG. There is.

<Control example of a robot arm with a robot hand according to an embodiment of the present invention>
Here, as an example, an example will be described in which a robot arm with a robot hand according to the present embodiment pulls out a banknote bundle from a paper leaf bundle storage box and moves the banknote bundle to a loading tray of a banknote organizer. Here, as an example of the paper leaf bundle storage box, the paper leaf bundle storage box 200 shown in FIG. 6 is adopted, and as an example of the mounting tray of the bill sorting machine, the bill sorting machine shown in FIG. 7 is used. A mounting tray 320 of 300 is adopted. It should be noted that this example does not limit the present invention.

Prior to the description of the control example of the robot arm with the robot hand, the paper leaf bundle storage box 200 and the bill organizer 300 will be briefly described below. As shown in FIG. 6, the paper leaf bundle storage box 200 is mainly composed of a housing 210, a front door 220, an upper support plate 230, and a lower support plate 240. As shown in FIG. 6, the housing 210 is a rectangular parallelepiped box body that opens to the front side. The front door 220 is a substantially rectangular plate member, and is pivotally supported on the upper side of the opening edge of the housing 210 via an opening / closing mechanism such as a hinge. The upper support plate 230 is a member that holds the banknote bundle MT in cooperation with the lower support plate 240, and as shown in FIG. 6, the upper support plate 230 can be moved up and down slightly upward from the center in the height direction of the housing 210. It is arranged in. Further, a semicircular notch Rs is formed in the center of the front side of the upper support plate 230. The lower support plate 240 is a member that holds the banknote bundle MT in cooperation with the upper support plate 230, and is fixed to the lower side of the housing 210 as shown in FIG. Further, a slit Rt is formed in the center of the lower support plate 240 in the width direction. Then, in the paper leaf bundle storage box 200, the upper support plate 230 is urged downward by an urging member (coil spring or the like) arranged on the upper side thereof. That is, the banknote bundle MT housed in the paper leaf bundle storage box 200 is pressed against the lower support plate 240 by the upper support plate 230.

The banknote organizer 300 is a device that counts various denominations while sorting the banknote bundle MT stored in the paper leaf bundle storage box 200 by denomination, and as shown in FIG. 7, the main body 310 and the mounting tray. It consists of 320. The main body 310 is provided with a bill sorting mechanism that counts various denominations while sorting the bill bundle MT supplied from the mounting tray 320 by denomination. The loading tray 320 is a tray for mounting the bill bundle MT, and is arranged beside the bill sucking mechanism of the bill organizing mechanism. That is, when the presence of the banknote bundle MT placed on the loading tray 320 is recognized by the banknote detection sensor of the banknote suction mechanism of the banknote sorting mechanism, the bill stack MT is automatically sucked into the bill sorting mechanism by the bill suction device. I will go.

When the robot arm with a robot hand extracts the banknote bundle MT in the paper leaf bundle storage box 200 and moves it to the loading tray 320 of the banknote organizer 300, the operation of the robot arm with the robot hand is controlled as follows. ..

First, the control device 400 controls the operation of the robot arm RA to move the robot hand 100 to a specified position and direct it in a specified direction. Here, the specified position is the position on the front side of the paper leaf bundle storage box 200, and the specified direction is the direction in which the image pickup apparatus DC can image the front surface of the paper leaf bundle storage box 200.

Next, when the robot hand 100 is moved to the specified position, the control device 400 transmits an imaging command signal to the imaging device DC to cause the imaging device DC to capture a front image of the paper leaf bundle storage box 200. At this time, the front door 220 of the paper leaf bundle storage box 200 is in the open state. By the way, at this time, the paper leaf bundle storage box 200 also needs to be placed at the specified position so as to face the specified direction, but the paper leaf bundle storage box 200 is moved to the specified position and is oriented in the specified direction. The work may be performed automatically by a conveyor, another robot arm with a robot hand, or the like, or may be performed manually. Further, the unlocking / opening process of the front door 220 of the paper leaf bundle storage box 200 may be realized by another robot arm with a robot hand that is communication-connected to the control device 400, and is performed manually. May be good. Then, the image pickup device DC transmits the front image data of the paper leaf bundle storage box 200 to the out-licensing unit 430 via the acquisition unit 440.

When the derivation unit 430 receives the front image data of the paper leaf bundle storage box 200, the derivation unit 430 collates the front image data with the image data Dt2 in the control table To0, and the image that most closely matches the image data. The thickness data Dt4 and the state index value data Dt5 corresponding to the data Dt2 are derived, and the data Dt4 and Dt5 are transmitted to the control unit 410. Then, the control unit 410 uses these data Dt4 and Dt5 to execute the control described in the following places on the robot hand 100 and the robot arm RA.

Next, the control unit 410 controls the robot arm RA and the robot hand 100 to raise the movable finger 110 to the position (thickness of the banknote bundle MT + α), and then fixes the finger 120 in the slit Rt of the lower support plate 240. Insert the tip of the. At this time, the movable finger 110 is located above the notch Rs of the upper support plate 230. Further, at this time, as shown in FIG. 8, the slide receiving portion 160 abuts on the wall portions on both sides of the slit Rt of the lower support plate 240 and retracts.

Subsequently, the control device 400 moves the movable finger 110 downward to grip the banknote bundle MT together with the fixed finger 120. At this stage, the control device 400 may control the descent distance of the movable finger 110 and the gripping pressure of the robot hand 100 by using the thickness data Dt4 and the state index value data Dt5. As specific control contents, for example, (i) the descent distance of the movable finger 110 is (thickness of banknote bundle MT + α-β (however, β> α)), and the thicker the banknote bundle MT, the more the banknote. As the state index value of the bundle MT increases, or as the thickness of the banknote bundle MT increases and the state index value of the banknote bundle MT increases, the value of β increases, and (ii) the movable finger 110 and A pressure sensor is provided on at least one of the fixed fingers 120, and the thicker the banknote bundle MT, the larger the state index value of the banknote bundle MT, or the thicker the banknote bundle MT and the state of the banknote bundle MT. The larger the index value, the higher the pressure sensor value at the completion of gripping. In such a case, the thickness of the banknote bundle MT and the state index value may be divided in stages, and the β value and the pressure sensor value at the completion of gripping may be specified in each stage.

Further, the control device 400 controls the operation of the robot arm RA to retract the robot hand 100 and pull out the banknote bundle MT from the paper leaf bundle storage box 200. At this time, as shown in FIG. 9, the slide receiving portion 160 is moved forward as the robot hand 100 retracts. At this stage, the control device 400 may control at least one of the retreat speed and the retreat acceleration of the robot hand 100 by using the thickness data Dt4 and the state index value data Dt5. Specific control contents include, for example, the thicker the banknote bundle MT, the smaller the state index value of the banknote bundle MT, or the thicker the banknote bundle MT and the state index value of the banknote bundle MT. As the value becomes smaller, at least one of the retreat speed and the retreat acceleration may be lowered. In such a case, the thickness of the banknote bundle MT and the state index value may be divided in stages, and the retreat speed and the retreat acceleration of the robot hand 100 may be defined in each stage.

Subsequently, the control device 400 controls the robot arm RA to insert the robot hand 100 from the tip side to the back side of the loading tray 320 of the banknote organizer 300 as shown in FIG. The pressing portion reciprocating mechanism 150 is operated to move the pressing portion 140 forward, and the movable finger reciprocating mechanism 130 is controlled to pull up the movable finger 110 upward to release the banknote bundle MT. In the transfer stage from the completion of the drawing process of the banknote bundle MT to the completion of the transfer process to the banknote organizer 300, the control device 400 uses the thickness data Dt4 and the state index value data Dt5 to move the robot hand 100 and the moving speed. At least one of the accelerations may be controlled. Specific control contents include, for example, the thicker the banknote bundle MT, the smaller the state index value of the banknote bundle MT, or the thicker the banknote bundle MT and the state index value of the banknote bundle MT. As the value becomes smaller, at least one of the moving speed and the moving acceleration may be lowered. In such a case, the thickness of the banknote bundle MT and the state index value of the banknote bundle MT may be divided stepwise, and the moving speed and moving acceleration of the robot hand 100 may be defined at each step.

Then, while the pressing portion 140 is moving forward, the control device 400 controls the robot arm RA and pulls up the robot hand 100 diagonally backward while maintaining the tilt angle of the robot hand 100. Let me. By this operation, the transfer of the banknote bundle MT to the loading tray 320 of the banknote organizer 300 is completed. After the transfer of the banknote bundle MT is completed, the control device 400 controls the operation of the robot arm RA while operating the pressing portion reciprocating mechanism 150 to pull the pressing portion 140 backward, and positions the robot hand 100 at a specified position. Move to and point in the specified direction. After that, as described above, the banknote bundle MT is extracted from the next paper leaf bundle storage box 200 transported to the same position, and the banknote bundle MT is conveyed to the loading tray 320 of the banknote organizer 300.

<Example of creating a control table>
The control table To0 is generated by, for example, an image data forming apparatus for determining the characteristics of a bundle of paper sheets described below.

<Configuration of image data forming device for determining the characteristics of paper leaf bundles>
The image data forming device 1 for determining the characteristics of a bundle of paper sheets is a so-called electronic computer (computer), and mainly includes a main body 10, an input device 31, and a display 32, as shown in FIG. Hereinafter, the operation of the image data forming apparatus 1 for determining the characteristics of the paper leaf bundle will be described after the components are described in detail.

<Components of the image data forming device for determining the characteristics of paper leaf bundles>
(1) Main body As shown in FIG. 10, the main body 10 is mainly composed of a central processing unit 11, a main memory 13, a storage 14, a connection unit 12, an STR interface 15, an input interface 16, and a DSP interface 17. There is. Then, as shown in FIG. 10, in the main body 10, the central processing unit 11 passes through the first bus line 21, the main memory 13 passes through the second bus line 22, and the various interfaces 15 to 17 are third. It is connected to the connection portion 12 via the bus line 23. Hereinafter, these components will be described.

(1-1) Central Processing Unit The central processing unit 11 is, for example, a semiconductor chip called a microprocessor, and is mainly composed of a control unit 11A and a calculation unit 11B (note that the central processing unit 11 includes the central processing unit 11). May also include a primary cache memory, a secondary cache memory, and the like).

(1-2) Main memory The main memory 13 is, for example, a volatile high-speed memory such as a RAM (random access memory).

(1-3) Connection part The connection part 12 is a semiconductor chip such as a chipset.

(1-4) Storage The storage 14 is an auxiliary storage device such as a hard disk drive or a solid state drive. Then, as shown in FIG. 11, the storage 14 stores programs such as an operating system 14a, a device driver 14b, and an image data forming application 14c for determining the characteristics of a bundle of paper sheets. The storage 14 is not limited to the built-in type, and may be an external type.

The operating system 14a is, for example, WINDOWS (registered trademark), MAC OS (registered trademark), OS / 2, UNIX (registered trademark) (for example, Linux (registered trademark), etc.), BeOS (registered trademark), or the like. , Each part 12-14, various interfaces 15-17, each device 31, 32, etc., provides a user interface, manages various data, processes common parts of various applications, and the like.

The device driver 14b is a dedicated program prepared for each of the storage 14, the connection unit 12, and the devices 31 and 32, and the operating system 14a controls the storage 14, the connection unit 12, and the devices 31 and 32. It plays the role of bridging the way.

The image data forming application 14c for determining the characteristics of a bundle of paper leaves is a program that generates big data for deep learning, and is mainly a basic module 14f, an image processing module 14g, a thickness derivation module 14h, and a first state index value. It is composed of a derivation module 14i and a database 14j.

In each of the above-mentioned modules 14f to 14i, various instructions for causing the central processing unit 11 to perform various processing are described. For example, in the basic module 14f, a) an input page display command for displaying an input page for inputting data necessary for creating a basic data set on the display 32, and b) a data set (described later) from the database 14j. A data call command to be called, c) a data set registration command for converting the output from the image processing module 14g, the thickness derivation module 14h, and the first state index value derivation module 14i into a data set and registering them in the database 14j are described. Further, in the image processing module 14g, an image expansion / contraction command, an image replacement command, and the like, which will be described later, are described. In the thickness derivation module 14h, a conversion thickness calculation command or the like for calculating the conversion thickness, which will be described later, is described. In the first state index value derivation module 14i, a processing state index value calculation command or the like for calculating the first state index value Dt5'described later is described.

The main table To1 shown in FIG. 13 and the image processing data table To2 shown in FIG. 14 are stored in the database 14j. As shown in FIG. 13, the main table To1 is mainly provided with a first ID field Fo11, an image field Fo12, an area field Fo13, a thickness field Fo14, and a first state index value field Fo15. In the first ID field Fo11, unique numerical data (hereinafter, referred to as the first ID data) Dt11 attached to each record is stored. The image field Fo12 stores the actual image data (hereinafter, referred to as basic actual image data) Dt12 of the front surface of the paper leaf bundle storage box 200 when the front door 220 is opened, which will be described later in FIG. .. The actual image of the front of the paper leaf bundle storage box includes the front frame of the housing 210 of the paper leaf bundle and the paper leaf bundle storage box 200, the upper support plate 230, the lower support plate 240, and the like. It has been. In the area field Fo13, the area data (hereinafter, referred to as the paper leaf bundle area data) Dt13 of the paper leaf bundle in the basic real image data Dt12 is stored. The area data Dt13 is trimmed image data of the corresponding basic image data, and is composed of only an image of a bundle of paper leaves. In the thickness field Fo14, the thickness data (hereinafter referred to as thickness data) Dt14 of the paper bundle bundle corresponding to the paper leaf bundle region data Dt13 is stored. In the first state index value field Fo15, data of the state index value of the bundle of paper leaves (hereinafter, referred to as the first state index value data) Dt15 is stored. In addition, this state index value is an index value of 0 to 1 indicating damage such as wrinkles and damages of a bundle of paper leaves, and the less the damage is, the more there is no gap between the paper leaves. It becomes close to 1 (note that the gap between the paper leaves is judged from the color of the actual image, etc.). The data Dt11 to Dt15 input to each of the above-mentioned fields Fo11 to Fo15 are associated with each record (each row of the main table To1 in FIG. 13), and constitute a data set.

As shown in FIG. 14, the image processing data table To2 is mainly provided with a second ID field Fo21, a replacement image field Fo22, and a second state index value field Fo23. In the second ID field Fo21, unique numerical data (hereinafter referred to as second ID data) Dt21 attached to each record is stored. The replacement image field Fo22 stores the replacement image data Dt22 used in the image processing module 14g. As the replacement image data Dt22, replacement image data Dt22a to Dt22e for various state index values are registered (see FIG. 16). The replacement image data Dt22 may be created by image composition, or may be created by cutting out a part of the basic real image data Dt12. In the second state index value field Fo23, the state index value data (hereinafter, referred to as the second state index value data) Dt23 corresponding to the above-mentioned replacement image is stored. The second state index value is an index value of 0 to 1 indicating damage such as wrinkles and scratches on the bundle of paper sheets as in the first state index value, and the less the damage is, the more. The closer there is no gap between the paper leaves, the closer to 1. The data Dt21 to Dt23 input to the above-mentioned fields Fo21 to Fo23 are associated with each record (each row of the image processing data table To2 in FIG. 14), and constitute a data set. ..

(1-5) Interface The STR interface 15 is an interface for an auxiliary storage device such as IDE (Integrated Drive Electronics) or Serial ATA, and connects the storage 14 to the connection unit 12. The input interface 16 is, for example, an interface such as PS / 2, USB, IEEE1284, RS232 or IrDA (Infrared Data Association), and is a keyboard, mouse, scanner, or OCR (Optical) for inputting data to the main memory 13. An input device 31 such as Character Reader) or the like is connected. The DSP interface 17 is, for example, an interface such as AGP (Accelerated Graphics Port), PCI (Peripheral Component Interconnect), or RS232, and is a CRT display for displaying data transmitted from the main memory 13 as characters or images. , A display 32 such as a liquid crystal display or a plasma display is connected.

(1-6) Operation of Image Data Forming Device for Determining the Characteristics of Paper Bundles Next, the operation of the image data forming apparatus 1 for determining the characteristics of the bundles of paper will be described with reference to FIG.

As shown in FIG. 12, the control unit 11A reads a program temporarily stored in the main memory 13 (see Fd6), and instructs each unit 13 and 14 and each device 31 and 32 to operate according to the read program (Fc1). ~ Fc5). The arithmetic unit 11B acquires necessary data from the main memory 13 (see Fd2) according to the instruction of the control unit 11A, and performs arithmetic processing (for example, arithmetic operation processing, logical operation processing, etc.). The main memory 13 acquires programs, data, and the like from the storage 14 (see Fd4) and temporarily stores the data, temporarily stores the data input by the input device 31 (see Fd1), and is transmitted from the arithmetic unit 11B. Data etc. (see Fd3) are temporarily stored. Further, the main memory 13 transmits data or the like temporarily stored in response to a command from the control unit 11A to the units 11 and 14 and the display 32 (see Fd2, Fd5, Fd6 and Fd7). The storage 14 supplies programs, data, and the like to the main memory 13 in response to an instruction from the control unit 11A (see Fd4), and stores data and the like transmitted from the main memory 13 (see Fd5).

(2) Input device The input device 30 is, for example, an input device such as a keyboard, a mouse, a scanner, or an OCR (Optical Character Reader).

(3) Display The display 32 is an information display device such as a CRT display, a liquid crystal display, or a plasma display.

<Data set multiplication method by image data formation application for character determination of paper leaf bundles>
As described above, the image data forming application 14c for determining the characteristics of the paper leaf bundle according to the embodiment of the present invention is a program that artificially generates big data for machine learning represented by deep learning. The image data forming application 14c for determining the characteristics of the bundle of paper sheets performs data processing on the data set of the main table To1 stored in the database 14j, and then uses the processed data set as a new data set. The data set is propagated by storing it in the table To1. Hereinafter, this data set multiplication process will be described in detail.

(1) Preparation of various data constituting the data set First, a person who intends to propagate the data set of the main table To1 using the image data forming application 14c for determining the characteristics of the bundle of paper sheets (hereinafter, "user"). ) Is a method in which a bundle of paper leaves to which the thickness is measured and the first state index value is given is stored in a specified position of the paper leaf bundle storage box 200 with the front door open, and then in that state. The paper leaf bundle storage box 200 is imaged from the front side with a fixed point digital camera (not shown), and the actual image data of the front of the paper leaf bundle storage box 200 including the paper leaf bundle (hereinafter referred to as "real image data"). Abbreviated.) Is obtained. Here, when assigning the first state index value, for example, it is preferable to use the average value of subjective evaluation by a large number of people. Next, the user trims a portion of the actual image other than the paper leaf bundle using an image editing application or the like to obtain the area image data of the paper leaf bundle (hereinafter, this is referred to as "area data"). create. Then, each time the user changes the thickness or state of the paper bundle, the thickness of the paper bundle is measured, the first state index value is given to the paper bundle, and the data is further changed. After obtaining the basic actual image data Dt12, the area data Dt13 is created. That is, a plurality of types of data sets including basic real image data Dt12, area data Dt13, thickness data Dt14, and first state index value data Dt15 are prepared. Here, the above-mentioned thickness measurement of the paper leaf bundle, the assignment of the first state index value to the paper leaf bundle, and the acquisition of the front image data of the paper leaf bundle storage box 200 including the paper leaf bundle are in no particular order. It doesn't matter if it is done.

Then, the user inputs the above-mentioned four types of data into the main table To1 as much as possible in units of data sets by using the input device 31 and the display 32. This completes the preparation. The various data described above may be input to the main table To1 by the user each time they are obtained.

(2) Automatic data set breeding process When the above preparation is completed and the automatic data set breeding process is started in the image data forming application 14c for determining the characteristics of the paper leaf bundle, a new data set is automatically propagated as follows. The dataset is propagated. Here, the basic module 14f, the image processing module 14g, the thickness derivation module 14h, and the first state index value derivation module 14i play the main roles. The basic module 14f reads the data set from the main table To1 of the database 14j, reads the data set from the image processing data table To2, and then further reads the basic actual image data Dt12 in the data set of the main table To1. , The image processing module 14g is made to process the basic actual image data Dt12. The image processing module 14g processes the basic actual image data Dt12 to create processed image data Dt12'for deriving the thickness data Dt14', or the processed image data Dt12 for deriving the first state index value data Dt15'. 'Create. The order in which the data set is read and the order in which the image data for data derivation is created may be regular or irregular. The image processing module 14g further processes the processed image data Dt12'processed by the image processing module 14g to create the processed image data Dt12'for deriving the thickness data Dt14', or the first state index value. Processed image data Dt12'for deriving the data Dt15' may be created. Then, the thickness derivation module 14h derives the thickness data Dt14'at the time of creating an image for deriving the thickness data Dt14', and the first state index value derivation module 14i creates an image for deriving the first state index value data Dt15'. Occasionally, the first state index value data Dt15'is derived. Therefore, in the following, the details of the automatic data set multiplication process will be described separately for the derivation of the thickness data Dt14'and the derivation of the first state index value data Dt15'.

(2-1) Image data creation and thickness data derivation for thickness data derivation Hereinafter, image data creation and thickness data derivation for thickness data derivation will be described with reference to FIG. In addition, in FIG. 15, both (a) and (b) are views of the paper leaf bundle storage box CB viewed from the front, but (a) shows the original actual image data Dt12, and (b). ) Indicates the processed image data Dt12'. That is, in FIG. 15, the region data Dt13 in the data set is stretched at a predetermined magnification along the vertical direction. In the figure, the code "OL" indicates the thickness of the paper leaf bundle corresponding to the area data Dt13 in the original real image data, and the code "ML" indicates the thickness of the paper leaf bundle corresponding to the area data Dt13'in the processed image data. The thickness is indicated, and the symbol "MD" indicates the moving distance of the presser foot portion PD before and after processing. The presser foot portion PD is composed of, for example, the upper support plate 230 and an urging member (coil spring or the like) arranged above the upper support plate 230 in the paper leaf bundle storage box 210 implemented in FIG.

First, the image processing module 14g performs processing to stretch the area data Dt13 in the data set along the vertical direction at a predetermined magnification (= ML / OL) (see FIG. 15). Here, the image processing module 14g performs a process of compressing the area data Dt13 in the data set at a predetermined magnification (= ML / OL) along the vertical direction to process the area data Dt13'of the paper leaf bundle. You can create. Next, the image processing module 14g replaces the area data Dt13 in the basic actual image data Dt12 with the processing area data Dt13'as shown in FIG. 15, and the lower surface of the presser foot portion PD is directly above the processing area data Dt13'. The processed image data Dt12'is created by moving the presser foot portion PD along the vertical direction by the amount of MD so as to be located at. In FIG. 15, the square frame represented by the reference numeral CB refers to the front frame of the paper leaf bundle storage box 200. Then, the thickness data Dt14 in the data set is multiplied by the magnification (expansion / contraction ratio) (= ML / OL) at the time of creating the processing area data Dt13' to derive new thickness data Dt14'. In this way, three data in the original data set (basic actual image data Dt12, area data Dt13, thickness data Dt14, first state index value data Dt15) are newly added to the new data set (processed image data Dt12', Machining area data Dt13', thickness data Dt14', first state index value data Dt15) are created, and this new data set is newly registered in the main table To1 of the database 14j together with the unique numerical data Dt11.

(2-2) Creation of image data for derivation of first state index value data and derivation of first state index value data First, as shown in FIG. 16, the image processing module 14g is a part of the area data Dt13 in the data set. Alternatively, all of them are replaced with one or more replacement image data Dt22 read from the image processing data table To2 of the database 14j to create the processing area data Dt13'. At this time, the replacement position of the region data Dt13 and the type of the replacement image data Dt22 to be used may be regularly determined or irregularly determined. Next, the image processing module 14g replaces the area data Dt13 in the basic real image data Dt12 with the processing area data Dt13'to create the processed image data Dt12'. Then, the linear sum of at least the second state index value data Dt23 of the first state index value data Dt15 associated with the region data Dt13 and the second state index value data Dt23 associated with the replacement image data Dt22 is obtained. A new first state index value data Dt15'is derived by calculating with the area ratio. That is, in the processing area data Dt13'in FIG. 16, the second state index value data Dt23 associated with the replacement image data Dt22b is "0.90", and the second state index value data Dt23 associated with the replacement image data Dt22c is The second state index value data Dt23 which is "0.80" and is associated with the replacement image data Dt22e is "0.60", and the second state index value data Dt23 associated with the replacement image data Dt22f is "0.50". When the second state index value data Dt23 associated with the replacement image data Dt22h is "0.30", the new first state index value data Dt15'is 0.61 (= 0.9 × (2). / 8) +0.8 × (1/8) +0.6 × (2/8) +0.50 × (1/8) +0.30 × (2/8)). In this way, three data in the original data set (basic actual image data Dt12, area data Dt13, thickness data Dt14, first state index value data Dt15) are newly added to the new data set (processed image data Dt12', Machining area data Dt13', thickness data Dt14, first state index value data Dt15') are created, and this new data set is newly registered in the main table To1 of the database 14j together with the unique numerical data Dt11.

<Correspondence between data in the control table and data in the main table>
The basic real image data Dt12 and the processed image data Dt12'of the main table To1 correspond to the image data Dt2 of the control table To0, and the thickness data Dt14 and Dt14'of the main table To1 correspond to the thickness data Dt4 of the control table To0. The first state index value data Dt15, Dt15'of the table To1 corresponds to the state index value data Dt5 of the control table To0.

<Characteristics of the robot arm control system with a robot hand according to the embodiment of the present invention>
In the robot arm control system 500 with a robot hand according to the embodiment of the present invention, the control device 400 causes the robot hand 100 and the robot arm RA to perform an operation in consideration of the thickness and the state of the banknote bundle MT. it can. Therefore, in the robot arm control system 500 with a robot hand, when the control device 400 causes the robot arm with a robot hand to pull out the banknote bundle MT from the paper leaf bundle storage box 200, a part of the banknote bundle MT is removed. It is possible to reduce the risk of falling off from the robot hand 100.

<Modification example>
(A)
In the robot arm control system 500 with a robot hand according to the previous embodiment, the image pickup device DC is attached to the robot hand 100, but the image pickup device DC may be arranged at a fixed point. In such a case, a plurality of image pickup devices DC may be arranged.

(B)
Although not particularly mentioned in the previous embodiment, even if the control device 400 of the robot arm control system 500 with a robot hand is provided with all the functions of the image data forming device 1 for determining the characteristics of the paper leaf bundle. Good.

(C)
In the robot arm control system 500 with a robot hand according to the previous embodiment, the control device 400 moves the movable finger 110 downward to grip the banknote bundle MT together with the fixed finger 120, and then retracts the robot hand 100. It was controlled to pull out the banknote bundle MT from the paper leaf bundle storage box 200, but after the robot hand 100 grasped the banknote bundle MT with the movable finger 110 and the fixed finger 120, the robot hand 100 retracted by a certain distance. The robot hand 100 may be controlled so that the banknote bundle MT is pulled out by a certain length and then the banknote bundle MT is released, and the portion of the pulled out banknote bundle MT is gripped again. In this way, the gripping length of the banknote bundle MT of the robot hand 100 can be increased, and the gripping state thereof can be further stabilized. At this stage, the control device 400 uses the thickness data Dt4 and the state index value data Dt5 to control at least one of the withdrawal allowance of the robot hand 100 and the gripping allowance (grasping allowance) at the time of re-grasping the bill bundle MT. You may do so. Specific control contents include, for example, the thicker the banknote bundle MT, the smaller the state index value of the banknote bundle MT, or the thicker the banknote bundle MT and the state index value of the banknote bundle MT. As the value becomes smaller, at least one of the pull-out allowance and the gripping allowance (grip allowance) at the time of re-grasping may be lengthened. In such a case, the thickness of the banknote bundle MT and the state index value may be divided stepwise, and the withdrawal allowance by the robot hand 100 and the gripping allowance (grasping allowance) at the time of re-grasping may be defined at each step.

(D)
In the previous embodiment, a stand-alone computer as shown in FIG. 10 was used as an image data forming device for determining the characteristics of a bundle of paper sheets, but a grid computer or the like interconnected by a communication network was used. May be done.

(E)
In the image data forming apparatus 1 for determining the characteristics of a bundle of paper leaves according to the previous embodiment, the area field Fo13 is provided in the main table To1 of the database 14j, and the area data Dt13 is stored in the area field Fo13 in advance. However, (i) the area data Dt13 may be automatically extracted from the basic real image data Dt12 by an edge extraction program or the like, and the area data Dt13 may be automatically stored in the area field Fo13, or (ii). ) Area field Fo13 may not be provided, and after the area data Dt13 is automatically extracted from the basic real image data Dt12 by an edge extraction program or the like, the processed image data Dt12'may be created using the area data Dt13.

(F)
Although not particularly mentioned in the image data forming apparatus 1 for determining the characteristics of the paper leaf bundle according to the previous embodiment, when the paper leaf bundle is a banknote of a plurality of countries, a country identification field is displayed on the main table To1. May be added.

(G)
In the image data forming apparatus 1 for determining the characteristics of the bundle of paper leaves according to the previous embodiment, the actual size data of the thickness is registered as the thickness data in the main table To1, but the relative data is registered instead of the actual size data. You may. Examples of this relative data include data on the ratio of the thickness of the paper leaf bundle to the maximum storage thickness of the paper leaf bundle storage box 200.

(H)
In the robot hand 100 according to the previous embodiment, the fixed finger 120 is fixed and only the movable finger 110 is movable, but the fixed finger 120 may be mobilized in the same manner as the movable finger 110.

(I)
In the robot hand 100 according to the previous embodiment, an air cylinder mechanism is adopted as the movable finger reciprocating mechanism 130, but a reciprocating mechanism known as the movable finger reciprocating mechanism 130, for example, a rack and pinion mechanism, a ball screw Mechanisms such as a mechanism, an air cylinder mechanism, a motor cylinder mechanism, an electric slider mechanism, a belt slider mechanism, and a linear slider mechanism may be adopted. In such a case, an electric motor may be used as the drive source.

(J)
In the robot arm control system 500 with a robot hand according to the previous embodiment, one image pickup device DC is attached to the robot hand 100, but a plurality of image pickup device DCs may be attached to the robot hand 100. In such a case, the average value of the values obtained from the collation result of each image data acquired by each image pickup device DC may be adopted, or the collation process using the average image of the image data acquired by each image pickup device DC. May be done.

100 Robot hand 400 Control device 410 Control unit 420 Storage unit 430 Derivation unit 440 Acquisition unit 500 Robot arm control system with robot hand Dt4 Thickness data (characteristic value information, information on thickness)
Dt5 state index value data (characteristic value information, state index value information)
RA robot arm DC imager

Claims (8)

A robot arm with a robot hand and
Imaging device and
A storage unit that stores the image information of the paper leaf bundle in association with the information of the damage state index value indicating the damaged state of the paper leaf bundle, and the acquisition of acquiring the image information of the paper leaf bundle from the imaging device. Derivation to derive the information of the damage state index value by collating the image information of the paper leaf bundle acquired in the acquisition unit and the image information of the paper leaf bundle stored in the storage unit with the image information of the paper leaf bundle. A robot arm control system with a robot hand, comprising a control device including a unit and a control unit that controls the operation of the robot arm with the robot hand based on the information of the damage state index value derived by the derivation unit. The robot hand has a pair of fingers facing each other.
According to claim 1, the control unit shortens the distance between the fingers when the robot hand grips the bundle of paper sheets as the damage state index value approaches a value indicating that the damage state is small. The robot arm control system with the robot hand described. The robot hand has a pair of fingers facing each other.
A pressure sensor is provided on at least one of the pair of fingers.
The robot hand according to claim 1, wherein the control unit controls the finger so that the value indicated by the pressure sensor becomes larger as the damage state index value approaches a value indicating that the damage state is smaller. Robot arm control system. The control unit requests that at least one of the moving speed and the moving acceleration of the robot hand at the time of grasping the bundle of paper sheets is lowered as the damage state index value approaches a value indicating that the damaged state is large. The robot arm control system with a robot hand according to any one of items 1 to 3. The moving speed is a retreating speed.
The robot arm control system with a robot hand according to claim 4, wherein the moving acceleration is a backward acceleration. After the robot hand grips the paper leaf bundle housed in the paper leaf bundle storage box, the control unit retracts the robot hand by a certain distance to bring the paper leaf bundle to a certain length. When the robot hand is controlled to hold the pulled-out portion of the paper leaf bundle again after pulling it out toward the front, the damage state index value is the damaged state. The robot arm control system with a robot hand according to any one of claims 1 to 5, wherein at least one of the pull-out allowance and the gripping allowance at the time of re-grasping becomes longer as the value indicates that the value is larger. .. A storage unit that stores the image information of the paper leaf bundle in association with the information of the damage state index value indicating the damage state of the paper leaf bundle, and
An acquisition unit that acquires image information of the paper leaf bundle, and
A derivation unit that derives information on the damage state index value by collating the image information of the paper leaf bundle acquired in the acquisition unit with the image information of the paper leaf bundle stored in the storage unit.
A robot arm control device with a robot hand, comprising a control unit that controls the operation of the robot arm with a robot hand based on the information of the damage state index value derived by the derivation unit. The acquisition step to acquire the image information of the paper leaf bundle, and
(A) Image information of the paper leaf bundle stored in a storage unit that stores the image information of the paper leaf bundle in association with information of a damage state index value indicating the damaged state of the paper leaf bundle, and (B) A derivation step of collating the image information of the paper leaf bundle acquired in the acquisition step to derive the information of the damage state index value.
A control step that controls the operation of the robot arm with a robot hand based on the information of the damage state index value derived in the derivation step.
Equipped with a robot hand with a robot arm control method.