JP2019025646A - Distribution device, placing system and learning data generation device - Google Patents

Abstract

To provide a distribution device that makes it possible to take a roughly correct quantity of some of a placed food before the quantity is measured and that is easy in maintenance.SOLUTION: A distribution device DD that grasps and distributes some of placed food such as noodle, granular, thin-plate-like or alimentary pasta, comprises: a multi-finger hand 30 for grasping the food; a measurement unit 20 that measures the food; a learning operation control unit that exerts control so as to perform a learning operation in which a series of measuring operations for grasping some of the placed food and measuring its weight is repeated while the control condition is changed; a learning data storage unit that, for each of the measuring operations, generates learning data in which the control condition is associated with the weight of some of the food grasped under the control condition and that stores, as a learning data set, a plurality of learning data generated by each measuring operation in the learning operation; and a distribution operation control unit that exerts control such that, on the basis of the learning data set, performs a distribution operation in which some of the placed food is grasped and distributed.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a distribution device, a serving system, and a learning data generation device.

  As a serving device for distributing cooked foods and placing them in a container such as a lunch box, Patent Document 1 introduces food into a hopper and from its gate provided on the lower end side of the hopper, The thing of the structure which drops and arrange | positions food with respect to the container which passes under the gate is disclosed.

  However, in the serving apparatus disclosed in Patent Document 1, when a highly viscous food such as spaghetti or cooked rice is introduced into the hopper, the food gradually adheres to the inner surface of the gate through which the food passes. There was a problem that the gate had to be frequently cleaned because it was impossible to accurately measure the amount.

  On the other hand, as a solution to the problem of the serving device using the hopper, Patent Document 2 discloses a serving device that grips and distributes food with a plurality of fingers.

  However, in the serving device disclosed in Patent Document 2, foods such as croquettes and hamburgers can be individually separated from the stacked state, but foods such as noodles, granules, thin plates, macaronis, etc. In the case where a predetermined amount is held together and separated, there is a problem that it cannot be separated by an accurate amount.

JP 2004-196382 A JP-A-9-65838

  Therefore, the present invention provides a dispensing device that can be dispensed in a somewhat accurate amount from a state in which foods that require weighing such as noodles, granules, thin plates, macaronis, etc. are piled up and that is easy to maintain. Is the main issue.

  That is, the dispensing device according to the present invention is a dispensing device that grasps and dispenses a part of noodle-like, granular, thin plate-like, macaroni-like food from a piled state, and a plurality of pieces from the piled food. A multi-fingered hand that grasps a part of food by opening and closing fingers, a measuring instrument that measures the part of food grasped by the plurality of fingers, and the multi-finger hand is controlled under arbitrary control conditions, A learning work control unit for controlling a series of weighing operations for grabbing a portion of food from a large amount of food and weighing the mass, while repeating the learning operation while changing the control conditions, and for each weighing operation Learning data that generates learning data associated with the mass of a part of the food grasped by the control condition and stores the plurality of learning data generated by each weighing operation in the learning operation as a learning data set Memory And a distribution operation control unit that controls to perform a distribution operation of grasping and distributing a part of the food from the serving food based on the learning data set. It is.

  If this is the case, use a multi-fingered hand that opens and closes multiple fingers to grab food, so when you open multiple fingers, the food will fall away from each finger, Therefore, the food is less likely to remain attached and maintenance is easy. Also, with multi-fingered hands, it is difficult to grab a specified amount of food such as noodles, granules, thin plates, macaroni, etc. Based on the learning data generated by grabbing and measuring while changing the control conditions with the finger hand, the distribution work can be executed, even if it is food such as noodle, granular, thin plate, macaroni You will be able to grab an accurate amount.

  In addition, the control conditions include: the width of each finger opening, the closing width of each finger, the closing speed of each finger, The gripping condition is selected from the gripping force of the finger and the insertion depth of each finger with respect to the piled food.

  The dispensing device further includes a height detector for detecting a height of each coordinate with respect to a reference plane of the piled food, and the insertion depth of each finger with respect to the piled food is determined as the height of the fill. The height detected by the height detector may be set as a reference.

  Further, before the weighing operation of the learning work control unit, the opening width X of each finger and the insertion depth Y of each finger included in the control conditions of the weighing operation, and the coordinates detected by the height detecting unit Referring to the height of the food, the shape data indicating the shape of the food placed in the height range of diameter X and depth Y centering on the highest coordinate that is the coordinate of the highest height of the food A measuring shape measuring unit for measuring the mass by grasping the food from the highest coordinate of the accumulated food and controlling the multi-fingered hand under the control conditions The operation may be performed, and the learning data storage unit may generate learning data by associating the control condition with the mass and the shape data. In this case, the fill shape data is a value represented by a ratio between the fill height of the highest coordinate and the volume or cross-sectional area of the food filled in the fill range.

  If it is such, since heap shape data is added to learning data, foods, such as a noodle shape, a granular form, a thin plate shape, and a macaroni shape, can be grasped by a more exact amount.

  Further, in any one of the distribution devices, the learning data storage unit selects learning data including a mass within a predetermined target mass range from the learning data set, and the plurality of selected learning data are stored. It is stored as a target learning data set, and based on the target learning data set, the distribution operation control unit controls to perform a distribution operation of grasping and distributing a part of food from the serving food It may be a thing.

  If it is such, the number of learning data referred in a distribution work control part can be reduced beforehand, and, thereby, the processing speed of the distribution work in a distribution work control part improves.

  Further, in the distribution device that generates the target learning data set, the learning work control unit may change the non-variable gripping condition to be changed from a plurality of gripping conditions included in the control conditions of the multi-fingered hand. A unit learning operation that is repeated a predetermined number of times while changing the variable gripping condition, and the non-variable gripping condition is added each time the unit learning operation is repeated. The learning data storage unit generates the target learning data set for each unit learning operation, and the target learning data set generated in an arbitrary unit learning operation in the learning operation control unit It further includes an upper and lower limit value specifying unit that specifies the upper and lower limits of the variation grasping condition with reference to the variation grasping condition of each learning data included, The upper limit value and the lower limit value of the variable gripping condition specified by the lower limit value specifying unit are configured to be set as the upper limit value and the lower limit value of the variable gripping condition selected in the next unit learning work in the learning work control unit. It may be.

  If this is the case, the number of weighing operations required to grasp the relationship between the control conditions of the multi-fingered hand and the mass of some food that can be grasped by the control conditions can be reduced, The time required for the learning work can be shortened.

  Further, when any one of the distribution work control units grabs and distributes a predetermined set mass of food from the serving food, the set mass is determined from each learning data stored in the learning data storage unit. The control condition of the learning data including the mass closest to is set as the distribution control condition, and according to the distribution control condition, control is performed so that a part of the food is grabbed and distributed from the serving food. Also good. Furthermore, when the distribution operation control unit grabs and distributes a food having a predetermined set mass from the active food to be distributed, among the learning data stored in the learning data storage unit, Refer to each learning data that includes the mass included in the specified error range with the set mass as the center, classify the control conditions included in each learning data into multiple classes between the maximum value and the minimum value. The learning data including the mass closest to the set mass is selected from each learning data having the control condition in the class in which the most values are classified in, and the control condition of the learning data is set as the distribution control condition, In accordance with the distribution control conditions, control is performed so that a part of the food is grabbed and distributed from the active food to be distributed, and the distribution operation control unit is the distribution target. When grabbing and distributing a predetermined set mass of food from a large amount of food, out of each learning data stored in the learning data storage unit, the mass included in a predetermined error range centered on the set mass Each learning data included was referred to, and the control conditions and peak shape data included in each learning data were classified into multiple classes between the maximum value and the minimum value, and the largest value was classified among all classes. The learning data including the mass closest to the set mass is selected from the learning data having the control condition or the shape data in the class, the control condition of the learning data is set as the distribution control condition, and the distribution control condition According to the above, control may be performed so that a part of the food is grabbed and distributed from the food to be distributed.

  If this is the case, for example, when it is necessary to serve a specified amount of food for each container that is the distribution destination, such as a convenience store lunch, the amount specified to some extent accurately for each container (Set mass) food can be served.

  In addition, when the distribution work control unit grabs a part of the food from the heaped food according to the distribution control condition and is weighed out of the set mass range including the set mass, the distribution work control unit again Depending on the distribution control conditions, control may be performed so as to grab a part of the food from the serving food.

  If this is the case, if the mass of food grabbed by the multi-fingered hand deviates significantly from the set mass, or if the food grabbed by the multi-fingered hand falls before being distributed to the distribution destination, It is possible to prevent the distribution work from continuing.

  Further, the multi-fingered hand of any one of the dispensing devices is configured to be capable of opening and closing inward and outward with one end side arranged and connected to the support block as a fulcrum. An outer elastic body connected to the fingers and pulling the fingers outward; an inner elastic body connected to the fingers and pulling the fingers inward; and the outer elastic body or And a tension fluctuation mechanism that fluctuates at least one tension of the inner elastic body.

  If this is the case, the gripping force is adjusted by pulling each finger outward and inward with an elastic body. For example, even if it is a fragile food such as a potato chip, apply excessive force. It can be grabbed without. In addition, as a mode in which the elastic body is connected to the finger, not only a mode in which the elastic body is directly connected to the finger, but also an indirect connection so that the tension of the elastic body is transmitted to the finger. Embodiments are also included.

  Moreover, the serving system according to the present invention includes any one of the dispensing devices, a first supply means for supplying the enriched food in the vicinity of the dispensing device, and the enriched food in the vicinity of the distributor. And a second supply means for supplying a container for placing a part of the food picked up from the container.

  Further, the learning data generation device according to the present invention includes a multi-finger hand that grips a part of a noodle-like, granular, thin plate, macaroni-like food, etc. by opening and closing a plurality of fingers, A series of weighers that weigh the part of food picked up with fingers and the multi-fingered hand under arbitrary control conditions, grab a part of the food from the piled food and weigh the mass The learning operation control unit that controls the operation to repeat the learning operation while changing the control condition, and for each weighing operation, the control condition is changed to the mass of a part of food grasped by the control condition. And a learning data storage unit that generates associated learning data and stores the generated plurality of learning data as a learning data set.

  If comprised in this way, the food which needs measurement, such as a noodle shape, a granular form, a thin plate shape, and a macaroni shape, can be separated from the state which piled up by a certain amount, and maintenance also becomes easy.

1 is a schematic diagram showing a serving system according to Embodiment 1. FIG. It is explanatory drawing which shows the height of the heightened food. It is a flowchart explaining the learning work of the serving system which concerns on Embodiment 1. FIG. It is a flowchart explaining the conveyance operation of the serving system which concerns on Embodiment 1. FIG. It is a schematic diagram which shows the external appearance of the multi-fingered hand of the serving system which concerns on Embodiment 2. FIG. It is a schematic diagram which shows the internal structure of the multi-fingered hand of the serving system which concerns on Embodiment 2. FIG. It is a schematic diagram which shows the multi-finger hand of the serving system which concerns on other embodiment. It is a schematic diagram which shows the multi-finger hand of the serving system which concerns on other embodiment. It is a schematic diagram explaining the peak range which concerns on other embodiment.

  Below, the distribution apparatus which concerns on this invention, and the arrangement | positioning system using this conveying apparatus are demonstrated based on drawing.

  The dispensing device according to the present invention is used for grasping and dispensing a predetermined amount of food that needs to be weighed, such as noodles, granules, thin plates, macaroni, and the like. In addition, the distribution apparatus which concerns on this invention can be used also as a serving system which grabs a predetermined amount of the said food and puts it on a container. In addition, noodle-like, granular, thin plate-like, macaroni-like foods are those that are grabbed as a lump of a large number of ingredients instead of a single ingredient lump. For example, as a noodle-like food, , Spaghetti, udon, soba, etc., granular foods include rice, and thin plate foods include potato chips.

  <Embodiment> As shown in FIG. 1, the serving system 100 according to the present embodiment includes a distribution device DD that distributes a large amount of food, and a tray T that accommodates the large amount of food F in the vicinity of the distribution device DD. A tray supply device SD1 to be supplied and a container supply device SD2 to supply a container B on which a portion of the food F that has been placed are provided are provided in the vicinity of the distribution device DD. The distribution device DD, the tray supply device SD1, and the container supply device SD2 are all connected to an information processing device (not shown) and controlled by the information processing device. The tray supply device SD1 according to the present embodiment corresponds to the first supply means in the claims, and the container supply device SD2 according to the present embodiment corresponds to the second supply means in the claims.

  The distribution device DD includes a hand support mechanism 10, a measuring instrument 20 connected to the tip of the hand support mechanism 10, a multi-finger hand 30 connected to the measuring instrument 20, and a vicinity of the distribution device DD by a tray supply device SD1. And four cameras C1 for photographing the tray T conveyed from above, and one camera C2 for photographing the container B conveyed to the vicinity of the distributor DD by the container supply device SD2 from above. .

  The hand support mechanism 10 is a 6-axis robot arm. Specifically, a support body 12 that is pivotably attached to the base 11, a three-joint arm 13 (first arm 13a, second arm 13b, and third arm 13c) that is attached to the support body 12, and not shown. An actuator (motor) for driving the six axes and various sensors for sensing a turning angle, a joint angle, and the like of the six axes (not shown) are provided. The second arm 13b has a structure in which two parts are pivotably connected to each other, and the multi-finger hand 30 is connected to the third arm 13c located at the most distal end of the three joint arm 13 via the measuring instrument 20. It is connected so that it can turn. Thereby, the hand support mechanism 10 can be moved by a total of six axes including three turning points and three joints.

  The multi-finger hand 30 includes a support block 31 connected to the measuring instrument 20, three fingers 32 connected to the support block 31, actuators for driving three fingers 32 (not shown), and three fingers (not shown). And various sensors for sensing a finger opening width, a closing width, a closing speed, a gripping force, and the like. And the three fingers 32 are comprised so that it can open and close by using the one end side arrange | positioned with respect to the support block 31 cyclically | annularly as a fulcrum.

  The weighing instrument 20 is configured so that the mass of only the food f picked up by the multi-finger hand 30 can be measured while the food f is held by the multi-finger hand 30.

  The camera C1 is for taking an image for detecting the height of the food F placed on the tray T supplied by the tray supply device SD1. The height is the height h from the reference surface reflected in the image to the outer surface of the whole food T, for example, as shown in FIG. 2, for example, the tray T reflected in the image. You may employ | adopt the height h to the outer surface of the food T whole from the bottom. The image may be a still image or a moving image.

  The camera C2 is used to detect the placement position in the container B supplied by the container supply device SD2.

  The tray supply device SD1 and the container supply device SD2 are so-called belt conveyors. The tray supply device SD1 extends, for example, from an upstream cooking place to a downstream empty tray collection place. In this case, the tray supply device SD1 conveys the food F cooked at the cooking place to the vicinity of the distribution device DD in a state of being stacked on the tray T, and all of the food F stacked on the tray T is transferred by the distribution device DD. After being distributed to the plurality of containers B, the empty tray T is transported to the tray collection place. The container supply device SD2 extends, for example, from an upstream container supply station to a downstream container collection station. In this case, the container supply device SD2 conveys the container B supplied at the container supply station to the distribution device DD, and a part of the food f on the tray T is placed on the container B by the distribution device DD. After that, the container B loaded with the food f is transported to the container collection place.

  The information processing apparatus is a so-called computer having a CPU, an internal memory, an I / O buffer circuit, an AD converter, and the like. And by operating according to a control program stored in a predetermined area of the internal memory, the CPU and peripheral devices operate cooperatively, a height detection unit, a learning work control unit, a learning data storage unit, an upper and lower limit value specifying unit, It functions as a distribution work control unit, a tray supply control unit, and a container supply control unit.

  The height detection unit is a height at each coordinate on the image plane of the food F stacked on the tray T from an image obtained by photographing the food F stacked on the tray T with the four cameras C1. (Altitude) is detected.

  The learning work control unit grabs a part of the food F stacked on the tray T supplied in the vicinity of the distribution device DD by the tray supply device SD1 by controlling the multi-finger hand 30 under an arbitrary control condition, Control is performed so that a unit learning operation is repeated a plurality of times by repeating a series of weighing operations for weighing a part of the food f picked up by a predetermined number of times while changing control conditions. More specifically, the learning work control unit selects a non-variable gripping condition that is not changed and a variable gripping condition that is changed from a plurality of gripping conditions included in the control conditions of the multi-fingered hand, The unit learning operation is repeated a plurality of times while the series of weighing operations are repeated a predetermined number of times while varying the grasping conditions. The learning work control unit adds the non-variable gripping condition and repeats the weighing operation every time the unit learning work is repeated. That is, the learning work control unit increases the non-variable gripping condition and repeats the weighing operation every time the unit learning work is repeated.

  The gripping conditions include: the opening width of each finger 32, the closing width of each finger 32, the closing speed of each finger 32, and each finger 32 when part of the food f is gripped from the food F placed on the tray T. Gripping force and insertion depth of each finger 32 with respect to the food F which is piled up. In addition, the insertion depth of each finger 32 with respect to the piled food F can be specified by the length of each finger inserted from the height measured by the height detection unit.

  The learning data storage unit generates, for each weighing operation in the learning work control unit, learning data that associates the control condition in the weighing operation with the mass of a part of food grasped under the control condition, and unit learning For each work, the generated plurality of learning data is stored as a learning data set. Further, the learning data storage unit selects learning data including a mass within a predetermined target mass range from the learning data set for each unit learning operation, and the plurality of selected learning data are set as the target learning data set. Remember as.

  The upper and lower limit value specifying unit specifies an upper limit value and a lower limit value from among the variation grasping conditions in each learning data included in the target learning data set generated in an arbitrary unit learning task in the learning task control unit. Then, the upper limit value and the lower limit value of the specified variation grasping condition are set as the upper limit value and the lower limit value of the variation grasping condition selected in the next unit learning operation in the learning operation control unit. This control is performed when the same gripping condition is selected as the variable gripping condition in the previous unit learning work and the next unit learning work.

  When the distribution work control unit grabs the food f having a predetermined set mass from the food F stacked on the tray T and distributes it to the container B, the distribution work control unit stores the target learning data set stored in the learning data storage unit. The learning data including the mass closest to the set mass is selected from the plurality of learning data included, and a part of the food f from the food F stored on the tray T is selected based on the control condition included in the selected learning data. The distribution work of grasping and distributing is performed.

  The tray supply control unit conveys the food F stacked on the tray T from the upstream side to the vicinity of the distribution device DD, and after the distribution of all the food F stacked on the tray T is completed, the tray T which has become empty Is carried out to carry downstream to the downstream side. Therefore, the tray supply control unit is configured to carry the tray T intermittently.

  The container supply control unit conveys the container B from the upstream side to the vicinity of the distribution device DD, and after the distribution of the food F stacked on the tray T to the container B is completed, the food f is placed Control for conveying the container B to the downstream side is executed.

  Next, operation | movement at the time of performing the learning operation | work of the serving system 100 which concerns on this embodiment is demonstrated based on FIG.

  When the learning work execution signal is input to the information processing apparatus, the tray supply control unit performs an operation of transporting the food F placed on the tray T by the tray supply apparatus SD1 to the vicinity of the distribution apparatus DD. After that, the learning work is executed.

  Then, the information processing device uses the tray T based on the image obtained by photographing the food F collected on the tray T conveyed to the vicinity of the distribution device SD by the four cameras C1 in the height detector. The height of each food F on the image plane on the image plane (hereinafter also referred to as “learning height information”) is detected (step S1).

  Next, in the learning work control unit, the information processing apparatus selects an arbitrary height from the learning height information and specifies coordinates corresponding to the selected height (step S2). . Further, the information processing apparatus selects one non-variable gripping condition that is not changed and a plurality of variable gripping conditions that are changed from a plurality of gripping conditions included in the control condition in the learning work control unit (step 3). . Then, the information processing apparatus sets a control condition, that is, each gripping condition in the learning work control unit (step 4).

  Next, the information processing apparatus controls the multi-finger hand 30 according to the set control condition in the learning work control unit, and picks up some food from the specified coordinate portion in the food F stacked on the tray T. Then, after weighing with the weighing instrument 20, a series of weighing operations for returning the part of the food f to the tray T again is performed (step S5). Thereafter, the information processing apparatus generates and stores learning data in the learning data storage unit that associates the control condition with the mass of the food grasped by the control condition (step S6).

  Then, the information processing apparatus repeats the series of weighing operations in steps S1 to S6 while changing each gripping condition included in the variable gripping conditions, and determines whether or not the weighing operation has been performed a specified number of times (step S7). . If the specified number of times has not been performed, a series of weighing operations of Steps S1 to S6 are performed again.

  On the other hand, when the specified number of times is carried out, the unit learning work is ended (step S8). Then, in the learning data storage unit, the information processing apparatus stores a plurality of learning data generated in each metric operation of the unit learning work as a learning data set (step S9). Furthermore, the information processing apparatus selects learning data including mass within a predetermined target mass range from the learning data set in the learning data storage unit, and sets the selected plurality of learning data as the target learning data set. Store (step S10).

  Next, the information processing apparatus determines whether or not the unit learning work has been performed a prescribed number of times (step 12). When the prescribed number of times has been implemented, the learning work is terminated.

  On the other hand, when the prescribed number of times is not implemented, the information processing apparatus refers to a plurality of learning data included in the target learning data set stored in the learning data storage unit in the upper and lower limit value specifying unit, and each learning data The largest upper limit value and the smallest lower limit value are specified from the variation grasping conditions included in (Step S12).

  Next, the information processing apparatus selects the variable gripping condition and the non-variable gripping condition in the next unit learning work in the learning work control unit (step S14). In this case, at least one of the variation grasping conditions in the previous unit learning work is selected, and the selected variation grasping condition is added to the non-variable grasping condition. Therefore, the number of variation grasping conditions decreases, and the number of non-variation grasping conditions increases.

  Next, when the same gripping condition is selected as the variable gripping condition in the next unit learning operation, the information processing apparatus determines the variable gripping condition specified by the upper and lower limit value specifying unit. Are set as the upper limit value and the lower limit value of the numerical value range (step S15).

  Then, the information processing apparatus again performs a series of unit learning operations in steps S1 to S10 and repeats this operation.

  Next, operation | movement at the time of performing the distribution work of the serving system 100 which concerns on this embodiment is demonstrated based on FIG.

  When the learning work is finished, the distribution work is started. First, the information processing apparatus is placed on the tray T based on the image obtained by photographing the food F placed on the tray T to be distributed by the four cameras C1 in the height detection unit. The height of the food F at each coordinate on the image plane (hereinafter also referred to as “distribution height information”) is detected (step S15).

  Next, the information processing apparatus selects learning data including the mass closest to the preset set mass from the target learning data set generated in the last unit learning task in the distribution task control unit (step S16).

  Next, the information processing apparatus determines whether or not the insertion depth of each finger included in the selected learning data is longer than any height included in the distribution height information in the distribution work control unit. (Step S17).

  If it is determined that it is long, the information processing apparatus subsequently determines whether or not the determination has continued for a specified number of times (step S18). If it is determined that the specified number of times has continued, it is determined that the tray T has become empty, and the distribution operation is terminated. On the other hand, if it is determined that the predetermined number of times has not been continued, the distribution device DD (multi-fingered hand 30) is controlled so that the bulk (height) of the food F on the tray T increases. Then, the food F placed on the tray T is re-prepared and executed again from step S15 (step S19). In addition, as this re-alignment operation | movement, operation | movement which lifts a part of the food F piled up with the multifingered hand 30, and returns again, for example, operation | movement which stirs the piled food F is considered.

  On the other hand, if it is determined that the information is short, the information processing apparatus controls the multi-finger hand 30 according to the control condition included in the selected learning data in the distribution work control unit, and starts from the food F on the tray T. A portion of the food f is picked up and the mass is measured by the measuring instrument 20 (step 20).

  Next, the information processing apparatus determines whether the mass of the weighed food f is within a predetermined set mass range in the distribution work control unit (step S21). The set mass range is an error range that can be allowed from the set mass. For example, when food f is to be placed on a lunch box, the set mass range can be More than mass.

  When the information processing apparatus determines that the value is within the set mass range, the distribution work control unit specifies the serving position based on the image of the camera C2 that captures the container B, and moves to the serving position. Food f is served (step S23). Thereafter, the processing is executed again from step 15.

  On the other hand, when the information processing apparatus determines that it is not within the set mass range, the distribution work control unit once returns a part of the food f gripped by the multi-fingered hand to the tray T and executes again from step 16.

  After the distribution operation is completed for one tray T, the information processing apparatus conveys the next tray T to the vicinity of the distribution device DD, and starts the distribution operation again.

  Note that the learning operation may be executed again when the type of food on the tray T supplied by the tray supply device SD1 is changed, for example.

  <Embodiment 2> This embodiment is a modification of the multi-finger hand 30 according to Embodiment 1 described above. In FIG. 4, the tension adjusting mechanism is omitted. The multi-finger hand 30 is connected to a support box 31, six outer fingers 32a arranged and connected to the support box 31 on a large-diameter circle, and a small-diameter circle to the support box. Four inner fingers 32b, an outer elastic body 33 connected to the outside of each finger 32a, 32b, an inner elastic body 35 connected via an inner wire 34 of each finger 32a, 32b, and an inner elastic body And a tension adjusting mechanism 36 that adjusts the tension 35.

  As shown in FIG. 4, the outer finger 32 a and the inner finger 32 b are arranged concentrically with respect to the outside of the bottom surface of the support box 31. The outer finger 32a and the inner finger 32b have a structure in which one end side is fixed to the support box 31 and can swing inward or outward with the one end side as a fulcrum. Each of the fingers 32a and 32b is provided with a joint in the middle so that the angle on the tip side can be adjusted. Incidentally, the inner finger 32b is shorter than the outer finger 32a.

  The outer elastic body 33 has one end fixed to the outside of the fingers 32 a and 32 b and the other end fixed to the outside of the bottom surface of the support box 31. Thus, the fingers 32a and 32b are always pulled outward by the outer elastic body 33 and are in an open state.

  The tension adjustment mechanism 36 is installed inside the support box 31 as shown in FIG. Specifically, the tension adjusting mechanism 36 includes a first restriction plate 36 a that is fixed to the inside of the bottom surface of the support box 31, and a second restriction plate 36 b that is fixed to the outside of the bottom surface of the support box 31. The tube 36c spanned between the first restricting plate 36a and the second restricting plate 36b, the servo motor 36d fixed to the inside of the top surface of the support box 31, and the space above the first restricting plate 36a. And a movable plate 36e fixed to the servo motor 36d. In addition, the movable plate 36e can change the space | interval with the 1st prescription | regulation board 36a by the servomotor 36d. The number of inner elastic bodies 35 corresponding to the number of fingers 32 is connected between the movable plate 36e and the first regulating plate 36a so as not to contact the first regulating plate 36a.

  The tube 36c is installed so as to connect the first restriction hole 36a 'provided in the first restriction plate 36a and the second restriction hole 36b' provided in the second restriction plate 36b. Note that one end of the tube 36c connected to the first restriction plate 36a opens toward the inner elastic body 35, and the other end of the tube 36c connected to the second restriction plate 36c faces the finger 32. It is open. The wires 34 extend from the inner elastic body 35 and are connected to the inner side of the corresponding finger 32 through the tube 36c.

  The operation of the multi-fingered hand 30 according to the present embodiment will be described. By moving the movable plate 36e upward by the servo motor 36b, in other words, in a direction away from each finger 32, it resists the tension of the outer elastic body 33. The force (tension) for pulling each finger 32 inward increases. When the force that pulls the finger 32 outward by the outer elastic body 33 exceeds the force that pulls the finger 32 outward by the inner elastic body 35, each finger 32 closes inward. Thereby, food can be grasped by each finger 32. On the other hand, by moving the movable plate 36a downward, in other words, in a direction approaching each finger 32 by the servo motor 36b, the force (tension) that pulls each finger 32 inward against the tension of the outer elastic body 33 is weak. Become. When the force pulling the finger 32 outward by the outer elastic body 33 exceeds the force pulling the finger 32 outward by the inner elastic body 35, the food grasped by each finger 32 can be released.

  In addition, what is necessary is just to change the outer side elastic body 33 and the inner side elastic body 35 to a thing with a different tension | tensile_strength when adjusting the holding force of each finger | toe 32. FIG. It can also be adjusted by adjusting the length of the wire 34 or adjusting the height position of the movable plate 36e.

  In such a configuration, when food is grasped with a multi-fingered hand, each finger moves independently, so that a biased force is applied to the food, for example, a fragile food such as a potato chip. It is possible to prevent breakage of easily crushed food such as tofu and tofu. Also, in this case, since each finger moves according to the shape of the food, when it is grabbed together like food such as noodles, granules, thin plates, macaroni, etc., the shape changes as needed. Even if it is a thing, since each finger follows and moves according to the change of the shape, it can be grasped without missing the food. Also, when grasping foods that are easily broken or easily crushed with a multi-fingered hand, increase the number of fingers provided on the multi-fingered hand to set the gripping force (torque) per finger weakly. This makes it possible to prevent the food from being damaged. Note that the gripping force can be easily changed for each finger 32.

  Further, since the wire 34 is guided by the tube 36c, even if the wire 34 slides on the tube 36c, a load is not applied to the wire 34, and disconnection of the wire 34 can be prevented.

  In the present embodiment, the tension adjusting mechanism 36 is provided for the inner elastic body 35, but the tension adjusting mechanism 36 may be provided for the outer elastic body 33, and both elastic bodies 35, 36 may be provided. A tension adjusting mechanism 36 may be provided.

  <Embodiment 3> This embodiment is a modification of the multi-finger hand 30 according to Embodiment 1 described above. The multi-fingered hand 30 according to the present embodiment includes a support box 31, a plurality of fingers 32 arranged and connected to the support box 31 so as to face each other, and an elastic body 37 connected to one end of each finger 32. And an elevating mechanism 38 that elevates and lowers the elastic body 37 with respect to each finger 32.

  The plurality of fingers 32 are arranged side by side so as to face the bottom surface of the support box 31 and are pivotally supported so that they can be opened and closed with one end side as a fulcrum. And the some finger | toe 32 is making the other end side which grasps food etc. protrude from the bottom face of the support box 31. FIG.

  The elastic body 37 is a so-called coil spring. The elastic body 37 is disposed inside the support box 31, one end is fixed to one end of each finger 32, and is connected to a lifting mechanism 38 disposed above each finger 32.

  The elevating mechanism 38 is a so-called servo motor. And the raising / lowering mechanism 38 is being fixed to the internal top surface of the support box 31, and operates so that each elastic body 37 may raise / lower.

  The operation of the multi-fingered hand 30 according to this embodiment will be described. Each elastic body 37 is lowered by the elevating mechanism 38, in other words, by moving one end of each finger 32 in the pushing direction, The side is pushed by each elastic body 37 to operate. In this case, the elastic body 37 transmits the pushing operation of the elevating mechanism 38 to the finger 32 while maintaining the contracted state.

  On the other hand, each elastic body 37 is lifted by the elevating mechanism 38, in other words, by moving each finger 32 in the pulling direction, each finger 32 operates so that its upper end side is pulled by each elastic body 37 and closes to each other. . In this case, the elastic body 37 maintains a contracted state until it is pulled by a predetermined distance by the lifting mechanism 38, but gradually expands when it is pulled by the lifting mechanism 38 for a predetermined distance or more. When the elastic body 37 is in an extended state, the force for pulling the finger 32 is increased or decreased depending on the degree of extension, and thereby the gripping force of each finger 32 can be adjusted. In addition, by adjusting the elastic force of each elastic body 37, the gripping force of each pair of fingers can be adjusted more finely.

  Even with such a configuration, the same effects as those of the multi-finger hand 39 according to the second embodiment can be obtained.

  <Embodiment 4> This embodiment is a modification of the information processing apparatus of Embodiment 1. The information processing apparatus according to the present embodiment is different from the information processing apparatus according to the first embodiment in that it further includes a peak shape data generation unit, and the learning work control unit in the information processing apparatus according to the first embodiment. The configurations of the learning data storage unit and the distribution work control unit are different. In the following, these differences will be described in detail.

  As shown in FIG. 9, before the measuring operation of the learning work control unit, the heap shape data generation unit, the opening width X of each finger and the insertion depth Y of each finger included in the control conditions of the measuring operation, With reference to the height of each coordinate detected by the height detection unit, the height of the food F that has the highest height P is a coordinate range of diameter X and depth Y centered on the highest coordinate P. The shape data indicating the shape of the filled food is generated.

The fill shape data is, for example, a value represented by a ratio of the following two values in the food F accumulated before the weighing operation of the learning work control unit.
-The height of the highest coordinate-The cross-sectional area of the food placed in the height range of the raised food F The cross-sectional area is the cross-sectional area of the cross-section passing through the highest coordinate of the raised food F. It may be two or more. In the case of two or more, the cross-sectional area of two orthogonal cross sections passing through the highest coordinate may be used. In addition, you may use the volume of the food piled up in the filling range of the piled food F instead of a cross-sectional area.

  The learning work control unit according to the present embodiment is the same as the learning work control unit according to the first embodiment in that when part of the food F is picked up, the part of the food is picked up from the highest coordinate of the food F. Is different.

  The learning data storage unit of the present embodiment generates learning data by associating the control condition with the mass of food caught under the control condition and the shape data for each weighing operation of the learning work control unit. This is different from the learning data storage unit of the first embodiment.

  The distribution work control unit of the present embodiment is different from the distribution work control unit of the first embodiment in the method for selecting the distribution control conditions. Specifically, when the distribution work control unit of the present embodiment grabs and distributes a food with a predetermined set mass from the active food to be distributed, first, each of the data stored in the learning data storage unit is stored. The primary learning data set including the mass included in the predetermined error range (allowable error range) around the set mass in the learning data is referred to, and the control condition and the shape data included in each learning data of the primary learning data set Are classified into multiple classes between the maximum and minimum values.

  Here, for example, when the control condition is the opening width of each finger, the plurality of classes refers to the maximum value and the minimum value of the opening width value of each finger included in each learning data of the primary learning data set. Each range formed by equally dividing the maximum value and the minimum value is shown.

  Then, the distribution work control unit of the present embodiment refers to the number of values included in each class, and the set mass from each learning data having the control condition or the shape data in the class in which the most values are classified. Learning data including the mass closest to is selected, and the control condition of the learning data is set as the distribution control condition.

  That is, for example, when the learning data includes the value of the opening width of each finger and the value of the insertion depth of each finger, first, the value of the opening width of each finger included in each learning data is classified into a plurality of classes. The value of the insertion depth of each finger is classified into a plurality of classes. At this time, it is preferable to make the number of classes the same under each control condition. If the class that includes the most values among all classes is a class that classifies the value of the finger opening width, each learning that has the finger opening width classified in this class. Select learning data including the mass closest to the set mass from the data.

  In addition, the operation | movement at the time of performing the learning operation | work of the arrangement | positioning system 100 which concerns on this embodiment is the point which produces | generates shape data by a shape shape data generation part before the measurement operation | movement of a learning work control part, Common to the operation of the first embodiment except that a part of the food is grabbed from the highest coordinate of the food F accumulated in the weighing operation and the learning data generated in the learning data storage unit includes the shape data. doing.

  Moreover, the operation | movement at the time of performing the distribution operation | work of the arrangement system 100 which concerns on this embodiment is common with the operation | movement of the said Embodiment 1 except the selection method of the control conditions in a distribution operation | movement control part differing.

  Other Embodiments In the first embodiment, one distribution device DD is arranged with respect to the serving system 100, but a plurality of distribution devices DD may be arranged. If it is such, it will become possible to arrange | position the foodstuffs which differ sequentially by each distribution apparatus DD with respect to the container B conveyed by the container conveying apparatus SD2, and work efficiency will improve markedly.

  The distribution device DD according to the first embodiment can also be used as a learning data generation device by being used only for the learning operation. In this case, a target learning data set group is created for each type of food by the learning data generation device, and the target learning data set group is generated by a robot arm having a multi-finger hand having the same configuration as the learning data generation device. Can be used for distribution.

  In the first embodiment, food in the state of being stacked on the tray T is distributed. However, the food in the state of being directly stacked on a conveying device such as a belt conveyor is not necessarily required to be stacked on the tray T. May be.

  Moreover, in the said Embodiment 1, although the distribution apparatus DD was used with respect to the serving system 100, the distributing apparatus DD can be used not only for the serving system 100 but also for food bagging.

  In addition, it goes without saying that the present invention is not limited to the above-described embodiments, and various modifications can be made without departing from the spirit of the present invention.

100 Assembling system DD Distribution device SD1 Tray supply device (first supply means)
SD2 container supply device (second supply means)
C1, C2 Camera 10 Hand support mechanism 20 Meter 30 Multi-finger hand 33 Outer elastic body 35 Inner elastic body 36 Tension adjustment mechanism

Claims (15)

A dispensing device that grabs and dispenses a portion of a noodle-like, granular, thin plate-like, macaroni-like food, etc.,
A multi-fingered hand that grabs part of the food by opening and closing a plurality of fingers from the food,
A measuring instrument for weighing the part of food picked up by the plurality of fingers;
The multi-fingered hand is controlled under arbitrary control conditions, and a learning operation is repeated in which a series of weighing operations for measuring a mass by grabbing a part of the food from the piled food is repeated while changing the control conditions. A learning work control unit for controlling
For each of the weighing operations, learning data associated with the mass of a part of the food grasped with the control condition under the control condition is generated, and a plurality of learning data generated in each of the weighing operations in the learning operation is set as a learning data set. Learning data storage unit for storing as,
A distribution apparatus comprising: a distribution operation control unit configured to perform a distribution operation of grasping and distributing a part of food from the serving food based on the learning data set. When the control condition is to grab a part of the food from the piled food by the multi-fingered hand, the opening width of each finger, the closing width of each finger, the closing speed of each finger, The dispensing apparatus according to claim 1, wherein the grasping condition is selected from a grasping force and an insertion depth of each finger with respect to the piled food. Further comprising a height detector for detecting the height of each coordinate relative to the reference plane of the food,
The dispensing apparatus according to claim 2, wherein the insertion depth of each finger with respect to the piled food under the control condition is set based on the pile height detected by the pile height detection unit. Before the weighing operation of the learning work control unit, the opening width X of each finger and the insertion depth Y of each finger included in the control conditions of the weighing operation, and the coordinates of each coordinate detected by the height detection unit With reference to the height, generating the shape data indicating the shape of the food placed in the height range of diameter X and depth Y centering on the highest coordinate which is the coordinate of the highest height of the food. Further comprising a prime shape data generation unit,
The learning work control unit controls the multi-fingered hand under the control conditions, and performs a weighing operation of grabbing food from the highest coordinate of the piled food and weighing the mass,
The distribution device according to claim 3, wherein the learning data storage unit generates learning data by associating the control condition with the mass and the shape data. The distribution device according to claim 4, wherein the peak shape data is a value represented by a ratio between the peak height of the highest coordinate and the volume or cross-sectional area of the food peaked in the peak range. The learning data storage unit selects learning data including a mass within a predetermined target mass range from the learning data set, and stores the selected plurality of learning data as a target learning data set. ,
The distribution operation control unit controls the distribution operation to grasp and distribute a part of the food from the accumulated food based on the target learning data set. The dispensing device described in 1. The learning work control unit selects a non-variable non-fluctuating gripping condition and a fluctuating gripping condition to be fluctuated from a plurality of gripping conditions included in the control conditions of the multi-fingered hand, A unit learning operation that is repeated a specified number of times while changing the variable gripping condition is performed a plurality of times, and the non-variable gripping condition is added each time the unit learning operation is repeated,
The learning data storage unit generates the target learning data set for each unit learning operation;
Upper and lower limit values for specifying the upper and lower limit values of the variation grasping condition with reference to the variation grasping condition of each learning data included in the target learning data set generated in the arbitrary unit learning task in the learning task control unit Further comprising a specific part,
The upper limit value and the lower limit value of the variable gripping condition specified by the upper and lower limit value specifying unit are set as the upper limit value and the lower limit value of the variable gripping condition selected in the next unit learning work in the learning work control unit. 7. The dispensing device according to claim 6, wherein the dispensing device is configured. When the distribution operation control unit grabs and distributes a predetermined set mass of food from the food that is to be distributed, it distributes the set mass from the learning data stored in the learning data storage unit. The control condition of the learning data including near mass is set as the distribution control condition, and the control is performed so that a part of the food is grabbed and distributed by the distribution control condition. 8. A distribution device according to any one of claims 1 to 7. When the distribution operation control unit grabs and distributes a predetermined set mass of food from the food that is to be distributed, the set mass among the learning data stored in the learning data storage unit Referring to each learning data including the mass included in the predetermined error range with the center as the center, the control conditions included in each learning data are classified into multiple classes between the maximum value and the minimum value. The learning data including the mass closest to the set mass is selected from the learning data having the control condition in a class in which many values are classified, and the control condition of the learning data is set as the distribution control condition, and the distribution is performed. The dispensing apparatus according to claim 1, wherein a part of the food is controlled by being grasped and distributed from the lively food to be distributed according to the control conditions for use. When the distribution operation control unit grabs and distributes a predetermined set mass of food from the food that is to be distributed, the set mass among the learning data stored in the learning data storage unit Refer to each learning data including mass included in the predetermined error range centering on, and classify the control condition and prime shape data included in each learning data into multiple classes between the maximum value and the minimum value. The learning data including the mass closest to the set mass is selected from the learning data having the control condition or the shape data in the class in which the most values are classified, and the control condition of the learning data is used for distribution. 5. The distribution according to claim 4, wherein the distribution is set as a control condition, and is controlled so as to grasp and distribute a part of the food from the active food to be distributed according to the distribution control condition. Location. When the distribution work control unit grasps and weighs a part of the food from the piled food according to the distribution control condition, the mass is out of the set mass range including the set mass again. 11. The dispensing apparatus according to claim 8, wherein the dispensing device is controlled so as to grab a part of the food from the piled food according to the distribution control condition. The multi-fingered hand according to any one of claims 1 to 11,
A plurality of fingers configured to be able to open and close inward and outward with one end side arranged and connected to the support block as a fulcrum,
An outer elastic body connected to each finger and pulling each finger outward;
An inner elastic body connected to each finger and pulling each finger inward;
And a tension adjusting mechanism that adjusts a tension of at least one of the outer elastic body and the inner elastic body. The multi-fingered hand according to any one of claims 1 to 11,
A plurality of fingers that are arranged oppositely or annularly and open and close with the upper end side as a fulcrum;
An elastic body connected to the upper end of each finger;
An elevating mechanism disposed above each finger and elevating and lowering the elastic body;
The upper end of each finger operates by lowering the elastic body by the elevating mechanism so that the upper end of each finger is pushed and opened by the elastic body, and the elastic body is raised by the elevating mechanism. So that the elastic body can be extended and the gripping force of each finger can be adjusted by raising the elastic body by a predetermined distance or more by the elevating mechanism. Configured dispensing device. A dispensing device according to any one of claims 1 to 13;
A first supply means for supplying the food in the vicinity of the dispensing device;
A serving system comprising: second supply means for supplying a container for serving a part of the food grasped from the served food in the vicinity of the dispensing device. A multi-fingered hand that grabs part of the food by opening and closing a plurality of fingers from the food,
A measuring instrument for weighing a part of the food grasped by the plurality of fingers;
The multi-fingered hand is controlled under arbitrary control conditions, and a learning operation is repeated in which a series of weighing operations for measuring a mass by grabbing a part of the food from the piled food is repeated while changing the control conditions. A learning work control unit for controlling
A learning data storage unit that generates learning data associated with the mass of a part of the food grasped by the control condition for each weighing operation, and stores the generated plurality of learning data as a learning data set And a learning data generation device.