Food partiting device and program

Abstract

A food serving device (1) includes: a gripper (11) that grips a portion of a food (21) having an uncertain shape; a determination unit (313, 314) that determines a first target value of the weight of the food product to be dispensed in one gripping operation, calculated on the basis of the final target value for the dispensing, and determines a first pickup position corresponding to the first target value on the basis of the captured image; and a control unit that moves the gripper 11 to the first pickup position and performs the portioning of the food 21. The determination unit determines a second target value of the weight of the food product to be dispensed by the next gripping operation when the weight of the food product dispensed by the single gripping operation of the gripper 11 satisfies the first target value, and determines a second pickup position corresponding to the second target value.

Description

Technical Field

[0001] The invention relates to a food portioning device and a program thereof. Background Art

[0002] In order to improve the work and service efficiency of restaurants, etc., automated work for portioning and placing food is required. For example, Non-Patent Document 1 discloses using a gripper to pick up a target weight of salad or herbs from a container.

[0003] Reference List

[0004] Patent Literature

[0005] Non-Patent Literature 1: Prabhakar Ra and Matthew J. Howard, “Robotic Untangling of Herbs and Salads with ParallelGrippers,” in 2020 IEEE / RSJ International Conference on Intelligent Robots and Systems (IROS), October 25-29, 2020, Las Vegas, NV, USA (Virtual). Summary of the invention

[0006] Technical issues

[0007] Non-patent document 1 describes a method of grabbing food of a preset target weight from a container [tray in a container] etc. for providing food and dividing the food into portions by adjusting the depth of the grabber inserted into the container for accommodating food and the grabbing mechanism of the grabber (for adjusting the width of the opening, etc.). However, even when the area or volume of the grabbing mechanism can be adjusted, it is difficult to accurately grab (portion out) food of a target weight when the density of the food is uneven or there are gaps in the food. The purpose of the present invention is to accurately portion out food of a target weight.

[0008] Technical Solution

[0009] In one aspect, the present invention provides a food portioning device, comprising: a gripper configured to grip a portion of a food having an uncertain shape; a moving mechanism configured to move the gripper; a weighing unit configured to measure the weight of the food gripped by the gripper; an imaging unit configured to image the surface shape of the food; a determining unit configured to determine a first target value of the weight of the food to be portioned out through a single gripping operation, the first target value being calculated based on a final target value, and configured to determine a first pickup position corresponding to the first target value based on an image captured by the imaging unit; and a control unit configured The invention relates to a method for performing food portioning by moving the gripper to a first picking position through a moving mechanism, so that when the weight of the food portioned out through one grabbing operation of the gripper meets the first target value, the decision unit determines a second target value for the weight of the food to be portioned out through the next grabbing operation, and determines a second picking position corresponding to the second target value, and the control unit performs food portioning by moving the gripper to the second picking position, and when the weight of the food portioned out through one grabbing operation of the gripper does not meet the first target value, the decision unit redetermines the first target value, and the control unit performs food grabbing with the redetermined first target value.

[0010] Therefore, according to the present invention, food of a target weight can be accurately portioned out.

[0011] In a preferred aspect, the distal end of the gripper tapers gradually in a direction toward gripping the food.

[0012] According to the present aspect, the smaller the target value of the weight of the food to be picked up is, the smaller the error amount of the target value of the weight of the food to be picked up can be.

[0013] In a preferred aspect, the shape of the gripper changes according to the first target value and the second target value.

[0014] According to the present aspect, the smaller the target value of the weight of the food to be picked up is, the smaller the error amount of the target value of the weight of the food to be picked up can be.

[0015] In a preferred aspect, the decision unit decides, for each food, a frequency of the grabbing operation to be performed and a target value of the weight of the food to be portioned out per grabbing operation.

[0016] According to this aspect, the conditions of the grabbing operation can be changed according to the characteristics (viscosity, density, etc.) of the food to be portioned.

[0017] In a preferred aspect, the decision unit generates a learning model that learns measurement data of the weight of food grasped by the grasping part at the pickup position and image data of the pickup position for each food, and decides the first pickup position and the second pickup position using the learning model.

[0018] According to this aspect, the gripping position can be appropriately determined according to the target value of the weight of the food to be gripped.

[0019] In a preferred aspect, the density of the food is non-uniform, and the decision unit decides the first pickup position and the second pickup position further based on the density calculated from the captured image.

[0020] According to this aspect, the pick-up position is determined based on the unevenness of the food density.

[0021] In addition, on the other hand, the present invention provides a program that enables a computer to have the following functions: a determination unit, which is configured to determine a first target value for the weight of food to be portioned out by a single grabbing operation, the first target value being calculated based on a final target value for the portioned amount when a portion of food having an uncertain shape is portioned, and is configured to determine a first pickup position corresponding to the first target value based on a captured image; and a control unit, which is configured to perform food portioning by moving a gripping portion that grips a portion of the food to the first pickup position, wherein, when the weight of food portioned out by a single grabbing operation of the gripper satisfies the first target value, the determination unit determines a second target value for the weight of food to be portioned out by a next grabbing operation, and determines a second pickup position corresponding to the second target value, and the control unit performs food portioning by moving the gripping portion to the second pickup position, and if the weight of food portioned out by a single grabbing operation of the gripping portion does not satisfy the first target value, the determination unit re-determines the first target value, and the control unit performs food grabbing with the re-determined first target value. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 is a schematic diagram illustrating the configuration of a food portioning device according to an embodiment.

[0023] Figure 2 is a block diagram illustrating a hardware configuration of a food portioning apparatus according to an embodiment.

[0024] Figure 3 is a block diagram illustrating a functional configuration of a food portioning apparatus according to an embodiment.

[0025] Figure 4 is a schematic diagram illustrating a configuration of a gripper of a food portioning device according to an embodiment.

[0026] Figure 5 Schematic diagram for describing a gripper of a food portioning device according to an embodiment grabbing food.

[0027] Figure 6Schematic diagram for describing a gripper of a food portioning device according to an embodiment grabbing food.

[0028] Figure 7 is a schematic diagram illustrating the configuration of a rotating mechanism of a food portioning device according to an embodiment.

[0029] Figure 8 2 is a diagram for describing rotation control of a gripper of a food portioning apparatus according to an embodiment.

[0030] Fig. 9 is a flowchart illustrating the processing of the food portioning device according to the embodiment.

[0031] Fig.10 is a flowchart illustrating a picking control of the food portioning device according to an embodiment.

[0032] Fig.11 2 is a schematic diagram for describing a gripper of a food portioning apparatus according to an exemplary modification to grip food.

[0033] Fig.12 are diagrams describing a container according to an exemplary modification. DETAILED DESCRIPTION

[0034] [Implementation Method]

[0035] Hereinafter, a food portioning device according to an embodiment of the present invention will be described. In the accompanying drawings and the following description, the left-right direction is defined as the X-axis direction, the front-back direction is defined as the Y-axis direction, the up-down direction is defined as the Z-axis direction, the directions or sides indicated by the arrows X, Y and Z are defined as right, backward and upward, or the right side, the rear side and the upper side, respectively, and the opposite directions or opposite sides thereof are defined as left, forward or downward, or the left side, the front side or the lower side, respectively. In addition, in the accompanying drawings, the case where "·" is shown in "○" refers to an arrow in the direction from the back to the front of the page, and the case where "×" is shown in "○" refers to an arrow in the direction from the front to the back of the page.

[0036] Figure 1 1 is a schematic diagram illustrating a configuration of a food portioning device 1 according to an embodiment. The food portioning device 1 includes a gripper 11 , a robot arm 12 , a rotating mechanism 13 , a weighing scale 14 , an imaging device 15 , and a scale 16 .

[0037] The gripper 11 is provided at a distal end of the robot arm 12, moves by the operation of the robot arm 12, and can grip a portion of the indefinite-shaped food 21 provided in the container 20. That is, the gripper 11 is an example of a gripper that grips a portion of the indefinite-shaped food 21.

[0038] Foods with indeterminate shapes are generally foods that are not considered to have an inherent shape, or are considered to have a substantially continuous body, and in the case of portioning, are managed by weight rather than the number of elements that make up the food. Examples include high viscosity kneaded salads such as potato salad, macaroni salad, pasta salad, shredded cabbage, seaweed stew, etc.

[0039] The robot arm 12 moves the gripper 11 attached to the distal end of the robot arm 12, and moves the gripper 11 to a position where the gripper 11 can grip a portion of the food 21. In addition, in a state where the gripper 11 grips a portion of the food 21, the gripper 11 moves to a position of a scale 16 on which a container 22 (described later) is set. The robot arm 12 can move the gripper 11 in any direction among the X-axis direction, the Y-axis direction, and the Z-axis direction. The robot arm 12 is an example of a moving mechanism that moves the gripper 11 (i.e., the gripping portion).

[0040] The rotating mechanism 13 is a mechanism provided between the distal end portion of the robot arm 12 and the gripper 11 and rotates the gripper 11 about a rotation axis along the Z-axis direction (up-down direction). The rotating mechanism 13 is an example of a rotating mechanism that rotates the gripper 11 (ie, a gripping portion).

[0041] The weight meter 14 is disposed above the gripper 11 and measures the weight of the gripper 11. When the gripper 11 grabs the food 21, the weight of the gripper 11 increases. Therefore, by detecting the increase in the weight of the gripper 11, the weight of the food 21 grabbed by the gripper 11 can be measured. The weight meter 14 is an example of a weighing unit that measures the weight of the food held by the gripper 11 (i.e., the gripping portion).

[0042] The imaging device 15 is a camera that is installed above the container 20 and captures an image showing the surface shape of the food in the container 20 from above. The imaging device 15 has a function of measuring the distance to the target object to be imaged, and can measure the height in the Z-axis direction of (each portion of) the food in the container 20. The imaging device 15 is an example of an imaging unit that images the surface shape of the food.

[0043] The scale 16 is installed outside the container 20, and the container 22 into which the food 21 is portioned is placed in the upper area of ​​the scale 16. The scale 16 measures the weight of the food 21 gripped by the gripper 11 and portioned into the container 22.

[0044] The container 20 is a box having an upper opening and side panels including walls extending upward at four sides of a rectangular bottom panel of the box. Food 21 is provided in the container 20. In the present embodiment, the food 21 is described as a food such as potato salad having high viscosity and an indefinite shape, but the present invention is not limited thereto.

[0045] The container supply machine 23 is installed outside the container 20 and adjacent to the scale 16. A plurality of containers 22 are stored in the container supply machine 23, and the containers 22 are taken out one at a time to be conveyed onto the scale 16. When portioning of the food 21 into the container 22 on the scale 16 is completed, the container 22 is moved from the scale 16 to the conveyor 24.

[0046] The conveyor 24 is installed outside the container 20 at a position on the side opposite to the container supply machine 23 with respect to the platform scale 16. The conveyor 24 is configured to be equipped with a conveyor belt, etc. The container 22 into which the food 21 has been portioned is moved from the platform scale 16 to the conveyor belt and conveyed.

[0047] Figure 2 1 is a block diagram illustrating a hardware configuration of the food portioning device 1. The food portioning device 1 obtains information from the weight meter 14, the imaging device 15, and the scale 16, and includes a control device 30 to control the operations of the gripper 11, the robot arm 12, the rotating mechanism 13, and the container supply machine 23. The installation position of the control device 30 is not particularly limited, but it can be installed near the robot arm 12, for example.

[0048] The control device 30 is a computer including a processor 301, a memory 302, and an input / output interface 303. These elements are connected to each other to be able to communicate, for example, via a bus.

[0049] The processor 301 controls each part of the food portioning device 1 by reading out and executing a computer program (hereinafter referred to as a program) stored in the memory 302. The processor 301 is, for example, a central processing unit (CPU). The memory 302 is a storage device that stores an operating system and various programs, data, etc. read by the processor 301.

[0050] The memory 302 includes a primary storage device and an auxiliary storage device. The primary storage device includes, for example, a random access memory (RAM) and a read-only memory (ROM). The auxiliary storage device includes a solid state drive or a hard disk drive. The input / output interface 303 relays signals between the processor 301 and the gripper 11, the robot arm 12, the rotation mechanism 13, the weighing scale 14, the imaging device 15, the platform scale 16, and the container supply machine 23.

[0051] Figure 33 is a block diagram illustrating the functional configuration of the food portioning device 1. The control device 30 of the food portioning device 1 reads and executes the program stored in the memory 302 through the processor 301, and functions as the following units: an image acquisition unit 311, a weight acquisition unit 312, a target value determination unit 313, a position determination unit 314, a movement control unit 315, and a rotation control unit 316. The target value determination unit 313 and the position determination unit 314 are examples of determination units. The movement control unit 315 and the rotation control unit 316 are each an example of a control unit.

[0052] Image acquisition unit 311 acquires image data representing the surface shape of food 21 imaged by imaging device 15 and distance data representing the distance from the surface of food 21. Then, height data representing the height of each portion of the surface of food 21 is calculated from the distance data.

[0053] The weight acquisition unit 312 acquires weight data indicating the weight of the food 21 gripped by the gripper 11 measured by the weight meter 14. In addition, the weight acquisition unit 312 acquires weight data indicating the weight of the food 21 portioned into the container 22 measured by the scale 16.

[0054] The target value decision unit 313 decides a target value for the weight of the food 21 gripped by the gripper 11. The target value is determined as a final target value, a first target value, and a second target value (in some cases, a third target value).

[0055] The final target value is the weight of the food 21 to be portioned into the container 22. In this embodiment, the gripper 11 may perform the gripping operation of the food 21 multiple times so as to portion the food 21 having the weight of the final target value into the container 22.

[0056] The first target value is a target value of the weight of the food 21 acquired by the first gripping operation of the gripper 11, and is a value equal to or less than the final target value. The second target value is a target value of the weight of the food 21 acquired by the second gripping operation of the gripper 11. The second target value is a value obtained by subtracting the weight of the food 21 actually gripped and portioned into the container 22 by the first gripping from the final target value.

[0057] In a case where the total weight of the food 21 acquired through the first grasping operation and the second grasping operation does not reach the final target value, the target value decision unit 313 decides a third target value and then performs a third grasping operation.

[0058] The position determination unit 314 determines a pick-up position as a position where the gripper 11 can hold the food 21 having the weight determined by the target value determination unit 313 based on the image data and the height data acquired by the image acquisition unit 311. A plurality of positions are selected as candidates for the pick-up position, and one of the plurality of positions is determined. The pick-up position is represented by a coordinate value of each of the X-axis direction, the Y-axis direction, and the Z-axis direction of a predetermined portion (e.g., the distal end portion) of the gripper 11.

[0059] The movement control unit 315 moves the gripper 11 to the picking position determined by the position determination unit 314 by driving and controlling the robot arm 12. Next, the movement control unit 315 controls the gripper 11 to hold and grab a portion of the food 21, and moves the gripper 11 in the grabbing state to a position above the platform scale 16. Then, the movement control unit 315 controls the gripper 11 to make the food 21 being grabbed fall into the container 22 set on the platform scale 16.

[0060] Under the control of the movement control unit 315, the rotation control unit 316 executes control to rotate the gripper 11 at the position along the Z-axis direction of the gripper 11 with the center line of the gripper 11 as the rotation axis at the time point when the gripper 11 finishes the operation of gripping the food 21 at the picking position.

[0061] While the rotation control unit 316 performs rotation control, the movement control unit 315 performs control to move the rotation axis in a direction along the XY plane (a plane including the X axis and the Y axis) by driving and controlling the robot arm 12. That is, the gripper 11 moves along the XY plane while rotating.

[0062] Figure 4 is a schematic diagram illustrating the configuration of the gripper 11 . Figure 4 (A) is an external view illustrating a state in which the grasping claw 111 of the grasping member including the distal end of the grasper 11 is closed, Figure 4 (B) is an external view illustrating a state in which the gripping claw 111 at the distal end of the gripper 11 is opened, and Figure 4 (C) in FIG. 1 is a cross-sectional view illustrating the internal structure of the gripper 11 .

[0063] The gripper 11 is configured to have four gripping claws 111, a connecting portion 112, and a base 113. The four gripping claws 111 for gripping the food 21 are provided at a downward distal end portion of the gripper 11. Each gripping claw 111 has a shape obtained by equally dividing a hemisphere (or a part of a sphere) into four parts, and as shown in FIG. Figure 4 As shown in (A) in FIG. 1 , when the four grasping claws 111 are closed, the four grasping claws 111 form a hemispherical shape.

[0064] exist Figure 4 In the state shown in (A) (hereinafter referred to as the closed state), it is possible to grasp the food 21 in the hemispherical shape formed by the four grasping claws 111. In the present embodiment, the grasping claws 111 are provided as four parts, but may be provided as a plurality of parts other than four parts, the shapes of the plurality of parts being obtained by dividing the hemispherical shape into a plurality of equal parts.

[0065] Figure 4 (B) in the figure illustrates a state where the four gripping claws 111 move upward and the hemispherical shape is opened (hereinafter referred to as the open state). The open state is a state where the pickup position has moved and the food 21 located directly below has not yet been grabbed. When the open state is changed to Figure 4 In the closed state shown in (A), the food 21 located directly below is grasped. Figure 4 In the closed state shown in (A) of FIG. 1 , by converting the gripping claw 111 into Figure 4 The open state shown in (B) allows the food 21 grasped by the grasping claw 111 to fall downward. Figure 4 As shown in (B) in FIG. 1 , when the gripping claws 111 are in the open state, the internal wiping member 116 is exposed.

[0066] When the closed state of the gripping claw 111 gripping the food 21 is changed to the open state, the outer periphery of the internal wiping member 116 arranged inside the gripping claw 111 rubs the inner surface of the gripping claw 111 so that the food 21 adhered to the inner surface of the gripping claw 111 can be peeled off and dropped.

[0067] exist Figure 4 In (C), the connection part 112 is provided on the upper side of the grab claw 111 and the internal wiping member 116, and the base 113 is provided on the upper side of the connection part 112. The wiping member 117 is provided on the inner side of the internal wiping member 116, and the internal wiping member 116 is fixed to the wiping member 117. The connection part 112 has a connection gear 1121, a rotating shaft 1122 and a supporting member 1123, and the base 113 is provided with a motor 1131.

[0068] One end of the rotating shaft 1122 is connected to the motor 1131, and the other end is connected to the wiping member 117. Therefore, the wiping member 117 rotates together with the rotating shaft 1122 by the rotation of the motor 1131, and the inner wiping member 116 fixed to the wiping member 117 also rotates. Through the rotating operation, the food 21 adhered to the inner surface of the grab claw 111 is peeled off and dropped, and the food 21 adhered to the inner wiping member 116 can be peeled off.

[0069] The pinion gear is disposed on the rotating shaft 1122 and meshes with the connecting gear 1121. The connecting gear 1121 has an arc shape. Figure 4 Only one gear is illustrated in (C) of FIG. 1 , but four such gears are provided. The four connecting gears 1121 are respectively connected to the four supporting members 1123 . In addition, the four supporting members 1123 are connected to the four grab claws 111 and support the grab claws 111 .

[0070] Figure 4 (C) in the figure illustrates that the gripping claw 111 is in the following Figure 4 The state of the closed state shown in (A) in FIG. In this state, the connecting gear 1121 is meshed with the pinion gear of the rotatable shaft 1122 at the upper position. In this state, the rotatable shaft 1122 is rotated by the rotation of the motor 1131. By the rotation of the rotatable shaft 1122, the connecting gear 1121 meshed with the pinion gear provided on the rotatable shaft 1122 moves along an arc shape, and Figure 4 The lower portion of the connecting gear 1121 in (C) moves upward (ie, in a direction toward a position where the lower portion meshes with the rotatable shaft 1122).

[0071] By the movement of the connecting gear 1121, the supporting member 1123 also moves upward, and the grabbing claw 111 connected to the supporting member 1123 moves upward. As a result, the grabbing claw 111 is transformed into Figure 4 The open state shown in (B).

[0072] In the open state of the grab claw 111, by rotating the motor 1131 in the reverse direction, the connecting gear 1121 can be moved to Figure 4 The position shown in (C) in FIG. 1 and the grab claw 111 can be set to a closed state.

[0073] Figure 5 1 is a diagram for describing the gripping claw 111 of the gripper 11 gripping the food 21 . Figure 5 (A) in FIG. 1 is a diagram illustrating a situation where a relatively large amount of food 21-1 is grasped, and Figure 5 (B) in FIG. 1 is a diagram illustrating a case where a relatively small amount of food 21 - 2 is grasped.

[0074] like Figure 5 As shown in (A) in FIG. 1 , when a large amount of food 21-1 is to be grasped, the grasping claw 111 moves in the Z-axis direction to a position lower than the surface position of the food 21 so that the grasping claw 111 enters a closed state. In this case, since the distal end of the grasping claw 111 reaches a deeper position of the food 21, a larger amount of food 21-1 can be grasped by the grasping claw 111.

[0075] like Figure 5 As shown in (B), when a small amount of food 21-2 is to be grabbed, Figure 5Compared with the case shown in (A) in FIG. 1 , the gripping claw 111 moves in the Z-axis direction to an upward position relative to the surface position of the food 21, and the gripping claw 111 enters a closed state. In this case, due to the Figure 5 Compared with the situation shown in (A) in FIG. 1 , the distal end portion of the grasping claw 111 only reaches a shallower position of the food 21 , so a small amount of food 21 - 2 can be grasped by the grasping claw 111 .

[0076] exist Figure 5 The area S1 of the food 21 that can be grasped by the grasping claw 111 in (A) is larger than that in Figure 5 In (B), the area S2 is the range of the food 21 that can be grasped by the grasping claw 111. Figure 5 In FIG. 1 , although the regions S1 and S2 are illustrated as widths, they are actually illustrated as ranges of regions extending backward in the Y-axis direction.

[0077] In the present embodiment, as described above, it is assumed that the food 21 is grasped multiple times by the grasper 11 to portion out the food 21 having the weight of the final target value. Figure 5 Then, in the second and subsequent grabbing, the following steps are performed: Figure 5 The operation of grabbing a relatively small amount of food 21-2 shown in (B) in FIG.

[0078] like Figure 5 As shown in (A) of FIG. 1 , when grasping a relatively large area S1 on the surface of the food 21, the same as grasping Figure 5 Compared with the case of the relatively small area S2 shown in (B) in FIG. 1 , the error of the weight of the grasped food 21-1 relative to the target value increases. This is because the surface of the food 21 is easily affected by unevenness.

[0079] For example, when executing Figure 5 When the target value is 50g in the case of the grasping shown in (A) in FIG. 1 , the actual grasping weight is about 45g to 55g, and the error range is ±5g. Then, for example, when performing the following Figure 5 In the case of the grasping shown in (B) in FIG. 1 , when the target value is 10 g, the actual grasping weight is about 9 g to 11 g, and the error range is ±1 g, which is smaller than that in Figure 5 ±5g in case (A).

[0080] Therefore, in the first fetch operation, fetch Figure 5The relatively large amount of food 21-1 shown in (A) in the figure is used to obtain a weight close to the final target value, and in the second and subsequent grabbing operations, the remaining small amount of food 21-2 used to reach the final target value is grabbed. The error of the grab weight relative to the target value in the second and subsequent grabbing operations can be reduced, and the food 21 with a weight of the final target value can be reliably obtained through the second or third grabbing operation (or in some cases, a frequency equal to or greater than these).

[0081] As described above, the distal end of the gripping claw 111 of the gripper 11 according to the present embodiment has a tapered shape in the closed state. Therefore, the smaller the amount of food 21 to be gripped, the smaller the error of the gripped weight relative to the target value can be.

[0082] Figure 6 1 is a diagram for describing the gripping claw 111 of the gripper 11 gripping the food 21. Figure 6 In FIG. 1 , the food 21P is illustrated as a graph of surface height positions (Z-axis direction positions) in each predetermined range in the X-axis direction. Figure 6 A cross section along the X-axis direction is illustrated, but the food 21P may be represented by a figure extending also in the Y-axis direction.

[0083] like Figure 6 As shown, the image acquisition unit 311 of the control device 30 can acquire image data representing the surface shape of the food 21 and height data representing the heights of each surface portion of the food 21 from the imaging device 15 to generate a graphic showing the height direction position of the food 21P.

[0084] The position determination unit 314 of the control device 30 generates a position determination unit 314 based on the image data and height data acquired by the image acquisition unit 311. Figure 6 The graph shown is a graph showing the height of the food 21 (food 21P) at each position in the X-axis direction (and the Y-axis direction).

[0085] Based on the graph, the position determination unit 314 selects a position at which the food 21 having the target weight determined by the target value determination unit 313 can be grasped. In the control device 30, average density data of the food 21 is preset, and the position determination unit 314 calculates the volume of the food P to be grasped based on the weight as the target value and the set density data.

[0086] The position determination unit 314 selects the position (X-axis coordinate, Y-axis coordinate and Z-axis coordinate) of the grasping claw 111 that can grasp the food 21 having a volume corresponding to the weight of the target value based on the shape of the grasping claw 111 in the closed state, the height data of each part of the food 21P and the set density data.

[0087] like Figure 6 As shown, the volume of food 21P-1 grasped by the grasping claw 111 is determined by the shape of the grasping claw 111 (known), the position of the grasping claw 111 in each of the X-axis direction, the Y-axis direction and the Z-axis direction, the surface shape of the food 21P (height distribution) and the density of the food 21P (preset).

[0088] The position determination unit 314 determines multiple grasping positions (pickup positions) by calculating the grasping positions in the Z-axis direction at which food 21 having a desired volume can be grasped at multiple positions in the XY plane at which it is predicted that a volume corresponding to a target weight can be grasped.

[0089] Figure 7 1 is a diagram illustrating the structure of the rotating mechanism 13 of the food portioning device 1. Figure 7 As shown, the distal end of the robot arm 12 is provided with a gripper 11, a rotating mechanism 13 and a weight scale 14. The rotating mechanism 13 includes a connecting portion 131, a motor 132 and a rotating shaft 133 driven by the motor.

[0090] The connection part 131 is provided below the rotating mechanism 13, and connects the gripper 11, the weight scale 14, and the rotating mechanism 13. The gripper 11 is attached to the weight scale 14, and the weight scale 14 is attached and fixed to the connection part 131.

[0091] The motor rotating shaft 133 is rotated by the motor 132. The motor 132 is fixed to the robot arm 12. The motor rotating shaft 133 is fixed to the connecting portion 131, and each of the connecting portion 131, the weight scale 14, and the gripper 11 rotates integrally under the rotation of the motor rotating shaft 133. The motor rotating shaft 133 is arranged at the center line L of the gripper 11 (and the gripping claw 111). Under the rotation of the motor rotating shaft 133, the gripper 11 (and the gripping claw 111) has a symmetrical shape relative to the center line L and rotates around the center line L, and the center line L serves as the axis of rotation. In the following, the center line L is also referred to as the gripper rotating shaft L.

[0092] Figure 8 2 is a schematic diagram for describing the rotation control of the gripping claw 111 of the gripper 11 . Figure 8 (A) in FIG. 1 is a plan view for describing the rotation control of the gripping claw 111 in a state where the gripping claw 111 grips the food 21 - 1 . Figure 8 (B) and Figure 8 (C) in FIG. 1 are a cross-sectional view and a plan view respectively illustrating a control example of changing the position of the rotation axis L of the gripping claw 111 (ie, the gripper rotation axis L) in a state where the gripping claw 111 grips the food 21 - 1 .

[0093] Figure 8(A) in the figure illustrates a state where the gripping claw 111 of the gripper 11 is inserted into the pickup position of the food 21 and the gripping claw 111 is set in a closed state to grip the food 21-1. In this state, the rotation control unit 316 of the control device 30 performs rotation control of the gripper 11. By rotating the gripper 11, the gripping claw 111 also rotates in the same manner.

[0094] The gripper 11 rotates around the gripper rotation axis L. The outer shape of the gripper claw 111 in the closed state is a symmetrical shape with respect to the gripper rotation axis L. Preferably, the entire gripper 11 has a symmetrical shape with respect to the center line L.

[0095] The rotation control unit 316 controls the Figure 8 The rotation in the direction of arrow A (hereinafter referred to as the forward rotation direction) shown in (B) is controlled, and then the rotation in the direction of arrow B (hereinafter referred to as the reverse rotation direction) is controlled. Preferably, each rotation angle in the forward rotation direction and the reverse rotation direction is in the range of 45 degrees to 135 degrees.

[0096] The arrow B direction may be a forward rotation direction, and the arrow A direction may be a reverse rotation direction. That is, after rotating in the arrow B direction, rotation may be performed in the arrow A direction. The rotation control as described above is performed by the rotation control unit 316 that controls the rotation mechanism 13.

[0097] like Figure 8 As shown in (B) in FIG. 1 , in a state where the rotation control unit 316 performs rotation control of the gripper 11, that is, during the rotation of the gripper 11 and the gripping claw 111, the movement control unit 315 drives and controls the robot arm 12 to move the gripper 11 in the direction of arrow C within a plane intersecting the gripper rotation axis L (for example, in the XY plane or a horizontal plane orthogonal to the rotation axis), or in the direction of arrow D which is the opposite direction of the direction of arrow C. That is, the rotation control of the gripper 11 is performed while changing the position of the gripper rotation axis L (or the motor rotation axis 133) in the first direction (arrow C direction) or the second direction (arrow D direction).

[0098] For example, while the gripper claw 111 rotates in the forward direction, the gripper rotation axis L can move in the direction of arrow C, and while the gripper claw 111 rotates in the reverse direction, the gripper rotation axis L can move in the direction of arrow D, and vice versa. That is, the gripper rotation axis L performs a linear reciprocating motion in the XY plane in conjunction with the rotation direction.

[0099] Figure 8 (C) in FIG. 1 illustrates another example of the positional movement of the gripper rotation axis L (indicated by L1 to L4 in the drawing) performed during the rotation of the gripper 11 by the rotation control unit 316. Figure 8 In (C), the gripper claw 111 moves so that the gripper rotation axis L defines a circular trajectory centered on the central axis R (axis along the Z-axis direction) in the XY plane.

[0100] Figure 8 Point L1 and circle G in (C) in FIG. 1 represent the peripheral positions of the gripper rotation axis L and the gripping claw 111 at the time point of gripping the food 21-1. Symbols L2, L3, and L4 represent respective positions on the moving trajectory centered on the central axis R of the gripper rotation axis L. Circles G2, G3, and G4 represent the peripheral positions of the gripping claw 111 of the gripper 11 when the gripper rotation axis L is located at each of the positions L2, L3, and L4.

[0101] The gripper rotation axis L moves in the arrow E direction or the arrow F direction which is the opposite direction of the arrow E direction. Figure 8 The movement control of the gripper rotation axis L in (C) is performed by Figure 8 The movement control unit 315 of the control device 30 drives and controls the robot arm 12 in the same manner as shown in (B).

[0102] For example, when the gripper claw 111 rotates in the forward direction, the gripper rotation axis L can move in the direction of arrow E, and when the gripper claw 111 rotates in the reverse direction, the gripper rotation axis L can move in the direction of arrow F, and vice versa. Figure 8 In (C), although the gripper rotation axis L moves within a trajectory range close to a complete circle (close to 360 degrees), a semicircular range (180 degree rotation) can be used, or a 1 / 4 circle range (90 degree rotation) less than 180 degrees can be used.

[0103] As described above, by performing movement control of the position of the gripper rotation axis L while the gripper 11 is rotating, the outer surfaces of the gripping claws 111 are pressed against the food 21 located near them. In this way, by rubbing (wiping) on ​​the side of the food 21 near the outer surfaces of the gripping claws 111, the food 21 adhering to the outer surfaces of the gripping claws 111 is removed from the outer surfaces of the gripping claws 111.

[0104] In addition, if Figure 8 As shown in (A) of FIG. 1 , by rotating the gripper 11 and as Figure 8 (B) and Figure 8 By moving the gripper rotation axis L as shown in (C) in FIG. 1 , food 21 adhered to any position on the outer peripheral surface of the gripping claw 111 of the gripper 11 can also be rubbed evenly on the food 21 in the vicinity thereof.

[0105] Fig. 93 is a flowchart illustrating the processing of the control device 30 of the food portioning device 1. The processor 301 of the control device 30 reads out and executes the program stored in the memory 302 to perform Fig. 9 Processing shown.

[0106] First, the target value determination unit 313 of the control device 30 obtains the final target value of the weight of the food 21 to be portioned into the container 22 (step S601 ). The final target value is preset by the user and stored in the memory 302 of the control device 30 .

[0107] Subsequently, the target value determination unit 313 determines a first target value, which is a target value for the weight of the food 21 to be grasped by the gripper 11 in the first grasping operation (step S602). For example, assume that the final target value obtained in step S601 is 75g. When the error of the final target value is allowed to reach +3g, the final target value is 75g to 78g. For example, the first target value in the first grasping operation is set within a range of 35g to 75g equal to or less than the final target value. The reason for setting the first target value (its lower limit) is that, in the case where the grasping amount deviates significantly from the final target value (for example, 50% or less of the final target value), if the grasping amount is released and the grasping operation is restarted from the beginning, it is likely to shorten the time required for the final grasping operation or the total amount of portioned food to reach the final target value.

[0108] Subsequently, the image acquisition unit 311 acquires image data representing the surface shape of the food 21 and height data representing the height of each portion of the surface from the imaging device 15 (step S603). The position determination unit 314 calculates the volume of the food 21 to be grasped based on the weight of the first target value determined by the target value determination unit 313 and the preset density data of the food 21. Since the first target value is 35g to 75g as described above, 60g, which is a value between 35g and 75g, is used as a reference value here to calculate the volume of the food 21 to be grasped. Then, the position determination unit 314 determines a plurality of pickup positions (X-axis coordinates, Y-axis coordinates, and Z-axis coordinates) of the gripper 11 at which it is predicted that the food 21 having the corresponding volume can be grasped (step S604). Subsequently, the grasping control is performed by the movement control unit 315 and the rotation control unit 316 (step S605).

[0109] Fig.10 30 is a flowchart illustrating the pickup control performed by the movement control unit 315 and the rotation control unit 316 of the control device 30. The processor 301 of the control device 30 reads out and executes the program stored in the memory 302, and executes Fig.10 In the following, the processing shown in Fig.10 Grab control shown.

[0110] First, the movement control unit 315 selects one of the plurality of pick-up positions determined by the position determination unit 314, and moves the gripper 11 to the position of the X-coordinate value and the Y-coordinate value represented by the pick-up position (step S651). The movement is performed by driving and controlling the robot arm 12. During the movement, the gripping claw 111 of the gripper 11 is set to an open state. The position of the gripper 11 in the Z-axis direction is moved to a position sufficiently high relative to the surface height of the food 21, so that the gripper 11 does not contact the surface of the food 21.

[0111] When the gripper 11 is moved to the position of the X-coordinate value and the Y-coordinate value indicated by the pick-up position, the movement control unit 315 drives and controls the robot arm 12 to move the gripper 11 downward and to the position of the Z-axis coordinate value indicated by the pick-up position (step S652).

[0112] Next, the movement control unit 315 performs control to set the gripping claws 111 of the gripper 11 to a closed state (step S653). This control results in a state where the food 21 is gripped in the closed gripping claws 111. Hereinafter, the gripped food 21 may be referred to as food 21-1.

[0113] Subsequently, the rotation control unit 316 controls the rotation of the gripper 11 by driving and controlling the rotation mechanism 13 (step S654). In this case, during the rotation of the gripper 11, the movement control unit 315 drives and controls the robot arm 12 to perform control (wiping operation) of moving the gripper rotation axis L in the XY plane (horizontal plane). That is, the movement control unit 315 performs control (wiping operation) of moving the gripper rotation axis L in the XY plane (horizontal plane). Figure 8 The rotation control shown in (A) in FIG. 1 and the execution Figure 8 (B) or Figure 8 Movement control of the gripper rotation axis L shown in (C).

[0114] Subsequently, the movement control unit 315 drives and controls the robot arm 12 to move the gripper 11 upward and to a position sufficiently high relative to the surface height of the food 21 (step S655).

[0115] Return to reference Fig. 9 To describe, in a state where the food 21-1 is grasped by the grasping claw 111 of the grasper 11, the weight acquisition unit 312 acquires the weight measurement value of the food 21-1 grasped by the grasping claw 111 from the weight meter 14 (step S606). Then, the weight acquisition unit 312 determines whether the acquired weight measurement value satisfies the first target value, that is, whether it is within the range of the first target value (35 g to 75 g) (step S607).

[0116] When the acquired weight measurement value does not meet the first target value (step S607: No), that is, when the grasped weight is too small (less than 35g) or the grasped weight is too large (more than 75g), the movement control unit 315 performs control to set the grasping claw 111 of the grasper 11 to the open state. In this case, the grasped food 21-1 falls and is put back into the container 20 (step S608).

[0117] Subsequently, the target value determination unit 313 redetermines the first target value (step S609). The first target value may be redetermined to be the same as the set value at the previous time, or a value different from the set value at the previous time may be redetermined as the first target value. For example, when the weight measurement value is larger than the first target value at the previous time, the first target value may be determined to be a smaller value than the previous time. In addition, when the weight measurement value is less than the first target value at the previous time, the first target value may be determined to be a larger value than the previous time.

[0118] Then, the process returns to step S604, and the grasping process based on the re-determined first target value is repeated again. When the pick-up position is determined in step S604, since the pick-up position among multiple positions has been determined in the process of the previous time, the grasping process is performed at a pick-up position different from the previous time.

[0119] In the determination of step S607, when the weight that has been grasped is too large, the error relative to the final target value (here, for example, 75g) may be considered. That is, for example, in the case where an error of 3g is allowed, when the final target value is 78g or less, the process may proceed to the process of the next step S610.

[0120] When the acquired weight measurement value satisfies the first target value (step S607: Yes), that is, in the range of 35 g to 75 g, the movement control unit 315 moves the gripper 11 to the position of the scale 16 (step S610).

[0121] When the movement control unit 315 moves the gripper 11 to a position above the platform scale 16, the gripping claws 111 of the gripper 11 are set to an open state, and the gripped food 21-1 falls into the container 22 set on the platform scale 16 (step S611).

[0122] Next, the weight acquisition unit 312 acquires the weight measurement value of the food 21-1 in the container 22 measured by the scale 16 (step S612). Then, the weight acquisition unit 312 determines whether the weight measurement value is less than the final target value (step S613).

[0123] When the weight measurement value reaches the final target value (step S613: No), the food portioning process is completed, and the control device 30 performs control to end the process. For example, the control device 30 outputs a signal indicating that portioning is completed to the container supply machine 23 to end the process. Then, the container supply machine 23 moves the container 22 on the scale 16 in which the food 21-1 has been portioned to the conveyor 24, and conveys the next container 22 to the scale 16. Recognizing that the next container 22d is placed on the scale 16, the control device 30 starts again. Fig. 9 The process is shown in the flowchart.

[0124] When the weight measurement value is less than the final target value (step S613: yes), that is, when the weight measurement value of the food 21-1 in the container 22 of the scale 16 does not reach 75g which is the final target value, the target value determination unit 313 determines the second target value in the next (second) grasping operation.

[0125] The second target value is set to a value obtained by subtracting the weight measurement value obtained in step S612 (the weight measurement value obtained by the scale 16) from the final target value (step S614). For example, when the weight measurement value obtained in step S612 is 65g, the second target value is 10g obtained by subtracting 65g from the final target value 75g. Then, the process returns to step S602 to perform the second grasping operation.

[0126] The process of steps S602 to S614 is repeated until the weight measurement value reaches the final target value in step S613. That is, after the second grasping operation, the third grasping operation and subsequent grasping operations may be performed.

[0127] As described above, in the present embodiment, a target value having a relatively large weight in the first grabbing operation is determined, and the grabbing operation of the grabber 11 is performed. When grabbing a large weight, the error of the actual grabbing weight relative to the target value increases. However, in the second grabbing operation and subsequent grabbing operations, since the target value is lower than the first time, the error of the actual grabbing weight relative to the target value decreases. Therefore, by performing the second operation or the third operation (or a frequency equal to or greater than this), the food 21 can be portioned with a high-precision final target value. For example, although the amount of error allowed by law, industry practice or the final target value is small, appropriate portioning can still be achieved.

[0128] [Modification Example] The above-described embodiment can be modified in various ways. The following will illustrate an example of its modification. The above-described embodiment and the following modification example can be appropriately combined.

[0129] (1) In the above embodiment, the gripper 11 has a hemispherical shape in the closed state where the food 21 is gripped by the plurality of gripping claws 111, and therefore, the smaller the amount of food 21 to be gripped, the smaller the error of the gripping weight relative to the set target value. However, the configuration of the distal end portion of the gripper 11 is not limited thereto.

[0130] For example, in the case of a configuration having a spherical shape in the closed state, the number and shape of the gripping claws are not limited to the above examples. In addition to the spherical shape, for example, a cone shape (cone or pyramid) may be used. In short, it is preferred that the distal end of the shape tapers with respect to the Z-axis direction (direction of insertion of food; depth direction).

[0131] In addition, depending on the characteristics of the target object to be portioned, a structure in which a closed space such as a sphere or a cone is not formed (in other words, the distal ends of the respective claws do not contact each other) may be used in the grasping state.

[0132] Fig.11 1 and 2 are diagrams for describing a schematic shape of a gripping claw 511 of a gripper 51 according to a modified example and a gripping food 21 . Fig.11 (A) in FIG. 1 is a diagram illustrating a situation where a relatively large amount of food 21-3 is grabbed, and Fig.11 (B) in FIG. 1 is a diagram illustrating a case where a relatively small amount of food 21 - 4 is grasped.

[0133] As shown in the figure, a plurality of (two in the example of the drawing) flat plate-shaped grasping claws 511 as grasping members are provided at the distal end of the grasper 51 to face each other so that they are in a state of being respectively inclined inward (center side). The grasper 51 falls, the grasping claws 511 are inserted into the food 21, and the two grasping claws 511 are respectively moved inward (the distance between the grasping claws 511 is shortened), so that the food 21-3 or the food 21-4 between the two grasping claws 511 is grasped.

[0134] like Fig.11 As shown, the distance between the two gripping claws 511 can be changed by the gripper 51 . Fig.11 The distance between the two gripping claws 511 in (A) is Fig.11 The distance between the two gripping claws 511 in (B) is long. Fig.11 (A) and Fig.11 In (B), the length of the grasping claw 511 in the Z-axis direction (vertical direction) remains unchanged.

[0135] like Fig.11 As shown in (A) in FIG. 1 , by increasing the distance between the two gripping claws 511, the area S3 can be increased, and the area S3 is the range in which the food 21 can be gripped. Fig.11As shown in (B) in FIG. 1 , by shortening the distance between the two grasping claws 511 , the area S4 , which is the range in which the food 21 can be grasped, can be reduced.

[0136] As in the above embodiment Figure 5 (A) and Figure 5 (B) in Fig.11 Compared with the case where a relatively small area S4 is captured as shown in (B) in FIG. Fig.11 In the case where a relatively large area S3 of the surface of the food 21 is grasped as shown in (A) in FIG. 1 , the weight error of the grasped food 21-3 relative to the target value is large.

[0137] Therefore, in the first grab operation where the target value is relatively large, Fig.11 As shown in (A) in the figure, a relatively large amount of food 21-3 is grasped to obtain a weight close to the final target value, and in the second grasping operation and the subsequent grasping operation with a relatively small target value, a relatively small amount of food 21-4 is grasped. In this way, the error of the grasping weight relative to the target value in the second and subsequent times can be reduced, and the food 21 with the weight of the final target value can be obtained by the second grasping or the third grasping.

[0138] (2) In the above embodiment, in the container 20 in which the food 21 is placed, the side panels serving as walls extend from the four sides of the bottom panel, but a configuration may be adopted in which the side panels serving as walls are not required.

[0139] Fig.12 2 are diagrams illustrating a container 20A according to a modified example. Fig.12 (A) in FIG. 1 is a diagram showing a grabbing operation of a food 21 by using the container 20 according to the above embodiment. Fig.12 (B) in FIG. 1 is a diagram showing a grasping operation of a food 21 by using a container 20A according to a modified example.

[0140] exist Fig.12 In (A), the container 20 is configured to have a bottom panel 201 and a side panel 202. When the gripper 11 performs a gripping operation of the food 21 in the container 20, as described above with reference to Figure 8 (B) and Figure 8 As described in (C), in a state where food 21 is partially grasped by claw 111 to press nearby food 21, grasping claw 111 moves in a horizontal direction and performs an operation in which food 21 adhered to the outer surface of grasping claw 111 rubs against nearby food 21.

[0141] When such a grasping operation is repeated in the container 20, the grasping operation is performed at a position close to the side panel 202 on the outer peripheral side of the container 20. In this case, as shown in FIG. Fig.12 As shown in (A) in FIG. 2 , food 21 located at a position close to side panel 202 is pressed against side panel 202 , and food 21 gradually adheres to side panel 202 .

[0142] It is difficult to grasp the food 21 adhered to the side panel 202 with the gripping claw 111. In addition, in the case where the gripper 11 performs a gripping operation at a position close to the side panel 202, the food 21 adhered to the side panel 202 may come into contact with the outer peripheral portion of the gripper 11 located above the gripping claw 111 and adhere to the gripper 11. Therefore, the food 21 attached to the portion of the gripper 11 other than the gripping claw 111 is difficult to be wiped off, and as a result, the measurement accuracy of the weight meter 14 may be adversely affected.

[0143] exist Fig.12 In the container 20A of (B), the side panel 202 is not provided, and the food 21 is placed on the bottom panel 201. In this configuration, when the gripper 11 repeats the gripping operation of the food 21 in the container 21A, the food 21 spreads to the outer peripheral side of the container 20A. Fig.12 The side surface shown in (A) in FIG. 1 is formed so that the food 21 does not adhere to the portion of the gripper 11 other than the gripping claw 111 .

[0144] Furthermore, by sequentially performing the gripping operation of the gripper 11 on the food 21 on the outer peripheral side of the container 20A, it is possible to prevent the food 21 from being pushed outward to the outside of the side panel 202 of the container 20A, thereby bringing the food 21 into the inside.

[0145] (3) In the above-mentioned embodiment, the target value of the weight of the food to be grasped by the grasper 11 in the grasping operation is arbitrarily set by the user, but in the control device 30, the target value can be set by considering the physical properties (viscosity, etc.) or type of the food, the grasping frequency or time constraints, or the allowable error in the final target weight, etc.

[0146] Furthermore, in the above embodiment, although it is assumed that the grabbing operation is performed multiple times, an upper limit value of the frequency of the grabbing operation (frequency of the portioning operation) may be preset, and a target value each time may be determined based on the upper limit value each time.

[0147] (4) In the above-mentioned embodiment, although the pick-up position is determined by calculating the volume of the food corresponding to the weight of the target value and determining the position where the food with the calculated volume can be grasped based on the image data and height data of the food from the imaging device 15, in the control device 30, a learning model can be generated in advance, and the pick-up position can be determined using the learning model.

[0148] For example, using the food portioning device 1 according to the above-described embodiment, for each type of food, at a plurality of pickup positions, the food is grabbed by the gripper 11, and the weight of the grabbed food is measured by the weight meter 14 or the scale 16. A learning model is generated by the control device 30, and the learning model learns the measurement data and the image data at each pickup position imaged by the imaging device 15.

[0149] In actual food portioning processing, the target value determination unit 313 of the control device 30 determines the picking position (the picking position of the first picking operation and the picking position of the second and subsequent picking operations) according to the target value of the weight to be grabbed and the image data of the food from the imaging device 15 by using a learning model corresponding to the type of target food.

[0150] (5) In the above embodiment, the position determination unit 314 of the control device 30 determines the pickup position at which the food 21 having a volume corresponding to the weight of the target value can be grasped based on the preset average density data of the food 21. Alternatively, the position determination unit 314 may determine the pickup position based on the density of each part of the food 21 calculated based on the image data of the food 21 from the imaging device 15.

[0151] For example, when the food 21 is potato salad, by using image data according to image recognition, the density of each portion can be estimated by the distribution of potatoes, cucumbers, and carrots that are food ingredients constituting the potato salad, that is, the proportion of each food ingredient in each portion. By estimating the volume that can be grasped at the pickup position candidate using the estimated value of the density, the pickup position can be determined. As described above, even in the case where the food has uneven density, the pickup position can be appropriately determined.

[0152] (6) In the above embodiment, during the rotation control of the gripper 11 in the state of gripping the food 21-1, as shown in FIG. Figure 8 (B) and Figure 8 As shown in (C) in FIG. 1 , the movement control of the gripping claw 111 of the gripper 11 is performed in the XY plane (horizontal plane), but in addition to or instead of the movement control, the control of moving the gripping claw 111 downward in the gripper rotation axis L direction (the downward direction of the Z axis; the direction toward the bottom of the container) can also be performed. The movement control can be performed by the movement control unit 315 of the control device 30 that drives and controls the robot arm 12, as shown in FIG. Figure 8 (B) and Figure 8 Movement control shown in (C).

[0153] In this way, while the gripper 11 rotates or while performing movement control of the position of the gripper rotation axis L, the gripping claw 111 moves downward so that the outer surface of the gripping claw 111 can be pressed against the food 21 located below, and the food 21 adhered to the lower surface of the gripping claw 111 can rub against the food 21 located below and thus can be removed.

[0154] Similarly, while the gripper 11 is rotating or while the movement control of the position of the gripper rotation axis L is being performed, the gripping claw 111 may be moved upward. Figure 8 In step S655, while performing a rotation operation and / or a movement operation in the XY plane, the gripping claw 111 is pulled up so that food adhered to the gripping claw 111 can be rubbed on or shaken off to nearby food.

[0155] (7) In the above embodiment, when the rotation control about the gripper rotation axis L of the gripper 11 is performed after the food 21 is grasped, the rotation angle is optionally set, but the rotation angle may be set according to the viscosity of the food 21. For example, when the food 21 to be grasped has a high viscosity, the rotation angle may be increased. In addition, the rotation speed may be set instead of the rotation angle. For example, the rotation speed may be determined to be increased corresponding to the case of grasping the food 21 with a large viscosity.

[0156] In addition, regarding Figure 8 The movement control of the gripper rotation axis L in the horizontal direction shown in (B) can set the movement distance or movement speed according to the viscosity of the food 21. For example, when the food 21 to be grasped has high viscosity, the movement distance of the gripper rotation axis L in the horizontal direction can be increased. In addition, for example, the movement speed of the gripper rotation axis L in the horizontal direction can be determined to increase correspondingly to the case of grasping the food 21 with high viscosity.

[0157] In addition, regarding Figure 8 The rotation control centered on the central axis R of the gripper rotation axis L shown in (C) can set the rotation angle or rotation speed according to the viscosity and other physical properties of the food 21. For example, when the food 21 to be grasped has high viscosity, the rotation angle centered on the central axis R of the gripper rotation axis L can be increased. In addition, when grasping a food 21 with high viscosity, the rotation speed centered on the central axis R of the gripper rotation axis L can be increased. Similarly, according to the physical properties of the food 21, the movement speed of the gripper claw 111 in the Z-axis direction can be set, or the movement speed, movement amount (distance) and path of the gripper rotation axis L in the XY plane can be set.

[0158] (8) In the above-described embodiment, food is an object, but the present invention can be applied to objects other than food as long as the object can be grasped. The apparatus according to the embodiment of the present invention is particularly suitable for processing portioning of viscous objects having indefinite shapes.

[0159] (9) In the above embodiment, the food 21 is portioned into the container 22, but when the food ingredients of the meal of the customer in the restaurant etc. are portioned, the portioning can be performed on tableware such as plates. In this case, a tableware supply machine can be installed instead of the container supply machine 23.

[0160] In short, the portioning method according to the present invention includes the following steps: determining a first target value of the weight of an object to be portioned in one grasping operation, the first target value being calculated based on a final target value of the portioning amount in the case of portioning a portion of the object; determining a first pickup position corresponding to the first target value based on a captured image; and moving a gripper to the first pickup position to grab a portion of the object and perform portioning of the object. When the weight of the object portioned by one grasping operation meets the target value, determining a second target value of the weight of the object to be portioned by the next grasping operation, determining a second pickup position corresponding to the second target value, and moving the gripper to the second pickup position to grab and perform portioning of the object, and when the weight of the object portioned by one grasping operation of the gripper does not meet the first target value, re-determining the first target value to perform grasping of the object according to the re-determined first target value.

[0161] Reference numerals list

[0162] 1 Food portioning device 11 Grabber 12 Robot arm 13 Rotating mechanism 14 Weight meter

[0163] 15 imaging device 16 scale 20 container 21 food 22 container 23 container supply machine

[0164] 24 conveyor 30 control device 51 gripper 111 gripper claw 112 connection part

[0165] 113 base 116 internal wiping member 117 wiping member 201 bottom panel 202 side panel

[0166] 301 processor 302 memory 303 input / output interface 311 image acquisition unit

[0167] 312 weight acquisition unit 313 target value determination unit 314 position determination unit

[0168] 315 movement control unit 316 rotation control unit 511 grab claw 1121 connection gear

[0169] 1122 rotatable shaft 1123 supporting member 1131 motor

Claims

1. A food portioning device, comprising: a gripper configured to grasp a portion of a food product having an indeterminate shape and disposed in a container; a moving mechanism configured to move the gripper; a weighing unit configured to measure the weight of a food product held by the gripper; An imaging unit, the imaging unit being configured to image the surface shape of the food; a decision unit configured to decide a first target value of the weight of the food to be portioned out by one grabbing operation calculated based on the final target value to be portioned out, and the decision unit configured to decide a first pickup position corresponding to the first target value based on the image captured by the imaging unit; as well as a control unit configured to perform portioning of the food by moving the gripper to the first pick-up position via the moving mechanism, wherein, when the weight of the food portioned out by the one grabbing operation of the gripper satisfies the first target value, the decision unit determines a second target value for the weight of the food to be portioned out by the next grabbing operation, and determines a second picking position corresponding to the second target value, and the control unit performs the portioning of the food by moving the gripper to the second picking position, and When the weight of the food portioned out by the one grabbing operation of the grabber does not satisfy the first target value, the determination unit redetermines the first target value, and the control unit performs grabbing of the food with the redetermined first target value.

2. The food portioning device according to claim 1, in, The distal end of the gripper tapers gradually toward a position for gripping the food.

3. The food portioning device according to claim 1, in, The shape of the gripper changes according to the first target value and the second target value.

4. A food portioning device according to any one of claims 1 to 3, in, The decision unit decides, for each food, a frequency of a grabbing operation to be performed and a target value of a weight of the food to be portioned out in each grabbing operation.

5. A food portioning device according to any one of claims 1 to 4, in, The decision unit generates a learning model that learns, for each food, measurement data of the weight of the food gripped by the gripper at a pickup position and image data of the pickup position, and decides the first pickup position and the second pickup position using the learning model.

6. A food portioning device according to any one of claims 1 to 5, in, The density of the food is non-uniform, and The determination unit further determines the first pickup position and the second pickup position based on the density calculated from the image.

7. A program that causes a computer to: a determining unit configured to determine a first target value of a weight of food to be portioned out by one grasping operation, the first target value being calculated based on a final target value of a portioned amount when a portion of food having an indefinite shape is portioned, and to determine a first pickup position corresponding to the first target value based on a captured image; and a control unit configured to perform portioning of the food product by moving a gripper that grips a portion of the food product at the first pick-up position to the first pick-up position, in, When the weight of the food portioned out by the one grabbing operation of the gripper satisfies the first target value, the decision unit determines a second target value for the weight of the food to be portioned out by the next grabbing operation and determines a second pick-up position corresponding to the second target value, and the control unit performs the portioning of the food by moving the gripper to the second pick-up position, and When the weight of the food portioned out by the one grabbing operation of the grabber does not satisfy the first target value, the determination unit redetermines the first target value, and the control unit performs grabbing of the food with the redetermined first target value.

Images