JP2023171034A - Information processor, robot system, information processing method, article manufacturing method, program, and recording medium - Google Patents

Abstract

To reduce calculation loads.SOLUTION: An information processor includes an information processing part for outputting information on a holding position, wherein the information processing part executes a process of acquiring a workpiece model and a hand model as shape data, a process of setting a first point on the workpiece model, a process of setting a virtual straight line crossing the workpiece model at the first point, and a process of acquiring a second point crossing the virtual straight line in the workpiece model, when the virtual straight line crosses the workpiece model in any point other than the first point.SELECTED DRAWING: Figure 1

Description

The present invention relates to robot technology.

2. Description of the Related Art A picking operation is known in which a robot hand is used to pick out one workpiece from a plurality of workpieces stacked in bulk. In picking work, in order to take out one workpiece, it is necessary to set in advance information regarding the holding position, including positional information on the workpiece that can be held by the robot hand.

Since the plurality of works stacked in bulk overlap each other, it has been difficult to take out the workpiece to be held when the holding position of the workpiece to be held overlaps with another workpiece. Therefore, in order to increase the success rate of taking out the workpiece to be held, it is preferable to set information regarding a plurality of holding positions for one workpiece.

Patent Document 1 discloses that information regarding a holding position is obtained by geometric calculation using a hand model that is shape data of a robot hand and a workpiece model that is shape data of a workpiece. Specifically, Patent Document 1 describes how to find combinations of two parallel planes that are parallel to each other in a workpiece model through a full search, and determine whether or not all combinations can be maintained by the hand model. A technique for setting a surface as information regarding a holding position is disclosed.

Japanese Patent Application Publication No. 2015-044274

However, in Patent Document 1, since it is necessary to perform a complete search for combinations of two parallel surfaces, the calculation load for obtaining information regarding the holding position is large. Therefore, it has been desired to reduce the calculation load for obtaining information regarding the holding position.

The present invention aims to reduce the calculation load.

According to a first aspect of the present invention, there is provided an information processing apparatus including an information processing section that outputs information regarding holding positions, wherein the information processing section acquires a workpiece model and a hand model that are shape data; a process of setting a first point on the work model; a process of setting a virtual straight line that intersects the work model at the first point; and when the virtual straight line intersects the work model at a point other than the first point, A process of acquiring a second point intersecting the virtual straight line in the work model is performed.

According to a second aspect of the present invention, there is provided an information processing method for outputting information regarding holding positions, wherein a workpiece model and a hand model, which are shape data, are acquired, a first point is set on the workpiece model, and the first point is set on the workpiece model. setting a virtual straight line that intersects the work model at one point, and if the virtual straight line intersects the work model at a point other than the first point, obtaining a second point that intersects the virtual straight line in the work model; It is characterized by

According to the present invention, calculation load can be reduced.

FIG. 1 is an explanatory diagram showing a schematic configuration of a robot system according to an embodiment. FIG. 1 is an explanatory diagram of an image processing device according to an embodiment. FIG. 2 is a block diagram of a computer system in a robot system according to an embodiment. FIG. 3 is a functional block diagram of an information processing unit according to an embodiment. FIG. 3 is a functional block diagram of a work information acquisition unit according to the embodiment. It is an explanatory diagram of processing of a work information acquisition part concerning an embodiment. FIG. 3 is a functional block diagram of a retained information acquisition unit according to the embodiment. FIG. 6 is an explanatory diagram of processing of a retained information acquisition unit according to the embodiment. FIG. 3 is a functional block diagram of a sampling unit according to the embodiment. FIG. 3 is an explanatory diagram of processing by the sampling unit according to the embodiment. It is a functional block diagram of a search part concerning an embodiment. (a) and (b) are explanatory diagrams of processing of the straight line acquisition unit according to the embodiment. FIG. 3 is an explanatory diagram of processing of an intersection calculation unit according to the embodiment. (a), (b), and (c) are explanatory diagrams showing examples of data sets according to the embodiment. FIG. 2 is a functional block diagram of a determination unit according to an embodiment. (a) is an explanatory diagram of the determination processing of the interference determination unit according to the embodiment. (b) is an explanatory diagram of the determination processing of the holding allowance determination unit according to the embodiment. FIG. 3 is a functional block diagram of a data output unit according to the embodiment. FIG. 3 is an explanatory diagram of a user interface image according to the embodiment.

Hereinafter, embodiments for carrying out the present invention will be described in detail with reference to the drawings. FIG. 1 is an explanatory diagram showing a schematic configuration of a robot system 10 according to an embodiment. The robot system 10 includes a robot 100, an image processing device 200 that is an example of an information processing device, a robot controller 300, and a camera 401 that is an example of an imaging device. The robot 100 is an industrial robot, placed on a production line, and used to manufacture articles.

Robot 100 is a manipulator. The robot 100 is fixed to a pedestal, for example. A container 30 with an open top is arranged around the robot 100. Inside the container 30, a plurality of works W are stacked in bulk. That is, a plurality of works W are stacked in bulk on the inner bottom surface 301 of the container 30. Each workpiece W is an example of a holding target, and is, for example, a component. A plurality of works W in the container 30 are held one by one by the robot 100 and transported to a predetermined position. The plurality of works W have the same shape, the same size, and the same color. Further, the workpiece W is a rigid body in this embodiment.

The robot 100 and the robot controller 300 are communicably connected by wiring. The robot controller 300 and the image processing device 200 are communicably connected by wiring. The camera 401 and the image processing device 200 are communicably connected by wire or wirelessly.

The robot 100 has a robot arm 101 and a robot hand 102 that is an end effector, that is, a holding mechanism. The robot arm 101 is a vertical multi-joint robot arm. Robot hand 102 is supported by robot arm 101. The robot hand 102 is attached to a predetermined portion of the robot arm 101, for example, to the tip of the robot arm 101. The robot hand 102 is configured to be able to hold the workpiece W.

The robot hand 102 has a plurality of fingers, for example two fingers 111 and 112. The two fingers 111 and 112 are configured to be able to approach and separate from each other by a drive mechanism (not shown) of the robot hand 102. The robot hand 102 can hold the workpiece W with two fingers 111 and 112.

Note that holding the workpiece W by the robot hand 102 includes gripping the workpiece W by sandwiching the outer side of the workpiece W between the fingers 111 and 112. In addition, when the workpiece W is a hollow member such as a pipe, the robot hand 102 holds the workpiece W by pressing the fingers 111 and 112 against the inner wall of the workpiece W to prevent the workpiece W from falling from the robot hand 102. This includes holding and holding the object.

With the above configuration, the robot arm 101 can move the robot hand 102 to a desired position and cause the robot 100 to perform a desired work. For example, by preparing a workpiece W and another workpiece and having the robot 100 perform a task of assembling the workpiece W to the other workpiece, an assembled article can be manufactured. In addition, although this embodiment has been described by taking as an example the manufacture of an article by assembling workpieces by the robot 100, the present invention is not limited to this. For example, the robot arm 101 may be provided with a tool such as a cutting tool or a polishing tool, and the article may be manufactured by processing a workpiece with the tool.

Camera 401 is a digital camera and has an image sensor (not shown). The image sensor is, for example, a CMOS image sensor or a CCD image sensor. The camera 401 is fixed to a frame (not shown) placed around the robot 100. The camera 401 is arranged at a position where it can image an area including a plurality of works W arranged in the container 30. That is, the camera 401 can image an area including the workpiece W to be held by the robot 100. For example, the camera 401 is placed above the robot 100 so as to capture an image vertically downward.

The image processing device 200 is configured by a computer in this embodiment. The image processing device 200 can send an imaging command to the camera 401 to cause the camera 401 to perform imaging. The image processing device 200 is configured to be able to acquire image data generated by the camera 401, and is configured to be able to process the acquired image data. Then, the image processing device 200 generates information on the position and orientation of the workpiece W as information on the workpiece W by performing image processing on the image data.

FIG. 2 is an explanatory diagram of the image processing device 200 according to the embodiment. The image processing device 200 includes a main body 201, a display 202 that is an example of a display section, and a keyboard 203 and a mouse 204 that are examples of input devices. A display 202, a keyboard 203, and a mouse 204 are connected to the main body 201.

The robot controller 300 shown in FIG. 1 is composed of a computer in this embodiment. The robot controller 300 is configured to be able to control the operation of the robot 100, that is, the posture of the robot 100, based on information about the workpiece W obtained through image processing by the image processing device 200. Specifically, the robot controller 300 calculates a target posture of the robot 100 for causing the robot hand 102 to hold a holding position on the workpiece W based on information regarding the holding position from information on the position and posture of the workpiece W. Then, the robot controller 300 controls the robot 100 so that the robot 100 assumes the target posture, and causes the robot hand 102 to maintain the holding position of the workpiece W. Information regarding the holding position is generated by calculation in the image processing device 200, as will be described later. The information regarding the holding position includes coordinate information of a point on the workpiece W that is brought into contact with each finger 111, 112 of the robot hand 102. The information regarding the holding position may include information on the opening width of the fingers 111 and 112.

FIG. 3 is a block diagram of the computer system in the robot system 10 according to the embodiment. The main body 201 of the image processing device 200 includes a CPU (Central Processing Unit) 271, which is an example of a processor. The CPU 271 functions as an information processing unit by executing the program 281. The main body 201 also includes a ROM (Read Only Memory) 272, a RAM (Random Access Memory) 273, and an HDD (Hard Disk Drive) 274 as storage units. The main body 201 also includes a recording disk drive 275 and an interface 276 that is an input/output interface. The CPU 271, ROM 272, RAM 273, HDD 274, recording disk drive 275, and interface 276 are connected to each other via a bus so that they can communicate with each other.

A robot controller 300, a display 202, a keyboard 203, a mouse 204, and a camera 401 are connected to an interface 276 of the main body 201.

The ROM 272 stores basic programs related to the operation of the computer. The RAM 273 is a storage device that temporarily stores various data such as arithmetic processing results of the CPU 271. The HDD 274 records calculation results of the CPU 271 and various data acquired from the outside, as well as a program 281 for causing the CPU 271 to execute various processes. The program 281 is application software that can be executed by the CPU 271.

By executing the program 281 recorded on the HDD 274, the CPU 271 can perform arithmetic processing to be described later. Furthermore, by executing the program 281, the CPU 271 can control the camera 401, acquire image data from the camera 401, and perform image processing on the image data. The recording disk drive 275 can read various data, programs, etc. recorded on the recording disk 282.

In this embodiment, the computer-readable non-temporary recording medium is the HDD 274, and the program 281 is recorded on the HDD 274, but the present invention is not limited to this. The program 281 may be recorded on any computer-readable non-transitory recording medium. As a recording medium for supplying the program 281 to the computer, for example, a flexible disk, hard disk, optical disk, magneto-optical disk, magnetic tape, nonvolatile memory, etc. can be used.

The robot controller 300 includes a CPU 351 that is an example of a processor. The CPU 351 functions as a control unit by executing a program 361. The robot controller 300 also includes a ROM 352, a RAM 353, and an HDD 354 as storage units. The robot controller 300 also includes a recording disk drive 355 and an interface 356 that is an input/output interface. The CPU 351, ROM 352, RAM 353, HDD 354, recording disk drive 355, and interface 356 are connected to each other via a bus so that they can communicate with each other.

The ROM 352 stores basic programs related to the operation of the computer. The RAM 353 is a storage device that temporarily stores various data such as arithmetic processing results of the CPU 351. The HDD 354 records arithmetic processing results of the CPU 351 and various data acquired from the outside, and also records (stores) a program 361 for causing the CPU 351 to execute various processes. The program 361 is application software that can be executed by the CPU 351.

By executing the program 361 recorded on the HDD 354, the CPU 351 can execute control processing and control the operation of the robot 100 in FIG. The recording disk drive 355 can read various data, programs, etc. recorded on the recording disk 362.

In this embodiment, the computer-readable non-temporary recording medium is the HDD 354, and the program 361 is recorded on the HDD 354, but the present invention is not limited to this. The program 361 may be recorded on any computer-readable non-temporary recording medium. As a recording medium for supplying the program 361 to the computer, for example, a flexible disk, hard disk, optical disk, magneto-optical disk, magnetic tape, nonvolatile memory, etc. can be used.

In this embodiment, the functions of the information processing section and the control section are realized by a plurality of computers, that is, a plurality of CPUs 271 and 351, but the present invention is not limited to this. The functions of the information processing section and the control section may be implemented in one computer, that is, one CPU.

FIG. 4 is a functional block diagram of the information processing unit 20 according to the embodiment. The CPU 271 of the image processing device 200 functions as the information processing section 20 by executing the program 281. The information processing section 20 includes a work information acquisition section 21, a retained information acquisition section 22, a sampling section 23, a search section 24, a determination section 25, and a data output section 26, as shown in FIG. The information processing section 20 executes the processing of each section 21 to 26 and outputs information 611 regarding the holding position.

The workpiece information acquisition unit 21 acquires a workpiece model WM, which is three-dimensional shape data of the workpiece W. The held information acquisition unit 22 acquires a hand model HM, which is three-dimensional shape data of the robot hand 102. Hand model HM includes finger models corresponding to fingers 111 and 112. Each finger model includes area data corresponding to a real area that can hold the workpiece W included in the finger.

Each model WM, HM is polygon data such as three-dimensional CAD (Computer Aided Design) data or STL (Standard Triangled Language/Stereolithography) data.

The workpiece model WM is shape data corresponding to the surface of the workpiece W. Hand model HM is shape data corresponding to the surface of robot hand 102. The inner region surrounded by the workpiece model WM corresponds to the inside of the workpiece W. Furthermore, the inner region surrounded by the hand model HM corresponds to the inside of the robot hand 102.

The sampling unit 23 sets a first point on the workpiece model WM by sampling points on the workpiece model WM (surface) at regular intervals. The search unit 24 calculates a second point on the work model WM that corresponds to the first point sampled by the sampling unit 23, and obtains a data set including information (data) on these two points. The search unit 24 acquires a plurality of data sets. The determining unit 25 determines whether the hand model HM can hold the work model WM for each data set acquired by the searching unit 24, and includes the data set determined to be holdable as a candidate for information regarding the holding position. . The data output unit 26 outputs information (data) 611 regarding the holding position based on the candidates calculated by the determination unit 25.

The work information acquisition unit 21 will be explained using FIG. 5. FIG. 5 is a functional block diagram of the work information acquisition unit 21 according to the embodiment. The workpiece information acquisition section 21 includes a reading section 211 and a triangulation section 212, and outputs a workpiece model WM.

FIG. 6 is an explanatory diagram of the processing of the work information acquisition unit 21 according to the embodiment. The workpiece information acquisition unit 21 acquires a workpiece model WM as shown in FIG. The work model WM is shape data expressed by a plurality of polygons PG. Each polygon PG is a part of the workpiece model WM (surface shape). Each polygon PG is a polygon. It is preferable that the polygon PG is a triangle. An example in which the polygon PG is a triangle will be described below.

The reading unit 211 reads shape data of the workpiece W from a storage device such as the HDD 274 in FIG. 3 or a network, for example. Note that the read shape data of the workpiece W may be in any format as long as it represents the shape of the workpiece, and may be, for example, data acquired by a 3D scanner, CAD data, STL data representing polygon information, or the like.

The triangulation unit 212 unifies the shape data of the workpiece W read into the reading unit 211 into a polygon PG representation. That is, if the shape data read into the reading unit 211 is data expressed by polygons PG, the triangulation unit 212 outputs the shape data read into the reading unit 211 as is as the work model WM. Further, if the shape data read into the reading unit 211 is not data expressed by polygons PG, the triangulation unit 212 converts the shape data read into the reading unit 211 into data expressed by polygons PG. , and outputs the converted data as a work model WM.

Next, the held information acquisition unit 22 will be explained using FIG. 7. FIG. 7 is a functional block diagram of the retained information acquisition unit 22 according to the embodiment. The retained information acquisition section 22 includes a reading section 221, a triangulation section 222, and a definition section 223, and outputs a hand model HM, relational information IM1, and area information IM2.

FIG. 8 is an explanatory diagram of processing of the retained information acquisition unit 22 according to the embodiment. The held information acquisition unit 22 acquires a hand model HM as shown in FIG. In this embodiment, since the robot hand 102 has two fingers 111 and 112 as a plurality of fingers, the hand model HM has a finger model FM1 corresponding to the finger 111 and a finger model FM2 corresponding to the finger 112. . Finger models FM1 and FM2, like fingers 111 and 112, can be moved close to and separated from each other. Finger 111 is an example of a first finger, and finger model FM1 is an example of the first finger model. Finger 112 is an example of a second finger, and finger model FM2 is an example of the second finger model.

Note that the robot hand 102 may have three or more fingers. For example, when the robot hand 102 further includes a third finger and a fourth finger, the hand model HM further includes a third finger model and a fourth finger model.

The reading unit 221 reads the shape data of the robot hand 102 from a storage device such as the HDD 274 in FIG. 3 or a network, for example. Note that the read shape data of the robot hand 102 may be in any format as long as it represents the shape of the hand, and may be, for example, data acquired by a 3D scanner, CAD data, STL data representing polygon information, or the like.

The triangulation unit 222 unifies the shape data of the robot hand 102 read into the reading unit 221 into a polygon representation. That is, if the shape data read into the reading unit 221 is data expressed by polygons, the triangulation unit 222 outputs the shape data read into the reading unit 221 as it is as a hand model HM. Further, if the shape data read into the reading unit 221 is not data expressed by polygons, the triangulation unit 222 converts the shape data read into the reading unit 221 into data expressed by polygons, and converts the shape data read into the reading unit 221 into data expressed by polygons. The converted data is output as a hand model HM. Note that the polygons in the hand model HM are preferably expressed as triangles similarly to the workpiece model WM, but may be polygons other than triangles.

As shown in FIG. 8, the definition unit 223 defines relationship information IM1 indicating the geometric relationship between the finger model FM1 and the finger model FM2 in the hand model HM, and defines area information IM2 used for holding allowance determination to be described later. and outputs related information IM1 and area information IM2.

The region information IM2 includes information indicating a region R1 that is included in the finger model FM1 and corresponds to a region in which the finger 111 can hold the workpiece W. Further, the region information IM2 includes information indicating a region R2 that is defined in the finger model FM2 and corresponds to a region in which the finger 112 can hold the workpiece W. A center point PC1 is defined in the region R1, and a center point PC2 is defined in the region R2. Center point PC1 is an example of a first predetermined point, and center point PC2 is an example of a second predetermined point. Center point PC1 is a point fixed to finger model FM1, and center point PC2 is a point fixed to finger model FM2.

The relationship information IM1 includes information on the maximum opening distance between finger models FM1 and FM2, information on the minimum opening distance between finger models FM1 and FM2, and information on the distance from the center point PC1 of the region R1 to the center point PC2 of the region R2. Contains information on vector V21. Vector V21 is an example of a predetermined direction.

Note that when the hand model HM further includes a third finger model and a fourth finger model, the definition unit 223 generates a vector from the center point PC1 to the center point of the area defined in the third finger model, and a vector from the center point PC1 to the center point of the area defined in the third finger model. A vector directed toward the center point of the area defined in the fourth finger model may be further defined.

Next, the sampling section 23 will be explained using FIG. 9. FIG. 9 is a functional block diagram of the sampling section 23 according to the embodiment. The sampling unit 23 includes a grid calculation unit 231, an intersection calculation unit 232, and a shape determination unit 233, and sets at least one sampling point P1 for each of the plurality of polygons PG in the workpiece model WM.

FIG. 10 is an explanatory diagram of the processing of the sampling unit 23 according to the embodiment. In the present embodiment, the sampling unit 23 acquires, for one polygon PG, a number of sampling points P1 according to the size (area) of the polygon PG.

Description will be given focusing on one polygon PG shown in FIG. 10. The polygon PG shown in FIG. 10 is represented by a triangle having three vertices A, B, and C. The grid calculating unit 231 defines a grid G having an interval of sampling width _ra on the same plane as the polygon PG.

The intersection calculation unit 232 defines the grid G as follows. One side of grid G is defined to be parallel to side AB and at a position r _a /2 away from side AB. A plurality of intersection points in grid G are expressed as P(i,j) or P _i,j . Among the plurality of intersection points P(i,j), a point included inside the triangle ABC, that is, inside the polygon PG, is defined as a sampling point P1.

Here, if the point P(i,j) is expressed as a vector with respect to the vertex A, the following equation (1) is obtained.

Note that in equation (1), arrows represent vectors. In Equation (1), the AD vector is a vector that is perpendicular to the AB vector, has a length equal to the distance between the side AB and the point C, and is the vector that makes the smallest angle with the AC vector.

Here, the AD vector has the relationship of the following equations (2) and (3).

When formulas (2) and (3) are substituted into formula (1) and rearranged, the following formula (4) is obtained.

Next, the shape determining unit 233 selects the sampling point P1 existing within the triangle ABC from among the grid intersection points P(i,j) obtained by the intersection calculating unit 232. The condition that the grid intersection P(i,j) exists within the triangle ABC can be expressed using the following equation (5).

The sampling point P1 is obtained by sequentially increasing i and j in equation (4) from 0, and calculating all the combinations of i and j that satisfy the condition of equation (5). Note that if the size of the polygon PG is less than the sampling interval _ra , the sampling unit 23 sets the center of the polygon PG as the sampling point P1.

Further, during sampling, it is preferable that the sampling unit 23 sets a plurality of sampling points P1 at equal intervals in a grid pattern in the inner region of the polygon PG on the surface of the workpiece model WM. Thereby, in the polygon PG, the density of the sampling points P1 does not locally become too dense, and a sufficient number of sampling points P1 can be acquired.

Note that the method for setting the sampling point P1 is preferably the method described above, but is not limited thereto. For example, the sampling point P1 may be set at the center or apex of the polygon PG.

As described above, the sampling unit 23 sets at least one sampling point P1 for each of all polygons PG included in the workpiece model WM. The sampling point P1 explained above is an example of the first point.

Next, the search unit 24 will be explained using FIG. 11. FIG. 11 is a functional block diagram of the search unit 24 according to the embodiment. The search unit 24 includes a normal line acquisition unit 241, a straight line acquisition unit 242, and an intersection calculation unit 243, and outputs a data set 411 to be determined. Data set 411 is an example of a set including a first point and a second point.

FIG. 12A is an explanatory diagram of the processing of the straight line acquisition unit 242 according to the embodiment. The following description will focus on one sampling point P1 among the plurality of sampling points P1 on the workpiece model WM. As shown in FIG. 12(a), one sampling point P1 of interest is defined as a point s _i . The straight line acquisition unit 242 executes a process of setting a virtual straight line L1 that intersects the work model WM at the point s _i . In this embodiment, the intersection calculation unit 243 moves the center point PC1 of the finger model FM1 in a direction parallel to the vector V21 directed from the finger model FM1 to the finger model FM2 in a state where the center point PC1 is positioned with respect to the point s _i of the workpiece model WM. A virtual straight line L1 is set so as to extend. As described above, the vector V21 is the direction from the center point PC1 of the finger model FM1 to the center point PC2 of the finger model FM2.

The calculation processing of the intersection calculation unit 243 will be described in detail below. Let N _W be the normal line at point s _i of the workpiece model WM, and n _i be the normal vector. The normal acquisition unit 241 calculates the normal vector n _i . The normal N _W is a line that is orthogonal to the workpiece model WM at the point s _i . Information about the normal N _W is included in the normal vector n _i . The normal acquisition unit 241 may obtain the normal vector n _i using the normal information of the polygon PG to which the point s _i belongs, or may average the polygon information around the point s _i . The normal vector n _i may be obtained by performing smoothing processing.

The straight line acquisition unit 242 first positions the finger model FM1 so that the center point PC1 of the finger model FM1 coincides with, that is, overlaps the point s _i , as shown in FIG. 12(a). At this time, the straight line acquisition unit 242 makes sure that the normal N _H of the center point PC1 of the finger model FM1, that is, the normal vector, and the normal N _W of the point s _i , that is, the normal vector n _i are on a straight line. The finger model FM1 is positioned relative to the workpiece model WM. That is, the straight line acquisition unit 242 sets the center point PC1 of the finger model FM1 to the workpiece model WM so that the normal line _NH at the center _point PC1 of the finger model FM1 matches the normal line _NW at the point si of the workpiece model WM. Position with respect to point s _i of . The normal line N _H is a line orthogonal to the finger model FM1 at the center point PC1.

Note that the finger model FM1 can take a plurality of postures with the normal vector n _i as the center of rotation, and may select one posture or a plurality of postures from among these postures. Furthermore, the finger model FM1 may be positioned so that the center point PC1 of the finger model FM1 is separated from the point s _i by a certain distance. At this time, it is preferable that the straight line acquisition unit 242 positions the finger model FM1 with respect to the workpiece model so that the normal line N _H matches the normal line N _W.

In FIG. 12(a), the vector V21 from the center point PC1 of finger model FM1 to the center point PC2 of finger model FM2 matches the direction of the normal line N _H at point PC1 of finger model FM1, but they do not match. In some cases.

The straight line acquisition unit 242 may set a plurality of virtual straight lines, for example, three virtual straight lines L1, L2, and L3, so as to extend in mutually different directions at the point s _i , as shown in FIG. 12(b). One of the virtual straight lines L1, L2, and L3 is the virtual straight line L1. The virtual straight lines L2 and L3 other than the virtual straight line L1 are preferably set to intersect with the virtual straight line L1 at a point s _i at an angle included in a predetermined angle range Δθ. Moreover, it is preferable that the predetermined angle range Δθ is an angle range of 1 degree or more and 5 degrees or less.

Next, as shown in FIG. 13, when the virtual straight line L1 intersects the work model WM (surface) at a point other than the point s _i , the intersection calculation unit 243 calculates at least one intersection point that intersects with the virtual straight line L1 in the work model WM. get. FIG. 13 is an explanatory diagram of the processing of the intersection calculation unit 243 according to the embodiment. In the example of FIG. 13, at least one intersection is a plurality of intersections, and each intersection is a point l _ik (k is an integer). Each point l _ik is an example of a second point. A data set 411 including a combination of one point s _i and one point l _ik is a determination target of the determination unit 25, which will be described later.

Note that the intersection calculation unit 243 may use a general method such as raycasting to calculate the intersection. Since various studies have been conducted to speed up such methods, calculation can be performed faster by using these techniques.

Although one sampling point P1, that is, the point s _i has been described above, the search unit 24 obtains the data set 411 for all sampling points P1 included in each polygon PG. Furthermore, the search unit 24 obtains a data set 411 for all polygons PG. In this way, multiple data sets 411 are obtained. Furthermore, in this embodiment, since the hand model HM has two finger models FM1 and FM2, the data set 411 includes information on the two points s _i and l _ik ; however, the point information included in the data set 411 The number is the same as the number of finger models that the hand model HM has. For example, if the hand model HM has three finger models, the data set 411 includes three point information.

FIGS. 14(a), 14(b), and 14(c) are explanatory diagrams showing examples of the data set 411 according to the embodiment. In FIG. 14A, a data set 411 1 including a point s _i and a point l _i1 is illustrated as the data set ₄₁₁ . FIG. 14B shows, as the data set 411, a data set 411 ₂ including the point s _i and the point l _i2 . FIG. 14C shows, as the data set 411, a data set ₄₁₁₃ including the point s _i and the point l _i3 . The next determination unit 25 determines whether or not these data sets 411 ₁ to 411 ₃ are included as candidates for information regarding holding positions.

Next, the determination unit 25 will be explained using FIG. 15. FIG. 15 is a functional block diagram of the determination unit 25 according to the embodiment. The determining unit 25 includes an interference determining unit 251 and a holding allowance determining unit 252, and outputs candidates 511 of information regarding the holding position. The determining unit 25 performs a process of determining whether or not the data set 411 is included in the candidates 511 for information regarding holding positions. The candidate 511 may consist only of the data set 411, or may include other information, for example, information about the opening width of the fingers 111 and 112. The opening width of the fingers 111 and 112 can be calculated from the information of the point s _i and the point l _i2 included in the data set 411. In the example of this embodiment, the candidate 511 will be described as one that does not include information on the opening width.

Although the data set 411 includes a combination of points s _i and l _ik , the robot hand 102 is not necessarily able to hold the position on the actual work W corresponding to the data set 411 . Therefore, the determination unit 25 determines whether a predetermined condition is satisfied in the positioning state in which the hand model HM is positioned with respect to the points s _i and l _ik of the workpiece model WM, and if it is determined that the predetermined condition is satisfied, the data set 411 is Include in candidate 511. When a plurality of data sets 411 satisfying a predetermined condition are obtained, a plurality of candidates 511 in the same number as the data sets 411 are obtained.

Here, the predetermined condition is a condition under which the robot hand 102 is likely to successfully hold the workpiece W. The predetermined conditions include conditions 1 and 2 below.
Condition 1. Hand model HM should not interfere with work model WM.
Condition 2. There must be sufficient holding allowance for the hand model HM.

In addition, in the following determination process, the determination unit 25 makes the determination with the finger model FM1 positioned with respect to the point s _i of the workpiece model WM, and the finger model FM2 positioned with respect to the point _lik of the workpiece model WM. do. More specifically, the determining unit 25 makes the determination while positioning the center point PC1 of the finger model FM1 with respect to the point s _i and positioning the center point PC2 of the finger model FM2 with respect to the point l _ik .

The interference determination unit 251 performs the determination of condition 1. That is, the interference determination unit 251 determines whether the hand model HM interferes with the workpiece model WM. Here, the hand model HM interfering with the workpiece model WM means that the hand model HM overlaps the workpiece model WM, that is, the hand model HM is buried in the workpiece model WM. In other words, condition 1 is a condition that the hand model HM does not overlap the workpiece model WM. That is, the interference determination unit 251 determines whether at least a portion of the hand model HM overlaps at least a portion of the workpiece model WM.

In the examples shown in FIGS. 14(a) and 14(c), the hand model HM does not interfere with the workpiece model WM. That is, the hand model HM does not overlap the workpiece model WM. On the other hand, in the example of FIG. 14(b), the finger model FM of the hand model HM interferes with the workpiece model WM. In other words, the finger model FM overlaps with the workpiece model WM, that is, it is buried.

FIG. 16A is an explanatory diagram of determination processing by the interference determination unit 251 according to the embodiment. The explanation will focus on one data set 411. The data set 411 includes information on points s _i and l _ik . The interference determination unit 251 positions the hand model HM at a position separated by a predetermined distance D1 in the direction of the normal vector n _i at the point s _i of the workpiece model WM, and determines whether the hand model HM interferes with the workpiece model WM. judge. Data sets 411 that are determined to interfere are excluded from the candidates. In the examples shown in FIGS. 14(a) to 14(c), the data set 411 ₂ is excluded from the candidates, and the data sets 411 ₁ and 411 ₃ are determined by the retention allowance determination unit 252.

The holding allowance determination unit 252 performs the determination of condition 2. That is, the holding allowance determining unit 252 evaluates the holding allowance in the regions R1 and R2 of the hand model HM with respect to the data set 411 determined by the interference determining unit 251 to not interfere. In this embodiment, the robot hand 102 includes two fingers 111 and 112. That is, the hand model HM includes two finger models FM1 and FM2. Therefore, in this embodiment, the holding allowance determination unit 252 performs the determination of Condition 2 for each of the two finger models FM1 and FM2. In other words, condition 2 is that the area of the part of the finger model FM1 of the hand model HM that can come into contact with the area including point s _i of the workpiece model WM is equal to or larger than a predetermined area, and that the finger model FM2 of the hand model HM has This includes the condition that the area of the part that can come into contact with the area including the point _lik of the model WM is equal to or larger than a predetermined area.

The determination process for finger model FM1 will be described below, and the determination process for finger model FM2 will be omitted because it is the same as the determination process for finger model FM1. FIG. 16(b) is an explanatory diagram of determination processing by the holding allowance determination unit 252 according to the embodiment. In evaluating the holding allowance, when the robot hand 102 holds the workpiece W, the area of the area where the robot hand 102 can come into contact with the workpiece W, that is, the area of the area where the hand model HM can come into contact with the workpiece model WM is used. Let A1 be the area of the region where the finger model FM1 of the hand model HM can come into contact with the workpiece model WM. Further, the area of the above-mentioned region R1 is assumed to be A2.

The retention allowance ratio pc is expressed by the following equation (6).

In this embodiment, the holding allowance determination unit 252 determines whether the ratio pc is equal to or greater than a threshold value tc (0≦tc≦1). Area A1 is the area of a region included in region R1. The area A1 is the area of a portion of the workpiece model WM where the distance from the region R1 of the finger model FM1 is D1±Δd is projected in the direction of the normal vector n _i at the point s _i . The area A1 is also the area of a portion of the hand model HM that can come into contact with the area including the point s _i of the workpiece model WM. In other words, it is also the area of the area where the robot hand 102 can come into contact with the workpiece W. In this way, the holding margin determining unit 252 calculates the area A1 corresponding to the point s _i . Note that the same applies to the point l _ik , and the holding margin determining unit 252 calculates the area A1 corresponding to the point l _ik . Note that the area A2 and the threshold value tc are constants.

The holding allowance determination unit 252 includes the data set 411 in which the ratio pc of the two finger models FM1 and FM2 is determined to be equal to or greater than the threshold value tc as the candidate for information regarding the holding position 511. Data sets 411 for which the proportion pc of one or both of the two finger models FM1 and FM2 is determined to be less than the threshold tc are not selected as candidates 511 and are excluded. In this manner, through the processing of the determination unit 25, only the data set 411 that is highly likely to successfully hold the workpiece W is left as the candidate 511. It is preferable that the threshold value tc is 0.3 or more.

Note that, although the holding allowance determining unit 252 makes the determination based on the percentage pc, the present invention is not limited to this. Area A2 and threshold tc are constants. The area A1 is the area required by the holding allowance determination unit 252. Therefore, the holding allowance determination unit 252 may directly determine whether the area A1 is equal to or larger than a predetermined area. The predetermined area is A2×tc. That is, determining based on the ratio pc is synonymous with determining based on the area A1, and indirectly determines whether the area A1 is greater than or equal to a predetermined area. Then, the data set 411 whose area A1 is equal to or larger than a predetermined area may be set as the candidate 511 for information regarding the holding position.

Further, the order of processing by the interference determining section 251 and the holding allowance determining section 252 may be reversed. Further, the processing of the determination unit 25 may be performed after the normal acquisition unit 241 or the intersection calculation unit 243 in the search unit 24. In addition, in the search unit 24, if the angle between the normal vector of point s _i and the normal vector of point l _ik is 90 degrees or less, for example, 0 degrees, it is excluded from the data set to be determined. This makes it possible to speed up the processing of the determination unit 25.

The data output section 26 will be explained using FIG. 17. FIG. 17 is a functional block diagram of the data output unit 26 according to the embodiment. The data output unit 26 includes a visualization unit 261, a selection unit 262, a coordinate conversion unit 263, and a writing unit 264, and outputs information 611 regarding the holding position.

The holding position information candidates 511 calculated by the determination unit 25 are passed to the robot controller 300 as holding position information 611 by the data output unit 26 for use by the robot controller 300. The robot controller 300 can control the robot 100 based on the holding position information 611 to perform tasks such as picking workpieces W that are stacked in bulk.

In this embodiment, the CPU 351 of the robot controller 300 acquires information on the position and orientation of the workpiece W from the captured image data by capturing an image of the workpiece W with the camera 401, and acquires information on the position and orientation of the workpiece W based on information 611 regarding the holding position of the workpiece W. The robot arm 101 and the robot hand 102 are controlled to hold the robot arm 101 and the robot hand 102. Thereby, the robot 100 can perform a picking operation of picking the works W that are stacked in bulk.

To explain with a specific example, the CPU 351 of the robot controller 300 converts the position and orientation information of the workpiece W acquired from the captured image data and the point information included in the information 611 regarding the holding position into the robot coordinate system. , the posture of the robot 100 when holding the workpiece W is determined. Then, the CPU 351 generates trajectory data of the robot 100 within the movable range of the robot 100 so that the robot 100 does not interfere with surrounding objects. Then, the CPU 351 causes the robot 100 to pick the workpiece W by controlling the robot 100 according to the trajectory data. Thereafter, the CPU 51 causes the robot 100 to perform tasks such as assembling the workpiece W to another workpiece.

Note that the information on the above-mentioned points s _i and l _ik included in the information 611 regarding the holding position may be coordinate information of the workpiece coordinate system or coordinate information of the robot coordinate system. If the information on the points s _i and l _ik described above is coordinate information in the robot coordinate system, the robot controller 300 can omit the coordinate transformation process. Note that the coordinate information includes information on three position coordinates and three angular coordinates. Further, the information 611 regarding the holding position may additionally include information such as the opening width of the fingers 111 and 112 of the robot hand 102.

FIG. 18 is an explanatory diagram of a user interface (UI) image UI1 according to the embodiment. The visualization unit 261 executes display processing to display the UI image UI1 shown in FIG. 18 on the display 202 shown in FIG. 2. The UI image UI1 is an image that serves as a graphical user interface. The UI image UI1 includes an image display section 601, a selection reception section 602, an output button 603, and the like.

The visualization unit 261 displays a work image WI corresponding to the work model WM on the image display unit 601. Work image WI is an example of the first image. Furthermore, the visualization unit 261 displays a candidate image 511I corresponding to the candidate 511 on the work image WI so that the user can select it. Candidate image 511I is an example of the second image. Furthermore, the visualization unit 261 displays the image LI corresponding to the virtual straight line L1 in an overlapping manner with the workpiece image WI.

The selection unit 262 selects the candidate 511 by the user or automatically. The selection unit 262 receives the user's selection of the candidate 511 from the selection reception unit 602 shown in FIG. The selection unit 262 displays the currently selected candidate image 511I by highlighting it, for example, to indicate that it is being selected.

The user can select addition or deletion of the candidate 511 to be included in the information 611 regarding the holding position by operating the selection reception unit 602 or the like while referring to the image displayed on the image display unit 601. . Further, the selection unit 626 selects addition or deletion of the candidate image 511 to be included in the information 611 regarding the holding position by the user selecting the candidate image 511I displayed on the image display unit 601 with a mouse pointer or the like. be able to. Further, the selection unit 626 may automatically perform a process of deleting redundant candidates from among the plurality of candidates 511. For example, the selection unit 626 performs a process of comparing two candidates 511 and deleting one whose retention allowance is smaller than a predetermined value among the candidates 511 whose total distance and/or angle between the candidates 511 is less than or equal to a threshold value. It's okay.

When the output button 603 is operated, the selection unit 262 includes the candidate 511 corresponding to the selected candidate image 511I in the information 611 regarding the holding position to be output.

The coordinate conversion unit 263 converts the coordinates of the point information included in the information 611 regarding the holding position, as necessary. Note that the processing of the coordinate transformation unit 263 may be omitted.

The writing unit 264 outputs the information 611 regarding the holding position to a file in, for example, a comma-delimited text file format. The generated file is output to the robot controller 300.

The information 611 regarding the holding position includes information about the point s _i and the point l _ik . The coordinate information of the point s _i and the point l _ik may be expressed in the workpiece coordinate system, or may be expressed in the robot coordinate system if the coordinate transformation unit 263 performs transformation processing. Further, the information 611 regarding the holding position may include information on the opening width of the fingers 111 and 112. Further, the information 611 regarding the holding position may include other information such as additional information such as holding area.

In this way, the data output unit 26 generates information 611 regarding the holding position based on the candidate 511 corresponding to the candidate image 511I selected by the user in the UI image UI1, and sends the information 611 regarding the holding position to the robot controller 300. Output.

According to this embodiment, when the information processing unit 20 obtains the candidates 511, that is, the information 611 regarding the holding positions, it is possible to reduce the number of points determined as holding position candidates using virtual straight lines, and the calculation load on the information processing unit 20 is reduced. can be reduced. Therefore, when there are multiple types of workpieces W, it is necessary to perform calculations for each type of workpiece W, so the calculation load on the information processing section 20 is reduced, thereby shortening the calculation time of the information processing section 20. can do. In addition, in the robot 100, the success rate of picking workpieces W stacked in bulk can also be increased.

The present invention is not limited to the embodiments described above, and many modifications can be made within the technical idea of the present invention. Furthermore, the effects described in the embodiments are merely a list of the most preferable effects resulting from the present invention, and the effects of the present invention are not limited to those described in the embodiments.

In the above-described embodiment, a case has been described in which the robot arm 101 is a vertically articulated robot arm, but the present invention is not limited to this. The robot arm 101 may be any of various robot arms, such as a horizontal multi-joint robot arm, a parallel link robot arm, or an orthogonal robot. Furthermore, the present invention is also applicable to machines that can automatically extend and contract, bend and stretch, move up and down, move left and right, or turn, or a combination of these actions, based on information in a storage device provided in a control device. .

Further, in the above-described embodiment, the case where the imaging device is the camera 401 has been described, but the present invention is not limited to this. The imaging device may be an electronic device equipped with an image sensor, such as a mobile communication device such as a smartphone, a tablet PC, and a game console, or a wearable device.

(Other examples)
The present invention provides a system or device with a program that implements one or more functions of the embodiments described above via a network or a storage medium, and one or more processors in a computer of the system or device reads and executes the program. This can also be achieved by processing. It can also be realized by a circuit (for example, ASIC) that realizes one or more functions.

The disclosure of the above embodiments includes the following configurations and methods.

(Configuration 1)
An information processing device comprising an information processing unit that outputs information regarding a holding position,
The information processing unit includes:
A process of acquiring a work model and a hand model, which are shape data,
a process of setting a first point on the work model;
a process of setting a virtual straight line that intersects the work model at the first point;
If the virtual straight line intersects the work model at a point other than the first point, acquiring a second point intersecting the virtual straight line in the work model;
An information processing device characterized by:

(Configuration 2)
The information processing unit includes:
executing a process of determining whether information on the first point and the second point is included in candidates for information regarding the holding position;
The information processing device according to configuration 1, characterized in that:

(Configuration 3)
The information processing unit includes:
In the determining process, if a predetermined condition is satisfied in the positioning state in which the hand model is positioned with respect to the first point and the second point of the workpiece model, the first point and the second point are selected as the candidates. include,
The information processing device according to configuration 2, characterized in that:

(Configuration 4)
The hand model has a first finger model and a second finger model that can approach and separate from each other,
The positioning state is a state in which the first finger model is positioned with respect to the first point, and the second finger model is positioned with respect to the second point.
The information processing device according to configuration 3, characterized in that:

(Configuration 5)
The positioning state is a state in which a first predetermined point of the first finger model is positioned with respect to the first point, and a second predetermined point of the second finger model is positioned with respect to the second point. ,
The information processing device according to configuration 4, characterized in that:

(Configuration 6)
The predetermined condition includes a condition that the hand model does not overlap the workpiece model.
The information processing device according to any one of configurations 3 to 5, characterized in that:

(Configuration 7)
The predetermined condition includes a condition that, in the hand model, the area of a portion of the workpiece model that can come into contact with a region including the first point is equal to or larger than a predetermined area;
The information processing device according to any one of configurations 3 to 6, characterized in that:

(Configuration 8)
The predetermined condition includes a condition that, in the hand model, the area of a portion of the workpiece model that can come into contact with a region including the second point is equal to or larger than a predetermined area.
The information processing device according to any one of configurations 3 to 7, characterized in that:

(Configuration 9)
The hand model has a first finger model and a second finger model that can approach and separate from each other,
The information processing unit includes:
In the process of setting the virtual straight line, in a state in which the first finger model is positioned with respect to the first point of the workpiece model, a direction parallel to a predetermined direction from the first finger model toward the second finger model; setting the virtual straight line so that it extends to
9. The information processing device according to any one of configurations 1 to 8, characterized in that:

(Configuration 10)
The predetermined direction is a direction from a first predetermined point of the first finger model to a second predetermined point of the second finger model,
The information processing device according to configuration 9, characterized in that:

(Configuration 11)
The information processing unit includes:
In the process of setting the virtual straight line, the first finger model is set so that the normal line at the first point of the work model matches the normal line at the first predetermined point of the first finger model. positioning with respect to the first point of the workpiece model;
The information processing device according to configuration 10, characterized in that:

(Configuration 12)
The information processing unit includes:
In the process of setting the virtual straight line, positioning the first finger model with respect to the first point of the workpiece model so that the first predetermined point overlaps the first point;
The information processing device according to configuration 10, characterized in that:

(Configuration 13)
The information processing unit includes:
In the process of setting the virtual straight line, setting a plurality of virtual straight lines so as to extend in mutually different directions at the first point;
The information processing device according to any one of Configurations 1 to 12, characterized in that:

(Configuration 14)
The information processing unit includes:
In the process of setting the virtual straight line, a virtual straight line other than one virtual straight line among the plurality of virtual straight lines is set to intersect the one virtual straight line within a predetermined angular range;
The information processing device according to configuration 13, characterized in that:

(Configuration 15)
The predetermined angle range is 1 degree or more and 5 degrees or less,
15. The information processing device according to configuration 14.

(Configuration 16)
The work model is data expressed by a plurality of polygons,
The information processing device according to any one of Configurations 1 to 15, characterized in that:

(Configuration 17)
the polygon is a triangle;
17. The information processing device according to configuration 16.

(Configuration 18)
The information processing unit includes:
In the process of setting the first point, setting at least one first point for each of the plurality of polygons;
17. The information processing device according to configuration 16.

(Configuration 19)
the at least one first point is a plurality of first points;
19. The information processing device according to configuration 18.

(Configuration 20)
The plurality of first points are arranged at equal intervals from each other,
The information processing device according to configuration 19, characterized in that:

(Configuration 21)
The information processing unit includes:
executing a process of displaying a first image corresponding to the workpiece model on a display unit;
21. The information processing device according to any one of Configurations 1 to 20, characterized in that:

(Configuration 22)
The information processing unit includes:
In the process of setting the first point, a point on the workpiece model corresponding to the point selected in the first image is set as the first point;
The information processing device according to configuration 21, characterized in that:

(Configuration 23)
The information processing unit includes:
In the displaying process, a second image corresponding to the candidate is selectably displayed on the first image;
The information processing device according to configuration 22, characterized in that:

(Configuration 24)
The information processing unit outputs information regarding the holding position based on the candidate corresponding to the selected second image.
24. The information processing device according to configuration 23.

(Configuration 25)
The information processing device according to any one of Configurations 1 to 24;
A robot with a robot hand,
A control unit that controls the robot,
The control unit controls the robot based on information regarding the holding position to cause the robot hand to hold the workpiece.
A robot system characterized by:

(Method 26)
An information processing method for outputting information regarding holding positions, the method comprising:
Obtain the work model and hand model, which are shape data,
Setting a first point on the work model,
setting a virtual straight line that intersects the work model at the first point;
If the virtual straight line intersects the work model at a point other than the first point, obtaining a second point in the work model that intersects the virtual straight line;
An information processing method characterized by:

(Method 27)
A method for manufacturing an article, comprising manufacturing the article using the robot system according to configuration 25.

(Configuration 28)
A program for causing a computer to execute the information processing method described in Method 26.

(Configuration 29)
A computer-readable recording medium having recorded thereon the program according to configuration 28.

HM...hand model, WM...work model, 10...robot system, 20...information processing unit, 200...image processing device (information processing device)

Claims (29)

An information processing device comprising an information processing unit that outputs information regarding a holding position,
The information processing unit includes:
A process of acquiring a work model and a hand model, which are shape data,
a process of setting a first point on the work model;
a process of setting a virtual straight line that intersects the work model at the first point;
If the virtual straight line intersects the work model at a point other than the first point, acquiring a second point intersecting the virtual straight line in the work model;
An information processing device characterized by: The information processing unit includes:
executing a process of determining whether information on the first point and the second point is included in candidates for information regarding the holding position;
The information processing device according to claim 1, characterized in that: The information processing unit includes:
In the determining process, if a predetermined condition is satisfied in the positioning state in which the hand model is positioned with respect to the first point and the second point of the workpiece model, the first point and the second point are selected as the candidates. include,
The information processing device according to claim 2, characterized in that: The hand model has a first finger model and a second finger model that can approach and separate from each other,
The positioning state is a state in which the first finger model is positioned with respect to the first point, and the second finger model is positioned with respect to the second point.
The information processing device according to claim 3, characterized in that: The positioning state is a state in which a first predetermined point of the first finger model is positioned with respect to the first point, and a second predetermined point of the second finger model is positioned with respect to the second point. ,
The information processing device according to claim 4, characterized in that: The predetermined condition includes a condition that the hand model does not overlap the workpiece model.
The information processing device according to claim 3, characterized in that: The predetermined condition includes a condition that, in the hand model, the area of a portion of the workpiece model that can come into contact with a region including the first point is equal to or larger than a predetermined area;
The information processing device according to claim 3, characterized in that: The predetermined condition includes a condition that, in the hand model, the area of a portion of the workpiece model that can come into contact with a region including the second point is equal to or larger than a predetermined area.
The information processing device according to claim 3, characterized in that: The hand model has a first finger model and a second finger model that can approach and separate from each other,
The information processing unit includes:
In the process of setting the virtual straight line, in a state in which the first finger model is positioned with respect to the first point of the workpiece model, a direction parallel to a predetermined direction from the first finger model toward the second finger model; setting the virtual straight line so that it extends to
The information processing device according to claim 1, characterized in that: The predetermined direction is a direction from a first predetermined point of the first finger model to a second predetermined point of the second finger model,
The information processing device according to claim 9, characterized in that: The information processing unit includes:
In the process of setting the virtual straight line, the first finger model is set so that the normal line at the first point of the work model matches the normal line at the first predetermined point of the first finger model. positioning with respect to the first point of the workpiece model;
The information processing device according to claim 10. The information processing unit includes:
In the process of setting the virtual straight line, positioning the first finger model with respect to the first point of the workpiece model so that the first predetermined point overlaps the first point;
The information processing device according to claim 10. The information processing unit includes:
In the process of setting the virtual straight line, setting a plurality of virtual straight lines so as to extend in mutually different directions at the first point;
The information processing device according to claim 1, characterized in that: The information processing unit includes:
In the process of setting the virtual straight line, a virtual straight line other than one virtual straight line among the plurality of virtual straight lines is set to intersect the one virtual straight line within a predetermined angular range;
14. The information processing device according to claim 13. The predetermined angle range is 1 degree or more and 5 degrees or less,
The information processing device according to claim 14. The work model is data expressed by a plurality of polygons,
The information processing device according to claim 1, characterized in that: the polygon is a triangle;
17. The information processing apparatus according to claim 16. The information processing unit includes:
In the process of setting the first point, setting at least one first point for each of the plurality of polygons;
17. The information processing apparatus according to claim 16. the at least one first point is a plurality of first points;
The information processing device according to claim 18. The plurality of first points are arranged at equal intervals from each other,
The information processing device according to claim 19. The information processing unit includes:
executing a process of displaying a first image corresponding to the workpiece model on a display unit;
The information processing device according to claim 1, characterized in that: The information processing unit includes:
In the process of setting the first point, a point on the workpiece model corresponding to the point selected in the first image is set as the first point;
22. The information processing device according to claim 21. The information processing unit includes:
In the displaying process, a second image corresponding to the candidate is selectably displayed on the first image;
23. The information processing device according to claim 22. The information processing unit outputs information regarding the holding position based on the candidate corresponding to the selected second image.
24. The information processing device according to claim 23. The information processing device according to any one of claims 1 to 24,
A robot with a robot hand,
A control unit that controls the robot,
The control unit controls the robot based on information regarding the holding position to cause the robot hand to hold the workpiece.
A robot system characterized by: An information processing method for outputting information regarding holding positions, the method comprising:
Obtain the work model and hand model, which are shape data,
Setting a first point on the work model,
setting a virtual straight line that intersects the work model at the first point;
If the virtual straight line intersects the work model at a point other than the first point, obtaining a second point in the work model that intersects the virtual straight line;
An information processing method characterized by: A method for manufacturing an article, comprising manufacturing the article using the robot system according to claim 25. A program for causing a computer to execute the information processing method according to claim 26. A computer readable recording medium having recorded thereon the program according to claim 28.

Images