JP7450857B2 - Measurement parameter optimization method and device, and computer control program - Google Patents

Description

The present invention relates to a method for optimizing measurement parameters of an object in a robot system for manipulating the object.

In inspections and production lines in factory automation (FA), the position and orientation of objects such as bulk workpieces (parts, etc.) are measured, and the recognized objects are transferred to another location or container by a robot. There are known devices for processing objects. In such devices, parameters are set to optimally control the operations of robots and measuring devices, and various tasks are performed by the robots and measuring devices based on the control parameters.

For example, Patent Document 1 describes a measurement device that is equipped with a robot and a machine tool and performs multiple measurements (multi-view measurement) on multiple objects, and sequentially determines multiple measurement positions and orientations as measurement parameters. It describes how to do this. In this method, multiple end-point positions of the robot are memorized, and based on these, errors in the robot's mechanical parameters and the relative relationship between the robot's coordinate system and the machine tool's coordinate system are simultaneously calculated. will be held.

JP2017-56546A

By the way, in conventional measurement parameter settings such as in Patent Document 1, when optimizing measurement parameters, for example, the suitability of a combination of multiple parameters such as the shooting speed of the object, the number of shots, and the shooting time interval is evaluated. Therefore, adjusting measurement parameters and optimizing settings required a lot of effort and a long time. Furthermore, when the measurement device is mounted on a robot, the measurement parameters depend on the mechanical characteristics of the robot, so it is necessary to adjust the measurement parameters for each robot. Furthermore, changing the evaluation goal for object recognition requires even more effort and time, making adjustment and optimization settings of measurement parameters even more difficult.

Therefore, one aspect of the present invention has been made in view of the above circumstances, and it is possible to significantly simplify (labor and labor) measurement parameters when measuring an object with a measuring device mounted on a robot compared to the conventional method. The purpose of the present invention is to provide a method that can be adjusted and optimized to reduce the amount of time required, reduce time, and be independent of robots.

The present invention adopts the following configuration in order to solve the above-mentioned problems.

[1] That is, an example of the method for optimizing measurement parameters according to the present disclosure is a method for optimizing measurement parameters when measuring one or more objects with a measurement device (sensor) installed in a robot. This includes the first to fourth steps shown in (1) to (4) below. Note that the configuration of the "robot" is not particularly limited, and includes, for example, a configuration that includes a robot arm and a hand that is provided at the tip of the robot arm and that operates the object. Furthermore, the configuration of the "measuring device" is not particularly limited, and examples include devices that are installed on a robot arm and can measure positional information (e.g., two-dimensional or three-dimensional positional information) of an object. . More specific examples of these "robots" and "measuring devices" will be described later.

(1) A first step of photographing one or more objects to obtain a plurality of N photographed images while moving the measuring device at a speed V, a time interval T, and a total movement angle θ as the first measurement parameters. step.
(2) One or more objects are photographed while moving the measuring device at the second measurement parameter: speed V, time interval T x j (j: an integer of 2 or more), and total movement angle θ. Assuming that N/j captured images are acquired and image processing is performed to recognize the position and orientation of one or more objects, the number i (here, i=1, 2,..., N/ A second step of estimating an evaluation value Zi indicating the accuracy of recognition of the object at (j-1, N/j) and storing the evaluation value Zi associated with the second measurement parameter as first data.
(3) Based on the first data, while moving the measuring device at a speed V x k (k: an integer of 2 or more), a time interval T x j/k, and a total movement angle θ as third measurement parameters. , the number of images i (here i= 1, 2, ..., N/j/k-1, N/j/k), and the evaluation value Zi associated with the third measurement parameter is estimated as the second measurement parameter. The third step is to store it as data.
(4) A fourth step of selecting measurement parameters of data that satisfy predetermined criteria from the second data and determining them as optimized measurement parameters when the robot operates one or more objects.

In this configuration, when the measurement parameters are changed to different conditions (second measurement parameters, third measurement parameters) based on the first data, which is basic data acquired in advance before the actual operation of the robot system, after the change It is possible to estimate the recognition results of one or more objects without actually measuring the parameters. Therefore, there is no need to perform preliminary measurements for all possible combinations of conditions that can be assumed as measurement parameters. Measurement parameters can be optimized. Therefore, it is possible to adjust and optimize the measurement parameters used when measuring an object using a measuring device mounted on a robot, much more easily than before (reducing labor, shortening time, independent of the robot, etc.). can. As a result, it is possible to improve the robustness when measuring objects, the work efficiency of object manipulation, and the overall throughput, and as a result, user convenience and versatility are also significantly improved. becomes possible.

[2] In the above configuration, more specifically, the predetermined criterion may include that the evaluation value Zi of the object is equal to or greater than a preset evaluation value of the object. In this configuration, by setting a larger predetermined evaluation value in the determination criteria, the robustness can be further improved, which is advantageous when giving priority to improving measurement accuracy.

[3] In addition to the predetermined criterion being equal to or greater than a preset evaluation value of the object, the predetermined criterion may also include at least the time required for measurement being shorter. With this configuration, the time required for measurement can be minimized while satisfying a desired evaluation value, which is advantageous when prioritizing reduction of measurement processing time.

[4] In addition, in addition to the predetermined criterion being equal to or higher than a preset evaluation value of the object, the predetermined criterion may also include that the speed V of movement of the measuring device is faster. This is advantageous when giving priority to the speed V during movement of the measuring device while satisfying the evaluation value of .

[5] In addition, the predetermined criterion may include, in addition to being equal to or greater than a preset evaluation value of the object, that the number of shots i of one or more objects is smaller. In this case, it is advantageous to give priority to reducing the number of photographed images i while satisfying the desired evaluation value.

[6] Furthermore, in each of the above configurations, one or more objects are photographed using the first measurement parameter at least once, preferably multiple times, and when photographing is performed multiple times, the data is acquired for each photograph. The average value of the evaluation values Zi may be stored as the first data. With this configuration, it is possible to improve the accuracy and reliability of the first data obtained experimentally, and as a result, robustness when measuring one or more objects, work efficiency when operating one or more objects, Moreover, the overall throughput can be further improved.

[7] Furthermore, when the robot is changed as described above, the data corresponding to the measurement parameters corresponding to the speed V and the time interval T according to the characteristics of the robot different from the robot are changed from the first data to the first data. 3 data, select measurement parameters of data that satisfy predetermined criteria from the first data to third data, and optimize the operation of the plurality of objects by the different robots. It may be configured to be determined as a measurement parameter. With this configuration, as described above, it is possible to provide a simple method capable of optimizing measurement parameters without depending on the robot.

[8] Alternatively, similarly, when the first data to second data include data corresponding to measurement parameters corresponding to a speed V and a time interval T depending on the characteristics of a robot different from the robot, New second data is acquired and stored by performing the second to fourth steps using the data associated with the measurement parameters of the corresponding data as new first data, and from among the new second data. , measurement parameters of data satisfying predetermined criteria may be selected and determined as optimization measurement parameters when operating one or more objects by different robots. Even with this configuration, as described above, it is possible to provide a simple method that can realize optimization of measurement parameters without depending on the robot.

[9] Further, an example of the measurement parameter optimization device according to the present disclosure is a device for optimizing measurement parameters when measuring a plurality of objects with a measurement device installed in a robot. The apparatus has at least one processor that performs each step in the metrology parameter optimization method of the present disclosure.

[10] Further, an example of the computer control program according to the present disclosure is a computer control program having at least one processor, in order to optimize measurement parameters when measuring a plurality of objects with a measurement device installed in a robot. In other words, it is a program for causing a computer to effectively function as the measurement parameter optimization device according to the present disclosure. .

[11] Further, an example of a robot system according to the present disclosure includes a robot, a measuring device provided on the robot, and a control device connected to the robot and the measuring device, and the control device includes at least one processor. and at least one processor is a system that executes each step in the metrology parameter optimization method of the present disclosure. In other words, in the robot system, the measurement parameter optimization device according to the present disclosure functions as a control device.

Note that in the present disclosure, "units" and "devices" do not simply mean physical means, but also include configurations that implement the functions of the "units" and "devices" by software. Furthermore, the functions of one "department" and "device" may be realized by two or more physical means or devices, or the functions of two or more "departments" and "devices" may be realized by one physical means or device. It may be realized by physical means or devices. Furthermore, "unit" and "device" are concepts that can also be translated into, for example, "means" and "system."

According to the present invention, measurement parameters when measuring an object with a measuring device mounted on a robot can be adjusted and optimized much more easily than in the past (reducing labor, reducing time, independent of the robot, etc.) can be converted into This makes it possible to improve the robustness during measurement of the target object, the work efficiency of manipulating the target object, and the overall throughput, and as a result, user convenience and versatility are significantly improved.

FIG. 1 is a plan view schematically showing an example of an application scene of a robot system including a control device according to the present embodiment. FIG. 1 is a plan view schematically showing an example of an application scene of a robot system including a control device according to the present embodiment. FIG. 1 is a plan view schematically showing an example of the hardware configuration of a robot system including a control device according to the present embodiment. FIG. 1 is a plan view schematically showing an example of the functional configuration of a robot system including a control device according to the present embodiment. It is a flowchart which shows an example of the processing procedure in the robot system provided with the control device based on an example of operation. FIG. 6 is a plan view schematically showing the concept of the movement state of the sensor 1 in step S501 of the operation example. It is a figure which shows an example of the 1st data in step S502 of an example of operation|movement, and the 1st data in step S503 in a table format. It is a figure which shows an example of the 2nd data in step S504 of an example of operation in a table format. It is a figure which shows an example of the 2nd data in step S504 of an example of operation in a table format. It is a figure which shows an example of the 2nd data in step S504 of an example of operation in a table format. FIG. 7 is a diagram showing in a table format a specific example of second data obtained by experimentally performing steps S501 to S504 using the sensor 1 for a plurality of works 5 (hexagonal bolts). 12 is a plan view of an example of the data set shown in FIG. 11 in which recognition results (contours) are displayed superimposed on images taken by the sensor 1 of a plurality of works 5. FIG. 12 is a diagram obtained by sorting the second data illustrated in FIG. 11 in descending order of recognition number Zi, and sorting data with the same recognition number Zi in descending order of speed V. FIG. 12 is a diagram in which the second data illustrated in FIG. 11 is sorted in descending order of the number of recognitions Zi, and data with the same number of recognitions Zi is sorted in descending order of the number of photographed images i. It is a flow chart which shows an example of a processing procedure in a 4th modification. FIG. 3 is a plan view in which a plurality of works 5 having different shapes are measured, and a recognition result (contour line) of the position and orientation of the works 5 obtained by image processing is superimposed on the captured images thereof.

Embodiments (hereinafter referred to as "embodiments") according to an example of the present disclosure will be described below with reference to the drawings. However, the embodiments described below are merely examples, and are not intended to exclude the application of various modifications and techniques not explicitly described below. That is, an example of the present disclosure can be implemented with various modifications without departing from the spirit thereof. In addition, in the description of the drawings below, the same or similar parts are given the same or similar symbols, and the drawings are schematic and do not necessarily correspond to actual dimensions, proportions, etc. Further, the drawings may include portions with different dimensional relationships and ratios.

§1 Application Example First, an example of a scene to which an example of the present disclosure is applied will be described using FIGS. 1 and 2. 1 and 2 are plan views each schematically showing an example of an application scene of a robot system including a control device according to this embodiment. The robot system 100 according to the present embodiment uses a robot 10 to take out a plurality of works 5 stacked in bulk in a storage container 6 such as bottles, transfer them to another storage container 7, etc., and arrange them. and/or the operation of returning the robot 10 that has finished transferring a certain workpiece 5 to the storage container 6 side in order to take out the next workpiece 5 (the movement path P1 in FIG. 2). 2 movement route P2) can be performed. Note that the workpieces 5 may be stacked flat on a table, stand, etc., instead of inside the storage container 6. Further, the type of workpiece 5 is not particularly limited, and examples thereof include mechanical parts of an automobile's power train system (for example, an engine or a transmission, etc.), electronic parts of an electrical system, and the like. In addition to the robot 10, the robot system 100 also includes a sensor 1 provided on the robot 10 (an example of a "measuring device" in the present disclosure), and a control device 4 (in the present disclosure) connected to the sensor 1 and the robot 10. (an example of a "measuring parameter optimization device").

The sensor 1 is a 3D sensor that acquires measurement data including position information (for example, three-dimensional position information) of the workpiece 5, and is installed at the tip of the robot arm 3 of the robot 10, as shown in FIGS. As shown in B), the workpiece 5 is imaged with a predetermined field of view (angle) and with predetermined measurement parameters. The sensor 1 may be, for example, a distance sensor that measures a point group, or a distance image sensor that acquires a distance image by combining a distance sensor and a two-dimensional sensor. The distance sensor is a sensor that measures distance d as depth information. A two-dimensional sensor is an image sensor that takes a two-dimensional image, and a two-dimensional image differs from a distance image in that the distance d is not a pixel value. The distance image sensor is, for example, a camera that photographs a plurality of two-dimensional images of the workpiece 5 while changing the photographing position of the two-dimensional sensor, and acquires a distance image with a distance d as a pixel value through stereoscopic image processing. But that's fine. Alternatively, the distance image sensor may be a stereo camera that acquires a distance image with the distance d as a pixel value by simultaneously photographing the workpiece 5 from a plurality of different directions.

Although not essential, the sensor 1 may be equipped with so-called 3D illumination including appropriate measurement light (for example, pattern light or scan light used in an active method) or so-called 2D illumination, which is normal illumination, as needed. The workpiece 5 may include a projector (not shown) that projects lighting onto the workpiece 5. The configuration of such a projector is not particularly limited either, and for example, in the case of projecting pattern light, a configuration including a laser light source, a pattern mask, and a lens can be exemplified. The light emitted from the laser light source is converted into measurement light (pattern light) having a predetermined pattern by a pattern mask on which a predetermined pattern is formed, and is projected onto the workpiece 5 via a lens.

This "predetermined pattern" is not particularly limited, and can be exemplified by various patterns used in the active one-shot method, for example. More specifically, for example, so-called line-based patterns in which multiple lines are arranged two-dimensionally at predetermined intervals, multiple types of mutually distinguishable unit images, unit figures, geometric shapes, etc. arranged two-dimensionally. (It may be regular or random, and regular and random parts may be mixed or superimposed.) A so-called area-based pattern, a so-called grid graph in which graph symbols, etc. are arranged in a grid of vertical and horizontal lines. Examples include base patterns. Note that each predetermined pattern may include ID information for distinguishing, for example, a line or a unit figure for encoding.

The measurement method for the workpiece 5 is not particularly limited, and includes, for example, various active measurement methods that use the straightness of light (e.g., a space-coded pattern projection method based on triangulation, a time-coded pattern projection method, etc.). projection method, moiré topography method, etc.), various passive measurement methods that use the straightness of light (e.g., stereo camera method based on triangulation distance measurement, visual volume intersection method, factorization method, etc.), coaxial distance measurement method, etc. (e.g. Depth from focusing method based on the basic principle) and various active measurement methods using the speed of light (e.g. time of flight method based on simultaneous ranging, laser scanning method, etc.) as appropriate. It can be used as

The measurement data of the workpiece 5 includes image data obtained by these various measurement methods (for example, three-dimensional point cloud data, distance images, etc.), and appropriate data that can be compared with the three-dimensional model data of the workpiece 5. The following data can be exemplified. Here, the three-dimensional model data of the workpiece 5 includes, for example, three-dimensional coordinate data, two-dimensional coordinate data obtained by two-dimensionally projecting the three-dimensional coordinate data corresponding to various different positions and orientations of the workpiece 5, and other appropriate data. Examples include data corresponding to templates and patterns. Note that in recognizing the workpiece 5, matching with three-dimensional model data is not essential, and recognition that does not use model data (so-called model-less) is also applicable.

The robot 10 is, for example, an articulated robot that includes a hand 2 for manipulating (for example, gripping, suctioning, moving, assembling, or inserting) a workpiece 5, and a robot arm 3 with the hand 2 provided at the tip. (For example, vertically articulated robot, horizontally articulated robot). Each joint of the robot 10 is equipped with a drive device such as a servo motor for driving the joint, and a displacement detection device such as an encoder for detecting displacement (angular displacement) of the joint. Further, the robot 10 operates as an autonomous manipulator, and can be used for various purposes such as picking, assembling, transporting, painting, inspecting, polishing, or cleaning the workpiece 5, for example.

The hand 2 is an example of an end effector, and has a gripping mechanism capable of gripping and releasing (grabbing and releasing) each workpiece 5 . The robot arm 3 moves the hand 2 to the gripping position (pickup position) of the workpiece 5 in the storage container 6, and moves the hand 2 gripping the workpiece 5 from the gripping position to the release position (dropping position) in another storage container 7. position).

The control device 4 is connected to each of the sensor 1 and the robot 10, and performs processing for measuring the workpiece 5 by the sensor 1, processing for operating the workpiece 5 by the hand 2, and processing for driving the robot 10 (hand 2, robot arm 3, etc.). In addition, it controls processing related to various operations and calculations required in the robot system 100. Further, the control device 4 executes optimization of measurement parameters when measuring the plurality of works 5 with the sensor 1 prior to actual operation of the robot system 100.

In this optimization process, first, (1) first measurement parameters that enable more detailed measurement and evaluation of the positions and orientations of multiple workpieces 5 are set, and while moving the sensor 1 under those conditions, the assumed A plurality of works 5 (for example, a plurality of works 5 stacked in bulk in a storage container 6) are photographed multiple times. Next, (2) image processing is performed using a different number i of captured images selected from the plurality of N captured images obtained, and an evaluation value Zi (for example, recognition the number of workpieces 5 that have been measured), and its evaluation value Zi is stored as first data together with the first measurement parameter. Next, (3) assume that a plurality of workpieces 5 are photographed using a second measurement parameter that is different from the first measurement parameter except for the moving speed of the sensor 1, and that processing equivalent to the image processing described above is performed. An evaluation value Zi (for example, the number of recognized works 5) indicating the accuracy of recognition of the works 5 is estimated, and the evaluation value Zi is stored as first data together with the second measurement parameter.

Furthermore, (4) using the first data obtained in either or both of steps (2) and (3) above, a third measurement parameter different from the first measurement parameter and the second measurement parameter is set. , an evaluation value Zi (for example, the number of recognized workpieces 5) indicating the accuracy of recognition of the workpieces 5 when a plurality of workpieces 5 are photographed and processing equivalent to the image processing described above is performed. The estimated value Zi is stored as second data together with the third measurement parameter. (5) From the obtained second data, a predetermined criterion (for example, a predetermined evaluation value or more, and at least one of the following criteria: measurement time, moving speed, and number of shots) At least one measurement parameter of data that satisfies is selected, and from among them, for example, a measurement parameter desired by the user is determined as an optimized measurement parameter during actual operation of the robot system 100.

According to the control device 4 of this application example, the robot system 100 equipped with the same, and the measurement parameter optimization method implemented therein, the control device 4 of the robot system 100 uses the basic first measurement parameter. Based on the results of photographing and image processing of the plurality of workpieces 5 performed before actual operation, it is possible to estimate the recognition results of the plurality of workpieces 5 when the measurement parameters are changed to different conditions. Therefore, without performing preliminary measurements for all possible combinations of conditions that can be assumed as measurement parameters, by simply performing detailed preliminary measurements once before actual operation for each type of workpiece 5 that is assumed, measurement by the sensor 1 can be easily performed. Parameter optimization can be performed. Furthermore, even if the robot 10 is changed, by utilizing the parameter set of the first data and second data acquired in advance for a certain robot 10 equipped with the sensor 1, it is possible to The measurement parameters when operating the workpiece 5 can be optimized without performing new preliminary measurements.

From the above, according to the present disclosure, the optimization of measurement parameters by the sensor 1 in the task of manipulating a plurality of various workpieces 5 by the robot system 100 including various robots 10 is much simpler than in the past. (reduced effort, time, independence from robots, etc.). This makes it possible to improve robustness when measuring multiple works 5, work efficiency when operating multiple works 5, and overall throughput.As a result, user convenience and versatility are improved. Much improved.

§2 Configuration example [Hardware configuration]
Next, an example of the hardware configuration of the robot system 100 according to this embodiment will be described using FIG. 3. FIG. 3 is a plan view schematically showing an example of the hardware configuration of the robot system 100 including the control device 4 according to the present embodiment. In the example of FIG. 3 as well, the robot system 100 includes the robot 10 having the sensor 1, hand 2, and robot arm 3 illustrated in FIGS. 1 and 2, and the control device 4. Here, the control device 4 includes a control calculation section 41, a communication interface (I/F) section 42, a storage section 43, an input section 44, and an output section 45, and each section can communicate with each other via a bus line 46. can be connected to.

The control calculation unit 41 includes a CPU (Central Processing Unit), a RAM (Random Access Memory), a ROM (Read Only Memory), etc., and controls each component and performs various calculations according to information processing.

The communication I/F section 42 is, for example, a communication module for communicating with other constituent elements such as "sections" and "devices" by wire or wirelessly. The communication method used by the communication I/F unit 42 for communication is arbitrary, and examples include LAN (Local Area Network) and USB (Universal Serial Bus), and an appropriate communication line equivalent to the bus line 46 is applied. You can also do that. The sensor 1, the hand 2, and the robot arm 3 can all be provided so as to be able to communicate with the control calculation section 41 and the like via the communication I/F section 42.

The storage unit 43 is an auxiliary storage device such as a hard disk drive (HDD) or a solid state drive (SSD), and stores various programs ((1) to (7) above) executed by the control calculation unit 41. arithmetic programs for executing various processes including the processes shown in , control programs for controlling the respective operations of the sensor 1, hand 2, and robot arm 3), measurements output from the sensor 1; A database containing data, measurement parameters, recognition parameters, and various calculation parameters, data on various calculation results and calculation results, data on the position and orientation recognition results of each of the plurality of works 5, and information on the picking status and picking record of each work 5. data, three-dimensional model data of the workpiece 5, data regarding a measurement area that may include a plurality of workpieces 5, setting data for the position and orientation of the sensor 1 that measures the measurement area, and the like are stored. As described above, by executing the calculation program and control program stored in the storage unit 43 in the control calculation unit 41, various processing functions in the functional configuration example described later are realized.

The input unit 44 is an interface device for receiving various input operations from a user using the robot system 100, and can be realized by, for example, a mouse, a keyboard, a touch panel, an audio microphone, or the like. The output unit 45 is an interface device for notifying users of the robot system 100 of various types of information through display, audio output, print output, etc., and can be realized by, for example, a display, a speaker, a printer, etc. .

[Functional configuration]
Next, an example of the functional configuration of the robot system 100 including the object recognition processing device according to this embodiment will be described using FIG. 4. FIG. 4 is a plan view schematically showing an example of the functional configuration of the robot system 100 including the control device 4 according to the present embodiment.

The control calculation unit 41 of the robot system 100 shown in FIG. 4 loads various programs (control programs, calculation programs, etc.) stored in the storage unit 43 into the RAM. The control calculation unit 41 then uses the CPU to interpret and execute various programs loaded in the RAM, thereby controlling each component. As a result, the robot system 100 according to the present embodiment performs the operation of taking out the plurality of works 5 stacked in bulk in the storage container 6, transferring them to another storage container 7, etc., and aligning and arranging them, as described above. Movement path P1 in FIG. 2), and/or operation of returning the robot 10 that has finished transferring a certain workpiece 5 to the storage container 6 side in order to take out the next workpiece 5 (movement path P2 in FIG. 2) It can be performed. In addition, in order to optimize measurement parameters when measuring a plurality of workpieces 5 with the sensor 1 prior to actual operation of such a robot system 100, a function that can execute the processing of each step shown below is provided. The configuration includes a sensor control section 401, a robot control section 402, a captured image acquisition section 410, a first data acquisition section 411, a second data acquisition section 412, a third data acquisition section 413, and an optimization parameter determination section 414. , can be realized by the control calculation section 41.

In addition, in this embodiment, an example has been described in which each function realized by the control device 4 provided in the robot system 100 is realized by a general-purpose CPU. It may also be realized by a dedicated processor. Further, the functional configuration of the control device 4 included in the robot system 100 may be omitted, replaced, or added as appropriate depending on the embodiment or configuration example. Furthermore, a "control device" can be understood as a general information processing device (for example, a computer, a workstation, etc.).

§3 Operation example Next, as an example of the operation of the robot system 100, using FIG. An example of the procedure to be executed will be explained. That is, FIG. 5 is a flowchart showing an example of the processing procedure in the robot system 100 including the control device 4 according to the present operation example, and is also a flowchart showing an example of the processing procedure in the method for optimizing measurement parameters of the robot system 100. . Note that the processing procedures described below are merely examples, and each process may be modified as much as possible within the scope of the technical idea of the present disclosure. Further, in the processing procedure described below, steps can be omitted, replaced, and added as appropriate depending on the embodiment and each configuration example.

First, the user of the robot system 100 starts the robot system 100 and puts it into a state where various programs (calculation programs, control programs, optimization of measurement parameters, etc.) can be executed. Then, the control calculation unit 41 (at least one processor) in the control device 4 controls the respective operations of the sensor 1 and the robot 10 according to the following processing procedure, and also controls the calculation processing by each functional unit in the control device 4. conduct.

(Step S501: 1st step)
In step S501, first, the movement path P0 of the sensor 1 by the robot 10 (the robot arm 3 thereof), the movement speed V, the time interval T, and the total movement angle θ are set as first measurement parameters. Here, FIG. 6 is a plan view schematically showing the concept of the moving state of the sensor 1 in step S501. As shown in the figure, the moving path P0 can be set, for example, in an arc shape centered on the coordinate G0, which is approximately the center of volume of the plurality of works 5 stacked in bulk in the container 6. Note that the locus of movement of the sensor 1 is not limited to an arc shape (a shape with a constant curvature), and may be, for example, a linear shape, a non-linear shape, a shape with changing curvature, etc. It may be varied. Further, as the plurality of works 5 used experimentally here, the same types as the objects to be operated during actual operation of the robot system 100 are selected.

The speed V is not particularly limited, and, for example, can be set to any value within the speed range that can be realized as the moving speed of the sensor 1, and the slower the speed, the more detailed captured images will be obtained. This is suitable from the standpoint of being able to Further, the time interval T is not particularly limited, and can be set to any value within the interval range that can be realized as the imaging interval of the sensor 1, and in particular, if it is the minimum time interval, more detailed imaging can be performed. This is suitable from the viewpoint of being able to acquire images. Further, the total movement angle θ is not particularly limited, and may be set to an angle corresponding to the maximum distance of the movable range of the sensor 1, for example.

From these speed V, time interval T, and total movement angle θ, the number of shots N=θ/V/T in shooting the plurality of workpieces 5 using the first measurement parameter, and the movement angle each time (movement at each time interval T). Angle) μ=V×T is determined, and while the sensor 1 is moved in an arc along the movement path P0 under this condition, the sensor control unit 401 commands the robot control unit 401 to move the sensor 1 to The workpiece 5 is photographed multiple times to obtain a plurality of N photographed images. That is, in this step, as shown in FIG. (The angle of the position is the movement angle μ each time.) Accordingly, N images are taken, and a plurality of N photographed images are obtained.

(Step S502: Second step (1))
In step S502, the first data acquisition unit 411 sequentially extracts a different number i of captured images from the obtained plural number N of captured images, performs image processing, and evaluates the accuracy of recognition of the workpiece 5. Values Zi (for example, the number of recognized works 5) are acquired one after another. Here, the number of images i = 1, 2, ..., N-1, N (that is, i is an integer from 1 to N), and specifically, for example, the first captured image (initial image of sensor 1 Image processing is performed at position G1) (i=1), and then using the first and second captured images whose sensor positions are adjacent to each other (initial position G1 and next position G2 of sensor 1). Perform image processing (i=2). Then, such processing is sequentially and repeatedly executed until i=N (position Gi to position GN of sensor 1), and the evaluation value Zi obtained for each number of captured images i is associated with the first measurement parameter and used as the first data. It is stored in the storage unit 43.

(Step S503: Second step (2))
In step S503, the first data acquisition unit 412 first sets the movement path P0 of the sensor 1 by the robot 10 (robot arm 3), the movement speed V, and the time interval T×j(j : an integer of 2 or more) and the total movement angle θ. That is, in the second measurement parameter, the time interval of measurement by the sensor 1 is varied in various ways so that it becomes an integral multiple of the time interval in the first measurement parameter. However, in step S503, the plurality of workpieces 5 are photographed with the second measurement parameter using the plural number N of photographed images obtained in step S501, rather than performing actual measurement with the second measurement parameter. , and estimate the evaluation value Zi (for example, the number of recognized works 5) indicating the accuracy of recognition of the works 5 for each number of photographed images i, assuming that processing equivalent to the image processing in step S502 is performed. do. Then, the evaluation value Zi obtained for each number of photographed images i at each time j is associated with the second measurement parameter and stored in the storage unit 43 as first data.

Note that the processing in step S502 is the same as the processing when j=1 in step S503, so for convenience of explanation, the data obtained in steps S502 and 503 will be referred to as "first data." However, in acquiring the first data, it is not necessary to execute both steps S502 and S503, and it is sufficient to execute either one of the steps. Furthermore, when both steps S502 and S503 are executed, one of the steps may be executed first, and the other step may be executed later, and the order of execution is not particularly limited.

Furthermore, in the above description, an example was shown in which various variations of the image set in which the captured images are evenly thinned out are generated by fixing the speed V to a constant value and changing the time interval T in step S503. However, by fixing the time interval T to a constant value and changing the speed V, various variations of the image set in which the captured images are evenly thinned out may be generated.

Here, FIG. 7 is a diagram showing an example of the first data in step S502 (second step (1)) and the first data in step S503 (second step (2)) in a table format. The data set shown in FIG. 7(A) corresponds to the first data acquired in step S502, and this first data includes the time interval T at the time of measurement = 0.01 (sec), the number of captured images N = 120, This is an example of the movement angle μ (=θ/(120-1)) each time, and data of the evaluation value Zi (i=1 to 121) is acquired. That is, here, the total movement angle θ is divided into 119, and 120 images are taken.

Furthermore, the data sets shown in FIGS. 7(B) to (D) correspond to the first data acquired in step S503. The data set shown in FIG. 7(B) is an example where j = 2, the time interval at the time of measurement T x 2 = 0.02 (sec), the number of shots N = 60, and the movement angle μ x 2 each time. Become. Therefore, the data of the evaluation value Zi when the number of photographed images i = 1, 3, 5, ..., 117, 119 in the first data acquired in step S502 is used as the evaluation value of each number of photographed images i when j = 2. They can be assigned as data of Zi (i=1 to 60).

The data set shown in FIG. 7(C) is an example where j=4, the time interval at the time of measurement T x 4 = 0.04 (sec), the number of captured images N = 31, and the movement angle μ x each time. It becomes 4. Therefore, the data of the evaluation value Zi when the number of shots i = 1, 5, 9, ..., 113, 117 in the first data acquired in step S502 is used as the evaluation value of each number of shots i when j = 4. It can be assigned as data of Zi (i=1 to 30). FIG. 7(D) shows a generalized data set for "j".

(Step S504: Third step)
In step S504, the second data acquisition unit 413 first sets the movement path P0 of the sensor 1 by the robot 10 (robot arm 3) and the movement speed V×k (k: 2 or more) as the third measurement parameters. (integer), time interval T×j/k, and total movement angle θ. That is, the speed of sensor 1 in the third measurement parameter is set to k times the speed of sensor 1 in the first measurement parameter, and the time interval of measurement by sensor 1 in the third measurement parameter is set to k times the speed of sensor 1 in the first measurement parameter. The measurement time interval is set to (1/k) times the measurement time interval. However, in step S504 as well, the plurality of workpieces 5 are photographed with the second measurement parameter using the first data, which is the basic data, instead of performing actual measurement using the third measurement parameter, and step S502 An evaluation value Zi (for example, the number of recognized workpieces 5) indicating the accuracy of recognition of the workpieces 5 for each number of photographed images i is estimated, assuming that processing equivalent to the image processing in is performed. Then, the evaluation value Zi obtained for each number of photographed images i for each j and each k is associated with the third measurement parameter and stored in the storage unit 43 as second data.

Here, FIGS. 8 to 10 are diagrams showing examples of the second data in step S504 (third step) in a table format.

The data sets shown in FIGS. 8A to 8D correspond to FIGS. 7A to 7D when the speed V of the sensor 1 is multiplied by k=2. The data set shown in FIG. 8(A) is an example where k = 2 and j = 1, the time interval at the time of measurement T x 1 = 0.01 (sec), the number of shots N = 60, and the movement angle each time. μ×1×2. Therefore, the data of the evaluation value Zi when the number of shots i = 1, 3, 5, ..., 117, 119 in the first data is converted into the evaluation value Zi ( i=1 to 60).

The data set shown in FIG. 8(B) is an example of k = 2 and j = 2, the time interval at the time of measurement T x 2 = 0.02 (sec), the number of shots N = 30, and the movement angle each time. μ×2×2. Therefore, the data of the evaluation value Zi when the number of shots i = 1, 5, 9, ..., 113, 117 in the first data is converted into the evaluation value Zi ( i=1 to 30).

The data set shown in FIG. 8(C) is an example where k = 2 and j = 4, the time interval at the time of measurement T x 4 = 0.04 (sec), the number of shots N = 15, and the movement angle each time. It becomes μ×4×2. Therefore, the data of the evaluation value Zi when the number of shots i = 1, 9, 17, ..., 105, 113 in the first data is converted into the evaluation value Zi ( i=1 to 15). FIG. 8(D) shows a generalized data set for "k=2" and "j".

Further, the data sets shown in FIGS. 9A to 9D correspond to FIGS. 7A to 7D when the speed V of the sensor 1 is multiplied by k=3. The data set shown in FIG. 9(A) is an example where k=3 and j=1, the time interval at the time of measurement T x 1 = 0.01 (sec), the number of shots N = 40, and the movement angle each time. μ×1×3. Therefore, the data of the evaluation value Zi when the number of shots i = 1, 4, 7, ..., 115, 118 in the first data is converted into the evaluation value Zi ( i=1 to 40).

The data set shown in FIG. 9(B) is an example where k=3 and j=2, the time interval at the time of measurement T x 2 = 0.02 (sec), the number of shots N = 20, and the movement angle each time. It becomes μ×2×3. Therefore, the data of the evaluation value Zi when the number of shots i = 1, 7, 13, ..., 115, 121 in the first data is converted into the evaluation value Zi ( i=1 to 20).

The data set shown in FIG. 9(C) is an example where k = 3 and j = 4, the time interval at the time of measurement T x 4 = 0.04 (sec), the number of shots N = 10, and the movement angle each time. It becomes μ×4×3. Therefore, the data of the evaluation value Zi when the number of shots i = 1, 13, 25, ..., 97, 109 in the first data is converted into the evaluation value Zi ( i=1 to 10). FIG. 9(D) shows a generalized data set for "k=3" and "j". Furthermore, the data sets shown in FIGS. 10(A) to 10(D) show generalized data sets for "k", and in particular, FIG. 10(D) shows data sets for both "k" and "j". The following is a generalized data set for .

(Step S505: 4th step)
In step S505, the optimization parameter determination unit 414 selects at least one measurement parameter of data that satisfies a predetermined criterion from the obtained second data, and selects from among them, for example, a measurement parameter that the user wants to measure. The parameters are determined as optimized measurement parameters during actual operation of the robot system 100. Here, FIG. 11 shows the specifics of second data obtained by experimentally executing steps S501 to S504 using the sensor 1 for hexagonal bolts as 20 pieces of workpieces 5 stacked in bulk using a certain robot system 100. FIG. 2 is a diagram showing an example in a table format. In the illustration, the speed V of movement of the sensor 1 is expressed as a percentage (%) of the maximum speed that can be realized by the robot system 100. Strictly speaking, the "required time H" in the figure does not depend only on the time interval T and the number of captured images N, but on the transfer time of the images captured by the sensor 1 to the control calculation unit 41 (computer), Although it is expressed as a total time including the time for synthesizing multiple pieces of 3D point cloud data, etc., here, for convenience of explanation, it is calculated as the required time H=time interval T×number of captured images i. Further, in the same figure, only those workpieces 5 whose number of recognized pieces as evaluation value Zi is 17 or more are shown.

Further, FIG. 12 is a plan view of an example of the data set shown in FIG. 11, in which recognition results (contours) are displayed superimposed on images taken by the sensor 1 of 20 workpieces 5. For example, FIG. 12(A) shows the results when the speed V = 70%, the interval T = 0.05 (sec), the number of captured images i = 5, and the number of recognized workpieces 5 as evaluation value Zi = 19. "70%_0.05_5_19" written at the bottom of the figure indicates those conditions and results. Note that the same applies to FIGS. 12(B) to 12(D). In addition, in FIG. 12(C), the number of workpieces 5 whose outlines have been recognized is 17, but by adjusting the reliability of the recognition results, it was determined that 18 could be recognized. , the number of recognized works 5 as the final evaluation value Zi = 18. On the other hand, in FIG. 12(D), the number of workpieces 5 whose outlines have been recognized is 19, but as a result of adjusting the reliability of the recognition results, it was determined that 18 could be recognized. , the number of recognized works 5 as the final evaluation value Zi = 18.

In step S505, the predetermined criterion is, for example, that the evaluation value Zi of the workpiece 5 is greater than or equal to the predetermined evaluation value ZB, and in FIG. The data of Zi was sorted in descending order of required time H. For example, if the number of recognitions as the predetermined evaluation value ZB for determination is set to 19 (recognition rate = 19/20 = 95%), in FIG. For example, a user can appropriately select a desired measurement parameter from among the measurement parameters corresponding to the set and determine it as an optimized measurement parameter during actual operation of the robot system 100. This also applies to the case where the number of recognitions as the predetermined evaluation value ZB for determination is 17 or 18.

(Step S506)
In step S506, the robot system 100 is put into actual operation using the optimized measurement parameters determined in step S505, and a plurality of workpieces 5 are operated.

§4 Actions and Effects As described above, according to the control device 4 of the robot system 100 according to the present embodiment and an example of the method for optimizing measurement parameters using the control device 4, the measurement parameters are acquired in advance before the actual operation of the robot system 100. If the measurement parameters are changed to different conditions (second measurement parameters, third measurement parameters) based on the first data, which is the basic data that has been The recognition result of the workpiece 5 can be estimated. Therefore, it is no longer necessary to perform preliminary measurements for all possible combinations of conditions that can be assumed as measurement parameters. Measurement parameters can be optimized.

Furthermore, even if the robot 10 is changed, the characteristics (mechanical parameters ) (specifically, the moving speed V and time interval T of the sensor 1), a predetermined criterion is selected from the first data and second data corresponding to the condition. It is possible to select measurement parameters whose data satisfies the requirements and determine them as optimized measurement parameters when operating a plurality of workpieces 5 by different robots after the change.

Alternatively, if the parameter set of the first data to the second data includes a condition according to the characteristics of the robot 10 after the change, the results under that condition are used as the basic data (the first data) about the robot 10 after the change. 1 data). Then, by using the basic data and executing the same processes as the second to fourth steps above, the robot system 100 including the robot 10 after the change can be measured without performing new preliminary measurements. Measurement parameters can be optimized.

From the above, according to the present disclosure, the optimization of measurement parameters by the sensor 1 in the task of manipulating a plurality of various workpieces 5 by the robot system 100 including various robots 10 is much simpler than in the past. (reduced effort, time, independence from robots, etc.). This makes it possible to improve robustness when measuring multiple works 5, work efficiency when operating multiple works 5, and overall throughput.As a result, user convenience and versatility are improved. It can be improved significantly. Further, as in step S505 above, by setting the predetermined recognition number ZB larger, the robustness can be further improved, which is advantageous when giving priority to improving measurement accuracy.

§5 Modifications Although the exemplary embodiment of the present disclosure has been described in detail above, the above description merely shows an example of the present disclosure in all respects, and various modifications may be made without departing from the scope of the present disclosure. It goes without saying that improvements and modifications can be made, for example, the following changes are possible. In the following description, the same reference numerals are used for the same components as in the above embodiment, and the description of the same points as in the above embodiment is omitted as appropriate. Further, the above embodiment and each of the following modifications can be configured by appropriately combining them.

In the above-described embodiment, the number of recognized works 5 is exemplified as the evaluation value Zi indicating the accuracy of recognition of the works 5, but the present invention is not limited to this. For example, the effective number of three-dimensional point cloud data obtained as a result of the recognition process of the workpiece 5 may be set as the evaluation value Zi. Alternatively, the evaluation value Zi may be the degree of agreement between known three-dimensional information (for example, three-dimensional CAD (Computer Aided Design) data) of the work 5 and shape information obtained as a result of recognition processing of the work 5.

In the above-described embodiment, the speed of the sensor 1 in the third measurement parameter is set to k times the speed of the sensor 1 in the first measurement parameter, and the time interval of measurement by the sensor 1 in the third measurement parameter is set to k times the speed of the sensor 1 in the first measurement parameter. Although an example has been shown in which the parameter is set to (1/k) times the time interval of measurement by the sensor 1, the parameter is not limited to this. For example, the speed of sensor 1 in the first measurement parameter is V1, the speed of sensor 1 in the third measurement parameter is V2, the time interval of measurement by sensor 1 in the first measurement parameter is T1, and the speed of sensor 1 in the third measurement parameter is T1. Let T2 be the time interval of measurement according to 1. In this case, if (V2×T2) is an integer multiple of (V1×T1), the verification result of the first data includes the verification result of the second data, so the measurement parameter optimization method related to this embodiment can be applied.

In the above-described embodiment, it is assumed that V2 and T2 are always constant on the moving path of the sensor 1, but the present invention is not limited to this. For example, the moving route of the sensor 1 may be divided into a plurality of sections, and V2 and T2 may be constant in each section, and V2 and T2 do not necessarily need to be the same between different sections.

<5.1: First modification example>
In the first modification, the predetermined criterion is that the number of recognitions as the evaluation value Zi indicating the accuracy of recognition of the workpiece 5 is equal to or greater than the predetermined number of recognitions ZB, and the speed V of the movement of the sensor 1 is faster. That's it. Here, FIG. 13 is a diagram obtained by sorting the second data illustrated in FIG. 11 in descending order of evaluation value Zi, and re-sorting data with the same evaluation value Zi in descending order of velocity V. . According to the figure, there are four sets of measurement parameters for which the number of recognitions ZB = 19 and the speed V is the maximum (80%), and the number of recognitions ZB = 18 and the speed V is the maximum (90%). ), it was confirmed that there are 6 sets of measurement parameters, the number of recognition ZB = 17, and 1 set of measurement parameters for which the speed V is the maximum (90%). The optimization measurement parameters can be appropriately selected from these depending on the desired recognition number ZB. As shown above, by adding the fact that the speed V of sensor 1 is faster in addition to the predetermined recognition number ZB of workpiece 5 as a predetermined judgment criterion, it is possible to satisfy the desired recognition number ZB while moving sensor 1. This is advantageous when giving priority to the speed V.

<5.2: Second modification example>
In the second modified example, the predetermined judgment criteria are such that the number of recognitions as the evaluation value Zi indicating the accuracy of recognition of the workpieces 5 is greater than or equal to the predetermined number of recognitions ZB, and the number of photographed images i of the plurality of workpieces 5 is more Let's do less. Here, FIG. 14 is a diagram obtained by sorting the second data illustrated in FIG. 11 in descending order of the number of recognitions Zi, and then re-sorting the data with the same number of recognition Zi in descending order of the number of captured images i. be. According to the figure, the measurement parameters for which the number of recognition ZB = 19 and the number of photographed images i are the minimum (4 images) are: speed V of sensor 1 = 70%, time interval T = 0.06 sec, and photographing The number of sheets i=4, which can be determined as an optimization parameter. In addition, in FIG. 14, there are 6 sets of measurement parameters for which the number of recognitions ZB = 18 pieces and the number of shots i is the minimum (4 pieces), and the number of recognitions ZB = 17 pieces and the number of shots i is the minimum (4 pieces). It was confirmed that there are 4 sets of measurement parameters (3 sheets). As shown, by adding the fact that the number of captured images i is smaller in addition to the predetermined recognized number ZB of the workpiece 5 as a predetermined criterion, priority is given to reducing the number of captured images i while satisfying the desired number of recognized ZB. advantageous in some cases.

<5.3: Third modification example>
In the third modification, the plurality of workpieces 5 are photographed by the sensor 1 multiple times using the first measurement parameter, and the average value of the recognition number Zi of each number of photographed images obtained for each photographing is set as the first measurement parameter. The information is stored in association as first data. In this case, the position and orientation of the sensor 1, the movement path P0 of the sensor 1, the bulk stacking state of the plurality of works 5, etc. may be changed randomly. Here, FIG. 15 is a flowchart showing an example of the processing procedure in the fourth modification.

That is, as shown in FIG. 15, the processing in the third modified example is the same as an example of the processing procedure in the operation example shown in FIG. 5, except that steps S1501 to S1503 are performed instead of step S502. In step S1501, similarly to step S502 (second step (1)), image processing is performed using the obtained plural number N of photographed images, and the number of recognized works 5 Zi is obtained for each number of photographed images i. , the process of storing the number of recognitions Zi in association with the first measurement parameter has not yet been performed. Next, in step S1502, if the preset number of repetitions Q of step S501 has not been reached (step S1502 is "No"), step S501 is repeated and the workpiece is Obtain the recognition number Zi of 5. That is, for each number of photographed images, data of Q recognition numbers Zi are acquired. When the number of repetitions of step S501 reaches Q times (step S1502 is "Yes"), the process moves to step S1503, where the average value of the data of Q recognition numbers Zi is calculated, and the average value is used for the first measurement. The data is stored in the storage unit 43 as first data in association with the parameters.

According to the fourth modification, it is possible to improve the accuracy and reliability of the first data obtained experimentally, and as a result, the robustness when measuring a plurality of workpieces 5 and the work efficiency when operating a plurality of workpieces 5 are improved. , and the overall throughput can be further improved.

<5.4: Fourth modification example>
As mentioned in "§4 Actions and Effects" of the operation example, in the fourth modification, when the robot 10 of the robot system 100 is changed, the information is acquired in advance for a certain robot 10 equipped with the sensor 1. This is an example of a method for obtaining optimized measurement parameters in the robot system 100 after the robot 10 has been changed, by utilizing the first data and second data that have been used. That is, for example, during the parameter setting of the first data to the second data in the operation example, conditions (specifically, the moving speed V and time of the sensor 1) according to the characteristics (mechanical parameters) of the robot 10 after the change are set. If the interval T) is included, the measurement parameters of the data that satisfy the predetermined criteria are selected from the first data to the second data corresponding to the condition, and the measurement parameters of the data that satisfy the predetermined criteria are selected, and the measurement parameters are This is determined as the optimum measurement parameter during operation. This makes it possible to provide a simple method that can optimize measurement parameters without depending on the robot 10. .

<5.5: Fifth modification example>
In the fifth modification, as mentioned in "§4 Actions and Effects" of the operation example, when the robot 10 of the robot system 100 is changed, the information is acquired in advance for a certain robot 10 equipped with the sensor 1. This is an example of a method for obtaining optimized measurement parameters in the robot system 100 after the robot 10 has been changed, by utilizing the first data and second data that have been used. That is, for example, if the parameter set of the first data to second data in the operation example includes a condition corresponding to the characteristics of the robot 10 after the change, the results under that condition are It can be used as basic data (first data) for. Then, by using the basic data and executing the same processes as the second to fourth steps above, the robot system 100 including the robot 10 after the change can be measured without performing new preliminary measurements. Measurement parameters can be optimized. Even in this case, it is possible to provide a simple method that can realize optimization of measurement parameters without depending on the robot 10.

<5.6: Sixth variation>
Furthermore, as a sixth modification example, as shown in FIG. 16, a plurality of works 5 having shapes different from hexagonal bolts are measured, and the recognition results (outline lines) of the position and orientation of the works 5 through image processing are superimposed on the captured images. The top view is shown. By applying the measurement parameter optimization method according to the present disclosure to such various works 5, it is possible to improve the versatility in optimizing measurement parameters for various works 5.

§6 Supplementary Note The embodiments and modified examples described above are intended to facilitate understanding of the present invention, and are not intended to be interpreted as limiting the present invention. Each element included in the embodiment and the modified example, as well as its arrangement, material, conditions, shape, size, etc., are not limited to those illustrated and can be changed as appropriate. It is also possible to partially replace or combine the structures shown in different embodiments and modifications.

DESCRIPTION OF SYMBOLS 1...Sensor (measuring device), 2...Hand, 3...Robot arm, 4...Control device, 5...Work (object), 6, 7...Storage container, 10...Robot, 41...Control calculation unit, 42...Communication Interface (I/F) section, 43... Storage section, 44... Input section, 45... Output section, 46... Bus line, 100... Robot system, 401... Sensor control section, 402... Robot control section, 41
0... Captured image acquisition section, 411... First data acquisition section, 412... Second data acquisition section, 413...
Third data acquisition unit, 414...Optimization parameter determination unit, Gi...Sensor position, P0, P1
, P2... Movement route.

Claims (10)

A method for optimizing measurement parameters when measuring one or more objects with a measurement device installed on a robot, the method comprising:
A first step of photographing the one or more objects while moving the measuring device at a speed V, a time interval T, and a total movement angle θ as first measurement parameters to obtain a plurality of N photographed images. and,
While moving the measuring device at a speed V as a second measurement parameter, a time interval T x j (j: an integer of 2 or more), and a total movement angle θ, take a plurality of images of the one or more objects. Assuming that N/j captured images are acquired and image processing is performed to recognize the position and orientation of the one or more objects, the number of images is i (here, i=1, 2,..., N/ a second step of estimating an evaluation value Zi indicating accuracy of recognition of the target object at (j-1, N/j) and storing the evaluation value Zi associated with the second measurement parameter as first data;
Based on the first data, while moving the measuring device at a speed V x k (k: an integer of 2 or more), a time interval T x j/k, and a total movement angle θ as third measurement parameters, Assuming that one or more objects are photographed to obtain a plurality of N/j/k captured images, and the same processing as the image processing described above is performed, the number of images is i (here, i=1, 2, ..., N/j/k-1, N/j/k), and estimate the evaluation value Zi that indicates the accuracy of recognition of the object in A third step of storing it as data,
a fourth step of selecting a measurement parameter of data that satisfies a predetermined criterion from the second data and determining it as an optimized measurement parameter when the robot operates the one or more objects;
Optimization method of measurement parameters including. 2. The method according to claim 1, wherein the predetermined criterion includes that the evaluation value Zi of the object is greater than or equal to a preset evaluation value. 3. The method according to claim 2, wherein the predetermined criterion includes at least a shorter time required for measurement. The method according to claim 2 or 3, wherein the predetermined criterion includes that the speed V of movement of the measuring device is faster. 5. The method according to claim 2, wherein the predetermined criterion includes that the number i of images of the one or more objects is smaller. 6. The method according to claim 1, wherein the one or more objects are photographed a plurality of times using the first measurement parameter, and an average value of the evaluation value Zi obtained for each photograph is stored as the first data. Any method described. If the first data to second data include data corresponding to a measurement parameter corresponding to a speed V and a time interval T according to characteristics of a robot different from the robot, the first data to second data The method according to any one of claims 1 to 6, wherein measurement parameters of data satisfying predetermined criteria are selected from among the measurement parameters and determined as optimization measurement parameters when the plurality of objects are manipulated by the different robots. . If data corresponding to a measurement parameter corresponding to a speed V and a time interval T according to characteristics of a robot different from the robot is included in the first data or second data, the measurement parameter of the corresponding data is included. New second data is acquired and stored by performing the second to fourth steps using the associated data as new first data, and from among the new second data, a predetermined criterion is determined. 7. The method according to claim 1, wherein measurement parameters of data satisfying the following are selected and determined as optimized measurement parameters when the plurality of objects are operated by the different robots. A measurement parameter optimization device when measuring one or more objects with a measurement device installed on a robot,
The device has at least one processor, the at least one processor comprising:
A first step of photographing the one or more objects while moving the measuring device at a speed V, a time interval T, and a total movement angle θ as first measurement parameters to obtain a plurality of N photographed images. and,
While moving the measuring device at a speed V as a second measurement parameter, a time interval T x j (j: an integer of 2 or more), and a total movement angle θ, take a plurality of images of the one or more objects. Assuming that N/j captured images are acquired and image processing is performed to recognize the position and orientation of the one or more objects, the number of images is i (here, i=1, 2,..., N/ a second step of estimating an evaluation value Zi indicating accuracy of recognition of the target object at (j-1, N/j) and storing the evaluation value Zi associated with the second measurement parameter as first data;
Based on the first data, while moving the measuring device at a speed V x k (k: an integer of 2 or more), a time interval T x j/k, and a total movement angle θ as third measurement parameters, Assuming that one or more objects are photographed to obtain a plurality of N/j/k photographed images, and processing equivalent to the image processing described above is performed, the number of images is i (here, i=1, 2,..., N/j/k-1, N/j/k), and estimate the evaluation value Zi associated with the third measurement parameter as the second A third step of storing it as data,
a fourth step of selecting a measurement parameter of data that satisfies a predetermined criterion from the second data and determining it as an optimized measurement parameter when the robot operates the one or more objects;
Optimization device for measurement parameters. In order to optimize measurement parameters when measuring one or more objects with a measurement device installed on the robot, a computer having at least one processor,
A first step of photographing the one or more objects while moving the measuring device at a speed V, a time interval T, and a total movement angle θ as first measurement parameters to obtain a plurality of N photographed images. and,
While moving the measuring device at a speed V as a second measurement parameter, a time interval T x j (j: an integer of 2 or more), and a total movement angle θ, take a plurality of images of the one or more objects. Assuming that N/j captured images are acquired and image processing is performed to recognize the position and orientation of the one or more objects, the number of images is i (here, i=1, 2,..., N/ a second step of estimating an evaluation value Zi indicating accuracy of recognition of the target object at (j-1, N/j) and storing the evaluation value Zi associated with the second measurement parameter as first data;
Based on the first data, while moving the measuring device at a speed V x k (k: an integer of 2 or more), a time interval T x j/k, and a total movement angle θ as third measurement parameters, Assuming that one or more objects are photographed to obtain a plurality of N/j/k captured images, and the same processing as the image processing described above is performed, the number of images is i (here, i=1, 2, ..., N/j/k-1, N/j/k), and estimate the evaluation value Zi that indicates the accuracy of recognition of the object in A third step of storing it as data,
a fourth step of selecting a measurement parameter of data that satisfies a predetermined criterion from the second data and determining it as an optimized measurement parameter when the robot operates the one or more objects;
A computer-controlled program that runs

Images