WO2019244638A1 - Positioning system, monitor device, monitor method, and program - Google Patents

Abstract

Provided is a positioning system comprising: a movement mechanism for moving an object; a visual sensor for executing in each image capture period a position identification process for identifying the position of the object on the basis of a captured image of the object; a movement control unit for controlling the movement mechanism such that the identified position approaches a target position; a path determination unit; and a determination unit. The path determination unit determines an ideal path of the object from the position identified by the initial position identification process to the target position. On the basis of the result of a comparison between the ideal path and the actual path of the position identified by the position identification processes after the initial position identification process, the determination unit determines whether there is an abnormality in the positioning system. As a result, it is possible to precisely determine if there are abnormalities.

Description

Positioning system, monitoring device, monitoring method and program

(4) The present technology relates to a positioning system using a visual sensor, a monitoring device, a monitoring method, and a program.

In 各種 FA (factory automation), various positioning systems for adjusting the position of an object to a target position have been put to practical use. As a method of measuring a deviation (distance) between the position of the target object and the target position, there is a method of using an image captured by a visual sensor. In this method, calibration is performed, which is a process of associating the coordinate system of the visual sensor with the coordinate system of the moving mechanism that moves the target.

JP-A-2003-50106 (Patent Document 1) discloses a technique for determining a calibration parameter by performing the following steps (a) to (e). In step (a), the table or the imaging unit is moved, and the positional relationship between the table and the imaging unit is calculated. In step (b), the table or the imaging unit is moved, and the positional relationship between the table and a predetermined portion of the table is calculated. In step (c), the table or the imaging unit is moved, and a correction amount is obtained to correct the positional relationship between the table and a predetermined portion of the table. In the step (d), the table or the imaging unit is moved, and the positional relationship between the table and the imaging unit is calculated again. In step (e), steps (c) and (d) are repeated until the correction amount obtained in step (c) becomes equal to or less than a predetermined value.

JP-A-2003-50106

Calibration is performed at the start-up stage of the device. However, with the aging of the machine constituting the moving mechanism, the coordinate system of the visual sensor cannot be accurately converted to the coordinate system of the moving mechanism. In such a case, it is necessary to perform maintenance such as re-calibration, replacement of parts, and adjustment of the machine. Conventionally, whether or not maintenance is required has been determined based on a criterion depending on an operator. That is, the worker has empirically determined the necessity of maintenance based on trends such as an increase in the defect rate of the product and an increase in the production tact. Therefore, an abnormality in the positioning system may be overlooked.

The present invention has been made in view of the above problems, and has as its object to provide a positioning system capable of accurately determining the presence or absence of an abnormality, a monitoring device used in the positioning system, a monitoring method and a program for the positioning system. To provide.

According to an example of the present disclosure, a positioning system that performs a positioning process of an object includes a moving mechanism, a visual sensor, a movement control unit, a trajectory determination unit, and a determination unit. The moving mechanism moves the object. The visual sensor captures an image of an object, and executes a position specifying process for specifying the position of the object based on the captured image in each imaging cycle. The movement control unit controls the movement mechanism so that the position specified by the visual sensor approaches the target position. The trajectory determination unit determines an ideal trajectory of the target object from the position of the target object specified by the initial position specifying process to the target position. The determining unit determines whether there is an abnormality in the positioning system based on a comparison result between the actual trajectory of the position of the target object and the ideal trajectory specified by the position specifying process after the first position specifying process.

(4) If there is a deviation of the calibration parameter indicating the correspondence between the coordinate system of the visual sensor and the machine coordinate system of the moving mechanism, the actual trajectory deviates from the ideal trajectory. Therefore, according to the above disclosure, the determination unit can accurately determine the presence or absence of an abnormality that causes a deviation of a calibration parameter based on a comparison result between an actual trajectory and an ideal trajectory without depending on personal judgment. A good judgment can be made.

In the above disclosure, the visual sensor performs an initial position specifying process when the object is stopped, and performs a subsequent position specifying process when the object is moving. According to this disclosure, the positioning process can be speeded up.

In the above disclosure, the determination unit determines that an abnormality has occurred and notifies a warning when the feature amount indicating the degree of deviation between the actual trajectory and the ideal trajectory exceeds the first threshold. According to the present disclosure, an operator can perform maintenance for removing a cause of a deviation of a calibration parameter at an appropriate timing.

に お い て In the above disclosure, the determination unit stops the moving mechanism when the feature amount exceeds the second threshold. The second threshold is larger than the first threshold.

(4) If the feature value exceeds the second threshold value that is larger than the first threshold value, there is a high possibility that a sudden abnormality such as a catch of the moving mechanism has occurred. In such a case, if the moving mechanism is continuously driven, there is a possibility that the moving mechanism may fail. However, according to this disclosure, the moving mechanism is stopped when the feature amount exceeds the second threshold. As a result, a failure of the moving mechanism can be avoided.

In the above disclosure, the characteristic amount is a deviation between the position of the object specified by the subsequent position specification processing and the ideal trajectory.

Alternatively, the actual trajectory and the ideal trajectory are indicated by information that associates the elapsed time from the start of the control of the moving mechanism by the movement control unit with the position of the object. The feature amount may be a maximum value or an integral value of the deviation between the position on the actual trajectory and the position on the ideal trajectory, where the elapsed time is the same.

In the above disclosure, the trajectory determination unit determines an ideal trajectory by performing a simulation using the simulation model of the movement mechanism and the movement control unit and the position of the target object specified by the initial position specification processing. According to this disclosure, an ideal trajectory can be accurately determined by using a simulation model.

In the above disclosure, the trajectory determination unit is configured to output, by machine learning using learning data, information indicating the trajectory of the target object from the position of the input target object to the target position. The learned learning device is further provided. The learning data is data indicating the position of the target object specified by the visual sensor in the positioning processing executed when the positioning system is normal. The trajectory determination unit determines the trajectory indicated by the information output from the learning device as an ideal trajectory by inputting the position of the target object specified by the initial position specification processing to the learning device. According to this disclosure, the trajectory determination unit can determine an ideal trajectory that matches the actual situation.

に お い て In the above disclosure, the determination unit outputs a screen showing the actual trajectory and the ideal trajectory to the display device. According to this disclosure, the operator can grasp the degree of deviation of the calibration parameter by checking the screen.

In the above disclosure, the actual trajectory and the ideal trajectory are indicated by information that associates the elapsed time from the start of the control of the moving mechanism by the movement control unit with the position of the object. The movement mechanism includes a plurality of translation mechanisms that translate in different movement directions. The determination unit decomposes the deviation between the position on the actual trajectory and the position on the ideal trajectory having the same elapsed time into components in the movement direction corresponding to each of the plurality of translation mechanisms, and calculates the temporal change of each component. The displayed screen is output to the display device.

According to the present disclosure, the operator can infer the abnormal position of the moving mechanism by checking the screen of the display device.

に お い て In the above disclosure, the determination unit outputs a screen showing the transition of the feature amount to the display device. According to this disclosure, an operator can grasp a situation such as aging of the moving mechanism.

According to an example of the present disclosure, a monitoring device used for the positioning system includes the trajectory determination unit and the determination unit. According to this disclosure as well, the determination unit can accurately determine the presence or absence of an abnormality that causes a deviation of the calibration parameter based on the comparison result between the actual trajectory and the ideal trajectory without depending on personal judgment. Can be.

According to an example of the present disclosure, a method for monitoring a positioning system that performs a positioning process on an object includes first and second steps. The positioning system includes a moving mechanism for moving the object, a visual sensor for imaging the object, and executing a position specifying process for specifying the position of the object based on the captured image for each imaging cycle, A movement control unit for controlling the movement mechanism so that the position specified by the sensor approaches the target position. The first step is a step of determining an ideal trajectory of the object from the position of the object specified by the initial position specifying process to the target position. The second step is a step of determining the presence or absence of an abnormality in the positioning system based on a comparison result between the actual trajectory and the ideal trajectory of the position of the object specified by the position specifying processing after the first position specifying processing. is there. According to this disclosure as well, it is possible to accurately determine the presence or absence of an abnormality that causes a deviation of a calibration parameter.

According to an example of the present disclosure, a program for causing a computer to execute the above monitoring method causes the computer to execute the first and second steps. According to this disclosure as well, it is possible to accurately determine the presence or absence of an abnormality that causes a deviation of a calibration parameter.

According to the present invention, the presence or absence of an abnormality in the positioning system can be accurately determined.

1 is a schematic diagram illustrating an outline of a positioning system according to the present embodiment. It is a figure showing an example of an ideal locus and an actual locus. FIG. 2 is a schematic diagram illustrating a hardware configuration of an image processing device that configures the positioning system 1 according to the present embodiment. It is a schematic diagram which shows the hardware constitutions of the controller which comprises the positioning system concerning embodiment. FIG. 2 is a block diagram illustrating an example of a functional configuration of the positioning system illustrated in FIG. 1. 9 is a flowchart illustrating an example of a flow of a positioning process in the controller. 9 is a flowchart illustrating an example of a flow of movement control processing performed by a movement control unit. FIG. 9 is a diagram illustrating a method for calculating an encoder value EnsX at an imaging time. FIG. 9 is a diagram illustrating an example of a change in the position of a mark in a positioning process according to a comparative example and a positioning process according to an embodiment. FIG. 9 is a diagram illustrating an example of a change in the moving speed of the stage device in the positioning process of the comparative example and the positioning process according to the embodiment. 9 is a flowchart illustrating an example of the flow of a monitoring process in a controller. 12 is a flowchart showing the contents of a subroutine of an ideal trajectory determination process (step S21) shown in FIG. 12 is a flowchart showing the contents of a subroutine of a process (step S22) for determining the presence or absence of an abnormality shown in FIG. 13 is a flowchart illustrating the contents of a subroutine of a determination process according to Modification 2. 13 is a flowchart illustrating a flow of a monitoring process according to a third modification. 16 is a flowchart showing the contents of a subroutine of a process (step S121) for determining the presence / absence of abnormality and the level of abnormality shown in FIG. FIG. 14 is a diagram illustrating a functional configuration of a controller according to a modification 5. FIG. 14 is a diagram illustrating a configuration of a positioning system according to a modification 6. It is an example of a screen showing an ideal locus and an actual locus. It is a figure showing an example of a screen which shows a temporal change of each component of a deviation of a position on an actual locus and a position on an ideal locus in each of the X direction and the Y direction. FIG. 9 is a diagram illustrating an example of a screen showing a time change of a feature amount (integral value of deviation) indicating a degree of deviation between an ideal trajectory and an actual trajectory.

Embodiments of the present invention will be described in detail with reference to the drawings. The same or corresponding parts in the drawings have the same reference characters allotted, and description thereof will not be repeated.

§1 Application Example An example of a scene to which the present invention is applied will be described with reference to FIG. FIG. 1 is a schematic diagram showing an outline of a positioning system according to the present embodiment. The positioning system 1 shown in FIG. 1 positions an object (hereinafter, referred to as “target work W”) using image processing. The positioning typically means a process of arranging the target work W at an original position of a production line in a manufacturing process of an industrial product or the like. For example, the positioning system 1 positions the glass substrate with respect to the exposure mask before printing the circuit pattern on the glass substrate (exposure process) on the liquid crystal panel production line.

As shown in FIG. 1, the positioning system 1 includes a moving mechanism 10, a driver unit 20, a visual sensor 30, a controller 40, and a display device 50.

The moving mechanism 10 moves the target workpiece W to be placed. The moving mechanism 10 may have any degree of freedom as long as the mechanism can arrange the target work W at the target position. The moving mechanism 10 is, for example, an XYθ stage that can apply horizontal translation and rotation to the target workpiece W.

The moving mechanism 10 in the example shown in FIG. 1 is an XYθ stage, and includes an X stage 11, a Y stage 13, a θ stage 15, and servomotors 12, 14, and 16. The X stage 11 is a translation mechanism that translates along the X direction by driving the servo motor 12. The Y stage 13 is a translation mechanism that translates along the Y direction by driving a servo motor 14. stage 15 is a rotating mechanism that rotates and moves in the θ direction by driving a servo motor 16. The target work W is placed on the θ stage 15.

The servo motors 12, 14, 16 are provided with encoders 12E, 14E, 16E, respectively. Each of the encoders 12E, 14E, and 16E generates a pulse signal corresponding to the drive amount (rotation amount) of the corresponding servo motor. The encoder 12E measures the amount of movement of the X stage 11 from the initial position as an encoder value EnX by counting the number of pulses included in the pulse signal. The count value of the number of pulses and the movement amount are related by a predetermined coefficient. Therefore, the encoder 12E can measure the movement amount by multiplying the count value of the pulse number by the coefficient. Similarly, the encoder 14E measures the translation amount of the Y stage 13 in the Y direction from the initial position as an encoder value EnY. The encoder 16E measures the rotational movement amount of the θ stage 15 from the initial position as an encoder value Enθ.

The driver unit 20 controls the operation of the moving mechanism 10 in accordance with the movement command received from the controller 40 for each control cycle Ts. As shown in FIG. 1, the driver unit 20 includes servo drivers 22, 24, and 26. The servo drivers 22, 24, 26 acquire the encoder values EnX, EnY, Enθ from the servo motors 12, 14, 16 for each control cycle Ts. The control cycle Ts is fixed, for example, 1 ms.

(4) The servo driver 22 performs feedback control on the servomotor 12 so that the movement amount of the X stage 11 approaches the movement command. The servo driver 24 performs feedback control on the servo motor 14 so that the movement amount of the Y stage 13 approaches the movement command. The servo driver 26 performs feedback control on the servo motor 16 so that the movement amount of the θ stage 15 approaches the movement command.

The driver unit 20 outputs the encoder values EnX, EnY, Enθ acquired from the moving mechanism 10 to the controller 40.

The visual sensor 30 captures an image of the target work W and executes a position specifying process for specifying the position of the target work W based on the captured image for each imaging cycle Tb. The imaging cycle Tb varies according to the imaging situation and the like, and is, for example, about 60 ms. In the example illustrated in FIG. 1, the visual sensor 30 specifies, as the position of the target work W, the positions of the marks 5a and 5b, which are characteristic portions provided on the target work W.

The visual sensor 30 includes an imaging unit 31 installed at a fixed position and an image processing device 32. The imaging unit 31 performs an imaging process of imaging a subject existing in an imaging field of view and generating image data, and captures an image of the target work W. The imaging unit 31 is, for example, a camera.

The image processing device 32 performs image analysis on the image data generated by the imaging unit 31 and calculates the coordinates of the positions of the marks 5a and 5b. The coordinates are indicated by a local coordinate system (hereinafter, referred to as a “camera coordinate system”) corresponding to the visual sensor 30.

The controller 40 is, for example, a PLC (programmable logic controller) and performs various FA controls.

Based on the position of the target work W specified by the visual sensor 30, the controller 40 updates the movement command for each control cycle Ts and outputs it to the driver unit 20 so that the position of the target work W approaches the target position. . In the example shown in FIG. 1, the controller 40 updates the movement command for each control cycle Ts so that the position of each of the marks 5a and 5b specified by the visual sensor 30 approaches the corresponding target position, and updates the driver unit 20. Output to

As described above, the coordinates of the positions of the marks 5a and 5b specified by the visual sensor 30 are indicated in the camera coordinate system. On the other hand, the amount of movement of the moving mechanism 10 to be controlled by the controller 40 is indicated in a coordinate system of the moving mechanism 10 (hereinafter, referred to as “mechanical coordinate system”). Therefore, the controller 40 converts the coordinates of the positions of the marks 5a and 5b from the camera coordinate system to the machine coordinate system using the calibration parameters for associating the camera coordinate system with the machine coordinate system, and uses the converted coordinates. Generate a movement command MV.

{Circle around (4)} The controller 40 monitors the presence or absence of an abnormality that causes a deviation of the calibration parameter. The “calibration parameter deviation” means a deviation between a currently set calibration parameter and an ideal calibration parameter corresponding to the current state of the moving mechanism 10. The abnormalities that cause the deviation of the calibration parameters include, for example, aging of the moving mechanism 10 and external factors.

The controller 40 determines an ideal trajectory on the image of the target work W from the position (initial position) of the target work W specified in the initial position specifying process of the visual sensor 30 to the target work W to the target position. The ideal trajectory indicates a trajectory on the image of the target work W when it is assumed that the deviation of the calibration parameter is zero.

{For example, the controller 40 determines an ideal trajectory on the image of the mark 5a from the initial position of the mark 5a specified by the visual sensor 30 to the target position of the mark 5a. Further, the controller 40 determines an ideal trajectory on the image of the mark 5b from the initial position of the mark 5b specified by the visual sensor 30 to the target position of the mark 5b.

The controller 40 determines the presence or absence of an abnormality that causes a deviation of the calibration parameter based on a comparison result between the actual trajectory and the ideal trajectory of the position of the target work W specified by the second and subsequent position specifying processes. The determination unit 49 outputs the determination result to the display device 50.

As described above, the controller 40 controls the moving mechanism 10 so that the positions of the marks 5a and 5b specified by the visual sensor 30 for each imaging cycle Tb approach the corresponding target positions. Therefore, even if the calibration parameter is shifted, each of the marks 5a and 5b of the target work W finally reaches the corresponding target position. However, the actual trajectory deviates from the ideal trajectory because of the deviation of the calibration parameters.

FIG. 2 is a diagram showing an example of an ideal trajectory and an actual trajectory. FIG. 2 shows an ideal trajectory and an actual trajectory for one of the marks 5a and 5b. The same applies to the other mark.

In FIG. 2, the position P (0) indicates the initial position of the target mark on the image specified by the first position specifying process. A solid line 70 indicates an ideal trajectory from the position P (0) to the target position SP of the target mark. The solid line 72a shows an example of the actual trajectory of the target mark. A solid line 72b shows another example of the actual trajectory of the target mark.

The controller 40 sets, for example, an allowable area 71 including an ideal locus indicated by a solid line 70. The allowable area 71 is determined experimentally or theoretically. When the actual trajectory is within the allowable area 71, the controller 40 determines that an abnormality that causes a deviation of the calibration parameter has not occurred. In the example illustrated in FIG. 2, the controller 40 determines that an abnormality that causes a deviation of the calibration parameter has not occurred with respect to the actual locus indicated by the solid line 72a.

On the other hand, if the actual trajectory deviates from the allowable area 71, the controller 40 determines that an abnormality that causes a deviation of the calibration parameter has occurred. In the example illustrated in FIG. 2, the determination unit 49 determines that an abnormality that causes a deviation of the calibration parameter has occurred with respect to the actual locus indicated by the solid line 72b.

Thereby, the controller 40 can accurately determine the presence or absence of an abnormality that causes a deviation of the calibration parameter without depending on the personal judgment.

§2 Specific Example Next, an example of the positioning system according to the present embodiment will be described.

<2-1. Hardware configuration of image processing device>
FIG. 3 is a schematic diagram illustrating a hardware configuration of the image processing device 32 included in the positioning system 1 according to the present embodiment. The image processing device 32 typically has a structure according to a general-purpose computer architecture, and realizes various types of image processing as described later by executing a program installed in advance by a processor.

More specifically, the image processing device 32 includes a processor 310 such as a CPU (Central Processing Unit) or an MPU (Micro-Processing Unit), a RAM (Random Access Memory) 312, a display controller 314, and a system controller 316. , An input / output (I / O) controller 318, a hard disk 320, a camera interface 322, an input interface 324, a controller interface 326, a communication interface 328, and a memory card interface 330. These units are connected to each other so as to enable data communication with the system controller 316 at the center.

The processor 310 exchanges programs (codes) and the like with the system controller 316 and executes them in a predetermined order, thereby realizing the intended arithmetic processing.

The system controller 316 is connected to the processor 310, the RAM 312, the display controller 314, and the I / O controller 318 via buses, respectively, exchanges data with each unit, and performs processing of the entire image processing apparatus 32. Govern

The RAM 312 is typically a volatile storage device such as a DRAM (Dynamic Random Access Memory), and stores a program read from the hard disk 320, an image (image data) captured by the imaging unit 31, and an image. Holds processing results and work data. The processing result for the image includes the position coordinates of the marks 5a and 5b included in the image.

The display controller 314 is connected to the display unit 60, and outputs a signal for displaying various information to the display unit 60 according to an internal command from the system controller 316.

The I / O controller 318 controls data exchange between a recording medium connected to the image processing apparatus 32 and an external device. More specifically, I / O controller 318 is connected to hard disk 320, camera interface 322, input interface 324, controller interface 326, communication interface 328, and memory card interface 330.

The hard disk 320 is typically a non-volatile magnetic storage device, and stores various setting values in addition to a program executed by the processor 310.

The camera interface 322 corresponds to an input unit that receives image data generated by photographing the target work W, and mediates data transmission between the processor 310 and the imaging unit 31. The camera interface 322 includes an image buffer for temporarily storing image data from the imaging unit 31, respectively.

The input interface 324 mediates data transmission between the processor 310 and input devices such as a keyboard 334, a mouse, a touch panel, and a dedicated console.

The controller interface 326 mediates data transmission between the processor 310 and the controller 40.

The communication interface 328 mediates data transmission between the processor 310 and another personal computer or server device (not shown). The communication interface 328 is typically made of Ethernet (registered trademark), USB (Universal Serial Bus), or the like.

The memory card interface 330 mediates data transmission between the processor 310 and the recording medium 61.

<2-2. Controller hardware configuration>
FIG. 4 is a schematic diagram illustrating a hardware configuration of the controller 40 configuring the positioning system according to the embodiment. The controller 40 includes a chipset 412, a processor 414, a nonvolatile memory 416, a main memory 418, a system clock 420, a memory card interface 422, a display controller 426, a communication interface 428, and an internal bus controller 430. , A fieldbus controller 438. The chipset 412 and other components are respectively connected via various buses.

The processor 414 and the chipset 412 typically have a configuration according to a general-purpose computer architecture. That is, the processor 414 interprets and executes the instruction codes sequentially supplied from the chipset 412 according to the internal clock. The chipset 412 exchanges internal data with various connected components and generates an instruction code necessary for the processor 414. The system clock 420 generates a system clock having a predetermined cycle and provides the system clock to the processor 414. The chip set 412 has a function of caching data and the like obtained as a result of execution of arithmetic processing by the processor 414.

The controller 40 has a nonvolatile memory 416 and a main memory 418 as storage means. The non-volatile memory 416 non-volatilely stores data definition information, log information, and the like, in addition to the control program 440 executed by the processor 414. The control program 440 is distributed while being stored in the recording medium 424 or the like. The main memory 418 is a volatile storage area that holds various programs to be executed by the processor 414 and is also used as a working memory when executing various programs.

The controller 40 has a communication interface 428 and an internal bus controller 430 as communication means. These communication circuits transmit and receive data.

The communication interface 428 exchanges data with the visual sensor 30. The internal bus controller 430 controls data exchange. More specifically, the internal bus controller 430 includes a buffer memory 436, a DMA (Dynamic Memory Access) control circuit 432, and an internal bus control circuit 434.

The memory card interface 422 connects the recording medium 424 detachable to the controller 40 and the processor 414. The recording medium 424 stores information such as a program by an electrical, magnetic, optical, mechanical, or chemical action so that a computer or other device, machine, or the like can read information such as a recorded program. It is a medium to do. The recording medium 51 circulates in a state where a control program 440 executed by the controller 40 and the like are stored, and the memory card interface 422 reads the control program from the recording medium 424. The recording medium 424 may be a general-purpose semiconductor storage device such as SD (Secure Digital), a magnetic recording medium such as a flexible disk (Flexible Disk), or an optical recording medium such as a CD-ROM (Compact Disk Read Only Memory). Become. Alternatively, a program downloaded from a distribution server or the like may be installed in the controller 40 via the communication interface 417.

The field bus controller 438 is a communication interface for connecting to a field network. For the field network, for example, EtherCAT (registered trademark), EtherNet / IP (registered trademark), CompoNet (registered trademark), or the like is employed. The controller 40 is connected to the servo drivers 22, 24, 26 via a field bus controller 438.

The display controller 426 is connected to the display device 50, and outputs a signal for displaying various information to the display device 50 according to a command from the chipset 412.

<2-3. Processing example of image processing device>
FIG. 5 is a block diagram showing an example of a functional configuration of the positioning system shown in FIG. The image processing device 32 searches for the marks 5a and 5b (see FIG. 1) from the image captured by the imaging unit 31, and detects the positions of the marks 5a (hereinafter, referred to as “measurement positions PMa”) and the positions of the marks 5b ( Hereinafter, “measurement position PMb” is specified. The image processing device 32 may recognize the marks 5a and 5b from the image using a known pattern recognition technology. The image processing device 32 measures the coordinates of the measurement positions PMa and PMb. The coordinates are indicated in a camera coordinate system.

<2-4. Functional configuration of controller>
As shown in FIG. 5, the controller 40 includes a movement control unit 41, a model storage unit 46, and a monitoring unit 47. The movement control unit 41 and the monitoring unit 47 are realized by the processor 414 illustrated in FIG. The model storage unit 46 is realized by the nonvolatile memory 416 and the main memory 418 shown in FIG.

<2-4-1. Movement control section>
The movement control unit 41 generates a movement command such that the measured position PMa of the mark 5a approaches the target position SPa and the measured position PMb of the mark 5b approaches the target position SPb. Target positions SPa and SPb are predetermined. As shown in FIG. 5, the movement control unit 41 includes a coordinate conversion unit 42, a position determination unit 43, a subtraction unit 44, and a calculation unit 45.

As described above, the measurement positions PMa and PMb output from the visual sensor 30 are indicated by the camera coordinate system. On the other hand, the movement amount of the movement mechanism 10 to be controlled by the movement control unit 41 is shown in a machine coordinate system.

Therefore, the coordinate conversion unit 42 performs the coordinate conversion of the measurement positions PMa and PMb specified by the visual sensor 30 using the calibration parameters for converting the camera coordinate system into the machine coordinate system, and performs measurement in the machine coordinate system. The coordinates of the positions PMa and PMb are calculated. The coordinate conversion unit 42 may perform the coordinate conversion using, for example, affine transformation. The coordinate conversion unit 42 outputs the coordinates of the measurement positions PMa and PMb in the machine coordinate system to the position determination unit 43.

The measurement positions PMa and PMb are specified for each imaging cycle Tb. On the other hand, the movement command is generated for each control cycle Ts. As described above, the imaging cycle Tb is longer than the control cycle Ts. Therefore, if the moving mechanism 10 is controlled using only the measurement positions PMa and PMb specified by the visual sensor 30, overshoot and vibration are likely to occur. In order to avoid such overshoot and vibration, the position determination unit 43 determines the measurement positions PMa, PMb specified by the visual sensor 30 for each imaging cycle Tb and the encoder values EnX, EnY, Enθ output for each control cycle Ts. , The estimated positions PVa and PVb of the two marks 5a and 5b of the target work W are determined for each control cycle Ts. The method for determining the estimated positions PVa and PVb will be described later.

The subtraction unit 44 outputs a deviation (distance) between the estimated position PVa and the target position SPa, and a deviation (distance) between the estimated position PVb and the target position SPb.

The operation unit 45 performs an operation (P operation or PID operation) so that the deviation between the estimated position PVa and the target position SPa and the deviation between the estimated position PVb and the target position SPb converge to 0, and moves every control cycle Ts. The commands MVX, MVY, MVθ are calculated. The movement command MVX is a movement command for the X stage 11 (see FIG. 1). The movement command MVY is a movement command for the Y stage 13 (see FIG. 1). The movement command MVθ is a movement command for the θ stage 15 (see FIG. 1). The calculation unit 45 outputs the calculated movement commands MVX, MVY, MVθ to the driver unit 20. The movement commands MVX, MVY, MVθ are, for example, position commands or speed commands.

<2-4-2. Model storage>
The model storage unit 46 stores a simulation model simulating the moving mechanism 10, the driver unit 20, and the movement control unit 41. The simulation model is composed of design data of the moving mechanism 10, a program that defines processing of the moving control unit 41, and the like.

<2-4-3. Monitoring section>
The monitoring unit 47 monitors the presence or absence of an abnormality that causes a deviation of a calibration parameter for converting a camera coordinate system into a machine coordinate system. As shown in FIG. 5, the monitoring unit 47 includes a trajectory determination unit 48 and a determination unit 49.

The trajectory determination unit 48 performs a simulation using the simulation model stored in the model storage unit 46, so that an image of the target work W from the initial position to the target position of the target work W specified in the first position specification processing is displayed. Is determined.

More specifically, the trajectory determination unit 48 performs a simulation using a simulation model, and thereby performs the simulation of the mark 5a from the measurement position PMa of the mark 5a specified in the initial position specification processing by the visual sensor 30 to the target position SPa. Determine the ideal trajectory on the image. Similarly, the trajectory determination unit 48 performs a simulation using the simulation model, and thereby, on the image of the mark 5b from the measurement position PMb of the mark 5b specified in the initial position specification processing by the visual sensor 30 to the target position SPb. Is determined. A specific processing method of the trajectory determination unit 48 will be described later.

The determination unit 49 determines the presence or absence of an abnormality based on a comparison result between the actual trajectory and the ideal trajectory of the position of the target work W specified in the second and subsequent position specifying processes. The determination unit 49 outputs the determination result to the display device 50.

The determination unit 49 evaluates the degree of deviation between the ideal trajectory of the mark 5a determined by the trajectory determination unit 48 and the measurement position PMa of the mark 5a specified by the second and subsequent position specifying processes. Similarly, the determination unit 49 evaluates the degree of deviation between the ideal trajectory of the mark 5b determined by the trajectory determination unit 48 and the measurement position PMb of the mark 5b specified by the second and subsequent position specification processing. The determining unit 49 determines whether there is an abnormality based on the evaluation result. A specific processing method of the determination unit 49 will be described later.

§3 Operation example <3-1. Flow of controller positioning processing>
An example of the flow of the positioning process of the controller 40 will be described with reference to FIG. FIG. 6 is a flowchart illustrating an example of the flow of the positioning process in the controller.

First, in step S1, the controller 40 initializes the estimated positions PVa, PVb and the encoder values EnX, EnY, Ebθ.

Next, when the target work W is placed on the moving mechanism 10, the controller 40 outputs an imaging trigger to the visual sensor 30 in accordance with an instruction from a higher-level control device. Then, in step S2, the visual sensor 30 captures an image of the target work W on the stopped moving mechanism 10. In step S3, the visual sensor 30 specifies the measurement positions PMa and PMb of the marks 5a and 5b included in the captured image, respectively. Steps S2 and S3 correspond to the initial position identification processing by the visual sensor 30.

Next, in step S4, the movement control unit 41 starts the movement control of the movement mechanism 10. The details of the movement control by the movement control unit 41 will be described later.

Next, in step S5, the movement control unit 41 determines whether each deviation of the estimated positions PVa, PVb from the target positions SPa, SPb is less than a threshold Th0. The threshold value Th0 is predetermined in accordance with the required positioning accuracy. If the respective deviations of the estimated positions PVa, PVb from the target positions SPa, SPb are smaller than the threshold Th0 (YES in step S5), the movement control unit 41 ends the movement control of the movement mechanism 10. Thus, the positioning process ends.

(4) If at least one of the deviations of the estimated positions PVa and PVb from the target positions SPa and SPb is not less than the threshold value Th0 (NO in step S5), the processing in steps S6 to S8 is repeated for each imaging cycle Tb. Note that the movement control by the movement control unit 41 is also performed in parallel between steps S6 to S8.

In step S6, the controller 40 determines whether or not the current time is the imaging trigger output time. The imaging trigger output time is determined in advance according to the imaging cycle Tb. That is, a time at which the imaging cycle Tb has elapsed from the previous imaging trigger output time is determined as a new imaging trigger output time. If the current time is not the imaging trigger output time (NO in step S6), the positioning process returns to step S5.

If the current time is the imaging trigger output time (YES in step S6), the controller 40 outputs an imaging trigger to the visual sensor 30. Accordingly, in step S7, the visual sensor 30 that has received the imaging trigger captures an image of the target work W on the moving mechanism 10 that is moving. In step S8, the visual sensor 30 specifies the measurement positions PMa and PMb of the marks 5a and 5b included in the captured image, respectively. Steps S7 and S8 correspond to the position specifying process after the first position specifying process (the second and subsequent position specifying processes). After step S8, the positioning process returns to step S5.

<3-2. Processing of movement control unit>
FIG. 7 is a flowchart illustrating an example of the flow of the movement control process performed by the movement control unit. First, in step S11, the movement control unit 41 acquires the coordinates (camera coordinate system) of the latest measurement positions PMa and PMb specified by the visual sensor 30. Next, in step S12, the coordinate conversion unit 42 converts the coordinates of the measurement positions PMa and PMb into a machine coordinate system.

に お い て In step S13, the position determination unit 43 acquires the imaging time ti. The position determining unit 43 acquires a time when a fixed transmission delay time Tsd has elapsed from the time at which the imaging trigger was output, as the imaging time ti. The transmission delay time Tsd is a delay time from when the visual sensor 30 receives an imaging trigger to when imaging starts.

Next, in step S14, the position determination unit 43 acquires the encoder values EnX, EnY, Enθ output from the encoders 12E, 14E, 16E at a plurality of times near the imaging time ti (hereinafter, referred to as “output times”). . The encoder values detected in the past are stored in the storage unit of the controller 40 (for example, the nonvolatile memory 416 or the main memory 418 (see FIG. 4)).

Next, in step S15, the position determination unit 43 calculates an interpolation value of the encoder value EnX at a plurality of output times, and sets the interpolation value as the encoder value EnsX at the imaging time ti. Similarly, the position determination unit 43 calculates an interpolation value of the encoder value EnY at a plurality of times, and sets the interpolation value as the encoder value EnsY at the imaging time. The position determination unit 43 calculates an interpolation value of the encoder value Enθ at a plurality of times, and sets the interpolation value as the encoder value Ensθ at the imaging time.

FIG. 8 is a diagram illustrating a method of calculating the encoder value EnsX at the imaging time. Referring to FIG. 8, position determination section 43 calculates an interpolation value as follows. The encoder value EnX output at the output time t (j) is defined as an encoder value EnX (j). Note that the transmission is delayed by a certain transmission delay time Ted from when the encoder 12E detects the pulse signal to when the encoder value EnX is output. Therefore, the encoder value EnX (j) output at the output time t (j) indicates the drive amount of the servo motor 12 from the initial position at a time before the output time t (j) by the transmission delay time Ted. I have.

The position determination unit 43 specifies two output times that are close to the imaging time ti. For example, when the control cycle Ts, the transmission delay time Ted of the encoder value, and the transmission delay time Tsd of the imaging trigger satisfy Ts−Ted ≦ Tsd <2Ts−Ted, the position determination unit 43 sets the position immediately after the imaging time ti. The output time t (n) and the output time t (n + 1) are specified.

The position determining unit 43 acquires the encoder value EnX (n) output at the output time t (n) and the encoder value EnX (n + 1) output at the output time t (n + 1).

The position determination unit 43 calculates the encoder value EnsX (i) at the imaging time ti by using an interpolation value between the encoder value EnX (n) and the encoder value EnX (n + 1). Specifically, the position determination unit 43 calculates the encoder value EnsX (i) at the imaging time ti using the following equation (1).

EnsX (i) = EnX (n) + Kk * (EnX (n + 1) -EnX (n)) (1)
Here, Kk is an interpolation coefficient. When Ts−Ted ≦ Tsd <2Ts−Ted, the interpolation coefficient Kk is calculated using the following equation (2).

Kk = {Tsd- (Ts-Ted)} / Ts (2)
By using such a method of calculating the interpolation value, the encoder value EnsX (i) at the imaging time ti can be calculated with high accuracy. Similarly, the encoder values EnsY (i) and Ensθ (i) at the imaging time ti are calculated. If the imaging time ti matches the time before the transmission time of the encoder value by the transmission delay time Ted, the encoder value may be used as it is.

Next, in step S16 (see FIG. 7), the position determination unit 43 uses the measured positions PMa and PMb, the encoder values EnX, EnY, and Enθ after the imaging time, and the encoder values EnsX, EnsY, and Ensθ at the imaging time. Thus, the estimated positions PVa and PVb are calculated.

Specifically, the position determination unit 43 performs the affine transformation when the translation is performed by (EnX−EnsX) in the X direction, the translation is performed by (EnY−EnsY) in the Y direction, and the rotation is performed by (Enθ−Ensθ). The measurement position PMa is input into the equation. Thereby, the position determining unit 43 calculates the coordinates of the estimated position PVa of the mark 5a. Similarly, the position determination unit 43 calculates the coordinates of the estimated position PVb of the mark 5b by inputting the measurement position PMb into the affine transformation equation.

Next, in step S17, the calculation unit 45 generates the movement commands MVX, MVY, MVθ by, for example, P calculation based on the respective deviations of the estimated positions PVa, PVb with respect to the target positions SPa, SPb. Then, the arithmetic unit 45 outputs the movement commands MVX, MVY, MVθ to the driver unit 20.

こ と By executing such a process, the controller 40 uses the high-precision measurement positions PMa, PMb at the time when the high-precision measurement positions PMa, PMb are input by the image processing, and uses the high-precision measurement positions PMa, PMb. By calculating PVb, highly accurate positioning control can be realized. Here, the time interval at which the measurement positions PMa and PMb are input is the imaging cycle Tb, and is longer than the control cycle Ts at which the encoder values EnX, EnY, and Enθ are input. However, between the input times of the adjacent measurement positions PMa and PMb on the time axis, the position determination unit 43 determines the estimated positions PVa and PVb for each input time of the encoder values EnX, EnY and Enθ having a short input cycle. Then, the movement of the moving mechanism 10 is controlled. This enables high-accuracy and short-period positioning control. Further, the position determining unit 43 performs a process using the above-described simple four arithmetic operations. Therefore, high-speed and high-precision positioning can be realized by a simple configuration and processing.

<3-3. Mark Position Change>
FIG. 9 is a diagram illustrating an example of a change in the position of a mark in the positioning process of the comparative example and the positioning process according to the embodiment. FIG. 10 is a diagram illustrating an example of a change in the moving speed of the stage device between the positioning process of the comparative example and the positioning process according to the embodiment.

In the positioning process of the comparative example, the required moving amount of the moving mechanism 10 is determined from an image obtained by imaging the target work W, and a unit process of moving the moving mechanism 10 by the determined necessary moving amount is performed. Then, after the movement of the moving mechanism 10 by the unit process is completed, the target work W is imaged, and the unit process is repeated again. By repeating the unit processing a plurality of times in this manner, the position of the target work W is positioned at the target position.

In FIG. 9, reference numerals 81, 82, 83, and 84 denote trajectories on the image of the target mark (the mark 5 a or the mark 5 b) on the target work W in the first, second, third, and fourth unit processes, respectively. In FIG. 10, reference numerals 91, 92, 93, and 94 indicate changes in the moving speed of the moving mechanism 10 in the first, second, third, and fourth unit processes, respectively.

On the other hand, in FIG. 9, reference numeral 80 denotes a locus on the image of the target mark when the movement of the moving mechanism 10 is controlled by the movement control unit 41 according to the embodiment. In FIG. 10, reference numeral 90 indicates a change in the moving speed of the moving mechanism 10 that is controlled by the movement control unit 41 according to the embodiment.

As shown in FIGS. 9 and 10, in the positioning process of the comparative example, the target workpiece W is imaged after the moving mechanism 10 is stopped. Therefore, the time required for the positioning process is long. On the other hand, in the positioning system 1 according to the embodiment, the target work W is imaged while moving, and a movement command is generated based on the imaged image. Therefore, the time required for the positioning process can be shortened.

<3-4. Monitoring process>
With reference to FIG. 11, an example of a flow of a monitoring process of the positioning system 1 by the controller 40 will be described. FIG. 11 is a flowchart illustrating an example of the flow of a monitoring process in the controller. The monitoring process shown in FIG. 11 is performed for each positioning process of the target workpiece W. The monitoring process shown in FIG. 11 is executed in parallel with the positioning process shown in FIG.

In step S21, the trajectory determination unit 48 determines the ideal positions of the marks 5a and 5b on the image based on the measurement positions PMa and PMb specified by the initial position specifying process (steps S2 and S3 in FIG. 6) by the visual sensor 30. Determine the trajectories respectively. Hereinafter, the measurement positions PMa and PMb specified by the first position specification processing are referred to as initial positions Pa (0) and Pb (0), respectively.

Next, in step S22, the determination unit 49 compares, for each of the marks 5a and 5b, the actual trajectory of the measurement position specified by the second and subsequent position specification processing with the ideal trajectory determined in step S21. Then, the determining unit 49 determines whether there is an abnormality in the positioning system 1 based on the comparison result.

If the determination result indicates that there is an abnormality (YES in step S23), in step S24, the determination unit 49 notifies a warning indicating that an abnormality that causes a deviation of the calibration parameter has occurred. Specifically, the determination unit 49 causes the display device 50 to display a warning screen. After step S24, the process proceeds to step S25. If the determination result indicates that there is no abnormality (NO in step S23), the process proceeds to step S25.

In step S25, the monitoring unit 47 determines whether the positioning process has been completed. That is, if YES is determined in step S5 shown in FIG. 6, the monitoring unit 47 determines that the positioning process has been completed. If the positioning process has not been completed (NO in step S25), the monitoring process returns to step S22. If the positioning processing has been completed (YES in step S25), the monitoring processing ends.

<3-5. Determination process of ideal trajectory>
The trajectory determination unit 48 determines an ideal trajectory by performing processing such as that shown in the flowchart of FIG. FIG. 12 is a flowchart showing the contents of a subroutine of the ideal trajectory determination process (step S21) shown in FIG.

In step S31, the trajectory determination unit 48 sets the elapsed time t from the start of the control of the moving mechanism 10 by the movement control unit 41 to 0.

Next, in step S32, the trajectory determination unit 48 acquires from the visual sensor 30 the coordinates (XY coordinates) of the initial positions Pa (0) and Pb (0) specified by the initial position specification processing. The coordinates of the initial positions Pa (0) and Pb (0) acquired from the visual sensor 30 are indicated by a camera coordinate system. Further, the trajectory determination unit 48 stores the coordinates (camera coordinate system) of the initial positions Pa (0) and Pb (0) in a storage unit (for example, the nonvolatile memory 416 or the main memory 418 (see FIG. 4)) of the controller 40. save.

In step S33, the trajectory determination unit 48 converts the coordinates of the initial positions Pa (0) and Pb (0) from the camera coordinate system to the machine coordinate system using the calibration parameters.

In step S34, the trajectory determination unit 48 calculates the required movement amount of the movement mechanism 10 using the simulation model stored in the model storage unit 46 and the positions Pa (t) and Pb (t). In step S34 immediately after step S33, the positions Pa (t) and Pb (t) are the initial positions Pa (0) and Pb (0), respectively.

The trajectory determination unit 48 calculates the deviation between the position Pa (t) and the target position SPa and the deviation between the position Pb (t) and the target position SPb as the required movement amount of the moving mechanism 10. The calculation process is the same as the process of the subtraction unit 44 of the movement control unit 41, and is performed using the XY coordinates of the machine coordinate system.

Next, in step S35, the trajectory determination unit 48 calculates the movement commands MVX, MVY, MVθ according to the required movement amount. The calculation process is the same as the process of the calculation unit 45 of the movement control unit 41.

Next, in step S36, the trajectory determination unit 48 calculates the translation amount ΔX of the X stage 11, the translation amount ΔY of the Y stage 13, and the rotation amount Δθ of the θ stage 15 in one control cycle Ts. The trajectory determination unit 48 calculates the translation amount ΔX assuming that the X stage 11 has ideally moved according to the movement command MVX calculated in step S35. Similarly, the trajectory determination unit 48 assumes that the Y stage 13 and the θ stage 15 have ideally moved according to the movement commands MVY and MVθ calculated in step S35, and calculates the translational movement amount ΔY and the rotational movement amount Δθ, respectively. calculate.

Next, in step S37, the trajectory determination unit 48 calculates the coordinates (mechanical coordinate system) of the position Pa (t + Ts) of the mark 5a after one control cycle Ts according to the following equation (3). Similarly, the trajectory determination unit 48 calculates the coordinates (mechanical coordinate system) of the position Pb (t + Ts) of the mark 5b after one control cycle Ts according to the following equation (3). In Expression (3), x and y indicate the XY coordinates (machine coordinate system) of the position Pa (t) or the position Pb (t). x ′ and y ′ indicate XY coordinates (machine coordinate system) of the position Pa (t + Ts) or the position Pb (t + Ts). Xo and Yo indicate the X coordinate and the Y coordinate of the rotation center of the θ stage 15, respectively.

Next, in step S38, the trajectory determination unit 48 performs coordinate conversion of the XY coordinates (mechanical coordinate system) of the positions Pa (t + Ts) and Pb (t + Ts) into the camera coordinate system. Then, the trajectory determination unit 48 stores the XY coordinates (camera coordinate system) of the positions Pa (t + Ts) and Pb (t + Ts) in the storage unit of the controller 40.

Next, in step S39, the trajectory determination unit 48 determines whether the positions Pa (t + Ts) and Pb (t + Ts) match the target positions SPa and SPb, respectively. Specifically, when the respective deviations between the positions Pa (t + Ts) and Pb (t + Ts) and the target positions SPa and SPb are both smaller than the threshold value Th0, the trajectory determining unit 48 sets the positions Pa (t + Ts) and Pb It is determined that (t + Ts) coincides with the target positions SPa and SPb, respectively.

場合 If the position Pa (t + Ts) does not match the target position SPa, or if the position Pb (t + Ts) does not match the target position SPb (NO in step S39), the trajectory determination process proceeds to step S40. In step S40, the trajectory determination unit 48 resets the elapsed time t from the start of the movement control of the movement mechanism 10 to a time obtained by adding one control cycle Ts. After step S40, steps S34 to S39 are repeated.

If the positions Pa (t + Ts) and Pb (t + Ts) match the target positions SPa and SPb, respectively (YES in step S39), the trajectory determination processing ends.

The coordinates (camera coordinate system) of the positions Pa (0), Pa (Ts), Pa (2Ts),..., Pa (nTs) stored in the storage unit of the controller 40 are the control start times of the movement control unit 41. This is information that associates the elapsed time t from the position with the ideal position of the mark 5a on the image. The coordinates (camera coordinate system) of the positions Pa (0), Pa (Ts), Pa (2Ts),..., Pa (nTs) indicate an ideal trajectory of the mark 5a on the image. Similarly, the coordinates (camera coordinate system) of the positions Pb (0), Pb (Ts), Pb (2Ts),..., Pb (nTs) stored in the storage unit of the controller 40 are determined by the movement control unit 41. This is information that associates the elapsed time t from the control start time with the ideal position of the mark 5b on the image. The coordinates (camera coordinate system) of the positions Pb (0), Pb (Ts), Pb (2Ts),..., Pb (nTs) indicate an ideal trajectory of the mark 5b on the image.

<3-6. Processing for judging presence or absence of abnormality
The determination unit 49 determines whether or not the positioning system 1 is abnormal, for example, by performing a process as shown in the flowchart of FIG. FIG. 13 is a flowchart showing the contents of a subroutine of the processing (step S22) for determining the presence or absence of an abnormality shown in FIG.

In step S41, the determination unit 49 determines a first allowable area on an image through which the mark 5a passes based on the ideal trajectory of the mark 5a. Specifically, the determination unit 49 determines the distance from the curve (see the solid line 70 in FIG. 2) connecting the positions Pa (0), Pa (Ts), Pa (2Ts),. Is determined as a first allowable area (see the allowable area 71 in FIG. 2).

Similarly, in step S41, the determination unit 49 determines a second allowable area on the image through which the mark 5b passes based on the ideal trajectory of the mark 5b. Specifically, the determination unit 49 determines the deviation from the curve (see the solid line 70 in FIG. 2) that connects the positions Pb (0), Pb (Ts), Pb (2Ts),. An area whose (distance) is equal to or smaller than the threshold Th1 is determined as a second allowable area (see the allowable area 71 in FIG. 2).

In step S42, the determination unit 49 acquires the latest coordinates (camera coordinate system) of the measurement positions PMa and PMb from the visual sensor 30. The coordinates of the measurement positions PMa and PMb are specified by the second and subsequent position specification processing (steps S7 and S8 in FIG. 6).

Next, in step S43, the determination unit 49 determines whether the latest measurement position PMa is located in the first allowable area and the latest measurement position PMb is located in the second allowable area. When the latest measurement position PMa is located within the first allowable area, it indicates that the deviation (distance) between the measurement position PMa and the ideal trajectory of the mark 5a is equal to or smaller than the threshold Th1. The deviation (distance) between the measurement position PMa and the ideal trajectory of the mark 5a is one of the feature amounts indicating the degree of deviation between the actual trajectory and the ideal trajectory. Similarly, when the latest measurement position PMb is located in the second allowable area, it indicates that the deviation (distance) between the measurement position PMb and the ideal trajectory of the mark 5b is equal to or smaller than the threshold Th1. The deviation (distance) between the measurement positions PMa and PMb and the ideal trajectories of the marks 5a and 5b is a feature amount indicating the degree of deviation between the actual trajectory and the ideal trajectory.

場合 If NO in step S43, the determination unit 49 determines in step S44 that there is an abnormality. On the other hand, in the case of YES in step S43, the determination unit 49 determines in step S45 that there is no abnormality. After step S44 or step S45, the process of determining the presence or absence of abnormality ends.

The process of determining whether there is an abnormality shown in FIG. 13 is repeatedly performed until the positioning process is completed. Since step S41 is the same every time, it is omitted in the processing for determining the presence / absence of abnormality after the second time.

<3-7. Action / Effect>
As described above, the positioning system 1 that performs the positioning processing of the target work W includes the moving mechanism 10, the visual sensor 30, the movement control unit 41, the trajectory determination unit 48, and the determination unit 49. The moving mechanism 10 moves the target work W. The visual sensor 30 captures the target work W and performs a position specifying process for specifying the position of the target work W (specifically, the measurement positions PMa and PMb of the marks 5a and 5b) based on the captured image for each imaging cycle Tb. To run. The movement control unit 41 controls the movement mechanism 10 so that the measurement positions PMa and PMb specified by the visual sensor 30 approach the target positions SPa and SPb, respectively. The trajectory determination unit 48 determines an ideal trajectory of the mark 5a from the initial position Pa (0) of the mark 5a specified by the first position specifying process to the target position SPa. Further, the trajectory determination unit 48 determines an ideal trajectory of the mark 5b from the initial position Pb (0) of the mark 5a specified by the first position specifying process to the target position SPb. The determination unit 49 compares the actual trajectory of the measured position PMa of the mark 5a specified by the position specifying process after the initial position specifying process with the ideal trajectory of the mark 5a. Further, the determination unit 49 compares the actual trajectory of the measured position PMb of the mark 5b specified by the position specifying process after the first position specifying process with the ideal trajectory of the mark 5b. The determination unit 49 determines whether there is an abnormality in the positioning system 1 based on the comparison result.

(4) When there is no deviation of the calibration parameters indicating the correspondence between the camera coordinate system of the visual sensor 30 and the mechanical coordinate system of the moving mechanism 10, the actual trajectories of the marks 5a and 5b coincide with the ideal trajectories. On the other hand, when there is a deviation of the calibration parameters, the actual trajectories of the marks 5a and 5b deviate from the ideal trajectories. Therefore, the determination unit 49 accurately determines the presence or absence of an abnormality that causes a deviation of the calibration parameter based on the comparison result between the actual trajectories of the marks 5a and 5b and the ideal trajectory without depending on the personal judgment. Can be determined.

The visual sensor 30 executes the first position specifying process while the target work W is stopped, and executes the second and subsequent position specifying processes while the target work W is moving. This makes it possible to speed up the positioning process.

The determination unit 49 generates an abnormality when a feature amount (deviation (distance) between the ideal trajectories of the measurement positions PMa and PMb and the marks 5a and 5b) indicating the degree of deviation between the actual trajectory and the ideal trajectory exceeds the threshold Th1. Is determined, and a warning is notified. Thereby, the operator can perform maintenance for removing the cause of the deviation of the calibration parameter at an appropriate timing.

The trajectory determination unit 48 performs a simulation using the simulation models of the movement mechanism 10 and the movement control unit 41 and the initial positions Pa (0) and Pb (0) specified by the initial position specification processing, thereby obtaining a mark. The ideal trajectories 5a and 5b are respectively determined. By using a simulation model, an ideal trajectory can be determined with high accuracy.

§4 Modification <4-1. Modification 1>
In the above description, the determination unit 49 determines whether or not there is an abnormality according to whether or not the latest measurement positions PMa and PMb specified by the visual sensor 30 are located in the first allowable area and the second allowable area, respectively. Judged. On the other hand, the determination unit 49 determines whether the estimated positions PVa and PVb output from the position determination unit 43 for each control cycle Ts are located in the first allowable region and the second allowable region, respectively. May be determined.

Note that the estimated positions PVa and PVb are shown in a machine coordinate system. Therefore, the determination unit 49 converts the coordinates (mechanical coordinate system) of the estimated positions PVa and PVb into the camera coordinate system, and determines whether the estimated positions PVa and PVb are located in the first allowable area and the second allowable area, respectively. What is necessary is just to judge.

<4-2. Modification 2>
The determination unit 49 may execute the determination process of the presence or absence of the abnormality illustrated in FIG. 14 instead of the determination process of the presence or absence of the abnormality illustrated in FIG. FIG. 14 is a flowchart illustrating the processing content of a subroutine of the determination processing according to the second modification. In the second modification, similarly to the first modification, the presence or absence of an abnormality is determined using the estimated positions PVa and PVb.

First, in step S141, the determination unit 49 acquires the estimated positions PVa and PVb from the position determination unit 43.

In step S142, the determination unit 49 converts the coordinates (mechanical coordinate system) of the estimated positions PVa and PVb into a camera coordinate system.

In step S143, the determination unit 49 specifies the elapsed time t from the time when the movement control unit 41 starts control to the time when the estimated positions PVa and PVb are output. The estimated positions PVa and PVb are output for each control cycle Ts. Therefore, the time t is a time kTs obtained by multiplying the control cycle Ts by the number k of times the estimated positions PVa and PVb are output from the control start time.

In step S144, the determination unit 49 reads out the coordinates of the positions Pa (kTs) and Pb (kTs) on the ideal trajectory from the information stored in the storage unit in the trajectory determination processing shown in FIG.

In step S145, the determination unit 49 calculates deviations (distances) between the estimated positions PVa and PVb and the positions Pa (kTs) and Pb (kTs) on the ideal trajectory, respectively. Each deviation between the estimated positions PVa and PVb and the positions Pa (kTs) and Pb (kTs) on the ideal trajectory is one of the feature amounts indicating the degree of divergence between the actual trajectory and the ideal trajectory.

に お い て In step S146, the determination unit 49 determines whether the deviation is equal to or less than the threshold Th1.

場合 If NO in step S146, the determination unit 49 determines in step S147 that there is an abnormality. On the other hand, when YES is determined in the step S146, the determination unit 49 determines in the step S148 that there is no abnormality. After step S147 or step S148, the process of determining whether there is an abnormality ends.

According to the second modification, the presence or absence of an abnormality is determined based on the divergence between the actual trajectory and the ideal trajectory in consideration of the elapsed time t from the start of the control of the movement control unit 41.

<4-3. Modification 3>
The monitoring unit 47 may execute the monitoring process shown in FIG. 15 instead of the monitoring process shown in FIG. FIG. 15 is a flowchart illustrating the flow of the monitoring process according to the third modification. The monitoring process according to the third modification is different from the monitoring process shown in FIG. 11 in that step S121 is executed instead of step S22, and steps S122 and S123 are executed after step S24. Hereinafter, steps S121, S122, and S123 will be described.

In step S121, the determination unit 49 calculates, for each of the marks 5a and 5b, a feature amount indicating a degree of divergence between the actual trajectory and the ideal trajectory, and based on the feature amount, determines whether there is an abnormality and whether the abnormality degree is high or low. Make a decision. Details of step S121 will be described later.

に お い て In step S122, the level of the abnormality degree determined in step S121 is confirmed. If the degree of abnormality is high (YES in step S122), the determination unit 49 outputs an operation stop instruction to the movement control unit 41 in step S123. Thereby, the movement control unit 41 stops the movement control of the movement mechanism 10.

On the other hand, if the abnormality level is low (NO in step S122), the monitoring process proceeds to step S25.

FIG. 16 is a flowchart showing the processing contents of the subroutine of the processing (step S121) for judging the presence or absence of an abnormality and the degree of abnormality shown in FIG. 15 (step S121). The determination processing of the presence / absence of abnormality and the degree of abnormality shown in FIG. 16 is different from the determination processing of presence / absence of abnormality shown in FIG. 14 in that steps S149 to S151 are further executed. Hereinafter, steps S149 to S151 will be described.

After step S147, the determination unit 49 determines in step S149 whether the deviation between the measurement positions PMa and PMb and the positions Pa (kTs) and Pb (kTs) on the ideal trajectory is equal to or smaller than the threshold Th2. The threshold Th2 is larger than the threshold Th1.

場合 If NO in step S149, the determination unit 49 determines in step S150 that the degree of abnormality is high. On the other hand, when YES is determined in the step S149, the determination unit 49 determines in the step S151 that the degree of abnormality is low. After step S150 or step S151, the process of determining the presence or absence of abnormality and the level of abnormality is completed.

<4-4. Modification 4>
In the above description, the monitoring process is executed in parallel with the positioning process. However, the monitoring process may be executed after the positioning process ends. Since the positioning process has been completed, the actual trajectory is specified for each of the marks 5a and 5b. The actual trajectories of the marks 5a and 5b are specified by sequentially connecting the estimated positions PVa and PVb output from the position determination unit 43 during the positioning process. Alternatively, the actual trajectories of the marks 5a and 5b may be specified by sequentially connecting the measurement positions PMa and PMb output from the visual sensor 30 during the positioning process.

The determination unit 49 calculates, for each of the marks 5a and 5b, a feature amount indicating the degree of divergence between the actual trajectory and the ideal trajectory, and determines the presence or absence of an abnormality and the level of the abnormality based on the calculated feature amount. Just fine. As the feature amount, for example, the area of a region surrounded by the real trajectory and the ideal trajectory (integrated value of the deviation between the real trajectory and the ideal trajectory) can be used. Alternatively, the maximum value of the deviation (distance) between a point on the actual trajectory and a point on the ideal trajectory having the same elapsed time from the start of control by the movement control unit 41 may be used as the feature amount.

<4-5. Modification 5>
FIG. 17 is a diagram illustrating a functional configuration of a controller according to the fifth modification. As shown in FIG. 17, the positioning system 1A according to the fifth modification is different from the positioning system 1 shown in FIG. 5 in that a controller 40A is provided instead of the controller 40. The controller 40A is different from the controller 40 shown in FIG. 5 in that a monitoring unit 47A is provided instead of the monitoring unit 47 and the model storage unit 46 is not provided. The monitoring unit 47A is different from the monitoring unit 47 in that a trajectory determination unit 48A is provided instead of the trajectory determination unit 48.

The trajectory determination unit 48A has a learning unit 148 on which machine learning for outputting a function indicating an ideal trajectory in accordance with the input of the initial position is performed, and the ideal trajectories of the marks 5a and 5b are determined using the learning unit 148. To determine.

The learning device 148 is constructed by performing machine learning using, as learning data, coordinates of a plurality of measurement positions specified in each of a plurality of positioning processes performed when the positioning system is normal. The time when the positioning system is normal is, for example, the time when the positioning system is started up when the deviation of the calibration parameter is small.

Specifically, the learning device 148 sequentially connects the measurement position PMa specified in the first position specification process in each positioning process and the plurality of measurement positions PMa specified for each imaging cycle Tb in the positioning process. Is learned in correspondence with a function Pa (t) which is information indicating. The function Pa (t) represents the elapsed time t from the control start time by the movement control unit 41 and the coordinates (camera coordinate system) of the position of the mark 5a on the image when the elapsed time t has elapsed from the control start time. The associated function.

Similarly, the learning device 148 shows a locus that sequentially connects the measurement position PMb specified in the first position specification process in each positioning process and the plurality of measurement positions PMb specified for each imaging cycle Tb in the positioning process. The correspondence with the function Pb (t) as information is learned. The function Pb (t) is an elapsed time t from the start of control by the movement control unit 41, an XY coordinate (camera coordinate system) of a position on the image of the mark 5b when the elapsed time t has elapsed from the start of control. Is a function in which.

The trajectory determination unit 48A inputs the initial position Pa (0) to the learning device 148, and determines a trajectory represented by a function output from the learning device 148 as an ideal trajectory on the image of the mark 5a. By inputting the initial position Pb (0) to the learning device 148, the trajectory determination unit 48A determines the trajectory represented by the function output from the learning device 148 as the ideal trajectory of the mark 5b on the image.

According to the fifth modification, the trajectory determination unit 48A can determine an ideal trajectory that matches the actual situation.

<4-6. Modification 6>
FIG. 18 is a diagram illustrating a configuration of a positioning system according to the sixth modification. As shown in FIG. 18, the visual sensor 30 of the positioning system according to Modification 6 captures the target work W and the reference work W0 fixed at the fixed position. The reference work W0 is made of a light-transmitting material. Therefore, the visual sensor 30 can simultaneously capture the marks 5a and 5b, which are the characteristic portions of the target work W, and the marks 6a, 6b, which are the characteristic portions of the reference work W0.

(4) The visual sensor 30 also specifies the positions of the marks 6a and 6b of the reference work W0. The controller 40 sets the position of the mark 6a specified by the visual sensor 30 as the target position SPa, and sets the position of the mark 6b specified by the visual sensor 30 as the target position SPb.

<4-7. Modification 7>
The determination unit 49 may cause the display device 50 to display a screen showing the ideal trajectory and the actual trajectory for each positioning process.

FIG. 19 is an example of a screen showing an ideal trajectory and an actual trajectory. In FIG. 19, a solid line 70 indicates an ideal trajectory of the target mark (the mark 5a or the mark 5b), and a solid line 72 indicates a real trajectory of the target mark. The operator can grasp the degree of deviation of the calibration parameter by checking the screen as shown in FIG.

Further, the determination unit 49 decomposes the deviation between the position on the actual trajectory and the position on the ideal trajectory, in which the time elapsed since the control start by the movement control unit 41 is the same, into components in the X and Y directions, A screen showing changes with time of each component may be displayed on the display device 50. The X direction is the moving direction of the X stage 11, and the Y direction is the moving direction of the Y stage 13.

FIG. 20 is a diagram showing an example of a screen showing a temporal change of each component in the X direction and the Y direction of the deviation between the position on the actual trajectory and the position on the ideal trajectory. By checking the screen as shown in FIG. 20, the operator can infer the abnormal part of the moving mechanism 10. That is, when the deviation in the Y direction between the ideal trajectory and the actual trajectory is larger than the deviation in the X direction, the operator can infer that the Y stage 13 is abnormal. As a result, the time required for maintenance can be reduced.

(4) The determination unit 49 may cause the display device 50 to display a screen that indicates a transition of a feature amount that is calculated for each positioning process and that indicates the degree of deviation between the ideal trajectory and the actual trajectory. Thereby, the worker can grasp the situation such as the deterioration of the moving mechanism 10 over time.

The determination unit 49 determines, for example, the area of a region surrounded by the ideal trajectory and the actual trajectory (that is, the integrated value of the deviation between the ideal trajectory and the actual trajectory) (the area of the hatched portion in FIG. 19) Is calculated as a feature quantity indicating the degree of deviation of The determination unit 49 calculates the feature amount for each positioning process, and causes the display device 50 to display a screen showing the transition of the feature amount.

FIG. 21 is a diagram showing an example of a screen showing a temporal change of a feature amount (integral value of deviation) indicating a degree of deviation between an ideal trajectory and an actual trajectory. As shown in FIG. 21, the feature amount indicating the degree of deviation between the ideal trajectory and the actual trajectory gradually increases as the moving mechanism 10 deteriorates over time. By checking the screen shown in FIG. 21, the operator can grasp the difference between the value of the feature amount at the current time and the threshold Th1. As a result, the operator can predict when maintenance such as calibration is required. Note that the screen example shown in FIG. 21 includes a graph image showing the transition of the feature amount. However, the determination unit 21 may cause the display device 50 to display a screen in which the numerical values of the feature amounts are arranged in chronological order.

<4-8. Other Modifications>
In the above description, the trajectory determination units 48 and 48A have determined the ideal trajectories of the marks 5a and 5b. However, the trajectory determination units 48 and 48A may determine the ideal trajectory of the midpoint of the marks 5a and 5b. In this case, the determination unit 49 determines whether or not an abnormality has occurred in the positioning system 1 based on the comparison result between the actual trajectory of the midpoint of the measurement positions PMa and PMb specified by the visual sensor 30 and the ideal trajectory. Is also good.

In the above description, the target work W is positioned using the marks 5a and 5b provided on the target work W as characteristic features of the target work W. However, the target work W may be positioned using another part of the target work W as a characteristic portion. For example, a screw or a screw hole provided in the target work W may be used as the characteristic portion. Alternatively, a corner of the target work W may be used as a characteristic portion.

In the above description, the controller 40 includes the movement control unit 41 and the monitoring unit 47. However, the monitoring unit 47 may be provided in an information processing device different from the controller 40.

§5 Supplement As described above, the present embodiment and modifications include the following disclosure.

(Configuration 1)
A positioning system (1, 1A) for performing positioning processing of an object (W),
A moving mechanism (10) for moving the object (W);
A visual sensor (30) for taking an image of the object (W) and executing a position specifying process for specifying a position of the object (W) based on the picked-up image for each imaging cycle;
A movement control unit (41) for controlling the movement mechanism (10) such that the position specified by the visual sensor (30) approaches a target position;
A trajectory determiner (48, 48A) that determines an ideal trajectory of the object (W) from the position of the object (W) specified by the initial position specifying process to the target position;
An abnormality of the positioning system (1, 1A) is determined based on a comparison result between the actual trajectory of the position of the object (W) specified by the position specifying process after the initial position specifying process and the ideal trajectory. A positioning system (1, 1A), comprising: a determination unit (49) for determining presence / absence.

(Configuration 2)
Configuration 1 in which the visual sensor (30) executes the first position specifying process while the object (W) is stopped, and executes the subsequent position specifying process while the object (W) is moving. The positioning system (1, 1A) according to 1.

(Configuration 3)
A determining unit configured to determine that the abnormality has occurred and to issue a warning when a feature amount indicating a degree of deviation between the actual trajectory and the ideal trajectory exceeds a first threshold; Or the positioning system (1, 1A) according to 2.

(Configuration 4)
The determination unit (49) stops the moving mechanism (10) when the feature amount exceeds a second threshold,
The positioning system (1, 1A) according to configuration 3, wherein the second threshold is greater than the first threshold.

(Configuration 5)
The positioning system (1, 1A) according to configuration 3 or 4, wherein the feature amount is a deviation between a position of the object (W) specified by a position specifying process later and the ideal trajectory.

(Configuration 6)
The actual trajectory and the ideal trajectory are indicated by information that associates the elapsed time from the start of the control of the movement mechanism (10) by the movement control unit (41) with the position of the object (W). ,
The positioning system (1, 1) according to Configuration 3 or 4, wherein the feature amount is a maximum value or an integral value of a deviation between the position on the actual trajectory and the position on the ideal trajectory, where the elapsed time is the same. 1A).

(Configuration 7)
The trajectory determination unit (48) uses a simulation model of the movement mechanism (10) and the movement control unit (41), and a position of the object (W) specified by the first position specification processing. The positioning system (1) according to any one of Configurations 1 to 6, wherein the ideal trajectory is determined by performing a simulation.

(Configuration 8)
The trajectory determination unit (48A) calculates a trajectory of the object (W) from the position corresponding to the input position of the object (W) to the target position by machine learning using learning data. Further comprising a trained learner (148) configured to output the indicated information;
The learning data is data indicating a position of the object (W) specified by the visual sensor (30) in the positioning process performed when the positioning system is normal,
The trajectory determination unit (48A) is output from the learning device (148) by inputting the position of the object (W) specified by the initial position specification processing to the learning device (148). The positioning system (1A) according to any of Configurations 1 to 6, wherein a trajectory indicated by the information is determined as the ideal trajectory.

(Configuration 9)
The positioning system (1, 1A) according to any one of Configurations 1 to 8, wherein the determination unit (49) outputs a screen indicating the actual trajectory and the ideal trajectory to a display device (50).

(Configuration 10)
The actual trajectory and the ideal trajectory are indicated by information that associates the elapsed time from the start of the control of the moving mechanism by the movement control unit with the position of the object,
The movement mechanism (10) includes a plurality of translation mechanisms (11, 13) that translate in different directions of movement.
The determination unit (49) determines a deviation between a position on the actual trajectory and a position on the ideal trajectory, where the elapsed time is the same, for each of the plurality of translation mechanisms (11, 13). 3. The positioning system according to configuration 1 or 2, wherein the positioning system is decomposed into components in the moving direction, and outputs a screen showing a temporal change of each component to the display device (50).

(Configuration 11)
The positioning system (1, 1A) according to any one of Configurations 3 to 6, wherein the determination unit (49) outputs a screen indicating a transition of the feature amount to a display device (50).

(Configuration 12)
A monitoring device used in the positioning system (1, 1A) according to any one of the configurations 1 to 11,
The trajectory determination unit,
A monitoring device (40, 40A) including the determination unit (49).

(Configuration 13)
A monitoring method of a positioning system (1, 1A) for performing positioning processing of an object (W),
The positioning system (1, 1A) comprises:
A moving mechanism (10) for moving the object (W);
A visual sensor (30) for taking an image of the object (W) and executing a position specifying process for specifying a position of the object (W) based on the picked-up image for each imaging cycle;
A movement control unit (41) for controlling the movement mechanism (10) such that the position specified by the visual sensor (30) approaches the target position;
Determining an ideal trajectory of the object (W) from the position of the object (W) specified by the initial position specifying process to the target position;
Determining whether there is an abnormality in the positioning system based on a comparison result between the actual trajectory of the position of the object (W) specified by the position specifying process after the first position specifying process and the ideal trajectory A monitoring method comprising:

(Configuration 14)
A program for causing a computer to execute a method of monitoring a positioning system (1, 1A) for performing positioning processing of an object (W),
The positioning system (1, 1A) comprises:
A moving mechanism (10) for moving the object (W);
A visual sensor (30) for taking an image of the object (W) and executing a position specifying process for specifying a position of the object (W) based on the picked-up image for each imaging cycle;
A movement control unit (41) for controlling the movement mechanism (10) such that the position specified by the visual sensor (30) approaches the target position;
The monitoring method comprises:
Determining an ideal trajectory of the object (W) from the position of the object (W) specified by the initial position specifying process to the target position;
An abnormality of the positioning system (1, 1A) is determined based on a comparison result between the actual trajectory of the position of the object (W) specified by the position specifying process after the initial position specifying process and the ideal trajectory. A step of determining the presence or absence of the program.

The embodiments disclosed this time are to be considered in all respects as illustrative and not restrictive. The scope of the present invention is defined by the terms of the claims, rather than the description above, and is intended to include any modifications within the scope and meaning equivalent to the terms of the claims. Further, it is intended that the inventions described in the embodiments and the respective modified examples are implemented alone or in combination as much as possible.

1, 1A positioning system, 5a, 5b, 6a, 6b mark, 10 moving mechanism, 11 X stage, 12, 14, 16 servo motor, 12E, 14E, 16E encoder, 13 Y stage, 15 θ stage, 20 driver unit, 22, 24, 26 servo driver, 30 visual sensor, 31 imaging unit, 32 image processing device, 40, 40A controller, 41 movement control unit, 42 coordinate conversion unit, 43 position determination unit, 44 subtraction unit, 45 operation unit, 46 Model storage unit, 47, 47A monitoring unit, 48, 48A trajectory determination unit, 49 determination unit, 50 display unit, 51, 61, 424 recording medium, 60 display unit, 71 allowable area, 148 learning unit, 310, 414 processor, 312 RAM, 314, 426 display control LA, 316 system controller, 318 I / O controller, 320 hard disk, 322 camera interface, 324 input interface, 326 controller interface, 328, 417, 428 communication interface, 330, 422 memory card interface, 334 keyboard, 412 chipset, 416 Nonvolatile memory, 418 main memory, 420 system clock, 430 internal bus controller, 432 DMA control circuit, 434 internal bus control circuit, 436 buffer memory, 438 field bus controller, 440 control program, W target work, W0 reference work.

Claims (14)

1. A positioning system that performs a positioning process for an object,
   A moving mechanism for moving the object,
   A visual sensor for imaging the object, and performing a position specifying process for specifying the position of the object based on the captured image for each imaging cycle,
   A movement control unit for controlling the movement mechanism so that the position specified by the visual sensor approaches the target position,
   A trajectory determination unit for determining an ideal trajectory of the target object from the position of the target object specified by the initial position specifying process to the target position,
   A determining unit configured to determine whether there is an abnormality in the positioning system based on a comparison result between the actual trajectory of the position of the target object and the ideal trajectory specified by the position specifying process after the first position specifying process; A positioning system comprising:
2. 2. The positioning system according to claim 1, wherein the visual sensor executes the first position identification processing while the object is stopped, and executes the subsequent position identification processing while the object is moving. 3.
3. 3. The determination unit determines that the abnormality has occurred and notifies a warning when a feature amount indicating a degree of deviation between the actual trajectory and the ideal trajectory exceeds a first threshold. 4. The positioning system according to claim 1.
4. The determination unit stops the moving mechanism when the feature amount exceeds a second threshold,
   The positioning system according to claim 3, wherein the second threshold is larger than the first threshold.
5. 5. The positioning system according to claim 3, wherein the feature amount is a deviation between the position of the object specified by the subsequent position specifying process and the ideal trajectory.
6. The actual trajectory and the ideal trajectory are indicated by information that associates the elapsed time from the start of the control of the moving mechanism by the movement control unit with the position of the object,
   5. The positioning system according to claim 3, wherein the feature amount is a maximum value or an integral value of a deviation between the position on the actual trajectory and the position on the ideal trajectory having the same elapsed time.
7. The trajectory determination unit determines the ideal trajectory by performing a simulation using a simulation model of the movement mechanism and the movement control unit and a position of the target object specified by the first position specification processing. The positioning system according to any one of claims 1 to 6.
8. The trajectory determination unit is configured to output information indicating a trajectory of the object from the position to the target position corresponding to the position of the input object by machine learning using learning data. Further equipped with a learned learning device
   The learning data is data indicating the position of the object identified by the visual sensor in the positioning process performed when the positioning system is normal,
   The trajectory determination unit determines the trajectory indicated by the information output from the learning device as the ideal trajectory by inputting the position of the object specified by the first position specification processing to the learning device. The positioning system according to claim 1, wherein
9. The positioning system according to any one of claims 1 to 8, wherein the determination unit outputs a screen indicating the actual trajectory and the ideal trajectory to a display device.
10. The actual trajectory and the ideal trajectory are indicated by information that associates the elapsed time from the start of the control of the moving mechanism by the movement control unit with the position of the object,
    The movement mechanism includes a plurality of translation mechanisms that translate in different movement directions,
    The determination unit, the elapsed time is the same, the deviation between the position on the actual trajectory and the position on the ideal trajectory, decomposed into components in the movement direction corresponding to each of the plurality of translation mechanisms, The positioning system according to claim 1, wherein a screen showing a change with time of each component is output to a display device.
11. 7. The positioning system according to claim 3, wherein the determination unit outputs a screen indicating a transition of the feature amount to a display device. 8.
12. A monitoring device used for the positioning system according to any one of claims 1 to 11,
    The trajectory determination unit,
    A monitoring device comprising: the determination unit.
13. A monitoring method of a positioning system that performs a positioning process of an object,
    The positioning system comprises:
    A moving mechanism for moving the object,
    A visual sensor for imaging the object, and performing a position specifying process for specifying the position of the object based on the captured image for each imaging cycle,
    A movement control unit for controlling the movement mechanism so that the position specified by the visual sensor approaches the target position,
    Determining an ideal trajectory of the target object from the position of the target object specified by the initial position specifying process to the target position;
    Determining the presence or absence of an abnormality in the positioning system based on a comparison result between the actual trajectory of the position of the target object specified by the position specifying process after the first position specifying process and the ideal trajectory. , Monitoring method.
14. A program for causing a computer to execute a method of monitoring a positioning system that performs a positioning process of an object,
    The positioning system comprises:
    A moving mechanism for moving the object,
    A visual sensor for imaging the object, and performing a position specifying process for specifying the position of the object based on the captured image for each imaging cycle,
    A movement control unit for controlling the movement mechanism so that the position specified by the visual sensor approaches the target position,
    The monitoring method comprises:
    Determining an ideal trajectory of the target object from the position of the target object specified by the initial position specifying process to the target position;
    Determining the presence or absence of an abnormality in the positioning system based on a comparison result between the actual trajectory of the position of the target object specified by the position specifying process after the first position specifying process and the ideal trajectory. ,program.

Images