Tool discrimination device, workpiece processing system, and tool discrimination method
The tool discrimination device uses differential image analysis to simplify and enhance the accuracy of tool type and state determination on robot arms, addressing labor and cost issues in existing methods.
Patent Information
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- MAYEKAWA MFG CO LTD
- Filing Date
- 2025-12-08
- Publication Date
- 2026-06-25
AI Technical Summary
Existing methods for determining the type and state of tools attached to robot arms in work processing systems are labor-intensive, costly, and prone to accuracy issues due to ambient light changes and posture variations, necessitating complex model development.
A tool discrimination device that acquires first and second image data, creates differential image data, and compares it with registered data to determine tool conditions, using a simple image analysis approach.
Accurately determines the type and state of tools attached to robot arms with reduced complexity and cost, enhancing determination accuracy.
Smart Images
Figure JP2025042630_25062026_PF_FP_ABST
Abstract
Description
Tool Discrimination Device, Work Processing System, and Tool Discrimination Method
[0001] The present disclosure relates to a tool discrimination device, a work processing system, and a tool discrimination method.
[0002] In order to perform a processing operation on a work, a work processing system using a robot arm with a tool attached to its tip is known. For example, Patent Document 1 discloses a robot arm having a tool corresponding to the processing operation to be performed on the work attached to its tip.
[0003] In this type of work processing system, it is necessary to attach an appropriate type of tool in an appropriate state to the tip of the robot arm corresponding to the content of the processing operation to be performed on the work. For example, in Patent Documents 2 to 4, based on image data obtained by imaging the tool attached to the robot arm, a technique for determining whether the tool attached to the tip of the robot arm satisfies a tool condition that defines at least one of the tool type or state is disclosed.
[0004] Japanese Unexamined Patent Application Publication No. 2018-158405, Japanese Unexamined Patent Application Publication No. 2022-101324, Japanese Unexamined Patent Application Publication No. 2022-101326, Japanese Unexamined Patent Application Publication No. 2023-74599
[0005] In Patent Document 2 above, image data is obtained by imaging in a state where the position of the tool is adjusted so that the reflected light from the tool to be determined is maximized. Then, by performing a masking process on the image data obtained by imaging, an image area corresponding to the tool is extracted from the image data, and the determination of the tool condition is made based on the sum of the luminance values in the extracted image area. However, in Patent Document 2, it is necessary to create mask data corresponding to each type and state of the tool to be determined in advance, which requires a lot of labor and cost. Also, since the position of the tool is adjusted using the reflected light from the tool during imaging, there is a risk that the reflected light will change due to ambient light or a slight change in the posture of the tool, affecting the determination accuracy.
[0006] Furthermore, in the aforementioned Patent Document 3, deep learning is applied to image data obtained by capturing the tool to determine the type and state of the tool. However, in Patent Document 3, it is necessary to construct a determination model for each type and state of the tool, which increases development costs.
[0007] Furthermore, Patent Document 4 acquires distribution data of a tool attached to a robot arm in a three-dimensional coordinate system and determines the tool conditions based on the distribution data. However, since Patent Document 4 makes the determination based on distribution data in a three-dimensional coordinate system, it is necessary to create criteria for determining the type and state of the tool from the distribution data, which increases development costs.
[0008] At least one embodiment of this disclosure has been made in view of the above circumstances, and aims to provide a tool discrimination device, a workpiece processing system, and a tool discrimination method that can accurately determine the type and state of a tool by simple image analysis.
[0009] A tool discrimination device according to at least one embodiment of the present disclosure is a tool discrimination device for discriminating a tool attached to the tip of a robot arm for performing machining processing on a workpiece being transported on a transport device, in order to solve the above problems, and comprises: an image data acquisition unit for acquiring first image data of a background and second image data of the tool together with the background; a differential image data creation unit for creating differential image data based on the first image data and the second image data; and a tool condition determination unit for determining whether a tool condition relating to at least one of the type or state of the tool is satisfied by comparing the differential image data with registered image data that has been registered in advance corresponding to the tool.
[0010] To solve the above problems, a workpiece processing system according to at least one embodiment of this disclosure includes a tool discrimination device according to at least one embodiment of this disclosure.
[0011] A tool identification method according to at least one embodiment of the present disclosure is a tool identification method for identifying a tool attached to the tip of a robot arm for performing machining on a workpiece being transported on a transport device, in order to solve the above problems, comprising: a step of acquiring a first image data of a background and a second image data of the tool together with the background; a step of creating a difference image data based on the first image data and the second image data; and a step of determining whether a tool condition relating to at least one of the type or state of the tool is satisfied by comparing the difference image data with registered image data that has been registered in advance corresponding to the tool.
[0012] According to at least one embodiment of this disclosure, a tool discrimination device, a workpiece processing system, and a tool discrimination method can be provided that can accurately determine the type and state of a tool by simple image analysis.
[0013] This is a schematic diagram showing the overall configuration of a workpiece processing system according to one embodiment. This is a block diagram of the tool discrimination device in Figure 1. This is a flowchart showing the tool discrimination method performed by the tool discrimination unit in Figure 2. This is a conceptual diagram showing the process of creating differential image data in step S105 of Figure 3. This is a diagram showing one example of matching the discrimination image data and the registered image data in step S108 of Figure 3. This is a diagram showing another example of matching the discrimination image data and the registered image data in step S108 of Figure 3. This is a flowchart showing the method of registering registered image data performed by the image data registration unit in Figure 2.
[0014] Hereinafter, several embodiments of the present invention will be described with reference to the attached drawings. However, the dimensions, materials, shapes, relative arrangements, etc., of the configurations described or shown in the drawings as embodiments are not intended to limit the scope of the present invention, but are merely illustrative examples.
[0015] Figure 1 is a schematic diagram showing the overall configuration of a workpiece processing system 1 according to one embodiment. The workpiece processing system 1 is a system for performing processing on a workpiece 5 using a tool 40 mounted on a robot arm 30. The workpiece 5 is, for example, food products such as agricultural products, livestock products, or marine products, and may be either fresh food or processed food. The processing performed on the workpiece 5 is not limited, but some examples of processing processes will be described, such as cutting, clamping, chucking, or combinations thereof. Other specific examples of processing processes may include pressing, hammering, fluid discharge, or light irradiation of the workpiece 5.
[0016] The workpiece processing system 1 includes a transport device 7 for transporting the workpiece 5, a robot arm 30 for performing processing on the workpiece 5, an imaging device 8 (camera) for imaging the workpiece 5 transported by the transport device 7, a control device 100, and a tool discrimination device 200.
[0017] The conveying device 7 is a belt conveyor configured to convey the workpiece 5 in a substantially horizontal direction. The workpiece 5 conveyed by the conveying device 7 is processed by a robot arm 30 at a predetermined position. At that position, the conveying device 7 also functions as a workbench for performing the processing on the workpiece 5.
[0018] The robot arm 30 is an industrial robot realized by a vertical articulated robot, a horizontal articulated robot, or a combination thereof. A tool 40 corresponding to the machining process to be performed on the workpiece 5 is attached to the tip of the robot arm 30. In Figure 1, robot arms 30A, 30B, and 30C that can operate in conjunction with each other are shown as the robot arm 30.
[0019] A tool 40 is attached to the tip of the robot arm 30. The tool 40 includes a clamper 41 for clamping the workpiece 5, a chuck 42 for gripping the workpiece 5, and a knife 43 for cutting the workpiece 5. In Figure 1, the clamper 41 is attached to the tip of the robot arm 30A, the chuck 42 is attached to the tip of the robot arm 30B, and the knife 43 is attached to the tip of the robot arm 30C. Both the clamper 41 and the chuck 42 are connected to actuators (not shown), and their state (e.g., open / closed state, extended / retracted state, etc.) can be changed by driving the actuators. The actuators may be, for example, air cylinders, hydraulic cylinders, or motors.
[0020] The control device 100 is configured for controlling the workpiece processing system 1 and consists of, for example, a CPU (Central Processing Unit), RAM (Random Access Memory), ROM (Read Only Memory), and a computer-readable storage medium. A series of processes for realizing various functions are stored in the storage medium in the form of a program, for example. The CPU reads this program into the RAM and executes information processing and calculations to realize the various functions. The program may be pre-installed on the ROM or other storage medium, provided in a state where it is stored on a computer-readable storage medium, or distributed via wired or wireless communication. Computer-readable storage media include magnetic disks, magneto-optical disks, CD-ROMs, DVD-ROMs, semiconductor memory, etc.
[0021] The control device 100 can perform machining on the workpiece 5 on the transport device 7 by controlling the imaging device 8, the robot arm 30, and the tool 40, respectively, and comprises an imaging device control unit 110, an image analysis unit 120, and a robot arm control unit 130.
[0022] The imaging device control unit 110 is configured to control the imaging operation performed by the imaging device 8. Specifically, the imaging device control unit 110 transmits an imaging signal to the imaging device 8 at a predetermined timing to perform the imaging operation of the imaging device 8, and acquires image data from the said imaging operation.
[0023] The image analysis unit 120 is configured to identify the position and orientation of the workpiece 5 included in the image data by analyzing the image data acquired by the imaging device 8. The analysis results from the image analysis unit 120 are sent to the robot arm control unit 130 and used to control the robot arm 30.
[0024] In this embodiment, the imaging device 8 is shown as serving as both an imaging device for capturing image data used when the control device 100 controls the robot arm 30 and the tool 40, and an imaging device for capturing image data used by the tool discrimination device 200 to discriminate the tool 40. In other embodiments, different imaging devices may be used for capturing image data used when the control device 100 controls the robot arm 30 and the tool 40, and for capturing image data used by the tool discrimination device 200 to discriminate the tool 40.
[0025] The robot arm control unit 130 is configured to control at least one of the position, orientation, or state of the tool 40 attached to the tip of the robot arm 30 by controlling the robot arm 30. Specifically, the robot arm control unit 130 identifies the position and orientation of the workpiece 5 on the transport device 7 based on the analysis results obtained from the image analysis unit 120, and controls the robot arm 30 so that a predetermined machining process is performed based on the identified position and orientation of the workpiece 5.
[0026] In this way, the control device 100 can perform a predetermined machining process by having the robot arm 30 and the tool 40 cooperate to control the robot arm 30 and the tool 40 based on the position and orientation of the workpiece 5 on the transport device 7, which are determined based on the imaging data captured by the imaging device 8.
[0027] The tool identification device 200 is configured to identify the tool 40 attached to the tip of the robot arm 30. The tool 40 is identified by determining whether the tool 40 actually attached to the tip of the robot arm 30 satisfies tool conditions that define at least one of the appropriate type or state of tool 40 corresponding to the machining process to be performed on the workpiece 5 in the workpiece machining system 1.
[0028] The tool conditions are set according to each of the robot arms 30A, 30B, and 30C. For example, if a clamper 41 in the open position is to be mounted on robot arm 30A, the tool type and tool state corresponding to robot arm 30A are "clamper 41" and "open position," respectively. To give another example, if a chuck 42 in the open position is to be mounted on robot arm 30B, the tool type and tool state corresponding to robot arm 30B are "chuck 42" and "open position," respectively.
[0029] The attachment of the tool 40 to the tip of the robot arm 30 is performed, for example, as a manual operation by an operator. Therefore, if there is an error in the operator's work of attaching the tool 40 to the tip of the robot arm 30, the tool condition will not be satisfied. As a more specific example, if a tool 40 of a different type than the tool 40 that should be attached is mistakenly attached to the robot arm 30, the tool type will not be satisfied. To give another example, an error may occur in the work of connecting the air cylinder acting as an actuator and the clamper 41 using an air pipe. In this case, when the air cylinder is operated, the clamper 41 should be in the open state but will be in the closed state, and the tool condition will not be satisfied. To give yet another example, if the tool 40 is attached in the up and down direction, the tool condition will not be satisfied.
[0030] Figure 2 is a block diagram of the tool discrimination device 200 shown in Figure 1. The tool discrimination device 200 includes a robot arm motion command control unit 202 and an imaging command control unit 204. The robot arm motion command control unit 202 is configured to control the movement of the robot arm 30 via the robot arm control unit 130, which is provided by the control device 100, by transmitting motion commands to the robot arm control unit 130. The imaging command control unit 204 is configured to perform imaging operations by the imaging device 8 via the imaging device control unit 110, which is provided by the control device 100, by transmitting imaging commands to the imaging device control unit 110.
[0031] In this embodiment, the robot arm motion command control unit 202 and the imaging command control unit 204 control the robot arm 30 and the imaging device 8 in conjunction with each other, thereby enabling the acquisition of image data in which the position of the tool 40 attached to the tip of the robot arm 30 is appropriately adjusted relative to the imaging range of the imaging device 8.
[0032] In this embodiment, the tool discrimination device 200 is configured to indirectly control the imaging device 8 and the robot arm 30 via the control device 100 for controlling the workpiece processing system 1 by transmitting commands to the imaging device control unit 110 and the robot arm control unit 130, respectively, via the robot arm motion command control unit 202 and the imaging command control unit 204. This allows the tool discrimination method described later to be implemented using the existing configuration for performing processing on the workpiece 5, thereby effectively reducing the amount of additional configuration required to implement the tool discrimination method.
[0033] Furthermore, the tool discrimination device 200 may directly control the imaging device 8 and the robot arm 30 by transmitting control signals to the imaging device 8 and the robot arm 30 without going through the control device 100.
[0034] Furthermore, the tool discrimination device 200 also includes a tool discrimination unit 206, configured to perform a tool discrimination method for discriminating a tool 40 attached to the tip of the robot arm 30 using image data captured by the cooperation of the imaging device 8 and the robot arm 30 as described above. The tool discrimination unit 206 includes an image data acquisition unit 208, a differential image data creation unit 210, a tool condition determination unit 212, a registered image database 214, and a determination result output unit 216.
[0035] The tool discrimination device 200 also includes an image data registration unit 218 for registering new image data in the registered image database 214 provided by the tool discrimination unit 206. The image data registration unit 218 includes an image data acquisition unit 208, a differential image data creation unit 210, a tool condition acquisition unit 220, and a registration processing unit 222.
[0036] In Figure 2, for the sake of explanation, the image data registration unit 218 is shown as an example where it overlaps with the tool discrimination unit 206 and includes an image data acquisition unit 208 and a differential image data creation unit 210. However, the image data acquisition unit 208 and the differential image data creation unit 210 may be provided in either the tool discrimination unit 206 or the image data registration unit 218.
[0037] Next, the tool identification method performed by the tool identification unit 206 will be described. The tool identification method is a method for determining at least one of the type or state of the tool 40 attached to the tip of the robot arm 30 in the workpiece processing system 1 having the above configuration. Figure 3 is a flowchart showing the tool identification method performed by the tool identification unit 206 in Figure 2.
[0038] First, the robot arm motion command control unit 202 controls the robot arm 30 so that the tool 40 attached to the tip of the robot arm 30 is at a first position P1 by transmitting an motion command to the robot arm control unit 130 (step S100). The first position P1 is outside the imaging range 8a of the imaging device 8, and is a position where first image data D1 consisting only of the background, without the robot arm 30 and tool 40, can be captured in the imaging data captured by the imaging device 8 in the subsequent step S101.
[0039] Next, the imaging command control unit 204 transmits an imaging command to the imaging device control unit 110, causing the imaging device 8 to capture the first image data D1 (step S101). At this time, the tool 40 attached to the tip of the robot arm 30 is moved to the first position P1 in step S100 and is outside the imaging range 8a of the imaging device 8, so the first image data D1, which includes only the background, is captured.
[0040] Furthermore, the control of the robot arm 30 in step S100 may be performed based on the first reference coordinate system xyz of the imaging device 8. When the robot arm 30 is controlled by the robot arm control unit 130 when performing machining on the workpiece 5 in the workpiece machining system 1, the robot arm 30 is basically controlled based on the second reference coordinate system XYZ of the robot arm 30. In contrast, in step S100, the robot arm 30 may be controlled based on the first reference coordinate system xyz of the imaging device 8. In this case, the position of the tool 40 in the imaging range 8a of the imaging device 8 can be appropriately controlled to be outside the imaging range 8a of the imaging device 8, and when imaging is performed by the imaging device 8 in step S101, a first image data D1 consisting only of the background without the tool 40 can be suitably obtained.
[0041] Next, the robot arm motion command control unit 202 transmits an motion command to the robot arm control unit 130, thereby controlling the robot arm 30 so that the tool 40 attached to the tip of the robot arm 30 is at the second position P2 (step S102). The second position P2 is within the imaging range 8a of the imaging device 8, and is predetermined so that the tool 40 is captured at a predetermined position in the imaging data captured by the imaging device 8 in the subsequent step S103. Note that the second position P2 may also be predetermined as the position to which the tool 40 is moved in step S203 when registering the registered image data Dr, as will be described later with reference to Figure 6.
[0042] Subsequently, the imaging instruction control unit 204 transmits an imaging instruction to the imaging device control unit 110, causing the imaging device 8 to capture the second image data D2 (step S103). At this time, since the tool 40 mounted at the tip of the robot arm 30 is moved to the second position P2 in step S102 and is within the imaging range 8a of the imaging device 8, the second image data D2 including the tool 40 at a predetermined position is captured.
[0043] Note that the control of the robot arm 30 in step S102 is performed based on the first reference coordinate system xyz of the imaging device 8. When the robot arm 30 is controlled by the robot arm control unit 130 when performing a processing operation on the workpiece 5 in the workpiece processing system 1, basically, the robot arm 30 is controlled based on the second reference coordinate system XYZ of the robot arm 30. In contrast, in step S102, the robot arm 30 may be controlled based on the first reference coordinate system xyz of the imaging device 8. In this case, it becomes possible to accurately control the position of the tool 40 in the imaging range 8a of the imaging device 8 with respect to a predetermined position within the imaging range 8a of the imaging device 8. When the imaging device 8 performs imaging in step S103, the second image data D2 including the tool 40 at the predetermined position can be preferably obtained.
[0044] Also, the first image data D1 and the second image data D2 may each be captured within a predetermined time. That is, the capture of the first image data D1 in step S101 and the capture of the second image data D2 in step S103 may be performed at a sufficiently short time interval within a predetermined time. As a result, differences in the backgrounds (including objects placed on the transfer device 7 and dirt attached to the transfer device 7, etc.) included in the first image data D1 and the second image data D2 are less likely to occur. Therefore, as will be described later, when creating the difference image data Dd from the first image data D1 and the second image data D2, the difference image data Dd in which the image region corresponding to the tool 40 is preferably extracted from the second image data D2 can be obtained.
[0045] Furthermore, the first image data D1 and the second image data D2 may be captured while the transport device 7 is stopped. In this case, the transport device 7 is controlled in conjunction with the imaging device 8 and the robot arm 30, so that the transport device 7 is stopped at least temporarily at the time of imaging by the imaging device 8. This makes it less likely for there to be differences in the background (including objects placed on the transport device 7 and dirt attached to the transport device 7) included in the first image data D1 and the second image data D2, respectively. Therefore, when creating differential image data Dd from the first image data D1 and the second image data D2, it is possible to obtain differential image data Dd in which the image region corresponding to the tool 40 is suitably extracted from the second image data D2.
[0046] Next, the first image data D1 captured in step S101 and the second image data D2 captured in step S103 are acquired by the image data acquisition unit 208 (step S104). Then, the difference image data creation unit 210 creates difference image data Dd based on the first image data D1 and the second image data D2 acquired in step S104 (step S105). The difference image data Dd is created as the difference between the first image data D1 and the second image data D2. More specifically, the difference in brightness value is calculated for each pixel of the first image data D1 and the second image data D2, and the difference image data Dd is created as image data having pixels whose brightness value is that difference.
[0047] Here, Figure 4 conceptually illustrates the process of creating the differential image data Dd in step S105 of Figure 3. In this example, the first image data D1 does not show the tool 40, only the transport device 7 as the background, while the second image data D2 shows the tool 40 of a predetermined type and state along with the background. In the differential image data Dd created from the first image data D1 and the second image data D2, the background of the first image data D1 is removed from the second image data D2, leaving only the tool 40 shown in the second image data D2.
[0048] Subsequently, the tool condition determination unit 212 extracts the contour of the tool 40 from the differential image data Dd created in step S105 to obtain discrimination image data Da (step S106). Further, the tool condition determination unit 212 accesses the registered image database 214 to obtain registered image data Dr corresponding to the tool conditions from among a number of registered image data stored in the registered image database 214 (step S107). That is, the registered image database 214 is searched based on the tool conditions that define at least one of the correct tool 40 type or state to be mounted at the tip of the robot arm 30, and the registered image data Dr corresponding to the tool conditions is obtained.
[0049] Subsequently, the tool condition determination unit 212 compares the discrimination image data Da obtained in step S106 with the registered image data Dr obtained in step S107 to determine whether the tool 40 mounted at the tip of the robot arm 30 satisfies the tool conditions (step S108). The comparison between the discrimination image data Da and the registered image data Dr is performed based on, for example, whether the matching rate between the image regions corresponding to the tool 40 included in both is equal to or higher than a reference value.
[0050] Here, FIGS. 5A and 5B are diagrams showing an example of matching between the discrimination image data Da and the registered image data Dr in step S108 of FIG. 3. In the example shown in FIG. 5A, since the matching rate of the image regions corresponding to the tool 40A included in the discrimination image data Da and the tool 40B included in the registered image data Dr is equal to or higher than the reference value, it is determined that the tool conditions are satisfied. On the other hand, in the example shown in FIG. 5B, since the matching rate of the image regions corresponding to the tool 40A included in the discrimination image data Da and the tool 40B included in the registered image data Dr is less than the reference value, it is determined that the tool conditions are not satisfied.
[0051] If the tool conditions are determined to be met (step S108: YES), the tool condition determination unit 212 determines that the tool 40 attached to the tip of the robot arm 30 is correct. On the other hand, if the tool conditions are determined not to be met (step S108: NO), error information indicating this is output from the determination result output unit 216 (step S109).
[0052] Next, we will explain the method of registering registered image data Dr to the registered image database 214, which is performed by the image data registration unit 218. Figure 6 is a flowchart showing the method of registering registered image data Dr as performed by the image data registration unit 218 in Figure 2.
[0053] First, the tool 40 to be registered is attached to the tip of the robot arm 30 (step S200). The tool 40 to be registered is, for example, a tool 40 that requires new registration because registered image data Dr for a tool 40 of the same type and state is not stored in the registered image database 214. Alternatively, the tool 40 to be registered may be a tool 40 for which registered image data Dr for the same type and state is already stored in the registered image database 214, but which requires re-registration in order to update the registered image data Dr.
[0054] Next, similar to steps S100 to S101 described above, the robot arm motion command control unit 202 controls the robot arm 30 to move the tool 40 attached to the tip of the robot arm 30 to the first position P1 (step S201), and the imaging command control unit 204 controls the imaging device 8 to capture the first image data D1 (step S202).
[0055] Next, similar to steps S102 to S103 described above, the robot arm motion command control unit 202 controls the robot arm 30 to move the tool 40 attached to the tip of the robot arm 30 to the second position P2 (step S203), and the imaging command control unit 204 controls the imaging device 8 to capture the second image data D2 (step S204). In step S102 described above, the second position P2 to which the tool 40 is moved in order to identify the tool 40 is predetermined as the second position P2 to which the tool 40 is moved in step S203 when registering the registered image data Dr in this manner.
[0056] Next, similar to step S104 described above, the image data acquisition unit 208 acquires the first image data D1 captured in step S202 and the second image data D2 captured in step S204 (step S205). Then, similar to step S105 described above, the difference image data creation unit 210 creates difference image data Dd based on the first image data D1 and the second image data D2 acquired in step S205 (step S206).
[0057] Next, the tool condition acquisition unit 220 acquires tool conditions (step S207). The tool conditions are information regarding the type and state of the tool 40 attached to the tip of the robot arm 30 in step S200, and are input, for example, by the operator who performed the attachment work.
[0058] Next, the registration processing unit 222 associates the differential image data Dd created in step S206 with the tool conditions acquired in step S207 and registers it as registered image data Dr in the registered image database 214 (step S208). The registered image data Dr registered in the registered image database 214 in this way can be searched based on the tool conditions and can be read as needed.
[0059] As described above, according to each of the embodiments, a difference image data Dd is created based on a first image data D1 capturing the background and a second image data D2 capturing the tool 40 together with the background. The difference image data Dd includes an image region corresponding to the tool 40 from which the background has been removed from the second image data D2. By comparing this with a registered image data Dr that has been registered in advance corresponding to the tool 40 to be identified, it is determined whether the tool 40 included in the difference image data Dd satisfies the tool conditions relating to at least one of the type or state of the tool 40. This makes it possible to suitably determine whether the tool 40 attached to the tip of the robot arm 30 is of the appropriate type and state.
[0060] The contents described in some of the embodiments above can be understood, for example, as follows:
[0061] (1) A tool discrimination device according to one embodiment is a tool discrimination device for discriminating a tool attached to the tip of a robot arm for performing machining processing on a workpiece being transported on a transport device, and comprises: an image data acquisition unit for acquiring first image data of a background and second image data of the tool together with the background; a differential image data creation unit for creating differential image data based on the first image data and the second image data; and a tool condition determination unit for determining whether a tool condition relating to at least one of the type or state of the tool is satisfied by comparing the differential image data with registered image data that has been registered in advance corresponding to the tool.
[0062] According to the embodiment described in (1) above, differential image data is created based on first image data capturing the background and second image data capturing the tool together with the background. The differential image data includes an image region corresponding to the tool from which the background has been removed from the second image data. By comparing this differential image data with registered image data that has been registered in advance corresponding to the tool to be identified, it is determined whether the tool included in the differential image data satisfies tool conditions relating to at least one of the tool type or state. This makes it possible to suitably determine whether the tool attached to the tip of the robot arm is of the appropriate type and state.
[0063] (2) In another embodiment, in the embodiment of (1) above, the first image data is captured when the position of the tool is moved by the robot arm to a first position outside the imaging range, and the second image data is captured when the position of the tool is moved by the robot arm to a second position within the imaging range.
[0064] According to the embodiment of (2) above, first image data and second image data can be suitably obtained by controlling the movement of the tool by the robot arm in conjunction with the imaging operation. Specifically, first image data capturing the background is obtained by imaging with the tool moved to a first position outside the imaging range by the robot arm. Second image data capturing the tool together with the background is obtained by imaging with the tool moved to a second position within the imaging range by the robot arm.
[0065] (3) In other embodiments, the system further comprises a registered image database in which the registered image data is registered for each of the tool conditions, and the tool condition determination unit obtains the registered image data by searching the registered image database based on the tool conditions.
[0066] According to the embodiment of (3) above, a registered image database is provided in which registered image data used for tool identification is registered. Registered image data is pre-registered in the registered image database in association with tool conditions relating to at least one of the type or state of the tool, and registered image data necessary for tool identification can be searched based on the tool conditions.
[0067] (4) In other embodiments, the system further includes a registration processing unit for associating the differential image data with the tool conditions and registering it as registered image data in the registered image database, in any one embodiment of (1) to (3) above.
[0068] According to the embodiment described in (4) above, differential image data created by imaging a tool attached to the tip of a robot arm can be registered in a registered image database in association with tool conditions corresponding to the tool. The registered image data registered in the registered image database can be used for tool identification by reading it as appropriate, as described above.
[0069] (5) In other embodiments, in any one embodiment of (1) to (4) above, the robot arm is controlled based on the coordinate system corresponding to the first image data and the second image data.
[0070] According to the embodiment of (5) above, the control of the robot arm during the acquisition of the first image data and the second image data is performed based on the coordinate system corresponding to the first image data and the second image data. As a result, when acquiring the first image data, the robot arm is controlled so that the tool is outside the imaging range, thereby suitably obtaining first image data consisting of a background without the tool. Furthermore, when acquiring the second image data, the robot arm is controlled so that the tool is within the imaging range, thereby suitably obtaining second image data including the tool along with the background.
[0071] (6) In other embodiments, in any one embodiment of (1) to (5) above, the first image data and the second image data are each captured within a predetermined time.
[0072] According to the embodiment of (6) above, since the first image data and the second image data are captured within a predetermined time period (a relatively short time interval), differences in the background contained in each are less likely to occur. Therefore, as the difference between the first image data and the second image data, differential image data can be obtained by suitably extracting the image region corresponding to the tool from the second image data.
[0073] (7) In other embodiments, in any one embodiment of (1) to (6) above, the first image data and the second image data are captured with the transport device stopped.
[0074] According to the embodiment of (7) above, the first image data and the second image data are captured while the transport device is stopped, making it less likely for differences to occur in the background (including objects placed on the transport device and dirt attached to the transport device) included in the first image data and the second image data, respectively. By using such first image data and second image data, differential image data can be obtained as the difference between the first image data and the second image data, by suitably extracting the image region corresponding to the tool from the second image data.
[0075] (8) In other embodiments, in any one embodiment of (1) to (7) above, the first image data and the second image data are captured using an imaging device for imaging the workpiece on the transport device in order to control at least one of the transport device or the robot arm.
[0076] According to the embodiment of (8) above, when processing a workpiece, an imaging device is used to image the workpiece, and first image data and second image data used for workpiece identification are captured. This eliminates the need to add a new imaging device for workpiece identification, and the size of the apparatus can be suitably reduced.
[0077] (9) In other embodiments, in any one embodiment of (1) to (8) above, the tool includes at least one of a chuck tool, a clamping tool, or a knife tool.
[0078] According to the embodiment of (9) above, a tool including at least one of a chuck tool, a clamping tool, or a knife tool can be suitably identified.
[0079] (10) A workpiece processing system according to one embodiment is equipped with a tool discrimination device according to any one embodiment of (1) to (9) above.
[0080] According to the embodiment of (10) above, in a workpiece processing system, the tool attached to the tip of the robot arm for processing the workpiece can be suitably identified.
[0081] (11) A tool identification method according to one embodiment is a tool identification method for identifying a tool attached to the tip of a robot arm for performing machining on a workpiece being transported on a transport device, comprising: a step of acquiring first image data of a background and second image data of the tool together with the background; a step of creating differential image data based on the first image data and the second image data; and a step of comparing the differential image data with registered image data that has been registered in advance corresponding to the tool, to determine whether or not a tool condition relating to at least one of the type or state of the tool is satisfied.
[0082] According to the embodiment of (11) above, differential image data is created based on first image data capturing the background and second image data capturing the tool together with the background. The differential image data includes an image region corresponding to the tool from which the background has been removed from the second image data. By comparing this differential image data with registered image data that has been registered in advance corresponding to the tool to be identified, it is determined whether the tool included in the differential image data satisfies tool conditions relating to at least one of the tool type or state. This makes it possible to suitably determine whether the tool attached to the tip of the robot arm is of the appropriate type and state.
[0083] 1 Work Processing System 5 Work 7 Transfer Device 8 Imaging Device 8a Imaging Range 30 (30A, 30B, 30C) Robot Arm 40 Tool 41 Clamper 42 Chuck 43 Knife 100 Control Device 110 Imaging Device Control Unit 120 Image Analysis Unit 130 Robot Arm Control Unit 200 Tool Discrimination Device 202 Robot Arm Motion Command Control Unit 204 Imaging Command Control Unit 206 Tool Discrimination Unit 208 Image Data Acquisition Unit 210 Difference Image Data Creation Unit 212 Tool Condition Determination Unit 214 Registered Image Database 216 Determination Result Output Unit 218 Image Data Registration Unit 220 Tool Information Acquisition Unit 222 Registration Processing Unit D1 First Image Data D2 Second Image Data Da Discrimination Image Data Dd Difference Image Data Dr Registered Image Data P1 First Position P2 Second Position
Claims
1. A tool identification device for identifying a tool attached to the tip of a robot arm for performing machining operations on a workpiece being transported on a transport device, comprising: an image data acquisition unit for acquiring first image data of a background and second image data of the tool together with the background; a differential image data creation unit for creating differential image data based on the first image data and the second image data; and a tool condition determination unit for determining whether a tool condition relating to at least one of the type or state of the tool is satisfied by comparing the differential image data with registered image data that has been registered in advance corresponding to the tool.
2. The tool discrimination device according to claim 1, wherein the first image data is captured when the position of the tool is moved by the robot arm to a first position outside the imaging range, and the second image data is captured when the position of the tool is moved by the robot arm to a second position within the imaging range.
3. The tool determination device according to claim 1 or 2, further comprising a registered image database in which the registered image data is registered for each of the tool conditions, wherein the tool condition determination unit obtains the registered image data by searching the registered image database based on the tool conditions.
4. The tool discrimination device according to claim 1 or 2, further comprising a registration processing unit for associating the differential image data with the tool conditions and registering it as registered image data in the registered image database.
5. The tool discrimination device according to claim 1 or 2, wherein the robot arm is controlled based on a coordinate system corresponding to the first image data and the second image data.
6. The tool discrimination device according to claim 1 or 2, wherein the first image data and the second image data are each captured within a predetermined time.
7. The tool discrimination device according to claim 1 or 2, wherein the first image data and the second image data are captured while the transport device is stopped.
8. The tool discrimination device according to claim 1 or 2, wherein the first image data and the second image data are captured using an imaging device for imaging the workpiece on the transfer device in order to control at least one of the transfer device or the robot arm.
9. The tool discrimination device according to claim 1 or 2, wherein the tool includes at least one of a chuck tool, a clamping tool, or a knife tool.
10. A workpiece processing system comprising the tool discrimination device described in claim 1 or 2.
11. A tool identification method for identifying a tool attached to the tip of a robot arm for performing machining on a workpiece being transported on a transport device, comprising: a step of acquiring first image data of a background and second image data of the tool together with the background; a step of creating differential image data based on the first image data and the second image data; and a step of determining whether or not a tool condition relating to at least one of the type or state of the tool is satisfied by comparing the differential image data with registered image data that has been registered in advance corresponding to the tool.