JP7520608B2 - Robot hand position detection system - Google Patents

Description

The present invention relates to a robot hand position detection system, and in particular to a robot hand position detection system that detects the position of a robot hand equipped with an imaging device for measuring an object.

In the manufacturing process of automobiles and other vehicles, the accuracy of the vehicle body frame is measured to improve the assembly accuracy of the vehicle. The method used to measure the accuracy of the frame is to install multiple cameras and multiple laser displacement meters on a tower that is set up to surround the vehicle body, and calculate the vehicle body dimensions based on the data of the vehicle body obtained from each camera and each laser displacement gauge. The installation positions and number of cameras and laser displacement meters vary depending on the type of vehicle.

In recent years, instead of using fixed cameras and laser displacement meters, a method has been adopted in which a measurement robot with a camera for measuring the vehicle body attached to its robot hand is used.

For example, Patent Document 1 describes a measuring robot that measures the shape of a vehicle body in three dimensions. This measuring robot is equipped with a camera attached to the robot hand and a control unit that analyzes image data acquired by the camera and generates three-dimensional measurement data of the vehicle body contained in the image data. The robot hand is provided at the tip of the robot arm. The robot arm is controlled to move the camera attached to the robot hand to a predetermined measurement position relative to the vehicle body.

This measuring robot can perform three-dimensional measurements of the vehicle body by capturing images of the vehicle body using a camera at each measurement position on the vehicle body and analyzing the vehicle body shape from the captured image data.

In this way, by using a measurement robot that can control the movement of the camera position, measurements can be carried out according to the vehicle model without changing the location or number of cameras, even if the vehicle model is changed.

However, in a robot in which the measurement posture of the robot arm changes in this way, there is a problem with repeatability in that even if the robot arm returns to the same measurement posture, there will be a deviation in the camera position from the original measurement posture. The amount of this deviation also changes due to changes in the surrounding temperature and thermal dripping caused by heat generated by the robot itself, making it difficult to improve repeatability.

Therefore, a detection device is installed separately from the measurement robot to detect the amount of deviation due to the robot's measurement posture, and the measurement value is corrected according to the amount of deviation detected by this detection device.

For example, Patent Document 2 describes a robot system that includes a robot and a position detection device that detects the position of a robot hand (i.e., the mounting position of a measurement camera) attached to the tip of the robot's robot arm. In this system, the position detection device is installed at a position separated from the robot. The position detection device irradiates a laser beam toward the robot hand and receives the laser beam that is reflected back by the robot hand, and measures the position of the robot hand from the receiving position of the laser beam and the time until it is received.

In this robot system, the amount of deviation of the robot hand from the reference position can be detected by comparing data on the robot hand position measured by the position detection device with reference position data for the robot hand that is pre-stored in the position detection device. The robot corrects the data based on the detected amount of deviation.

JP 2007-24764 A JP 2019-153776 A

However, in the robot system described in Patent Document 2, it is necessary to install a position detection device at a position away from the robot. Depending on the measurement posture of the robot arm, the laser beam may not be able to be reflected by the robot hand, making it impossible to detect the position of the robot hand.

In addition, because position detection devices require sensors that can perform highly accurate measurements at long distances from the robot, the devices themselves are expensive, which creates the problem of high facility costs.

The present invention has been made in consideration of the above problems, and aims to provide a robot hand position detection system that can detect the position of a robot hand regardless of the measurement posture of the robot arm, and can reduce equipment costs.

In order to achieve the above-mentioned object, a robot hand position detection system according to the present invention is a robot hand position detection system that detects the position of a robot hand provided at the tip of a robot arm, the system comprising: three imaging devices attached to the robot hand and arranged facing three mutually perpendicular directions; a control device that controls the movement of the robot hand; and at least two markers arranged at positions spaced apart from the robot arm and at positions that can be imaged by each of the remaining two imaging devices when a measurement object is measured by one of the three imaging devices, the control device comprising a position detection unit that detects the position of the robot hand in the reference coordinate system based on information related to a reference coordinate system that is preset based on the positions of the markers and image data of the markers acquired by each of the remaining two imaging devices when the robot hand is moved to a predetermined measurement position and the measurement object is measured by the one imaging device, and the one imaging device that measures the measurement object can be arbitrarily selected from the three imaging devices at the predetermined measurement position .

According to this configuration, when measuring an object to be measured using one imaging device attached to the robot hand, the remaining two imaging devices each capture an image of a marker to obtain image data of the two markers, and the three-dimensional position of the markers in the reference coordinate system of the robot hand can be detected by using this obtained image data of the markers and a reference coordinate system that is preset based on the positions of these markers.

In addition, in this system, the two imaging devices used to detect the position of the robot hand are attached to the robot hand and move together with the robot hand, so the position of the robot hand can be detected regardless of the measurement posture of the robot arm. Also, with a simple and inexpensive structure in which three imaging devices are attached to the robot hand and markers are placed at positions away from the robot arm, it is possible to measure the object to be measured and detect the position of the robot hand, thereby reducing equipment costs.

The present invention is also characterized in that in the robot hand position detection system, the marker is formed in a shape whose inclination can be recognized in the image data.

With this configuration, the rotation angle of the robot hand in the reference coordinate system can be detected from the inclination of the marker contained in the image data acquired by the imaging device, thereby improving the accuracy of detecting the position of the robot hand.

The present invention is also characterized in that, in the robot hand position detection system, the position detection unit calculates the amount of deviation of the robot hand from the reference measurement position based on a reference measurement position of the robot hand that is preset in the reference coordinate system and the position of the robot hand detected based on image data of the marker acquired by each of the remaining two imaging devices when measuring the measurement object with the one imaging device, and the control device includes a correction unit that corrects the measurement result of the measurement object acquired by the one imaging device based on the amount of deviation.

With this configuration, the amount of deviation of the robot hand from a specified measurement position is calculated, and this deviation is used to correct the measurement results of the object being measured, eliminating problems with the robot's repeatability and enabling highly accurate measurement results to be obtained.

The present invention is also characterized in that, in the robot hand position detection system, one of the three imaging devices used to measure the object is arbitrarily selected so that the amount of movement of the robot hand is minimized when the robot hand moves from a predetermined measurement position to the next predetermined measurement position.

With this configuration, when the robot hand moves from one specified measurement position to the next specified measurement position, the measurement imaging device is selected so that the amount of movement of the robot hand is minimized, thereby suppressing the amount of displacement of the robot arm and improving the repeatability of the measurement posture of the robot arm.

The robot hand position detection system according to the present invention can detect the position of the robot hand regardless of the measurement posture of the robot arm, thereby reducing equipment costs.

1 is a schematic explanatory diagram of a robot hand position detection system according to an embodiment of the present invention. FIG. 1 is a block diagram showing a configuration of a robot hand position detection system. FIG. 2 is a perspective view showing an installation state of a camera attached to a robot hand. FIG. 2 is a front view of a first imaging object. FIG. 11 is a diagram showing an example of image data captured by a second camera. FIG. 4 is a diagram showing an example of image data captured by a first camera. FIG. 11 is a diagram showing an example of image data captured by a third camera.

Figure 1 is a schematic diagram of a robot hand position detection system according to one embodiment of the present invention, and Figure 2 is a block diagram showing the configuration of the robot hand position detection system. The robot hand position detection system 10 is a system capable of detecting the position of a robot hand to which an imaging device is attached in a robot that uses an imaging device to measure an object. Figure 1 shows, as an example of a robot, a measurement robot 20 that measures the skeletal accuracy of a car body 1, which is an object to be measured.

The robot hand position detection system 10 comprises a measurement robot 20 having a robot hand 24, three cameras 31, 32, 33 that are image capture devices, and at least two markers 13, 15 arranged at positions spaced apart from the measurement robot 20. Each of the cameras 31, 32, 33 is attached to the robot hand 24. The measurement robot 20 comprises a control device 40 that controls the movement of the robot hand 24. The control device 40 is electrically connected to each of the cameras 31, 32, 33, and performs measurements of the vehicle body 1 and detection of the position of the robot hand 24 based on image data acquired from each of the cameras 31, 32, 33.

The measurement robot 20 comprises a base 21 fixedly installed at the measurement site of the vehicle body 1, and a robot arm 22 extending from the base 21. The robot arm 22 is configured to be movable by a robot arm actuator (not shown) built into the measurement robot 20.

The robot hand 24 is provided at the tip of the robot arm 22 and moves three-dimensionally in accordance with the movement of the robot arm 22. In this embodiment, the robot hand 24 is configured to be capable of rotating around a predetermined axis (for example, around the axis of the robot arm 22) by a robot hand actuator (not shown) built into the robot hand 24.

Figure 3 is a diagram showing a part of the robot hand 24, and is a perspective view showing the installation state of the cameras 31, 32, and 33 attached to the robot hand 24. As shown in Figures 1 and 3, the robot hand 24 is equipped with three imaging devices that acquire image data by photographing, namely, a first camera 31, a second camera 32, and a third camera 33. Note that in Figure 1, the three cameras 31, 32, and 33 are drawn large relative to the robot hand 24 so that each of the cameras 31, 32, and 33 can be easily understood. Also, in Figure 1, the symbols 31a and 33a respectively indicate the lenses of the first camera 31 and the third camera 33, and in Figure 3, the symbol 32a indicates the lens of the second camera 32.

As shown in FIG. 3, the robot hand 24 includes a mounting base 26 to which a first camera 31, a second camera 32, and a third camera 33 are fixed, and a direction regulating member 27 that regulates the orientation of each of the cameras 31, 32, and 33. The mounting base 26 is formed in a substantially disk shape. The direction regulating member 27 is a rectangular parallelepiped member fixed to the substantially circular surface of the mounting base 26.

The first camera 31, the second camera 32, and the third camera 33 are arranged along three mutually orthogonal faces of the direction defining member 27 so as to face three mutually orthogonal directions. In this embodiment, the first camera 31, the second camera, and the third camera are arranged so as to face the mutually orthogonal X-direction, Y-direction, and Z-direction, respectively. Note that in FIG. 3, the hollow arrows indicate the directions in which the cameras 31, 32, and 33 face on the X-direction axis, the Y-direction axis, and the Z-direction axis, respectively.

Of the first camera 31, the second camera 32, and the third camera 33, any one of them is used to measure the vehicle body 1, and the remaining two cameras are used to detect the position of the robot hand 24. In FIG. 1, as an example, the second camera 32 is used for measurement, and the first and third cameras 31, 33 are used for position detection, but instead, the first camera 31 can be used for measurement and the second and third cameras 32, 33 can be used for position detection, or the third camera 33 can be used for measurement and the first and second cameras 31, 32 can be used for position detection. In addition, it is possible to arbitrarily change the camera used for measurement at each measurement position on the vehicle body 1.

In the following explanation, in order to make the invention easier to understand, an example will be described in detail in which the second camera 32 is used to measure the vehicle body 1, and the first camera 31 and the third camera 33 are used to detect the position of the robot hand 24.

When measuring the vehicle body 1 using the second camera 32, each of the markers 13 and 15 is placed at a position where it can be captured by the remaining two cameras, i.e., the first camera 31 and the third camera 33. Each of the markers 13 and 15 is used to define a reference coordinate system for identifying the position of the robot hand 24.

As shown in FIG. 1, in this embodiment, the multiple markers 13, 15 are attached to the surfaces of multiple image capture objects (i.e., the first image capture object 12 and the second image capture object 14) that are fixedly installed at a position away from the robot arm 22. Each image capture object 12, 14 is flat and arranged around the vehicle body 1 so that the surface to which the markers 13, 15 are attached faces the vehicle body 1. In the example shown in FIG. 1, the first image capture object 12 is arranged in front of the vehicle body 1 and the second image capture object 14 is arranged below the vehicle body 1 so that the first camera 31 and the first image capture object 12 face each other and the third camera 33 and the second image capture object 14 face each other when the second camera 32 is used for vehicle body measurement.

Each marker 13, 15 can be image-recognized by each camera 31, 32, 33, and can be, for example, a figure, a letter, a symbol, etc. Alternatively, the markers 13, 15 may be the image-captured objects 12, 14 themselves, which have a predetermined shape. In addition, a configuration may be used in which a video projection device such as a projector is used to project multiple markers 13, 15 onto the wall surface of the measurement site of the vehicle body 1.

In this embodiment, each of the imaging objects 12, 14 is a flat plate of the same shape, and markers 13, 15 of the same shape are attached to the surface facing the robot hand 24, but each of the imaging objects 12, 14 and each of the markers 13, 15 may be of different shapes and sizes.

Figure 4 is a front view of the first image capture object 12. The markers 13, 15 marked on each image capture object 12, 14 are preferably shaped such that when the image data is acquired by capturing an image of the markers 13, 15 with the respective cameras 31, 32, 33, the inclination of the markers 13, 15 can be recognized in the image data. In this embodiment, the markers 13, 15 are formed in an isosceles triangle, and the inclination can be recognized based on the orientation of the apex angle of the isosceles triangle.

It is preferable to place three or more markers so that they always face the two cameras used to detect the position of the robot hand 24 when the measurement position of the robot hand 24 relative to the vehicle body 1 changes. In FIG. 1, virtual lines show an example in which image capture objects 16A, 16B, and 16C with markers are placed at the rear, top, and left of the vehicle body 1, respectively.

The control device 40 is a calculator including a microcomputer, and is configured with an information processing unit such as a central processing unit (CPU) or an application specific integrated circuit (ASIC), and a storage unit such as a RAM or ROM. The control device 40 functions as various function realization units (e.g., a control unit, an arithmetic unit, a processing unit, etc.) by the central processing unit reading and executing programs recorded in the storage unit.

As shown in FIG. 2, the control device 40 includes a memory unit 41, a robot arm control unit 42, a camera control unit 43, a position detection unit 45, a measurement unit 46, a correction unit 47, and a measurement unit 48.

The memory unit 41 stores programs for controlling the movement of the robot arm 22 and the robot hand 24, and programs for controlling the operation of the cameras 31, 32, and 33. Each control program is set individually depending on the type of vehicle body 1 to be measured by the measurement robot 20.

The robot arm control unit 42 operates the actuator for the robot arm and the actuator for the robot hand according to a control program preset in the memory unit 41, and controls the operation of the robot arm 22 and the robot hand 24 so that the robot hand 24 moves to a predetermined measurement position. In this embodiment, the movement of the robot arm 22 and the robot hand 24 is controlled so that the robot hand 24 moves to a plurality of different measurement positions relative to the vehicle body 1.

The camera control unit 43 controls the operation of each of the cameras 31, 32, 33 according to a preset control program. Specifically, when the robot hand 24 moves to each measurement position relative to the vehicle body 1, the second camera 32 photographs the vehicle body 1, and the remaining two cameras (the first camera 31 and the third camera 33) control each of the cameras 31, 32, 33 so as to photograph the two markers 13, 15 facing it. The image data of the vehicle body 1 acquired by the second camera 32 (hereinafter also referred to as "measurement image data") is image-processed by the measurement unit 46, and the image data of each of the markers 13, 15 acquired by the first and third cameras 31, 33 (hereinafter also referred to as "image data for position detection") is image-processed by the position detection unit 45.

The storage unit 41 further stores information (hereinafter also referred to as "reference coordinate information") about a reference coordinate system that is preset based on the positions of each marker 13, 15. In this embodiment, the reference coordinate system is a three-dimensional coordinate system.

The reference coordinate information includes information on the reference measurement positions that define each measurement position of the robot hand 24 relative to the vehicle body 1 in the reference coordinate system. For example, if three positions, a first measurement position, a second measurement position, and a third measurement position, are set as measurement positions relative to the vehicle body 1, the reference coordinate information includes information on the first reference measurement position, the second reference measurement position, and the third reference measurement position that correspond to the three positions in the reference coordinate system. The information on the reference assumed position also includes information on the orientation of the robot hand 24.

As an initial setting, such reference coordinate information can be acquired by moving the robot hand 24 to each measurement position relative to the vehicle body 1 and capturing images of each marker 13, 15 at each measurement position using the first camera 31 and the third camera 33. Specifically, the reference coordinate information can be obtained by setting a reference coordinate system based on the positions of the markers 13, 15 from the acquired image data of each marker 13, 15, and setting each measurement position as each reference measurement position in the reference coordinate system of the robot hand 24.

The position detection unit 45 detects the position of the robot hand 24 in the reference coordinate system based on the reference coordinate information registered in the memory unit 41 and the image data (image data for position detection) of each marker 13, 15 acquired by the first camera 31 and the third camera 33. In this embodiment, the position detection unit 45 can detect the position and orientation of the robot hand 24 in the reference coordinate system. The position of the robot hand 24 in the reference coordinate system can be detected by performing image registration, in which the acquired image data of each marker 13, 15 is moved to the reference coordinate system using the reference coordinate information.

When measuring the vehicle body 1 using the second camera 32 at a predetermined measurement position of the robot hand 24 that has been set in advance, the control device 40 operates the first camera 31 and the third camera 33 to obtain image data for position detection, and the position detection unit 45 can detect the position of the robot hand 24 in the reference coordinate system of the measurement position.

The position detection unit 45 further calculates the amount of deviation of the robot hand 24 from the reference measurement position based on the position of the robot hand 24 detected based on the position detection image data acquired by the first camera 31 and the third camera 33 at a predetermined measurement position of the robot hand 24 and information about the reference measurement position set in the memory unit 41.

The measurement unit 46 measures a predetermined portion of the vehicle body 1 based on image data (measurement image data) of the vehicle body 1 acquired by the second camera 32. In this embodiment, the measurement unit 46 measures the vehicle body 1 by detecting the positions of holes in the vehicle body 1 that serve as the reference for the framework from the measurement image data.

The correction unit 47 corrects the measurement results of the measurement unit 46 based on the amount of deviation of the robot hand 24 from the reference measurement position calculated by the position detection unit 45.

The measurement unit 48 measures the frame accuracy of the vehicle body 1 based on the measurement results corrected by the correction unit 47. The measurement results can be output to a display device such as a display provided in the control device 40.

Next, the operation of the robot hand position detection system 10 described above will be explained.

When measurement of the vehicle body 1 begins, the robot arm control unit 42 of the measurement robot 20 activates the robot arm 22 and the robot hand 24 to move the robot hand 24 to a specified measurement position.

As shown in FIG. 1, when the robot hand 24 moves to a predetermined measurement position, the robot arm 22 and the robot hand 24 stop moving. At this measurement position, the second camera 32 faces the vehicle body 1, and the first camera 31 and the third camera 33 face the first imaged object 12 and the second imaged object 14, respectively.

In this state, the measurement robot 20 operates each of the cameras 31, 32, and 33 to obtain measurement image data using the second camera 32, and obtain image data for position detection using the first camera 31 and the third camera 33.

Figure 5 is an example of measurement image data 50 acquired by the second camera 32. In Figure 5, the X and Z directions indicate the X and Z directions of the robot hand 24 shown in Figure 3. The measurement image data 50 shows a hole 50A formed in the vehicle body 1 that serves as a reference for skeletal measurement. The measurement unit 46 of the measurement robot 20 measures the vehicle body 1 based on this image data 50.

The position detection unit 45 detects the position of the robot hand 24 in the reference coordinate system based on the reference coordinate information registered in the storage unit 41 and the image data for position detection acquired by the first camera 31 and the third camera 33. The position detection unit 45 also calculates the amount of deviation of the robot hand 24 from the reference measurement position based on the detected measurement position of the robot hand 24 and information on the reference measurement position previously set in the storage unit 41.

Figure 6 is an example of image data 51 for position detection acquired by the first camera 31, and Figure 7 is an example of image data 52 for position detection acquired by the third camera 33. In Figure 6, the Y direction and Z direction indicate the Y direction and Z direction of the robot hand 24 shown in Figure 3, and in Figure 7, the Y direction and X direction indicate the Y direction and X direction of the robot hand 24 shown in Figure 3. In Figures 6 and 7, the markers 13, 15 shown by dashed lines indicate the positions of the markers 13, 15 included in the image data obtained by capturing the markers 13, 15 (hereinafter also referred to as "reference marker positions") at the reference measurement position of the robot hand 24 in the reference coordinate system preset in the memory unit 41.

As shown in Fig. 6, the marker 13 included in the image data for position detection 51 is shifted from the reference marker position indicated by the dashed line by a displacement ΔY in the Y direction and a displacement ΔZ in the Z direction, and is shifted by a rotation angle of ΔθX with the _X direction as the axial direction. As shown in Fig. 7, the marker 15 included in the image data for position detection 52 is shifted from the reference marker position indicated by the dashed line by a displacement ΔY in the Y direction and a displacement ΔX in the X direction, and is shifted by a rotation angle of _ΔθZ with the Z direction as the axial direction. In this way, by extracting the amount of deviation from the reference marker position, it is possible to calculate the amount of deviation from the reference measurement position of the robot hand 24 set in the reference coordinate system.

Measurement of the vehicle body 1 by the measurement unit 46, detection of the position of the robot hand 24 by the position detection unit 45, and calculation of the amount of deviation from the reference measurement position are performed at each measurement position of the robot hand 24 on the vehicle body 1. The correction unit 47 corrects the measurement results of the vehicle body 1 by the measurement unit 46 based on the amount of deviation calculated by the position detection unit 45. The measurement unit 48 measures the skeletal accuracy of the vehicle body 1 based on the measurement results corrected by the correction unit 47.

As described above, in the robot hand position detection system 10 of this embodiment, when measuring the vehicle body 1 using the second camera 32 attached to the robot hand 24, the first camera 31 and the third camera 33 capture images of the markers 13, 15 to obtain image data for position detection, and the three-dimensional position of the robot hand 24 in the reference coordinate system can be detected by using this image data for position detection and a reference coordinate system previously set in the storage unit 41. In addition, the rotation angle of the robot hand 24 in the reference coordinate system can be detected from the inclination of the markers 13, 15 contained in the image data, thereby improving the position detection accuracy of the robot hand 24.

In addition, the position detection unit 45 calculates the amount of deviation of the robot hand 24 from a predetermined measurement position, and this deviation is used to correct the measurement results of the vehicle body 1, thereby solving the problem of repeatability accuracy of the measurement robot 20 and obtaining highly accurate measurement results.

In addition, the robot hand position detection system 10 of this embodiment has a simple and inexpensive structure in which three cameras 31, 32, and 33 are attached to the robot hand 24 and multiple markers 13 and 15 are positioned away from the robot arm 22, and can measure the vehicle body 1 and detect the position of the robot hand 24, thereby reducing equipment costs.

Furthermore, the two cameras (first camera 31 and third camera 33) used to detect the position of the robot hand 24 move together with the robot hand 24, so that the position of the robot hand 24 can be detected regardless of the measurement posture of the robot arm 22.

In the above example, the second camera 32 is used as a measurement camera, but as already mentioned, the first camera 31 or the third camera 32 may be used to measure the vehicle body 1, and the remaining two cameras may be used to detect the position of the robot hand 24. Also, the measurement camera may be changed at each measurement position of the robot hand 24.

When changing the measurement camera for each measurement position, it is preferable that the measurement camera is arbitrarily selected so that the amount of movement of the robot hand 24 is minimized when the robot hand 24 moves from a given measurement position to the next given measurement position. By selecting the measurement camera in this manner, the amount of displacement of the robot arm 22 and the robot hand 24 can be reduced, improving the repeatability of the measurement posture of the measurement robot 20.

The present invention is not limited to the above-described embodiment, and various modifications are possible without departing from the spirit of the invention.

1. Vehicle body (measurement object)
10 Robot hand position detection system 12, 14 Image capture object 13, 15 Marker 20 Measurement robot (robot)
22 Robot arm 24 Robot hand 31 First camera (imaging device)
32 Second camera (imaging device)
33 Third camera (imaging device)
40 Control device 45 Position detection unit 47 Correction unit

Claims (4)

A robot hand position detection system for detecting the position of a robot hand provided at the tip of a robot arm, comprising:
Three imaging devices are attached to the robot hand and arranged to face three directions perpendicular to each other;
A control device for controlling the movement of the robot hand;
at least two markers are disposed at positions spaced apart from the robot arm and at positions that can be imaged by the remaining two imaging devices when one of the three imaging devices measures the measurement object,
the control device includes a position detection unit that detects a position of the robot hand in the reference coordinate system based on information about a reference coordinate system that is preset based on the position of the marker and on image data of the marker acquired by each of the remaining two imaging devices when the robot hand is moved to a predetermined measurement position and the measurement target is measured by the one imaging device ,
A robot hand position detection system, characterized in that one imaging device for measuring the measurement object can be arbitrarily selected from among the three imaging devices at the specified measurement position . The robot hand position detection system according to claim 1, characterized in that the marker is formed in a shape whose inclination can be recognized in the image data. the position detection unit calculates an amount of deviation of the robot hand from the reference measurement position based on a reference measurement position of the robot hand that is preset in the reference coordinate system and a position of the robot hand detected based on image data of the marker acquired by each of the remaining two imaging devices when measuring the measurement object by the one imaging device,
The robot hand position detection system according to claim 1 or 2, characterized in that the control device is provided with a correction unit that corrects the measurement results of the object to be measured acquired by the one imaging device based on the amount of deviation. A robot hand position detection system as described in any one of claims 1 to 3, characterized in that, of the three imaging devices, one imaging device used to measure the object to be measured is arbitrarily selected so that the amount of movement of the robot hand is minimized when the robot hand moves from a predetermined measurement position to the next predetermined measurement position.

Images