JP7065343B2 - Tool control methods, programs, tool control systems, and tools - Google Patents

Description

The present disclosure relates generally to tool control methods, programs, tool control systems, and tools, and more particularly to tool control methods, programs, tool control systems, and tools controlled by them.

Conventionally, there is a work management system that manages work using tools (see, for example, Patent Document 1). The work management system described in Patent Document 1 includes a tool and a work management device. Tools are used to perform work on the work object. The work management device includes a work information acquisition unit, a position information acquisition unit, a work target information acquisition unit, and an information management unit. The work information acquisition unit acquires work information regarding the content of the work performed on the work target from the tool used for performing the work on the work target. The position information acquisition unit acquires the position information of the place where the work was performed on the work target by using the tool. The work target information acquisition unit acquires work target information that identifies the work target based on the information read from the work target. The information management unit stores the work information, the position information, and the work target information in the storage unit in association with each other.

The position information acquisition unit acquires the position information of the work place based on the positioning data input from the GPS receiver that measures the current position based on the radio wave received from the GPS (Global Positioning System) satellite, for example.

Further, Patent Document 1 describes a positioning system that receives beacon radio waves radiated from a plurality of points on the ground and positions the current position.

Japanese Unexamined Patent Publication No. 2016-91316

In a system that positions positions by receiving radio waves, it is difficult to identify these work target locations when the positions of a plurality of work targets are close to each other.

The present disclosure has been made in view of the above reasons, and an object thereof is to provide a tool control method, a program, a tool control system, and a tool capable of improving the specific accuracy of a work target.

In the tool control method according to one aspect of the present disclosure, an image similar to a question image in which the image pickup unit of the tool captures a work target is searched from a set of search target images having a control value corresponding to each, and the search result is obtained. The control value corresponding to is set in the tool. The tool control method includes an extraction step and a search step. In the extraction step, question-side position data indicating the positional relationship between the question-side reference point and the question-side feature portion in the question-side image is extracted. In the search step, the question image is similar to the question image based on the comparison result between the question side position data and the search side position data indicating the positional relationship between the search side reference point and the search side feature portion in the search target image. Images are searched from the set of search target images. The work target is attached to the target location by the tool. The question-side feature portion exists in a portion corresponding to the target portion in the question image. The search-side feature portion exists in a portion of the search target image corresponding to the target location.

The program according to one aspect of the present disclosure causes a computer system to execute the tool control method.

The tool control system according to one aspect of the present disclosure searches for an image similar to a question image in which the image pickup unit of the tool captures a work target from a set of search target images to which a control value corresponds to each, and the search result. The control value corresponding to is set in the tool. The tool control system includes an extraction unit and a search unit. The extraction unit extracts question-side position data indicating the positional relationship between the question-side reference point and the question-side feature in the question image. The search unit resembles the question image based on a comparison result between the question side position data and the search side position data indicating the positional relationship between the search side reference point and the search side feature unit in the search target image. Images are searched from the set of search target images. The work target is attached to the target location by the tool. The question-side feature portion exists in a portion corresponding to the target portion in the question image. The search-side feature portion exists in a portion of the search target image corresponding to the target location.

The tool according to one aspect of the present disclosure is controlled by the tool control system and has the image pickup unit that images the work object.

The tool control method, program, tool control system, and tool of the present disclosure have an effect that the accuracy of specifying a work target can be improved.

FIG. 1 is a block diagram of a tool control system according to an embodiment of the present disclosure. FIG. 2A is an external perspective view of the tool according to the embodiment of the present disclosure. FIG. 2B is an external perspective view of the same tool from another direction. FIG. 3 is a flowchart of the tool control method according to the embodiment of the present disclosure. FIG. 4 is a schematic diagram of the question image. FIG. 5A is a schematic diagram of the first search target image. FIG. 5B is a schematic diagram of the second search target image. FIG. 6 is a schematic diagram of another question image. FIG. 7 is a schematic diagram of yet another question image. FIG. 8 is a block diagram of a tool control system according to a first modification of the embodiment of the present disclosure. FIG. 9 is a flowchart of the tool control method according to the first modification of the embodiment of the present disclosure. FIG. 10 is a block diagram of a tool control system according to a second modification of the embodiment of the present disclosure. FIG. 11 is a flowchart of the tool control method according to the second modification of the embodiment of the present disclosure. FIG. 12 is an explanatory diagram for explaining a common area. FIG. 13 is a flowchart of the tool control method according to the third modification of the embodiment of the present disclosure. FIG. 14A is an explanatory diagram for explaining another common area. FIG. 14B is an explanatory diagram for explaining a search target area. FIG. 14C is an explanatory diagram for explaining another search target area.

Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. However, the embodiments described below are merely one of the various embodiments of the present disclosure. The following embodiments can be variously modified according to the design and the like as long as the object of the present disclosure can be achieved.

Embodiment 1
(1) Overview A block diagram of the tool control system 1 of the present embodiment is shown in FIG. The tool control system 1 of the present embodiment is used, for example, in an assembly line for assembling products in a factory. In the present embodiment, in the assembly line, there are a plurality of tightening target points for one product, and the operator uses the tool 2 to tighten parts (for example, for example, each of the plurality of tightening target points in the same work place. , Bolts, nuts, etc.) are supposed to be installed. The “tightening target location” is a portion around the screw hole including the screw hole to which the tightening component is attached. In this embodiment, the case where the tightening part is the work target of the tool 2 will be described as an example. The tool control system 1 of the present embodiment is configured to specify a work target in which the tool 2 is set among a plurality of work targets. "The tool 2 is set" indicates a state in which the tool 2 is prepared so that the work can be performed on the work target. The "prepared state" here includes not only a state in which the tool 2 hits the work target but also a state in which the tool 2 is about to hit the work target. That is, in the state where the tool 2 is set on the work target, the tool 2 may hit the work target or may be separated from the work target. The usage of the tool control system 1 is not limited to the above assembly line, and may be other usage.

In the tool control system 1 and the tool control method of the present embodiment, an image similar to a question image in which the image pickup unit 26 of the tool 2 captures a work target (tightening component) is searched from a set of search target images, and the search is performed. The tool 2 is controlled according to the result.

The tool control system 1 of the present embodiment includes a processing device 4. The processing device 4 is configured to be able to communicate with the tool 2. The tool 2 includes an image pickup unit 26 that captures an image of a set work target. The processing device 4 includes a search unit 52 that searches an image similar to an image (question image) captured by the image pickup unit 26 from a set of search target images. The processing device 4 outputs the target torque value (control value) corresponding to the searched search target image to the tool 2. The tool 2 operates so that the tightening torque becomes the target torque value. That is, in the tool control system 1 of the present embodiment, the work target of the tool 2 is specified by searching for a search target image similar to the question image captured by the image pickup unit 26 of the tool 2. Then, the tool control system 1 controls the tool 2 so that the torque set value of the tool 2 becomes the target torque value corresponding to the searched search target image.

(2) Configuration The detailed configuration of the tool control system 1 of the present embodiment will be described below with reference to FIG.

(2.1) Tool First, the configuration of the tool 2 will be described. The tool 2 is, for example, an electric impact wrench (see FIGS. 2A and 2B), and can perform tightening work for attaching tightening parts to a work target. The tool 2 is not limited to the impact wrench, and may be another electric tool such as an impact wrench. Further, the tool 2 is not limited to a power tool, but may be an air tool or the like.

The tool 2 has a drive unit 24, a control unit 3, an image pickup unit 26, a communication unit 27, and a battery pack 201.

As shown in FIGS. 2A and 2B, the body 20 of the tool 2 is detachably attached with a tubular body portion 21, a grip 22 protruding radially from the peripheral surface of the body portion 21, and a battery pack 201. It has a mounting portion 23 and.

The drive unit 24 is housed in the body unit 21. The drive unit 24 has a motor and is configured to rotate by using the electric power supplied from the battery pack 201, which is a power source, as a power source. The output shaft 241 protrudes from one end side of the body portion 21 in the axial direction (see FIGS. 2A and 2B). The output shaft 241 is configured to rotate by the rotational operation of the drive unit 24. A cylindrical socket 242 for tightening or loosening tightening parts (bolts, nuts, etc.) is detachably attached to the output shaft 241. The size of the socket 242 attached to the output shaft 241 is appropriately selected by the operator according to the size of the tightening component. The tool 2 can perform operations such as tightening or loosening the tightening parts by rotating the output shaft 241 by the rotational operation of the drive unit 24.

Further, a socket anvil can be detachably attached to the output shaft 241 instead of the socket 242, and a bit (for example, a driver bit, a drill bit, etc.) can be attached via the socket anvil.

The tool 2 of the present embodiment further includes an impact mechanism 25. The impact mechanism 25 is configured to apply a striking force in the rotational direction of the output shaft 241 when the tightening torque (working value) exceeds a predetermined level. This makes it possible to apply a larger tightening torque to the tightening parts.

The grip 22 is a portion to be gripped by an operator when performing work, and is provided with a trigger switch 221 and a forward / reverse changeover switch 222. The trigger switch 221 is a switch for controlling the on / off of the rotation operation of the drive unit 24, and the rotation speed of the drive unit 24 can be adjusted according to the pull-in amount. The forward / reverse changeover switch 222 is a switch that switches the rotation direction of the output shaft 241 between forward rotation and reverse rotation. A mounting portion 23 is provided at an end portion of the grip 22 opposite to the body portion 21.

The mounting portion 23 is formed in a flat rectangular body shape, and the battery pack 201 is detachably mounted on one surface opposite to the grip 22. The battery pack 201 has a resin case 202 (see FIGS. 2A and 2B) formed in a rectangular shape, and a rechargeable battery (for example, a lithium ion battery) is housed inside the case 202. The battery pack 201 supplies electric power to the drive unit 24, the control unit 3, the image pickup unit 26, the communication unit 27, and the like.

Further, the mounting portion 23 is provided with an operation panel 231. The operation panel 231 is provided with, for example, a plurality of pushbutton switches 232 and a plurality of LEDs 233 (Light Emitting Diodes), and can perform various settings, status confirmation, and the like of the tool 2. By operating the operation panel 231 (push button switch 232), for example, the operator can change the operation mode of the tool 2, check the remaining capacity of the battery pack 201, and the like. Further, the mounting unit 23 is provided with a light emitting unit 234. The light emitting unit 234 is composed of, for example, an LED. The light emitting unit 234 is arranged so as to irradiate the work target with light during work. The light emitting unit 234 can be turned on / off by operating the operation panel 231. Further, the light emitting unit 234 may be configured to light up when the trigger switch 221 is turned on.

The communication unit 27 is a communication module capable of wireless communication such as Wi-Fi (registered trademark), and is housed in the body 20. The communication unit 27 transmits and receives information to and from the processing device 4. The communication unit 27 may be a communication module compatible with wired communication.

Further, the control unit 3 is housed in the mounting unit 23. The control unit 3 includes, for example, a microcomputer having a processor and a memory. The control unit 3 realizes the functions of the drive control unit 31, the image pickup control unit 32, the extraction unit 33, the notification control unit 34, the determination unit 35, and the like by executing the program stored in the memory by the processor. The program executed by the processor is stored in the memory of the microcomputer in advance, but may be recorded in a recording medium such as a memory card and provided, or may be provided through a telecommunication line. If the operation input to the trigger switch 221 or the operation panel 231 is not performed for a certain period of time, the control unit 3 goes into a sleep state. The control unit 3 is activated when an operation input is made to the trigger switch 221 or the operation panel 231 during the sleep state.

The drive control unit 31 is configured to control the drive unit 24. Specifically, the drive control unit 31 rotates the drive unit 24 in the rotation direction set by the forward / reverse changeover switch 222 at a rotation speed based on the pull-in amount of the trigger switch 221.

Further, the drive control unit 31 is configured to control the drive unit 24 so that the tightening torque becomes a torque set value (working set value). The drive control unit 31 acquires a target torque value from the processing device 4 via the communication unit 27, and sets the acquired target torque value as the torque set value. Further, the drive control unit 31 has a torque estimation function for estimating the magnitude of the tightening torque. Until the estimated value of the tightening torque reaches the seating determination level, the drive control unit 31 has a large tightening torque based on the rotation speed of the drive unit 24 (motor) during the impact of the impact mechanism 25, changes in the amount of rotation, and the like. Estimate the torque. When the estimated value of the tightening torque reaches the seating determination level, the drive control unit 31 estimates the magnitude of the tightening torque based on the number of hits of the impact mechanism 25. When the number of hits of the impact mechanism 25 reaches the threshold number based on the torque set value, the drive control unit 31 determines that the tightening torque has reached the torque set value and stops the motor. As a result, the tightening torque when mounting the tightening component becomes the torque set value.

The tool 2 may include a torque sensor for measuring the tightening torque. In this case, the drive control unit 31 controls the drive unit 24 so that the tightening torque measured by the torque sensor becomes the torque set value.

The image pickup control unit 32 is configured to control the image pickup unit 26.

The image pickup unit 26 is composed of, for example, a camera having an image pickup element and a lens, and is housed in a body portion 21 of the body 20. The image pickup unit 26 is arranged so as to take an image of a work target during work. In the present embodiment, the imaging unit 26 is arranged within a predetermined range from the output shaft 241 along the output shaft 241 so as to image the tip end side of the output shaft 241. Further, the image pickup unit is provided so that the socket 242 attached to the output shaft 241 fits within the image pickup range. The image pickup unit 26 is fixed to the body 20 of the tool 2. Therefore, the tip end portion of the output shaft 241 is located at a predetermined position on the captured image (question image). Further, the imaging unit 26 is configured to continuously perform imaging while the control unit 3 is activated, and generates continuous captured images in a time series in a moving image format and outputs them to the extraction unit 33.

The extraction unit 33 extracts the question-side position data indicating the positional relationship between the question-side reference point and the question-side feature in the question image. The extraction unit 33 extracts the question side position data in the question image by performing image processing on the image (question image) captured by the image pickup unit 26.

The question-side reference point is a predetermined reference point in the question image, and is a position corresponding to a part of the tool 2. In the present embodiment, the reference point on the question side is a position corresponding to the tip of the output shaft 241 of the tool 2. Therefore, when the tool 2 is set as the work target, the question reference point corresponds to the position of the tightening part or the screw hole in the question image. As described above, since the image pickup unit 26 is fixed to the body 20 of the tool 2, the question side reference point is a predetermined position in the image (question image) captured by the image pickup unit 26.

The question-side feature portion is an image local feature location (point) in the question image. The local featured part of the image is a point, an edge, or the like that stands out in the image due to unevenness, a pattern, a mark, a character, or the like of the work target. As a method for extracting an image local feature portion (question-side feature portion) and a feature amount thereof from an image, for example, there is an ORB (Oriented FAST and Rotated BRIEF) or the like. When the work target is normally imaged, a plurality of (for example, several hundred) image local feature points (question side feature portions) are extracted from one question image.

The extraction unit 33 extracts the question-side reference point and the question-side feature unit from the question image, and extracts the question-side position data which is the data indicating the positional relationship between the question-side reference point and the question-side feature unit. The question-side position data includes data indicating the distance between the question-side reference point and the question-side feature portion (question-side distance data). As described above, a plurality of question-side feature portions are extracted from one question image. Therefore, the extraction unit 33 extracts a plurality of question-side distance data from one question image. That is, the question-side position data includes a plurality of question-side distance data. Further, the extraction unit 33 extracts the feature amount of each of the plurality of question-side feature units from the question image in association with the question-side feature unit. That is, the extraction unit 33 extracts the question side position data including the feature amount corresponding to each of the plurality of question side feature units and the question side distance data from the question image. The extraction unit 33 transmits the extracted question-side position data to the processing device 4 via the communication unit 27.

As will be described in detail later, the processing device 4 searches for an image similar to the question image from a plurality of search target images based on the question side position data transmitted from the tool 2, and a target corresponding to the searched search target image. The torque value is output to the tool 2. The drive control unit 31 sets the target torque value output from the processing device 4 to the torque set value, and controls the drive unit 24 so that the tightening torque becomes the torque set value (target torque value).

The notification control unit 34 is configured to control the notification unit 211 provided on the tool 2. The notification unit 211 is composed of, for example, an LED. The notification unit 211 is provided at an end portion of the body unit 21 of the body 20 opposite to the output shaft 241 so that the operator can easily see the notification unit 211 during work (see FIG. 2B). When the notification control unit 34 receives the target torque value from the processing device 4, the notification control unit 34 turns on the notification unit 211. By visually observing that the notification unit 211 is lit, the operator can recognize that the torque set value is set and that normal tightening work is possible.

The determination unit 35 is configured to determine whether or not the tightening torque is normal when the tightening component is attached to the tightening target portion. When the drive control unit 31 stops the drive unit 24 when the number of hits of the impact mechanism 25 reaches the threshold number, the determination unit 35 determines that the tightening torque is normal. Further, when the drive control unit 31 stops the drive unit 24 by turning off the trigger switch 221 before the number of hits of the impact mechanism 25 reaches the threshold value, the determination unit 35 does not have a tightening torque. Judged as sufficient (not normal). The determination unit 35 transmits the determination result to the processing device 4 via the communication unit 27. As a result, it is possible to control whether or not the tightening operation using the tool 2 is normally performed in the processing device 4.

When the tool 2 is provided with a torque sensor for measuring the tightening torque, the determination unit 35 compares the measurement result of the torque sensor with the target torque value to determine whether the tightening torque is normal or not. It may be configured to determine whether or not. When the measurement result of the torque sensor is within a predetermined range based on the target torque value, the determination unit 35 determines that the tightening torque is normal. Further, when the measurement result of the torque sensor is out of the predetermined range based on the target torque value, the determination unit 35 determines that the tightening torque is insufficient (not normal).

(2.2) Processing device The processing device 4 is, for example, a server, and includes a communication unit 41, a control unit 5, and a storage unit 6.

The communication unit 41 is a communication module capable of wireless communication such as Wi-Fi (registered trademark). The communication unit 41 transmits and receives information to and from the communication unit 27 of the tool 2. The communication unit 41 may be a communication module compatible with wired communication. When the communication unit 27 of the tool 2 supports only wireless communication, the communication unit 41 is configured to communicate with the communication unit 27 via a communication device that performs mutual conversion between wireless communication and wired communication. You may be.

The storage unit 6 is composed of a semiconductor memory such as a flash memory, and has an image storage unit 61, a position data storage unit 62, and a target torque value storage unit 63. In the present embodiment, the image storage unit 61, the position data storage unit 62, and the target torque value storage unit 63 are composed of one memory, but are composed of a plurality of memories, and each storage unit is composed of a plurality of memories. May consist of separate memories. The storage unit 6 is not limited to the semiconductor memory, but may be a memory card, a hard disk, or the like.

The image storage unit 61 stores a plurality of search target images. The search target image is a still image showing the work target.

The position data storage unit 62 stores a plurality of search-side position data corresponding to each of the plurality of search target images. The search side position data is data showing the positional relationship between the search side reference point and the search side feature portion in the search target image.

The search side reference point is a predetermined reference point in the search target image. In this embodiment, it corresponds to the position of the tightening part or the screw hole in the image to be searched.

The search-side feature portion is an image local feature location (point) in the search target image. The local featured part of the image is a point, an edge, or the like that stands out in the image due to unevenness, a pattern, a mark, a character, or the like of the work target. As a method of extracting an image local feature portion (question side feature portion) and a feature amount thereof from an image, for example, there is an ORB or the like. A plurality of (for example, several hundred) image local feature points (question-side feature portions) are extracted from one search target image.

The target torque value storage unit 63 stores a plurality of target torque values (control values) corresponding to a plurality of search target images on a one-to-one basis.

Extraction of the search side reference point and the search side feature unit from the plurality of search target images stored in the image storage unit 61 is performed by the extraction unit 51 possessed by the control unit 5. The control unit 5 includes, for example, a microcomputer having a processor and a memory. The control unit 5 realizes the functions of the extraction unit 51, the search unit 52, the torque selection unit 53, and the like by executing the program stored in the memory by the processor. The program executed by the processor is stored in the memory of the microcomputer in advance, but may be recorded in a recording medium such as a memory card and provided, or may be provided through a telecommunication line.

The extraction unit 51 extracts the search side reference point and the search side feature unit for each of the plurality of search target images, and is data indicating the positional relationship between the search side reference point and the search side feature unit. Extract position data. The search-side position data includes search-side distance data indicating the distance between the search-side reference point and the search-side feature unit. As described above, a plurality of search-side feature portions are extracted from one search target image. Therefore, the extraction unit 51 extracts a plurality of search side distance data from one search target image. That is, the search side position data includes a plurality of search side distance data. Further, the extraction unit 51 extracts the feature amounts of each of the plurality of search-side feature units from the search target image in association with the search-side feature unit. That is, the extraction unit 51 extracts the search side position data including the feature amount corresponding to each of the plurality of search side feature units and the search side distance data from the search target image. The extraction unit 51 stores a plurality of search-side position data extracted from each of the plurality of search target images in the position data storage unit 62 in association with the search target image.

The search unit 52 searches for an image similar to the question image based on the comparison result between the question side position data and the search side position data indicating the positional relationship between the search side reference point and the search side feature unit in the search target image. Search from a set of target images. Specifically, the search unit 52 compares the question-side position data transmitted from the tool 2 with the plurality of search-side position data stored in the position data storage unit 62 to obtain an image similar to the question image. Is searched from the set of search target images. The search unit 52 compares the question-side position data with each of the plurality of search-side position data, and obtains the number of matching points with the question-side position data for each of the plurality of search-side position data. The number of matching points is when the feature amount and the search side distance data of the search side feature part in the search side position data match or are close to the feature amount and the question side distance data of the question side feature part in the question side position data. It is a score to be added to. Nearest neighbor search is a method for finding approximate features. In the nearest neighbor search, an approximation method such as full search or FLAN (Fast Library for Approximate Nearest Neighbors) is used. The search unit 52 searches for the search side position data having the highest number of matching points from the plurality of search side position data. The search unit 52 determines that the search target image corresponding to the searched side position data is an image similar to the question image.

The torque selection unit 53 refers to the target torque value storage unit 63, and selects the target torque value corresponding to the search target image searched by the search unit 52. The torque selection unit 53 transmits the selected target torque value to the tool 2 via the communication unit 41. In the tool 2, the drive control unit 31 sets the target torque value transmitted from the processing device 4 as the torque set value.

The processing device 4 may be realized by cloud computing, and the extraction unit 51, the search unit 52, the torque selection unit 53, the image storage unit 61, the position data storage unit 62, and the target torque value storage unit 63. However, it may be distributed in a plurality of devices.

(3) Operation Example Next, an operation example of the tool control system 1 of the present embodiment will be described with reference to FIG. The tool control method by the tool control system 1 includes an imaging step S1, an extraction step S2, a search step S3, a control value selection step S4, and a control value setting step S5.

In the imaging step S1, the imaging unit 26 images the work target and generates a question image.

In the extraction step S2, the question side position data indicating the positional relationship between the question side reference point and the question side feature portion in the question image is extracted. Here, the extraction unit 33 extracts the question side position data from the question image. FIG. 4 shows an example of the question image P11. Question image P11 shows two tightening parts B1 and B2. The position of the tightening component B1 near the center in the question image P11 is the question side reference point C11. Further, in FIG. 4, the feature portions (question side feature portions) T1, T2, ..., Tn are schematically shown. Of the plurality of question-side feature parts, the question-side feature parts having the same feature amount are designated by the same reference numerals. The extraction unit 33 extracts the question side reference point C11 and the question side feature units T1, T2, ..., Tn from the question image P11. The extraction unit 33 extracts the question-side position data including the question-side distance data indicating the distance between the question-side reference point C11 and each of the question-side feature units T1, T2, ..., Tn. The extraction unit 33 transmits the extracted question-side position data to the processing device 4.

In the search step S3, an image similar to the question image is searched based on the comparison result between the question side position data and the search side position data indicating the positional relationship between the search side reference point and the search side feature portion in the search target image. Search from a set of target images. Here, the search unit 52 searches for an image similar to the question image from the set of search target images by comparing the question side position data with the plurality of search side position data. FIG. 5A shows an example of the first search target image P21 included in the plurality of search target images, and FIG. 5B shows an example of the second search target image P22 included in the plurality of search target images. Two tightening parts B1 and B2 are shown in the first search target image P21 and the second search target image P22. The first search target image P21 is a search target image in which the position of the tightening component B1 is set as the search side reference point C21, and a target torque value corresponding to the tightening component B1 is associated with the first search target image P21. The second search target image P22 is a search target image in which the position of the tightening component B2 is set as the search side reference point C22, and a target torque value corresponding to the tightening component B2 is associated with the second search target image P22. Further, in FIGS. 5A and 5B, the feature portions (search side feature portions) T1, T2, ..., Tn are schematically shown.

The position data storage unit 62 stores the search-side position data extracted from each of the plurality of search target images (including the first search target image P21 and the second search target image P22) by the extraction unit 51. That is, the position data storage unit 62 includes the search side distance data indicating the distance between the search side reference point C21 in the first search target image P21 and each of the search side feature units T1, T2, ..., Tn. Side position data is stored. Further, the position data storage unit 62 includes a search side distance data indicating a distance between the search side reference point C22 in the second search target image P22 and each of the search side feature units T1, T2, ..., Tn. Side position data is stored.

The search unit 52 compares the question-side position data with the plurality of search-side position data. Specifically, the search unit 52 obtains the number of matching points with the question-side position data for each of the plurality of search-side position data. As shown in FIGS. 5A and 5B, since the distance between the tightening component B1 and the tightening component B2 is relatively short, the first search target image P21 and the second search target image P22 have a common search side. The feature part is included. However, the search side reference point C21 of the first search target image P21 is the position of the tightening part B1, while the search side reference point C22 of the second search target image P22 is the position of the tightening part B2. Therefore, the search side distance data of the first search target image P21 and the search side distance data of the second search target image P22 are different. As shown in FIG. 4, the question-side reference point C11 of the question image P11 is the position of the tightening component B1. Therefore, the number of matching points between the search-side position data and the question-side position data in the first search target image P21 is higher than the number of matching points between the search-side position data and the question-side position data in the second search-target image P22. Here, it is assumed that the number of matching points between the search side position data and the question side position data in the first search target image P21 is the highest among the plurality of search target images. The search unit 52 determines that the first search target image P21 is an image similar to the question image P11.

In the control value selection step S4, the torque selection unit 53 selects a target torque value (control value) corresponding to the search target image (first search target image P21) searched by the search unit 52 from the target torque value storage unit 63. do. The torque selection unit 53 transmits the selected target torque value (control value) to the tool 2.

In the control value setting step S5, the drive control unit 31 of the tool 2 sets the target torque value (control value) transmitted from the processing device 4 as the torque set value. As a result, the tightening torque becomes a target torque value corresponding to the image (questionnaire image) captured by the image pickup unit 26 of the tool 2.

As described above, in the tool control method of the present embodiment, in the search step S3, the question side position data extracted in the extraction step S2 is compared with the search side position data, so that the search target image similar to the question image is obtained. You are searching for. Therefore, even when a plurality of work targets (tightening parts) are shown in the question image, the work target (tightening parts) in which the tool 2 is set can be specified, and the specified work target can be specified. Work can be performed with the control value (target torque value).

Here, the question image captured by the image pickup unit 26 is generated so that the grip 22 (see FIG. 2) side faces the image pickup unit 26. Therefore, when the direction of the grip 22 changes, the position of the question-side reference point does not change in the question image, but the direction of the question-side feature portion with respect to the question-side reference point changes (see FIG. 6). FIG. 6 is an example of the question image P11a taken by rotating the direction of the grip 22 by 180 degrees with respect to the time of taking the question image P11 (see FIG. 4). That is, the question image P11a in FIG. 6 is an image obtained by rotating the question image P11 in FIG. 4 by 180 degrees. Therefore, the orientation of the question image and the search target image may not match (see FIGS. 5A and 6).

In the present embodiment, the question side position data includes the question side distance data. The question-side distance data shows the distance between the question-side reference point and the question-side feature. Therefore, the question-side distance data is constant regardless of the orientation of the question image. Therefore, even if the image captured by the imaging unit 26 is the question image P11a whose orientation is different from that of the first search target image P21, the search unit 52 is an image in which the first search target image P21 is similar to the question image P11a. Can be judged.

Further, in the present embodiment, the tool 2 includes an extraction unit 33 for extracting the question side position data from the question image, and the question side position data is transmitted from the tool 2 to the processing device 4. That is, the question image itself is not transmitted to the processing device 4. As a result, the communication capacity between the tool 2 and the processing device 4 can be reduced.

(4) Modification example The modification of the tool control system 1 and the tool control method will be described below. The modifications described below can be applied in combination as appropriate.

(4.1) First Modification Example The data included in the question-side position data is not limited to the question-side distance data, but may include question-side direction data. The question-side direction data is data indicating the direction of the question-side feature portion with respect to the question-side reference point. The question-side direction data is shown, for example, at an angle within the range of 360 degrees centered on the question-side reference point and 0 degrees in the upward direction on the question image.

The extraction unit 33 extracts the question side position data including the feature amount corresponding to each of the plurality of question side feature units, the question side distance data, and the question side direction data from the question image.

Further, when the question side position data includes the question side direction data, the search side position data also includes the search side direction data. The search-side direction data is data indicating the direction of the search-side feature unit with respect to the search-side reference point. The search-side direction data is shown, for example, at an angle within a range of 360 degrees with the search-side reference point as the center and the upward direction as 0 degrees on the search target image.

The search unit 52 obtains the number of points of agreement with the question-side position data for each of the plurality of search-side position data.

The search process when the question side position data and the search side position data include the question side distance data and the search side distance data will be described with reference to FIGS. 5A and 5B.

For example, as shown in FIGS. 5A and 5B, there may be two search-side feature portions T1 having the same feature amount at the same distance for each of the two tightening parts B1 and B2. When the question side position data and the search side position data do not include the question side direction data and the search side direction data, respectively, both the first search target image P21 and the second search target image P22 have two search sides. The feature portion T1 is counted as the number of matching points. However, in this modification, since the question-side position data and the search-side position data include the question-side direction data and the search-side direction data, respectively, in the second search target image P22, the two search-side feature portions T1 Is not counted as a match score. This improves the search accuracy of the search target image similar to the question image.

Here, when the orientation of the grip 22 changes, the orientation of the question image changes, so that the question-side direction data also changes. Further, when the question image is captured with the image pickup unit 26 tilted with respect to the work target, the work target or the like on the question image P11b is tilted as shown in FIG. 7, and accurate question side distance data is extracted. Becomes difficult. In the question image P11b of FIG. 7, the direction of the grip 22 is rotated 180 degrees with respect to the time of imaging of the question image P11 (see FIG. 4), and the tool 2 is tilted toward the grip 22 with respect to the vertical direction of the work target. It is an image taken.

As shown in FIG. 8, the tool control system 1A of this modification further includes a correction unit 36. The same reference numerals are given to the same configurations as those in the above embodiment, and the description thereof will be omitted.

The correction unit 36 is included in the control unit 3 of the tool 2. The control unit 3 realizes the function of the correction unit 36 when the processor executes a program stored in the memory.

The correction unit 36 performs correction processing on the question image captured by the image pickup unit 26. The correction unit 36 corrects the question image by rotating it so that the question image is in the reference direction. The reference direction is a direction corresponding to the direction of the image to be searched. Further, the correction unit 36 corrects the inclination of the question image so that the question image becomes an image captured from the vertical direction of the work target. The correction unit 36 corrects the rotation and inclination of the question image by using, for example, optical flow calculation. By the correction process by the correction unit 36, for example, the question image P11b in FIG. 7 is corrected as in the question image P11 in FIG. The tool 2 may include a gyro sensor (accelerometer) or the like, and the correction unit 36 may correct the question image using the detection result of the gyro sensor.

As a result, the extraction unit 33 can more accurately extract the question-side direction data and the question-side distance data from the corrected question image. Therefore, the search accuracy of the search target image similar to the question image is improved.

Further, as shown in FIG. 9, the tool control method by the tool control system 1A of this modification includes the imaging step S1, the correction step S11, the extraction step S2, the search step S3, the control value selection step S4, and the control value setting. Step S5 is included. The same steps as those in the above embodiment are designated by the same reference numerals and the description thereof will be omitted.

In the correction step S11, the correction unit 36 makes a correction so as to rotate the question image. Further, in the correction step S11, the correction unit 36 corrects the inclination of the question image. That is, in the correction step S11, the correction unit 36 corrects the rotation and the inclination of the question image captured by the image pickup unit 26. In the extraction step S2, the question side position data is extracted from the corrected question image.

(4.2) Second Modification Example The tool control system 1B of this modification further includes an angle of view changing portion 37 as shown in FIG. The angle of view changing unit 37 is included in the control unit 3 of the tool 2. The control unit 3 realizes the function of the angle of view changing unit 37 by executing a program stored in the memory by the processor.

The angle of view changing unit 37 is configured to change the size of the angle of view of the question image. In this modification, the image pickup unit 26 has a zoom function, and the size of the angle of view can be adjusted. The angle of view changing unit 37 changes the size of the angle of view of the question image based on the number of feature points, which is the number of feature units on the question side extracted from the question image by the extraction unit 33. Specifically, the angle of view changing unit 37 is an imaging unit 26 so that the angle of view of the question image becomes larger when the number of feature points of the question side feature unit extracted from the question image by the extraction unit 33 is less than the lower limit value. Adjust the size of the angle of view. The extraction unit 33 extracts the question-side feature unit again from the question image after the angle of view is changed. If the number of feature points of the question feature unit extracted from the question image by the extraction unit 33 is equal to or greater than the lower limit, the question side position data extracted by the extraction unit 33 is transmitted to the processing device 4.

As a result, the search unit 52 can search for a search target image similar to the question image by using the question side position data corresponding to more question side feature units. Therefore, the search accuracy of the search target image similar to the question image is improved.

Further, as shown in FIG. 11, the tool control method of this modification includes an imaging step S1, an extraction step S2, a feature score comparison step S21, an angle of view changing step S22, a search step S3, a control value selection step S4, and a control value selection step S4. The control value setting step S5 is included. The same steps as those in the above embodiment are designated by the same reference numerals and the description thereof will be omitted.

In the feature score comparison step S21, the angle of view changing section 37 compares the feature score of the question-side feature section extracted from the question image by the extraction section 33 with the lower limit value. When the number of feature points is less than the lower limit (S21: No), the angle of view changing unit 37 performs the angle of view changing step S22.

In the angle of view change step S22, the size of the angle of view of the question image is changed. Here, the angle of view changing unit 37 adjusts the size of the angle of view of the imaging unit 26 so that the angle of view of the question image becomes large. Then, in the extraction step S2, the extraction unit 33 extracts the question side feature unit again from the question image after the angle of view is changed. When the number of feature points is equal to or greater than the lower limit, the question-side position data extracted by the extraction unit 33 is transmitted to the processing device 4, and the search step S3 is performed.

In the above, the size of the angle of view of the imaging unit 26 is adjusted so that the angle of view of the question image becomes large when the number of feature points is less than the lower limit, but the present invention is not limited to this. The angle of view changing unit 37 compares the number of feature points with the upper limit value, and if the number of feature points is larger than the upper limit value, even if the size of the angle of view of the image pickup unit 26 is adjusted so that the angle of view of the question image becomes smaller. good. As a result, the number of feature points is limited, so that the processing load of the search unit 52 in the search step S3 can be reduced, and the search time can be shortened. As a method of reducing the angle of view of the question image, the zoom function of the imaging unit 26 may be used, or the question image may be trimmed.

Further, the angle of view changing unit 37 may be configured to compare the number of feature points with the upper limit value and the lower limit value and change the angle of view of the question image based on the comparison result.

(4.3) Third Modification Example In the tool control system 1 of this modification, the extraction unit 51 of the processing device 4 has a function as an exclusion unit.

The extraction unit 51 (exclusion unit) is a search side included in the common area for at least one duplicate image among the plurality of duplicate images in a plurality of duplicate images including the common area in the set of search target images. Exclude the feature part. The common area is an area that is common (overlapped) to a plurality of search target images. The duplicate image is a search target image in which a common area is shown.

When the positions of a plurality of work targets are close to each other, a common area is likely to occur. For example, as shown in FIG. 12, when the tightening parts B1 and the tightening parts B2 are close to each other, the common area A1 is captured in the first search target image P21 and the second search target image P22. It becomes. FIG. 12 is an external view of the product M1 conceptually showing the range of the first search target image P21 and the range of the second search target image P22. In FIG. 12, the area with dot hatching is the common area A1. Further, in FIG. 12, the feature portion (search side feature portion) is schematically shown by T1, T2, ..., Tn.

The extraction unit 51 excludes the search-side feature unit (search-side feature unit T1, T1, T2, T3, T4, Tn in FIG. 12) included in the common area A1 from the extraction target. That is, the search-side feature portion included in the common area A1 is excluded from each of the first search target image P21 and the second search target image P22.

As a result, in the plurality of duplicate images, confusion of the search-side feature portion included in the common area A1 is suppressed, and the search accuracy of the search target image similar to the question image is improved.

Further, as shown in FIG. 13, the tool control method of this modification includes the exclusion step S6, the extraction step S7, the storage step S8, the imaging step S1, the extraction step S2, the search step S3, the control value selection step S4, and the control value selection step S4. The control value setting step S5 is included. The same steps as those in the above embodiment are designated by the same reference numerals and the description thereof will be omitted.

In the exclusion step S6, in a plurality of duplicate images including a common area in the set of search target images, the search side feature portion included in the common area is excluded for at least one of the plurality of duplicate images. do. Here, the extraction unit 51 (exclusion unit) excludes the search-side feature unit included in the common area A1 from the duplicate image.

In the extraction step S7, the extraction unit 51 extracts the search side position data from each of the plurality of search target images including the duplicate image.

In the storage step S8, the search-side position data extracted by the extraction unit 51 is associated with the search target image and stored in the position data storage unit 62.

In the above, the search-side feature portion included in the common area A1 is excluded from both the duplicate images (first search target image P21 and second search target image P22), but the present invention is not limited to this. The extraction unit 51 (exclusion unit) is a search side included in the common area for at least one duplicate image among the plurality of duplicate images in a plurality of duplicate images including the common area in the set of search target images. Any configuration may be used as long as the feature portion is excluded.

When a plurality of work targets are close to each other, all the areas may be common areas in the duplicate image. FIG. 14A is an external view of the product M2 conceptually showing the range of the five search target images P23 to P27. The search target image P23 is an image in which the tightening parts B3 and B7 are included and the position of the tightening part B3 is set as the search side reference point C23. The search target image P24 is an image in which the tightening parts B4 and B7 are included and the position of the tightening parts B4 is set as the search side reference point C24. The search target image P25 is an image in which the tightening parts B5 and B7 are included and the position of the tightening parts B5 is set as the search side reference point C25. The search target image P26 is an image in which the tightening parts B6 and B7 are included and the position of the tightening parts B6 is set as the search side reference point C26. The search target image P27 is an image in which the tightening parts B3 to B7 are included and the position of the tightening parts B7 is set as the search side reference point C27.

Some areas of the search target images P23 to P26 are common areas. The entire area of the search target image P27 is a common area. Therefore, if the search-side feature portion is excluded from the common area of the search target image P27, the search-side feature portion included in the search target image P27 disappears. Therefore, the extraction unit 51 (exclusion unit) leaves only one duplicate image for the search-side feature unit included in the common area, and excludes it from the other duplicate images. FIG. 14B is a diagram conceptually showing the search target areas A23a to A27a including the search side feature portion in the search target images P23 to P27.

As shown in FIG. 14B, the entire area of the search target image P27 corresponds to the search target area A27a. That is, the search-side feature portion is not excluded from the search target image P27 in which the entire area is a common area. Further, the search target area A23a corresponding to the search target image P23 is an area in which the common area with the search target images P26 and P27 is omitted from the area of the search target image P23 and the common area with the search target image P24 is included. The search target area A24a corresponding to the search target image P24 is an area in which the common area with the search target images P23 and P27 is omitted from the search target image P24 area and the common area with the search target image P25 is included. The search target area A25a corresponding to the search target image P25 is an area in which the common area with the search target images P24 and P27 is omitted from the search target image P25 area and the common area with the search target image P26 is included. The search target area A26a corresponding to the search target image P26 is an area in which the common area with the search target images P25 and P27 is omitted from the area of the search target image P26 and the common area with the search target image P23 is included.

As a result, each of the search target images P23 to P27 can secure the search target areas A23a to A27a including the search side feature portion.

Further, the search target area including the search side feature portion may be determined by dividing the common area (see FIG. 14C). In FIG. 14C, in each of the search target images P23 to P27, the search target areas A23b to A27b including the search side feature portion are conceptually shown.

In the example shown in FIG. 14, the common area is equally divided by the number of overlapping images. In the search target areas A23b to A27b corresponding to the search target images P23 to P27, the common area among the areas of the search target images P23 to P27 is equally divided by the number of search target images (overlapping images) including the common area. It corresponds to the area partially omitted.

In the above, the common area is equally divided by the number of overlapping images, but the present invention is not limited to this. The ratio of dividing the common area may be determined based on the size (area) of the search target area, the number of search-side feature portions included, and the like.

(4.4) Other variants The other variants are listed below.

In the above-mentioned example, the tool 2 includes an extraction unit that extracts question-side position data from the question image, but the configuration is not limited to this. The question image may be transmitted from the tool 2 to the processing device 4, and the extraction unit 51 of the processing device 4 may be configured to extract the question side position data from the question image. This makes it possible to simplify the configuration of the tool 2.

Further, the tool 2 may include a search unit 52, a torque selection unit 53, a position data storage unit 62, and a target torque value storage unit 63. In this case, the tool 2 can search for a search target image similar to the question image and set a target torque value according to the search result as the torque set value.

Further, the same functions as those of the tool control systems 1, 1A and 1B of the embodiment and each modification may be embodied by a tool control method, a (computer) program, a non-temporary recording medium on which the program is recorded, or the like. .. The program is a program for causing a computer system to execute a tool control method according to an embodiment or each modification.

Further, the tool control systems 1, 1A, 1B include a computer system in the control unit 3, the control unit 5, and the like. The computer system mainly consists of a processor and a memory as hardware. By executing the program recorded in the memory of the computer system by the processor, the functions of the extraction unit 33, the correction unit 36, the angle of view changing unit 37 of the control unit 3, the extraction unit 51 of the control unit 5, the search unit 52, and the like are performed. Is realized. The program may be pre-recorded in the memory of the computer system, may be provided through a telecommunication line, and may be recorded on a non-temporary recording medium such as a memory card, optical disk, hard disk drive, etc. that can be read by the computer system. May be provided. The processor of a computer system is composed of one or more electronic circuits including a semiconductor integrated circuit (IC) or a large scale integrated circuit (LSI). A plurality of electronic circuits may be integrated on one chip, or may be distributed on a plurality of chips. A plurality of chips may be integrated in one device, or may be distributed in a plurality of devices.

(summary)
In the tool control method according to the first aspect, an image similar to the question image (P11, P11a, P11b) in which the image pickup unit (26) of the tool (2) captures the work target (B1 to B7) is searched for as a search target image. A search is performed from the set of (P21 to P27), and the tool (2) is controlled according to the search result. The tool control method includes an extraction step (S2) and a search step (S3). In the extraction step (S2), the question-side position data indicating the positional relationship between the question-side reference point (C11) and the question-side feature portions (T1 to Tn) in the question-side image (P11, P11a, P11b) is extracted. In the search step (S3), the search side position indicating the positional relationship between the question side position data, the search side reference points (C21 to C27) in the search target images (P21 to P27), and the search side feature units (T1 to Tn). Based on the comparison result with the data, an image similar to the question image (P11, P11a, P11b) is searched from the set of search target images (P21 to P27).

According to this aspect, in the search step (S3), using the question side position data extracted in the extraction step (S2), an image similar to the question image (P11, P11a, P11b) is searched for the search target image (P21 to P11b). Searching from the set of P27). Therefore, the search accuracy of the search target images (P21 to P27) similar to the question images (P11, P11a, P11b) can be improved, and the specific accuracy of the work target (B1 to B7) can be improved.

In the tool control method according to the second aspect, in the first aspect, the question side reference point (C11) is a position corresponding to a part of the tool (2).

According to this aspect, the position of the question side reference point (C11) is fixed in the question image (P11, P11a, P11b). Therefore, it becomes easy to specify the reference point (C11) on the question side.

In the tool control method according to the third aspect, in the first or second aspect, the question side position data indicates the distance between the question side reference point (C11) and the question side feature portion (T1 to Tn). Includes distance data. The search-side position data includes search-side distance data indicating the distance between the search-side reference points (C21 to C27) and the search-side feature units (T1 to Tn).

According to this aspect, since the question side distance data is constant regardless of the orientation of the question images (P11, P11a, P11b), the search target images (P21 to P27) similar to the question images (P11, P11a, P11b) It is possible to improve the search accuracy of the work target (B1 to B7) and improve the specific accuracy of the work target (B1 to B7).

In the tool control method according to the fourth aspect, in any one of the first to third aspects, the question side position data indicates the direction of the question side feature unit (T1 to Tn) with respect to the question side reference point (C11). Includes directional data. The search-side position data includes search-side direction data indicating the direction of the search-side feature units (T1 to Tn) with respect to the search-side reference points (C21 to C27).

According to this aspect, since the identification accuracy of the search side feature unit (T1 to Tn) corresponding to the question side feature unit (T1 to Tn) is improved, the search target image similar to the question image (P11, P11a, P11b) is improved. The search accuracy of (P21 to P27) can be improved, and the specific accuracy of the work target (B1 to B7) can be improved.

The tool control method according to the fifth aspect includes a correction step (S11) in which a correction is performed so as to rotate the question image (P11, P11a, P11b) in any one of the first to fourth aspects.

According to this aspect, since the deviation of the direction of the question image (P11, P11a, P11b) with respect to the reference direction can be corrected, the search target images (P21 to P27) similar to the question image (P11, P11a, P11b) can be corrected. It is possible to improve the search accuracy of the work target (B1 to B7) and improve the specific accuracy of the work target (B1 to B7).

The tool control method according to the sixth aspect includes an angle of view changing step (S22) for changing the size of the angle of view of the question image (P11, P11a, P11b) in any one of the first to fifth aspects.

According to this aspect, the search target images (P21 to P27) similar to the question images (P11, P11a, P11b) are obtained by using the question side position data corresponding to more question side feature units (T1 to Tn). Since the search can be performed, the search accuracy of the search target images (P21 to P27) similar to the question images (P11, P11a, P11b) can be improved, and the specific accuracy of the work target (B1 to B7) can be improved. Can be planned.

The tool control method according to the seventh aspect includes the exclusion step (S6) in any one of the first to sixth aspects. In the exclusion step (S6), in a plurality of duplicate images including the common area (A1) in the set of search target images (P21 to P27), it is common to at least one duplicate image among the plurality of duplicate images. The search side feature portion (T1 to Tn) included in the region (A1) is excluded.

According to this aspect, since the confusion of the search side feature portions (T1 to Tn) included in the common region (A1) is suppressed, the search target images (P21 to P27) similar to the question images (P11, P11a, P11b) are suppressed. ) Can be improved, and the specific accuracy of the work target (B1 to B7) can be improved.

The program according to the eighth aspect causes a computer system to execute the tool control method according to any one of the first to seventh aspects.

According to this aspect, in the search step (S3), using the question side position data extracted in the extraction step (S2), an image similar to the question image (P11, P11a, P11b) is searched for the search target image (P21 to P11b). Searching from the set of P27). Therefore, the search accuracy of the search target images (P21 to P27) similar to the question images (P11, P11a, P11b) can be improved, and the specific accuracy of the work target (B1 to B7) can be improved.

The tool control system (1,1A, 1B) according to the ninth aspect is similar to the question image (P11, P11a, P11b) in which the image pickup unit (26) of the tool (2) captures the work target (B1 to B7). The resulting image is searched from the set of search target images (P21 to P27), and the tool (2) is controlled according to the search result. The tool control system (1,1A, 1B) includes an extraction unit (33) and a search unit (52). The extraction unit (33) extracts question-side position data indicating the positional relationship between the question-side reference point (C11) and the question-side feature units (T1 to Tn) in the question-side image (P11, P11a, P11b). The search unit (52) is a search side position indicating the positional relationship between the question side position data, the search side reference points (C21 to C27) in the search target images (P21 to P27), and the search side feature units (T1 to Tn). Based on the comparison result with the data, an image similar to the question image (P11, P11a, P11b) is searched from the set of search target images (P21 to P27).

According to this aspect, the search unit (52) uses the question side position data extracted by the extraction unit (33) to search target images (P21 to P27) similar to the question images (P11, P11a, P11b). It is possible to improve the search accuracy of the work target (B1 to B7) and improve the specific accuracy of the work target (B1 to B7).

The tool (2) according to the tenth aspect is controlled by the tool control system (1,1A, 1B) of the ninth aspect, and has an image pickup unit (26) for imaging a work object (B1 to B7).

According to this aspect, in the tool control system (1,1A, 1B), the search accuracy of the search target images (P21 to P27) similar to the question images (P11, P11a, P11b) can be improved, and the work target can be improved. It is possible to improve the specific accuracy of (B1 to B7).

1,1A, 1B Tool control system 2 Tool 26 Imaging unit 33 Extraction unit 52 Search unit S2 Extraction step S3 Search step S6 Exclusion step S11 Correction step S22 Angle of view change step B1 to B7 Work target P11, P11a, P11b Question image P21 to P27 Search target image C11 Question side reference point T1 to Tn Question side feature part, Search side feature part C21 to C27 Search side reference point A1 Common area

Claims (11)

A tool that searches an image similar to a question image obtained by an image pickup unit of a tool from a set of search target images to which a control value corresponds to each, and sets a control value corresponding to the search result to the tool. It ’s a control method,
An extraction step for extracting question-side position data indicating the positional relationship between the question-side reference point and the question-side feature in the question image, and
Based on the comparison result between the question-side position data and the search-side position data indicating the positional relationship between the search-side reference point and the search-side feature in the search-target image, the search target is an image similar to the question-side image. Including search steps to search from a set of images,
The work target is attached to the target location by the tool, and the work target is attached to the target location.
The question-side feature portion exists in a portion corresponding to the target portion in the question image.
The search-side feature portion exists in a portion of the search target image corresponding to the target location.
Tool control method. The tool control method according to claim 1, wherein the question-side reference point is a position corresponding to a part of the tool. The question-side position data includes question-side distance data indicating a distance between the question-side reference point and the question-side feature portion.
The tool control method according to claim 1 or 2, wherein the search-side position data includes search-side distance data indicating a distance between the search-side reference point and the search-side feature unit. The question-side position data includes question-side direction data indicating the direction of the question-side feature portion with respect to the question-side reference point.
The tool control method according to any one of claims 1 to 3, wherein the search-side position data includes search-side direction data indicating the direction of the search-side feature portion with respect to the search-side reference point. The tool control method according to any one of claims 1 to 4, which includes a correction step of performing correction such as rotating the question image. The tool control method according to any one of claims 1 to 5, further comprising an angle of view changing step of changing the size of the angle of view of the question image. In a plurality of duplicate images including a common area in the set of search target images, the search-side feature portion included in the common area is excluded from at least one of the plurality of duplicate images. The tool control method according to any one of claims 1 to 6, which includes an exclusion step. A program for causing a computer system to execute the tool control method according to any one of claims 1 to 7. A tool that searches an image similar to a question image obtained by an image pickup unit of a tool from a set of search target images to which a control value corresponds to each, and sets a control value corresponding to the search result to the tool. It ’s a control system,
An extraction unit that extracts question-side position data indicating the positional relationship between the question-side reference point and the question-side feature portion in the question image, and an extraction unit.
Based on the comparison result between the question-side position data and the search-side position data indicating the positional relationship between the search-side reference point and the search-side feature in the search-target image, the search target is an image similar to the question-side image. Equipped with a search unit that searches from a set of images ,
The work target is attached to the target location by the tool, and the work target is attached to the target location.
The question-side feature portion exists in a portion corresponding to the target portion in the question image.
The search-side feature portion exists in a portion of the search target image corresponding to the target location.
Tool control system. A tool controlled by the tool control system according to claim 9.
A tool having the image pickup unit for imaging the work object. A tool that searches an image similar to a question image obtained by an image pickup unit of a tool from a set of search target images to which a control value corresponds to each, and sets a control value corresponding to the search result to the tool. It ’s a control method,
An extraction step for extracting question-side position data indicating the positional relationship between the question-side reference point and the question-side feature in the question image, and
Based on the comparison result between the question-side position data and the search-side position data indicating the positional relationship between the search-side reference point and the search-side feature in the search-target image, the search target is an image similar to the question-side image. Search steps to search from a set of images and
In a plurality of duplicate images including a common area in the set of search target images, the search-side feature portion included in the common area is excluded from at least one of the plurality of duplicate images. Exclude steps and include
Tool control method.

Images