AUTOMATED POLISHING SYSTEM AND METHOD

Description

CROSS-REFERENCE TO RELATED APPLICATION

The present application claims priority to Korean Patent Application No. 10-2024-0140791 filed on Oct. 16, 2024, the entire contents of which is incorporated herein for all purposes by this reference.

BACKGROUND OF THE PRESENT DISCLOSURE

Field of the Present Disclosure

The present disclosure relates to an automated surface polishing system and a method thereof.

Description of Related Art

Recently, with the rapid spread of electric vehicles, methods of reducing the weight of a vehicle body are being actively researched. For example, application of aluminum panels to the vehicle body is expanding.

Aluminum has many defects, such as chips, unevenness, scratches, and dents that occur during a manufacturing process due to characteristics of the material. Such defects may be seen with the naked eye after a painting process and may adversely affect the appearance of the vehicle. Accordingly, manual full inspection and full polishing are performed to remove the defects.

However, the present polishing process, which is performed manually by workers, is a factor that causes excessive labor and increases the unit price of parts. Furthermore, aluminum dust is known to be a hazardous substance (see Korean Unexamined Patent Publication No. 10-2023-0136805 (Publication date: 2023 Sep. 27)).

The information included in this Background of the present disclosure is only for enhancement of understanding of the general background of the present disclosure and may not be taken as an acknowledgement or any form of suggestion that this information forms the prior art already known to a person skilled in the art.

BRIEF SUMMARY

Various aspects of the present disclosure are directed to providing an automated polishing system that enables automation of a polishing process, and a method thereof.

Furthermore, another object of the present disclosure is to provide an automated polishing system configured for reducing labor and costs, and a method thereof.

Yet another object of the present disclosure is to provide an automated polishing system configured for absorbing manufacturing tolerances and distributions which may occur during a manufacturing process, and a method thereof.

The present disclosure is not limited to the objects mentioned above, and other objects not mentioned may be clearly understood by one having ordinary skill in the art from the description below.

To achieve the objects of the present disclosure as described above and to perform the characteristic functions of the present disclosure described below, the features of the present disclosure are as follows.

In one aspect, the present disclosure provides a method of automatically performing polishing including obtaining an image of a panel, by an imaging device, obtaining a position of a defective portion which is present on the panel based on the obtained image, by a computer, directing a polishing robot including a polishing tool to the position, surface-contacting the polishing tool with the panel at the position, and operating the polishing robot while maintaining the surface-contact between the polishing tool and the panel.

In another aspect, the present disclosure provides an automated polishing system including an imaging device configured to obtain three-dimensional data of an object, a multi-joint robot including a polishing tool configured to polish the object, and a computer configured to determine a position of a defective portion which is present on the object based on the three-dimensional data and to control the robot so that the robot polishes the defective portion at the position thereof. The computer may be configured to control each axis of the robot so that the polishing tool performs polishing while uniformly maintaining a pressure over the defective portion.

The methods and apparatuses of the present disclosure have other features and advantages which will be apparent from or are set forth in more detail in the accompanying drawings, which are incorporated herein, and the following Detailed Description, which together serve to explain certain principles of the present disclosure.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1 is a schematic diagram of an automated polishing system according to an exemplary embodiment of the present disclosure;

FIG. 2 is a diagram showing a deep learning model of an automated polishing system according to an exemplary embodiment of the present disclosure;

FIG. 3 is a diagram showing a robot of an automated polishing system according to an exemplary embodiment of the present disclosure;

FIG. 4 is a diagram showing a force-torque sensor of an automated polishing system according to an exemplary embodiment of the present disclosure;

FIG. 5 is a diagram showing a polishing process using a polishing tool of an automated polishing system according to an exemplary embodiment of the present disclosure;

FIG. 6 is a flowchart of an automated polishing method according to an exemplary embodiment of the present disclosure; and

FIG. 7 is a flowchart of operations of a robot in an automated polishing method according to an exemplary embodiment of the present disclosure.

It may be understood that the appended drawings are not necessarily to scale, presenting a somewhat simplified representation of various features illustrative of the basic principles of the present disclosure. The specific design features of the present disclosure as included herein, including, for example, specific dimensions, orientations, locations, and shapes will be determined in part by the particularly intended application and use environment.

In the figures, reference numbers refer to the same or equivalent parts of the present disclosure throughout the several figures of the drawing.

DETAILED DESCRIPTION

Specific structural or functional descriptions presented in the exemplary embodiments of the present disclosure are merely exemplified for describing embodiments according to the concept of the present disclosure, and embodiments according to the concept of the present disclosure may be implemented in various forms. Furthermore, the present disclosure should not be construed as limited to the exemplary embodiments described in the present specification, but should be understood to include all modifications, equivalents, or substitutes included in the concept and technical scope of the present disclosure.

It will be understood that, although the terms “first”, “second”, etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, a first element may be termed a second element, and similarly, a second element may be termed a first element, without departing from the scope of the exemplary embodiments of the present disclosure.

Furthermore, it will be understood that, when an element is “connected” or “coupled” to another element, it may be directly connected or coupled to the other element, or may be indirectly connected or coupled to the other element with a different element being interposed therebetween. In contrast, when an element is “directly connected” or “directly coupled” to another element, this means that there is no intervening element therebetween. Other expressions used to describe the relationship between elements should be interpreted in a similar manner (for example, “between” and “directly between”, “adjacent” and “directly adjacent”, etc.).

Wherever possible, the same reference numbers will be used throughout the drawings to refer to the same or like parts. The terminology used herein is for describing various exemplary embodiments only and is not intended to limit exemplary embodiments of the present disclosure. As used herein, the singular forms “a”, “an”, and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprise”, “include”, and “have” used herein specify the presence of stated components, steps, operations, and/or elements, but do not preclude the presence or addition of one or more other components, steps, operations, and/or elements.

Hereinafter, exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings.

Manual polishing of materials such as aluminum, as mentioned above, may result in increased labor and costs, as well as adverse health effects on workers. Therefore, although there is an urgent need for development of automated polishing, there are cases where it is difficult in automate polishing. Application of aluminum to automated polishing is not easy due to the characteristics of the material. Aluminum generates excessive dust during forming and manufacturing processes due to the characteristics of the material, and defects such as unevenness or dents occur sporadically in irregular surface portions.

To automatically polish the defects such as unevenness and dents that occur in the material in such irregular surface portions, a robot including a polishing tool should move to a location of such a defect portion, and should perform polishing while conforming the polishing tool to a curved surface in real time. However, it is possible to obtain products without defects during mass production through the present method.

Automation may be achieved by teaching a robot how to operate. However, in a case where the robot moves only along a pre-taught path or to a pre-taught location, it is difficult to deal with a product distribution, a robot distribution, and a manufacturing process distribution. Therefore, it is difficult to secure uniform polishing quality, and thus, there is a high possibility of defects occurring. Furthermore, calibration of teaching processes for all preset areas of a product is required periodically, which requires excessive labor.

Accordingly, the present disclosure provides an automated polishing system that does not require teaching and which is capable of achieving compliance control in real time so that a polishing tool adheres closely to a curved surface to be polished, and a method thereof.

As shown in FIG. 1, a polishing system 1 according to an exemplary embodiment of the present disclosure is configured to polish a surface of an object 2. The surface of the object 2 may have curvature or a curved portion. In one example, the object 2 may be a panel of a vehicle body. In one example, the object 2 may be a portion including a welded bend of a moving portion of the vehicle body. In one example, the object 2 may be an aluminum panel. However, the object 2 to be polished by the polishing system 1 is not limited thereto. The object 2 of the polishing system 1 may be applied to objects in all processes that require polishing or sanding, such as a vehicle body process and a painting process.

The polishing system 1 may polish a defective portion 4 formed on the surface of the object 2. The defective portion 4 may include unevenness, scratches or dents formed on the surface of the object 2. These defective portions 4 may be formed sporadically in the object 2. The polishing system 1 may polish the defective portion 4 without separate teaching while adapting to the surface in real time during polishing for the defective portion 4 of the curved portion on the surface of the object 2.

In other words, the polishing system 1 is configured to determine a precise three-dimensional position of the defective portion 4 through image processing and analysis of the object 2 and to perform polishing while adapting to the surface in real time at the corresponding position thereof. To the present end, the polishing system 1 includes an imaging device 20, a polishing device, and a computer 100. The computer 100 is configured to perform determinations for operation of the polishing system 1 and to control the imaging device 20 and the polishing tool. In one example, the computer 100 may perform a determination to obtain three-dimensional position information of the defective portion 4 based on an image obtained by the imaging device 20. Furthermore, in one example, the computer 100 may be configured for controlling the polishing tool to perform polishing based on the obtained three-dimensional position information.

The computer 100 includes a memory and a processor. The processor, which is hardware, may execute computer-readable code or a series of commands stored in the memory and perform data processing. As a non-limiting example, the processor may include a central processing unit, a graphics processing unit, a multi-core processor, a multiprocessor, an application-specific integrated circuit (ASIC), or a field programmable gate array (FPGA).

The memory may store data, code, or a series of commands which may be executed by the processor. The memory may be a volatile or non-volatile memory. As another non-limiting example, the volatile memory may include a dynamic random access memory (DRAM) or a static random access memory (SRAM). As yet another non-limiting example, the non-volatile memory may include an electrically erasable programmable read-only memory (EEPROM), a flash memory, a magnetic RAM (MRAM), a CD-ROM, or a DVD-ROM.

The imaging device 20 is configured to obtain an image of the object 2. In some examples, the imaging device 20 may obtain three-dimensional data of the object 2 through a structured light method. The imaging device 20 includes a camera and a projector. The camera is configured to obtain two-dimensional data or two-dimensional position information of the object 2 by capturing a light pattern projected onto the object 2. In one example, the camera may be a two-dimensional camera. The projector is configured to project a light pattern onto the object 2. The imaging device 20 may configure three-dimensional data by combining depth information through the camera and the projector. The computer 100 is configured to match position information of two-dimensional data to three-dimensional data through the configured three-dimensional data to obtain position coordinates in a three-dimensional coordinate system. In one example, the imaging device 20 may be a three-dimensional machine vision system.

The computer 100 may use intrinsic parameters, extrinsic parameters, and depth information of the camera to transform specific coordinates in two-dimensional image data into three-dimensional space coordinates.

The intrinsic parameters of the camera may include an intrinsic parameter matrix (K) based on an x-direction focal length (fx), a y-direction focal length (fy), an x-coordinate of a principal point (Cx), and a y-coordinate of the principal point (Cy). The intrinsic parameter matrix (K) may be determined by Expression 1.

K = [ fx 0 Cx 0 fy Cy 0 0 1 ] [ Expression ⁢ 1 ]

The extrinsic parameters of the camera may include a rotation matrix (R), a translation vector (T), and an extrinsic parameter matrix (M1). The extrinsic parameter matrix (M1) may be obtained by Expression 2. The extrinsic parameters of the camera may include a rotation matrix (R), a translation vector (T), and an extrinsic parameter matrix (M1).

M ⁢ 1 = [ R ❘ T ] [ Expression ⁢ 2 ]

The computer 100 may perform a determination to transform two-dimensional position coordinates into three-dimensional space coordinates using the intrinsic parameters and extrinsic parameters. Since the above determination may be performed using a known technique for transforming coordinates of a two-dimensional image into coordinates of a three-dimensional image, detailed description thereof will be omitted. Referring to FIG. 2, according to some examples, the accuracy of identification of the defective portion 4 in the image obtained by the imaging device 20 may be improved through deep learning of the computer 100. To the present end, the computer 100 may include a deep learning model 110. The deep learning model 110 is configured to learn an image of the object 2 including the defective portion 4, a two-dimensional position of the defective portion 4 in the image of the object 2, and data of the defective portion 4 in the image of the object 2. Since the data of the defective portion 4 has a value in a different range from data of a non-defective portion of the object 2, a portion having the value in that range may be determined to include the defective portion 4. In a case where an image P1 of the object 2 is input based on learned data, the deep learning model 110 may output location coordinates of the defective portion 4 in the image of the object 2 and data of the defective portion 4 in the image of the object 2 as an output P2. Accordingly, in a case where the defective portion 4 is present in the image obtained from the imaging device 20, the computer 100 may identify the defective portion 4 with a high probability. That is, by determining pixel values on a two-dimensional image and matching the result with three-dimensional data, three-dimensional data of a specific desired area, i.e., the defective portion 4, may be obtained. The obtained three-dimensional data is transformed into robot coordinates as described later, and the robot 40 may move based on the result. The present disclosure enables, instead of robot programming that relies on teaching, the robot 40 to find the defective portion 4 on its own without teaching. In one example, the deep learning model 110 may be based on a YOLO (You Only Look Once) deep learning algorithm.

According to some examples of the present disclosure, at least some of the defective portion 4 may undergo a pre-emphasis process prior to image acquisition by the imaging device 20. For example, at least some of the defective portion 4 of the object 2 may be displayed in advance through color processing or the like to be seen with the naked eye. In another example, a polishing mark may be formed artificially on the defective portion 4 which may be visually confirmed using an oilstone or sandpaper, etc., to emphasize shade of the defective portion 4 with unevenness, dents, etc., making it easy to identify the defective portion 4 using the imaging device 20. In a case where the degree of defect in the defective portion 4 of the object 2 is minor, the defective portion 4 may not be identified by the imaging device 20 or the computer 100. In the instant case, the identification ability of the defective portion 4 may be improved through the above-described process.

In some examples, the two-dimensional image obtained by the camera may be preprocessed by the computer 100. The computer 100 may preprocess the defective portion 4 in the two-dimensional image through Hue, Saturation, and Value (HSV) color analysis. The preprocessing may include increasing saturation among hue, saturation and value. A detection rate of the defective portion 4 may be improved through the preprocessing process for adjusting the saturation of the defective portion 4.

In one example, the imaging device 20 may be mounted on a multi-joint robot 30. The computer 100 may be configured for controlling the movement of the multi-joint robot 30, and may be configured for controlling an obtaining position of the imaging device 20 for the object 2 under the control of the multi-joint robot 30.

The polishing system 1 includes a polishing device. In one example, the polishing device may be the robot 40, and may be the multi-joint robot. As a non-limiting example, the polishing device may be a multi-joint collaborative robot configured for performing multi-axis control. As a non-limiting example, the polishing device may be a multi-joint collaborative robot configured for performing six-axis control.

The robot 40 includes a polishing tool 50. The polishing tool 50 is a member configured to polish the surface of the object 2, such as sandpaper. The polishing tool 50 may be detachably mounted on a working end portion of the robot 40. The polishing tool 50 may be rotated by a spindle mounted on the robot 40. The polishing tool 50 may be rotated while applying pressure to the surface of the object 2 by the robot 40.

As shown in FIG. 3, the robot 40 includes a force-torque sensor 60. In one example, the force-torque sensor 60 may be a multi-axis force-torque sensor. As a non-limiting example, the force-torque sensor 60 may be a six-axis force-torque sensor. The force-torque sensor 60 detects the applied force, and the robot 40 may adjust the force applied to the surface of the object 2 based on the detection result.

Referring to FIG. 4, according to an example of the present disclosure, the force-torque sensor 60 may be a resistive sensor that converts deformation caused by an external force into an electrical signal. In one example, the force-torque sensor 60 includes a strain gauge 62. The force-torque sensor 60 may detect deformation as an electrical signal, i.e., a change in resistance, through the strain gauge 62 and provide the detection result to the robot 40.

According to an example of the present disclosure, the force-torque sensor 60 may include a plurality of strain gauges 62. The strain gauges 62 may be placed on the force-torque sensor 60 at preset intervals. As in the shown example, the strain gauges 62 may be disposed at preset intervals along the circumference of the force-torque sensor 60. In some examples, the force-torque sensor 60 may include four or more strain gauges 62, each of which may be spaced approximately 90° apart in the circumferential direction (62a, 62b, and 62c are shown in FIG. 4, and 62d is omitted). However, the number of strain gauges 62 may be changed.

The force-torque sensor 60 may measure the pressure applied to the polishing tool 50 as a change in resistance when the surface of the polishing tool 50 and the object 2 come into contact. According to an exemplary embodiment of the present disclosure, when polishing the surface of the object 2, it is possible to control each axis of the robot 40 so that the resistance values measured by the respective strain gauges 62 are uniform, providing equal pressure control. According to an exemplary embodiment of the present disclosure, it is possible to allow the robot 40 to perform polishing in real time while adapting to the surface of the object 2 regardless of the curved portion or curvature of the surface of the object 2, providing an automatic polishing operation.

In one example, as shown in FIG. 5, the movement of the robot 40 may be controlled so that the polishing tool 50 moves along a path P that surrounds the defective portion 4 with the defective portion 4 as the center of the path P. In one example, the polishing tool 50 may be controlled by the robot 40 to move along a rectangular path with the defective portion 4 as the center of the path P. For example, in the case of rough grinding, the movement of the polishing tool 50 may be made along a path that follows a square with a side of 30 mm, and in the case of smooth grinding, along a path that follows a square with a side of 50 mm. Polishing the panel of the vehicle body requires a large area of work. This is because, in a case where polishing is concentrated on only one portion, excessive marks or scratches may remain. Accordingly, the present disclosure may prevent the above-mentioned problem by configuring the polishing tool 50 to move along a path surrounding the defective portion 4 during polishing.

The robot 40 includes a robot controller 70. The robot controller 70 is configured to receive a detecting value of the force-torque sensor 60. Additionally, the robot controller 70 is configured to control each axis of the robot 40 based on the detecting value of the force-torque sensor 60.

The robot controller 70 is configured to communicate with the computer 100. The computer 100 is configured to transmit the three-dimensional position coordinates of the defective portion 4 to the robot controller 70. Furthermore, the robot controller 70 is configured to cause the robot 40 to perform polishing work at the corresponding location based on the received three-dimensional position coordinates. In one example, an Ethernet TCP (Transmission Control Protocol) method may be used as a communication method between the computer 100 and the robot controller 70.

According to an example of the present disclosure, the computer 100 is configured to perform a determination for correlating a coordinate system of the imaging device 20, a coordinate system of the robot 40, and a coordinate system of the polishing tool 50.

The computer 100 is configured to transform coordinates of the defective portion 4 observed by the imaging device 20, i.e., the coordinate system (xi, yi, zi) of the imaging device 20, into the coordinate system (xr, yr, zr) of the robot 40. In some examples, a transformation matrix (R) may be used to map the coordinate system (xi, yi, zi) of the imaging device 20 to the orthogonal coordinate system (xr, yr, zr) of the robot 40. In one example, the coordinate system (xr, yr, zr) of the robot 40 may be the orthogonal coordinate system of the robot 40. The orthogonal coordinate system represents the amount of movement along the x-axis, y-axis, and z-axis with reference to the origin of the robot 40. by determining a distance between the three-dimensional position coordinates of the defective portion 4 measured by the imaging device 20 and the origin of the robot 40 through calibration of the imaging device 20 and the robot 40, the movement distance of the robot 40 to the defective portion 4 may be set. That is, the computer 100 may obtain target coordinates (x, y, z) to which the robot 40 must move in the x-axis direction, y-axis direction, and z-axis direction to the defective portion 4 with reference to the origin of the robot 40. The computer 100 may obtain the target coordinates (x, y, z) and transmit the obtained target coordinates (x, y, z) to the robot controller 70, allowing the robot 40 to move to the target coordinates (x, y, z) indicating the defective portion 4 and perform polishing.

Furthermore, in one example, the computer 100 is configured to transmit the target coordinates (x, y, z) taking into account a rotation value of the polishing tool 50. The coordinate system (xt, yt, zt) of the polishing tool 50 is a coordinate system that moves with reference to a tip point of the polishing tool 50. Even in a case where the movement of the robot 40 is determined through the orthogonal coordinate system (xr, yr, zr) of the robot 40 since the robot 40 rotates about each axis of the coordinate system (xt, yt, zt) of the polishing tool 50, a rotation value of the robot 40 should be determined according to the curvature of the object 2. For example, when determining the rotation direction of the coordinate system (xt, yt, zt) of the polishing tool 50, in a state where an axial direction thereof may be aligned with the right thumb, a direction in which the remaining fingers are pointed may be set as a positive (+) direction, and the opposite direction may be set as a negative (−) direction. In the present way, the computer 100 may transmit coordinates (x, y, z, Rx, Ry, Rz) as final target coordinates to the robot controller 70. Here, x, y, z may represent linear movement amounts of the three axes of the robot 40, and Rx, Ry, Rz may represent rotation amounts of the robot 40 for the respective axes.

Furthermore, the computer 100 is configured to determine the curvature of the defective portion 4. The rotation values of the robot 40 should be determined according to the curvature of the object 2 so that the polishing tool 50 can be in close contact with the defective portion 4 to facilitate compliance control. In a case where the polishing is performed without reflecting a rotation correction value in a portion with a large curvature, the surface adhesion compliance control may not be performed smoothly. To the present end, the computer 100 may be configured to determine the amount of change in curvature of the object 2 based on a normal vector in the three-dimensional image. The normal vector may be determined when the computer 100 obtains three-dimensional position information from the obtained two-dimensional image.

The computer 100 may obtain the rotation amount of the normal vector in the defective portion 4 using Rodrigues' rotation formula. Rodrigues' rotation formula may determine the amount of rotation for each axis between two vectors. This allows the curvature of a measurement point to be determined with reference to a reference point which is arbitrarily set. However, since the rotation amount is the rotation amount of the imaging device 20, the computer may transform the rotation amount into the rotation amount of the robot 40 by multiplying a rotation matrix by the rotation amount of the normal vector obtained from the three-dimensional image. Furthermore, since the rotation amount of the robot 40 follows the rotation amount of the coordinate system of the polishing tool 50, an additional process of transforming the rotation amount of the orthogonal coordinate system of the robot 40 into values in the coordinate system of the polishing tool 50 may be performed. Through these determinations, the amount of rotation of the robot 40 may be determined, and the position coordinates (x, y, z, Rx, Ry, Rz) of the final target point may be transmitted to the robot controller 70.

As described above, the position of the defective portion 4 obtained through image analysis is position information generated based on the coordinate system (xi, yi, zi) of the imaging device 20. In a case where the position information of the defective portion 4 is input to the coordinate system (xr, yr, zr) of the robot 40, the robot 40 may move along the robot coordinate system. By mapping the coordinate system (xi, yi, zi) of the imaging device 20 to the coordinate system (xr, yr, zr) of the robot 40, the robot 40 may be moved to the defective portion 4. A transformation matrix (R) may be used to unify two different coordinate systems. The transformation matrix (R) is a 4×4 matrix, where the first 3×3 matrix portion (rotation transformation portion) represents different coordinate systems, and the remaining 4×1 portion (translation transformation portion) represents the amount of movement of the origin between the two coordinate systems.

R = [ r 11 r 12 r 13 d x r 21 r 22 r 23 d y r 31 r 32 r 33 d z 0 0 0 1 ] [ Expression ⁢ 3 ]

A rotation transformation portion may be determined from the transformation matrix (R) using Euler's angle formula (Expression 4) based on the difference in the amount of rotation between two different coordinate systems and the amount of translation of the origin.

A x = [ 1 0 0 0 cos ⁢ θ x - sin ⁢ θ x 0 sin ⁢ θ x cos ⁢ θ x ] [ Expression ⁢ 4 ] A y = [ cos ⁢ θ x 0 sin ⁢ θ x 0 1 0 - sin ⁢ θ x 0 cos ⁢ θ x ] A z = [ cos ⁢ θ x - sin ⁢ θ x 0 sin ⁢ θ x cos ⁢ θ x 0 0 0 1 ]

Here, Ax, Ay, and Az represent an x-axis rotation value, a y-axis rotation value, and a z-axis rotation value, respectively, and θ_x is an angle by which Ax, Ay and Az rotate vectors about x-, y- or, z-axis in three dimensions using the right-hand rule. In a case where the amount of rotation is known, the rotation transformation portion may be determined using Expression 4. However, even in a case where the imaging device 20 and the robot 40 are mounted as preset, it is difficult to know the precise amount of rotation due to a slope of the ground where they are mounted, an error in a mounting position, and the like. Accordingly, the present disclosure employs a method of actually obtaining the rotation amount to reduce such errors. That is, by detecting the axial movement of the robot 40 within the obtaining area of the imaging device 20, the displacement of the coordinate system (xr, yr, zr) of the robot 40 may be obtained based on the coordinate system (xi, yi, zi) of the imaging device 20. By inputting error values identified based on the above description into Expression 4, the rotation transformation portion may be determined.

A movement transformation portion may be obtained by setting up three additional equations. That is, these three equations may be obtained through the coordinate system (xr, yr, zr) of the imaging device 20 and the robot 40. The coordinates of the robot 40 may be obtained through the product of the transformation matrix (R) and the coordinates of the imaging device 20. Information on the coordinates (in the coordinate system of the imaging device 20) of the defective portion 4 may be obtained through the imaging device 20, and information on the coordinates of the robot 40 of the defective portion 4 may be obtained through teaching of the robot 40. Then, since the three-dimensional coordinates of the robot 40 and the three-dimensional coordinates of the imaging device 20 are known, the three unknown movement transformation portions may be determined with three equations, so that the movement of the robot 40 to the defective portion 4 may be performed based on the mapped coordinate system.

As shown in FIG. 6, in step S600, the polishing system 1 obtains a three-dimensional image of the surface of the object 2. As described above, a two-dimensional image of the object 2 may be obtained by the imaging device 20.

In step S610, the position coordinates of the defective portion 4 may be obtained. The computer 100 is configured to perform a determination for correlating the coordinate system of the robot 40, the coordinate system of the imaging device 20, and the coordinate system of the polishing tool 50, so that the position coordinates at which the robot 40 can move to the defective portion 4 in the coordinate system of the robot 40 may be determined.

Automated polishing of the surface of the object 2 by the robot 40 may be performed based on the obtained position coordinates, in step S620. Regardless of whether the surface of the object 2 is curved, the polishing tool 50 may perform the polishing while conforming to the surface of the object 2 through the force-torque sensor 60.

In the automated polishing process, referring to FIG. 7, in step S700, the robot 40 moves to the defective portion 4 based on the obtained position coordinates.

In a case where a plurality of defective portions 4 is present, the computer 100 may be configured to generate an optimal movement path of the robot 40. In one example, in a case where the plurality of defective portions 4 is present in the object 2, the optimal movement path may be the shortest distance for connecting all the defective portions 4.

In step S710, it is determined whether the polishing tool 50 of the robot 40 is in surface-contact with the surface of the object 2. Here, surface-contact refers to a state in which the polishing tool 50 is evenly in contact with the surface of the object 2. The computer 100 may be configured to determine whether there is surface-contact based on a resistance value in each direction of the strain gauge 62 of the force-torque sensor 60. In a case where the resistance values in the respective directions are uniform, the computer 100 may be configured to determine that the surfaces of the polishing tool 50 and the object 2 are in surface-contact.

In a case where it is determined that surface-contact occurs, the computer 100 starts polishing by the robot 40 (S720). The robot controller 70 rotates the spindle to rotate the polishing tool 50, applying a preset pressure to the surface of the object 2 through axis control of the robot 40.

After the start of polishing, the robot controller 70 collects detecting values of the force-torque sensor 60 in real time (S730). The robot controller 70 may receive the resistance values of the respective strain gauges 62 and determine whether these values are uniform.

The robot controller 70 is configured to control each axis of the robot 40 so that the pressures in the respective directions of the force-torque sensor 60 are uniform (S740). The uniform pressure in the respective directions may mean that the polishing tool 50 performs polishing while in close contact with the surface of the object 2. Therefore, according to an exemplary embodiment of the present disclosure, the polishing work may be performed automatically without teaching the robot 40.

Generally, teaching is performed on a sample-by-sample basis. Generally, based on that distribution occurs on a curved surface, flexible response is difficult, causing polishing defects. However, according to an exemplary embodiment of the present disclosure, an automated polishing system is provided in which a change in the position of a robot along a curvature surface of an object is possible without teaching.

Generally, a worker identifies a defective portion in a polishing target divided into a plurality of areas, and then, a polishing robot moves along a set pattern in the area where the defective portion exists according to teaching content set by the worker to perform the polishing work. That is, the teaching of the robot's path is necessary in advance. Furthermore, the polishing robot moves only in the set pattern without reflecting the curvature of the polishing target. On the other hand, according to an exemplary embodiment of the present disclosure, precise coordinates of a defective portion (i.e., precise position) are obtained based on an obtained image of a target, and the polishing robot moves to the obtained position and automatically performs polishing without teaching while following the curvature of the target at the corresponding position.

Due to characteristics of press forming, aluminum has a curvature distribution. The present disclosure provides an automated polishing system configured for performing polishing while flexibly contacting with the surface regardless of whether there is distribution or not.

The polishing system and method according to an exemplary embodiment of the present disclosure may be applied to all processes that require surface polishing.

According to an exemplary embodiment of the present disclosure, it is possible to provide an automated polishing system that enables automation of a polishing process and a method thereof.

According to an exemplary embodiment of the present disclosure, it is possible to provide an automated polishing system configured for reducing labor and costs and a method thereof.

According to an exemplary embodiment of the present disclosure, it is possible to provide an automated polishing system configured for absorbing manufacturing tolerances and distributions which may occur during a manufacturing process and a method thereof.

The foregoing descriptions of specific exemplary embodiments of the present disclosure have been presented for purposes of illustration and description. They are not intended to be exhaustive or to limit the present disclosure to the precise forms disclosed, and obviously many modifications and variations are possible in light of the above teachings. The exemplary embodiments were chosen and described in order to explain certain principles of the invention and their practical application, to enable others skilled in the art to make and utilize various exemplary embodiments of the present disclosure, as well as various alternatives and modifications thereof. It is intended that the scope of the present disclosure be defined by the Claims appended hereto and their equivalents.