Lacquer surface defect detection and polishing system and method

Abstract

A lacquer surface defect detection and polishing system, comprising: a defect detection apparatus, which is arranged at a defect detection station; a defect polishing apparatus, which is arranged at a defect polishing station, wherein the defect polishing station is a downstream station of the defect detection station; and a control apparatus, which is connected to the defect detection apparatus and the defect polishing apparatus, wherein the control apparatus is configured to control the defect detection apparatus to perform lacquer surface defect detection on a target object, so as to obtain a lacquer surface defect of the target object and the defect position of the lacquer surface defect, and the control apparatus is also configured to control, on the basis of the defect position, the defect polishing apparatus to polish the lacquer surface defect.

Description

Paint surface defect detection and polishing system and method

[0001] This application claims priority to Chinese patent applications numbered 2023215363591, filed on June 15, 2023, entitled “Paint surface defect detection system and paint surface defect detection and polishing system”, and numbered 2023107131737, filed on June 15, 2023, entitled “A method and system for detecting and polishing automobile paint surface defects”, the entire text of which is hereby incorporated by reference. Technical Field

[0002] The present application relates to the field of intelligent technology for automobile body production and manufacturing, and in particular to a paint defect detection and polishing system, method, device, computer equipment, storage medium and computer program product. Background Art

[0003] The painting process is a crucial step in automobile body manufacturing. Spraying paint onto the surface enhances the car's rust and corrosion resistance, as well as its aesthetic appeal. However, painting is a highly precise and challenging task, with the paint, coating environment, and spray parameter settings all impacting process quality.

[0004] However, if the coating process doesn't meet production requirements, defects such as stains and damage will occur on the vehicle's paint surface. For example, bumps and concavities caused by surface impurities during spraying, or scratches caused by improper handling during handling, can directly impact the vehicle's marketability and the manufacturer's brand image. Therefore, pre-shipment inspection for paint defects is an essential process.

[0005] Currently, automotive paint defect detection is primarily performed manually. In specialized lighting workshops, workers detect defects by visual inspection and touch, and then record the defect information. While this manual method can meet production needs, it relies heavily on worker experience and work habits, resulting in low efficiency and inconsistent quality.

[0006] Summary of the Invention

[0007] According to various embodiments of the present application, a paint surface defect detection and polishing system and method are provided.

[0008] In a first aspect, the present application provides a paint surface defect detection and polishing system, the system comprising:

[0009] A defect detection device provided at a defect detection station;

[0010] A defect polishing device is provided at a defect polishing station; the defect polishing station is a downstream station of the defect detection station;

[0011] a control device connecting the defect detection device and the defect grinding device; and

[0012] The control device is used to control the defect detection device to perform paint defect detection on the target object to obtain the paint defect of the target object and the defect position of the paint defect; and is also used to control the defect polishing device to polish the paint defect based on the defect position.

[0013] In some embodiments, the defect detection device includes a first robotic arm moving guide rail, a detection robotic arm, and an optical imaging assembly;

[0014] The detection mechanical arm is arranged on the first mechanical arm moving guide rail;

[0015] The optical imaging component is provided on the detection robot arm and is used to capture the paint surface image of the target object; and

[0016] The control device is respectively connected to the detection robot arm and the optical imaging component, and is used to control the detection robot arm to drive the optical imaging component to move, so that the optical imaging component can capture the paint surface image of the target object, and perform image processing on the paint surface image to determine the paint surface defects of the target object.

[0017] In some embodiments, the control device is further connected to the first mechanical movable guide rail, and is used to control the first mechanical movable guide rail to drive the detection robot arm to move.

[0018] In some embodiments, the system further comprises:

[0019] A collection and guidance device is provided at an object production station; the object production station is an upstream station of the defect detection station; and

[0020] The acquisition and guidance device is used to acquire the posture of the target object; the control device specifically controls the defect detection device to perform paint defect detection on the target object based on the posture.

[0021] In some embodiments, the defect grinding device includes a second robotic arm moving guide rail, a grinding robotic arm, and a force-controlled grinding head;

[0022] The polishing robot arm is arranged on the second robot arm moving guide rail;

[0023] The force-controlled grinding head is provided on the grinding robot arm and is used for grinding the paint surface defects; and

[0024] The control device is connected to the polishing robot arm and the force-controlled polishing head respectively, and is used to control the polishing robot arm to drive the force-controlled polishing head to move, so that the force-controlled polishing head polishes the paint surface defects.

[0025] In some embodiments, the control device is further connected to the second mechanical movable guide rail, and is used to control the second mechanical movable guide rail to drive the grinding robot arm to move.

[0026] In some embodiments, the first robotic arm movement guide rail is docked with the second robotic arm movement guide rail.

[0027] In some embodiments, the defect detection device further comprises:

[0028] A 3D positioning camera for the inspection station is used to collect a local point cloud of the target object located at the defect inspection station to obtain first local point cloud data; and

[0029] The control device is connected to the 3D positioning camera of the inspection station, and is specifically used to determine the defect position of the paint surface defect in combination with the first object position represented by the first local point cloud data and the inspection posture of the inspection robot arm.

[0030] In some embodiments, the defect grinding device further comprises:

[0031] A 3D positioning camera for the polishing station is used to collect a local point cloud of the target object located at the defect polishing station to obtain second local point cloud data; and

[0032] The control device is connected to the 3D positioning camera of the inspection station, and is specifically used to control the polishing robot arm to drive the force-controlled polishing head to polish the paint surface defects in combination with the second object position represented by the second local point cloud data and the polishing posture of the polishing robot arm.

[0033] In some embodiments, the installation layout and working space of the inspection robot arm correspond one-to-one with the polishing robot arm, and the installation layout and acquisition area of ​​the inspection station 3D positioning camera correspond one-to-one with the polishing station 3D positioning camera.

[0034] In some embodiments, when the position of the second object is consistent with the position of the first object, the control device determines the polishing posture of the polishing robot arm according to the detection posture corresponding to the defect position; and controls the polishing robot arm to drive the force-controlled polishing head to polish the paint surface defect based on the polishing posture.

[0035] In a second aspect, the present application further provides a method for detecting and polishing paint surface defects, the method comprising:

[0036] Controlling the defect detection device to perform paint surface defect detection on the target object to obtain the paint surface defect of the target object and the defect location of the paint surface defect; and

[0037] Based on the defect position, the defect grinding device is controlled to grind the paint surface defect.

[0038] In some embodiments, controlling the defect detection device to perform paint surface defect detection on a target object to obtain the paint surface defects of the target object includes:

[0039] Controlling a detection robot arm in the defect detection device to drive an optical component in the defect detection device to move and collect an image of the paint surface of the target object, wherein the optical component is disposed on the detection robot arm; and

[0040] Image processing is performed on the paint surface image to determine paint surface defects of the target object.

[0041] In some embodiments, the method further comprises:

[0042] Controlling the acquisition guidance device to acquire the position and posture of the target object; and

[0043] The defect detection device is controlled based on the posture of the target object to perform paint surface detection on the target object.

[0044] In some embodiments, controlling the defect detection device to detect paint defects on a target object to obtain a defect location of the paint defect includes:

[0045] Controlling a 3D positioning camera of a detection station in a defect detection device to collect a local point cloud of a target object located at the defect detection station to obtain first local point cloud data; and

[0046] The defect position of the paint surface defect is determined by combining the first object position represented by the first local point cloud data and the detection posture of the detection robot arm in the defect detection device.

[0047] In some embodiments, controlling a defect polishing device to polish the paint surface defect based on the defect position includes:

[0048] Controlling a 3D positioning camera of a grinding station in a defect grinding device to perform local point cloud acquisition on a target object located at the defect grinding station to obtain second local point cloud data; and

[0049] In combination with the second object position represented by the second local point cloud data and the polishing posture of the polishing robot arm in the defect polishing device, the polishing robot arm is controlled to drive the force-controlled polishing head to polish the paint surface defect, and the force-controlled polishing head is set on the polishing robot arm.

[0050] In some embodiments, combining the second object position represented by the second local point cloud data and the polishing posture of a polishing robot arm in a defect polishing device to control the polishing robot arm to drive a power-controlled polishing head to polish the paint surface defect includes:

[0051] comparing a second object position represented by the second partial point cloud data with a first object position represented by the first partial point cloud data;

[0052] When the second object position is consistent with the first object position, determining the grinding posture of the grinding robot arm according to the detection posture corresponding to the defect position; and

[0053] Based on the polishing posture, the polishing robot arm is controlled to drive the force-controlled polishing head to polish the paint surface defects.

[0054] In a third aspect, the present application further provides a paint surface defect detection and polishing device, the device comprising:

[0055] a defect detection module, configured to control a defect detection device to perform paint surface defect detection on a target object, and obtain paint surface defects of the target object and defect locations of the paint surface defects; and

[0056] The defect polishing module is used to control the defect polishing device to polish the paint surface defect based on the defect position.

[0057] In some embodiments, the defect detection module is also used to: control the detection robot arm in the defect detection device to drive the optical component in the defect detection device to move, collect the paint surface image of the target object, and the optical component is arranged on the detection robot arm; and perform image processing on the paint surface image to determine the paint surface defects of the target object.

[0058] In some embodiments, the apparatus further comprises:

[0059] The guidance module is used to control the acquisition guidance device to acquire the posture of the target object; and control the defect detection device to perform paint surface inspection on the target object based on the posture of the target object.

[0060] In some embodiments, the defect detection module is also used to: control the 3D positioning camera of the inspection station in the defect detection device to perform local point cloud acquisition on the target object located at the defect detection station to obtain first local point cloud data; and determine the defect position of the paint defect in combination with the first object position represented by the first local point cloud data and the detection posture of the detection robot arm in the defect detection device.

[0061] In some embodiments, the defect polishing module is also used to: control the 3D positioning camera of the polishing station in the defect polishing device to perform local point cloud acquisition on the target object located at the defect polishing station to obtain second local point cloud data; and combine the second object position represented by the second local point cloud data and the polishing posture of the polishing robot arm in the defect polishing device to control the polishing robot arm to drive the force-controlled polishing head to polish the paint surface defects, and the force-controlled polishing head is set on the polishing robot arm.

[0062] In some embodiments, the defect polishing module is also used to: compare the second object position represented by the second local point cloud data with the first object position represented by the first local point cloud data; when the second object position is consistent with the first object position, determine the polishing posture of the polishing robot arm according to the detection posture corresponding to the defect position; and control the polishing robot arm to drive the force-controlled polishing head to polish the paint defect based on the polishing posture.

[0063] In a fourth aspect, the present application also provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above-mentioned paint defect detection and polishing method when executing the computer program.

[0064] In a fifth aspect, the present application also provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the above-mentioned paint defect detection and polishing method when executed by a processor.

[0065] In a sixth aspect, the present application also provides a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the above-mentioned paint defect detection and polishing method.

[0066] The details of one or more embodiments of the present application are set forth in the accompanying drawings and the description below. Other features, objects, and advantages of the present application will become apparent from the description, drawings, and claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the conventional technology, the following briefly introduces the drawings required for use in the embodiments or the conventional technology descriptions. Obviously, the drawings described below are merely embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the disclosed drawings without any creative work.

[0068] FIG1 is a block diagram of a paint surface defect detection and polishing system according to some embodiments;

[0069] FIG2 is a schematic structural diagram of a defect detection device according to some embodiments;

[0070] FIG3 is a schematic structural diagram of a paint surface defect detection and polishing device including a defect polishing device according to some embodiments;

[0071] FIG4 is a schematic structural diagram of a defect detection device according to some other embodiments;

[0072] FIG5 is a schematic structural diagram of an off-line point position external calibration device for a paint surface imaging acquisition component according to some embodiments;

[0073] FIG6 is a schematic diagram of the structure of a paint surface imaging acquisition component and an off-line calibration device for extrinsic parameters of a 3D positioning camera at an inspection station according to some embodiments;

[0074] FIG7 is a schematic structural diagram of a paint surface defect detection and polishing system according to some embodiments;

[0075] FIG8 is a schematic flow chart of a paint surface defect detection and polishing method according to some embodiments;

[0076] FIG9 is a flowchart illustrating steps for controlling the polishing robot arm to drive the power-controlled polishing head to polish a paint surface defect, based on the position of the second object represented by the second local point cloud data and the polishing posture of the polishing robot arm in the defect polishing device, according to some embodiments;

[0077] FIG10 is a schematic flow chart of a paint surface defect detection and polishing method according to other embodiments;

[0078] FIG11 is a flowchart illustrating a method for offline calibration of external parameters of a paint surface imaging acquisition component and a 3D positioning camera at an inspection station at a reference point according to some embodiments;

[0079] FIG12 is a schematic diagram of a process for transferring coordinates of a defect location according to some embodiments;

[0080] FIG13 is a structural block diagram of a paint surface defect detection and polishing device according to some embodiments;

[0081] FIG14 is a diagram illustrating the internal structure of a computer device according to some embodiments.

[0082] Explanation of the accompanying reference numerals: 101-defect detection device; 102-defect polishing device; 1011-first robotic arm moving guide rail; 1012-detection robotic arm; 1013-paint surface imaging component; 1014-detection station 3D positioning camera; 1021-second robotic arm moving guide rail; 1022-polishing robotic arm; 1023-force-controlled polishing head; 1024-polishing station 3D positioning camera; 103-control device; 1031-defect detection control component; 1032-polishing control component; 104-target object; 105-two-degree-of-freedom base; 106-plane calibration plate; 107-angle-adjustable bracket; 108-double-sided calibration plate. DETAILED DESCRIPTION

[0083] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0084] The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0085] In the description of this application, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating the orientation or position relationship, are based on the orientation or position relationship shown in the accompanying drawings, and are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on this application.

[0086] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. Throughout the description of this application, "plurality" means two or more, unless otherwise specifically defined.

[0087] In this application, unless otherwise specified or limited, the terms "assemble," "connect," "connect," "fix," and the like should be understood in a broad sense. For example, they may refer to fixed connection, detachable connection, or integration; mechanical connection or electrical connection; direct connection or indirect connection through an intermediate medium; and internal communication between two components or interaction between two components. Those skilled in the art will understand the specific meanings of the above terms in this application based on the specific circumstances.

[0088] In some embodiments, as shown in FIG1 , a paint surface defect detection and polishing system is provided, the system specifically comprising:

[0089] A defect detection device 101 is provided at a defect detection station.

[0090] The defect grinding device 102 is provided at the defect grinding station, which is a downstream station of the defect detection station.

[0091] A control device 103 is connected to the defect detection device 101 and the defect grinding device 102.

[0092] Specifically, the control device 103 is used to control the defect detection device 101 to perform paint defect detection on the target object, obtain the paint defects of the target object and the defect locations of the paint defects, and further control the defect polishing device 102 to polish the paint defects based on the defect locations. The target object can be any product containing a paint surface, such as a vehicle body. It is understood that the defect polishing device can polish away the paint defects by polishing them away or by performing other polishing and other repair processes on the paint defects.

[0093] The paint defect detection and polishing system described above includes a defect detection device installed at the defect detection station, and a defect polishing device installed at a station downstream of the defect detection station, namely, the defect polishing station. Both the defect detection device and the defect polishing device are connected to a control device. The control device can control the defect detection device to perform paint defect detection on the target object, obtain the paint defects of the target object, and obtain the defect locations of the paint defects. Subsequently, based on the defect locations, the control device can control the defect polishing device to polish the paint defects. By collaboratively controlling the defect detection device and the defect polishing device, a streamlined operation of target object detection and polishing can be achieved. While improving the efficiency and accuracy of target object paint defect detection, the detected paint defects can also be automatically polished, further improving the production efficiency of the target object.

[0094] In some embodiments, as shown in FIG. 2 , the defect detection device 101 includes a first robotic arm moving guide rail 1011 , a detection robotic arm 1012 , and a paint surface imaging component 1013 .

[0095] The detection robot arm 1012 is disposed on the first robot arm moving guide rail 1011 .

[0096] The paint surface imaging component 1013 is provided on the detection robot arm 1012 and is used to collect the paint surface image of the target object 104 .

[0097] The control device 103 is respectively connected to the detection robot arm 1012 and the paint surface imaging component 1013, and is used to control the detection robot arm 1012 to drive the paint surface imaging component 1013 to move, so that the paint surface imaging component 1013 collects the paint surface image of the target object 104, and performs image processing on the paint surface image to determine the paint surface defects of the target object 104.

[0098] The control device 103 may be integrated with a robot controller connected to the detection robot 1012 , an imaging component controller connected to the paint surface imaging component, and an image processor.

[0099] Specifically, the robot arm controller in the control device 103 is connected to the detection robot arm 1012 and can control the movement of the detection robot arm 1012. It is understandable that the movement dimensions of the detection robot arm 1012 can be multiple, for example, including translational movement or rotational movement. The imaging component controller in the control device 103 is connected to the paint imaging component 1013 and can control the paint imaging component 1013 to capture the paint surface image of the target object 104. The paint surface image captured by the paint imaging component 1013 is processed by the image processor to obtain the paint surface defects of the target object 104.

[0100] The detection robot arm 1012 can move along the first robot arm moving guide rail 1011 , and there are many ways for the two to achieve movement.

[0101] For example, in some embodiments, a sliding or rolling device may be provided on the detection robot arm 1012 , and the sliding or rolling device moves along the first robot arm moving rail 1011 to achieve relative movement between the detection robot arm 1012 and the first robot arm moving rail 1011 .

[0102] In addition, in some other embodiments, the control device 103 is also connected to the first robotic arm moving guide rail 1011 to control the first robotic arm moving guide rail 1011 to drive the detection robotic arm 1012 to move.

[0103] Specifically, the control device 103 may further include a first guide rail controller, which may be connected to the first robotic arm moving guide rail 1011 and configured to control the first robotic arm moving guide rail 1011 to drive the detection robotic arm 1012 to move.

[0104] In some embodiments, the first robotic arm moving guide rail 1011 may include a fixed part and a movable part, the movable part can move relative to the fixed part, the detection robotic arm 1012 can be set on the movable part, and the robotic arm controller in the control device 103 drives the detection robotic arm 1012 to move along the first robotic arm moving guide rail 1011 by controlling the movable part.

[0105] In some of the embodiments, not only can a sliding or rolling device be provided on the detection robot arm 1012, but the first robot arm moving guide rail 1011 can also be provided with a fixed part and a moving part. This can further expand the movement capability of the detection robot arm 1012 and improve the flexibility of the system.

[0106] The above are only some exemplary embodiments of the present application. The present application does not limit the specific connection method between the detection robot arm 1012 and the first robot arm moving guide rail 1011.

[0107] In some embodiments, one or more detection robotic arms may be installed on the first robotic arm moving guide rail, and each detection robotic arm may also be installed with one or more paint surface imaging components.

[0108] Furthermore, the paint surface imaging assembly can be installed at the end of the inspection robot arm to improve the flexibility of the paint surface imaging assembly. Of course, the paint surface imaging assembly can also be installed at other positions of the inspection robot arm, such as at the middle section of the inspection robot arm, and the present application is not limited thereto.

[0109] In some embodiments, the paint surface imaging assembly may include more than two cameras and more than one diffuse light source system.

[0110] In the above embodiment, the defect detection device in the paint defect detection and polishing system adopts a guide rail design, which can improve the flexibility of the detection robot arm and enhance the convenience of the defect detection device in detecting the target object. At the same time, the guide rail and the robot arm are used to complete the data collection of the car body paint surface. The detection process does not affect the start and stop of the car body production line, thereby improving production efficiency.

[0111] In order to accurately locate the position of the target object and perform paint defect detection on the target object, in some embodiments, the paint defect detection and polishing system further includes:

[0112] The collection and guidance device is installed at the object production station, which is an upstream station of the defect detection station. The collection and guidance device is used to guide the defect detection device to collect the position and posture of the target object. The control device specifically controls the defect detection device to perform paint defect inspection on the target object based on the position and posture.

[0113] Specifically, when a target object passes through an object production station and is transported to a defect detection station, a collection and guidance device installed at the object production station generates an arrival signal and transmits the arrival signal to a control device. Based on the arrival signal, the control device controls the defect detection device to collect the position and posture of the target object at the defect detection station, obtain the position and posture of the target object, and then controls the defect detection device to perform paint defect detection on the target object based on the position and posture. By providing a collection and guidance device, the system can more accurately detect defects in target objects.

[0114] In some embodiments, the control device controls the paint surface imaging component in the defect detection device to collect object point cloud of the target object based on the reaching signal, and calculates the object point cloud collected by the paint surface imaging component through the image processor to obtain the position and posture of the target object.

[0115] In some embodiments, as shown in FIG. 3 , the defect grinding device 102 of the paint surface defect detection and grinding system includes a second robotic arm moving guide rail 1021 , a grinding robotic arm 1022 , and a force-controlled grinding head 1023 .

[0116] A grinding robot arm 1022 is mounted on a second robot arm motion rail 1021. A force-controlled grinding head 1023 is mounted on the grinding robot arm 1022 and is used to grind away paint defects. A control device 103 is connected to the grinding robot arm 1022 and the force-controlled grinding head 1023, respectively, to control the grinding robot arm 1022 to drive the force-controlled grinding head 1023 to move, thereby causing the force-controlled grinding head 1023 to grind away paint defects.

[0117] The control device 103 may be integrated with a grinding robot arm controller connected to the grinding robot arm 1022 and a force-controlled grinding head controller connected to the force-controlled grinding head 1023 .

[0118] In some embodiments, the force-controlled grinding head 1023 can be installed at the end of the grinding robot arm 1022, or in other embodiments, it can be installed at other positions on the grinding robot arm 1022, such as in the middle section of the grinding robot arm 1022, as long as the grinding operation can be completed.

[0119] Specifically, the polishing robot arm controller in the control device 103 is connected to the polishing robot arm 1022 and can control the polishing robot arm 1022 to drive the force-controlled polishing head 1023 to move. Similarly, the polishing robot arm 1022 can also have multiple motion dimensions, such as translational motion or rotational motion. The force-controlled polishing head controller in the control device 103 is connected to the force-controlled polishing head 1023 and can control the force-controlled polishing head 1023 to polish away paint defects.

[0120] Among them, the polishing robot arm 1022 can move along the second robot arm moving guide rail 1021, and there are many ways for the two to achieve movement.

[0121] For example, in some embodiments, the polishing robot arm 1022 may be provided with a sliding or rolling device, which moves along the second robot arm moving guide rail 1021 to achieve relative movement between the polishing robot arm 1022 and the second robot arm moving guide rail 1021.

[0122] In addition, in some other embodiments, the control device 103 is also connected to the second robotic arm moving guide rail 1021 to control the second robotic arm moving guide rail 1021 to drive the polishing robotic arm 1022 to move.

[0123] Specifically, the control device 103 may further include a second guide rail controller, which may be connected to the second robot arm moving guide rail 1021 and configured to control the second robot arm moving guide rail 1021 to drive the grinding robot arm 1022 to move. The second guide rail controller and the first guide rail controller may be one controller or independent controllers.

[0124] It is understood that in some embodiments, the defect detection device includes at least two first robot arm movable rails, and the two first robot arm movable rails are respectively arranged on both sides of the detection station. The defect polishing device includes at least two second robot arm movable rails, and the two second robot arm movable rails are respectively arranged on both sides of the polishing station.

[0125] Furthermore, in some embodiments, the first robot arm movable guide rail is docked with the second robot arm movable guide rail. Specifically, when the target object is located at the inspection station or the polishing station, the first robot arm movable guide rail and the second robot arm movable guide rail located on the same side of the target object can be docked to form a single guide rail. In this case, the inspection robot arm and the polishing robot arm located on the same side of the target object can both be arranged on this single guide rail. It is understood that this application does not impose any specific restrictions on the number and arrangement of the guide rails.

[0126] In some embodiments, as shown in FIG4 , the defect detection device 101 further includes: a detection station 3D positioning camera 1014 for performing local point cloud acquisition on the target object 104 located at the defect detection station to obtain first local point cloud data.

[0127] The control device 103 (not shown in the figure) is connected to the inspection station 3D positioning camera 1014, and is specifically used to determine the defect position of the paint surface defect in combination with the first object position represented by the first local point cloud data and the inspection posture of the inspection robot 1012.

[0128] Specifically, the control device 103 is connected to the inspection station 3D positioning camera 1014. When the target object 104 is transported to the defect inspection station, the control device 103 can control the inspection station 3D positioning camera 1014 to collect a local point cloud of the target object 104 at the defect inspection station to obtain first local point cloud data. The first local point cloud data is processed using an image processor to obtain a first object position represented by the first local point cloud data. The control device 103 obtains the inspection posture of the inspection robot 1012, and combines the first object position represented by the first local point cloud data and the inspection posture of the inspection robot 1012 to determine the defect position of the paint surface defect, thereby effectively improving the detection accuracy of the paint surface defect position.

[0129] In some embodiments, the defect grinding device further includes: a grinding station 3D positioning camera, which is used to collect local point cloud data of the target object located at the defect grinding station to obtain second local point cloud data.

[0130] The control device is connected to the 3D positioning camera of the polishing station, and is specifically used to control the polishing robot arm to drive the power-controlled polishing head to polish the paint surface defects based on the second object position represented by the second local point cloud data and the polishing posture of the polishing robot arm.

[0131] Specifically, the control device is connected to the 3D positioning camera of the polishing station. When the target object is transported to the defect polishing station, the control device can control the 3D positioning camera of the polishing station to collect a local point cloud of the target object at the defect polishing station, obtain second local point cloud data, and process the second local point cloud data using an image processor to obtain the second object position represented by the second local point cloud data. The control device obtains the detection posture of the polishing robot arm, combines the second object position represented by the second local point cloud data with the polishing posture of the polishing robot arm, and controls the polishing robot arm to drive the power-controlled polishing head to polish the paint surface defects, effectively improving the polishing accuracy of the polishing process.

[0132] In some embodiments, the installation layout and workspace of the inspection robot arm correspond one-to-one with the polishing robot arm, and the installation layout and acquisition area of ​​the inspection station 3D positioning camera correspond one-to-one with the polishing station 3D positioning camera, so that the inspection robot arm and the polishing robot arm can work together better to complete the precise polishing of paint defects and achieve the best polishing and repair effect.

[0133] In some embodiments, when the position of the second object is consistent with the position of the first object, the control device determines the polishing posture of the polishing robot arm according to the detection posture corresponding to the defect position; and controls the polishing robot arm to drive the power-controlled polishing head to polish the paint surface defects based on the polishing posture.

[0134] Specifically, when the position of the second object is consistent with the position of the first object, the control device can consider that the polishing robot arm has moved to the paint defect, and only the position of the force-controlled polishing head on the polishing robot arm needs to be adjusted. Therefore, the control device determines the polishing posture of the polishing robot arm according to the detection posture corresponding to the defect position, and controls the polishing robot arm to drive the force-controlled polishing head to polish the paint defect based on the polishing posture, so that the paint defect can be polished accurately.

[0135] In some embodiments, the paint defect detection and polishing system also includes an offline point external parameter calibration device for the paint imaging component and an offline external parameter calibration device for the paint imaging component and the inspection station 3D positioning camera.

[0136] In a specific application example, as shown in Figure 5, the offline point external calibration device of the paint surface imaging acquisition component includes a two-degree-of-freedom base 105 and a large-size plane calibration plate 106, wherein the two-degree-of-freedom base 105 can move up and down and rotate on a single axis, and the large-size calibration plate 106 is composed of thousands of calibration blocks with different IDs.

[0137] Furthermore, as shown in FIG6 , in some embodiments, the paint surface imaging acquisition component and the inspection station 3D positioning camera external parameter offline calibration device include a set of angle-adjustable brackets 107 and a set of double-sided calibration plates 108 , which can be adapted to different camera field of view layouts.

[0138] Furthermore, in a specific application example, the defect detection device performs paint defect detection on the target object, and the paint defects of the target object obtained may include defect size, defect type, spatial position of the defect center point, and defect surface normal vector.

[0139] In some embodiments, as shown in FIG. 7 , a paint defect detection and polishing system is provided. The system is described using the example of a vehicle body paint polishing system. The operating area of ​​the system is divided into a defect detection station and a defect polishing station. A vehicle body 104 to be inspected enters one of the two stations. The system includes:

[0140] The defect detection device 101 is used to detect and locate vehicle body paint defects. It includes more than two sets of detection robotic arms 1012, more than two sets of paint imaging components 1013 and a defect detection control component 1031. The defect detection device 101 also includes more than two sets of detection station 3D positioning cameras 1014. The defect detection control component 1031 includes a detection robotic arm controller, an acquisition component controller and an image processor; the detection robotic arm controller is connected to the detection robotic arm 1012, and the acquisition component controller and the image processor are connected to the paint imaging acquisition component 1013.

[0141] The defect polishing device 102 is used to repair paint defects detected at the inspection station. It includes two or more polishing robot arms 1022, two or more force-controlled polishing heads 1023, a polishing control assembly 1032, and two or more polishing station 3D positioning cameras 1024. The polishing control assembly 1032 includes a polishing robot arm controller and a force-controlled polishing head controller. The polishing robot arms 1022 are connected to the polishing robot arm controller. The force-controlled polishing head 1023 is installed at the end of the polishing robot arm 1022 and is connected to the force-controlled polishing head controller.

[0142] The system also includes a set of offline point external parameter calibration devices for paint surface imaging acquisition components (not shown in the figure), and a set of offline external parameter calibration devices for paint surface imaging acquisition components and inspection station 3D positioning cameras (not shown in the figure).

[0143] Among them, the installation layout and workspace of the inspection robot 1012 in this application correspond one-to-one with the polishing robot 1022, and the installation layout and vehicle body acquisition area of ​​the inspection station 3D positioning camera 1014 correspond one-to-one with the polishing station 3D positioning camera 1024. The paint surface imaging acquisition component offline point external parameter calibration device includes a set of two-degree-of-freedom bases and a set of large-size flat calibration plates, wherein the two-degree-of-freedom bases can move up and down and rotate on a single axis, and the large-size calibration plates are composed of thousands of calibration blocks with different IDs. The paint surface imaging acquisition component and the inspection station 3D positioning camera offline external parameter calibration device include a set of angle-adjustable brackets and a set of double-sided calibration plates, which can be applied to different camera field of view layouts.

[0144] The paint defect detection and polishing system in this embodiment can realize the streamlined operation of the inspection and polishing of the vehicle body to be inspected, improve the degree of automation and production efficiency of automobile paint defect detection and polishing, and can form a one-to-many or one-to-one layout. The guide rail can make the movement of the execution components such as the inspection robot arm and the polishing robot arm more flexible, accurate and reasonable, avoiding interference. Moreover, the guide rail design can make the defect detection operation and the defect polishing operation more accurate. The two can correspond one-to-one to form the best repair effect. At the same time, by matching the 3D positioning camera of the inspection station with the 3D positioning camera of the polishing station one-to-one, it is also possible to avoid the errors of the global calibration of the offline collection points of the inspection station and the global calibration of multiple polishing robots at the polishing station.

[0145] Based on the same inventive concept, an embodiment of the present application also provides a paint surface defect detection and polishing method applied to the above-mentioned paint surface defect detection and polishing system.

[0146] In some embodiments, as shown in FIG8 , a paint surface defect detection and polishing method is provided, comprising:

[0147] S802, controlling the defect detection device to perform paint surface defect detection on the target object to obtain the paint surface defects of the target object and the defect locations of the paint surface defects.

[0148] Specifically, when the target object is at the defect detection station, the control device controls the defect detection device to perform paint surface defect detection on the target object to obtain the paint surface defect of the target object and the defect position of the paint surface defect.

[0149] S804: Based on the defect position, control the defect polishing device to polish the paint surface defect.

[0150] Specifically, the control device controls the defect polishing device to polish the paint defect based on the detected defect location. It is understandable that the defect polishing device can polish the paint defect to remove the paint defect or perform a polishing or other repair process on the paint defect.

[0151] In the above-mentioned paint surface defect detection and polishing method, a defect detection device is provided at a defect detection station, and a defect polishing device is provided at a station downstream of the defect detection station, i.e., a defect polishing station. Both the defect detection device and the defect polishing device are connected to a control device. The control device can control the defect detection device to perform paint surface defect detection on the target object, obtain the paint surface defects of the target object, and the defect locations of the paint surface defects. Subsequently, based on the defect locations, the defect polishing device can be controlled to polish the paint surface defects. By collaboratively controlling the defect detection device and the defect polishing device, a streamlined operation of target object detection and polishing can be achieved. While improving the efficiency and accuracy of target object paint surface defect detection, the detected paint surface defects can also be automatically polished, further improving the production efficiency of the target object.

[0152] In some embodiments, controlling a defect detection device to perform paint defect detection on a target object to obtain the paint defect of the target object includes: controlling a detection robot arm in the defect detection device to drive an optical component in the defect detection device to move, thereby capturing an image of the paint surface of the target object, the optical component being disposed on the detection robot arm; and performing image processing on the paint surface image to determine the paint defect of the target object and the location of the paint defect.

[0153] Specifically, when the target object is at the defect detection station, the control device controls the detection robot arm in the defect detection device to drive the optical components in the defect detection device to move, collect an image of the target object's paint surface, process the image of the target object's paint surface, and obtain the target object's paint surface defects and the defect locations of the paint surface defects. It is understood that the control device may include an image processor, and after obtaining the target object's paint surface image, the image processor processes the target object's paint surface image to obtain the target object's paint surface defects and the defect locations of the paint surface defects.

[0154] In some embodiments, the paint surface defect detection and polishing method further includes:

[0155] The defect detection device is controlled based on the acquisition guidance device to collect the posture of the target object. The defect detection device is controlled based on the posture of the target object to perform paint surface inspection on the target object.

[0156] The collection and guidance device is arranged at the object production station, which is a downstream station of the defect detection station.

[0157] Specifically, when a target object passes through an object production station and is transported to a defect detection station, a collection and guidance device located at the object production station generates an arrival signal and transmits the arrival signal to a control device. Based on the arrival signal, the control device controls the defect detection device to collect the position and posture of the target object at the defect detection station, obtain the position and posture of the target object, and then controls the defect detection device to perform paint defect detection on the target object based on the position and posture. The guidance of the collection and guidance device enables the system to more accurately detect defects on the target object.

[0158] In some embodiments, controlling a defect detection device to detect paint defects on a target object to obtain a defect location of the paint defect includes:

[0159] A 3D positioning camera in the defect detection device is controlled to collect a local point cloud of a target object located at the defect detection station to obtain first local point cloud data. The position of the first object represented by the first local point cloud data and the detection posture of the detection robot arm in the defect detection device are combined to determine the defect location of the paint surface defect.

[0160] Specifically, when a target object is transported to a defect inspection station, the control device can control the inspection station's 3D positioning camera to collect a partial point cloud of the target object, obtaining first partial point cloud data. The image processor processes the first partial point cloud data to obtain a first object position represented by the first partial point cloud data. The control device then obtains the inspection posture of the inspection robot arm and, combining the first object position represented by the first partial point cloud data with the inspection posture of the inspection robot arm, determines the defect location of the paint surface defect, effectively improving the accuracy of detecting the paint surface defect location.

[0161] In some embodiments, based on the defect location, controlling the defect polishing device to polish the paint surface defect includes:

[0162] A 3D positioning camera at a polishing station in the defect polishing device is controlled to collect a local point cloud of a target object located at the defect polishing station, thereby obtaining second local point cloud data. The position of the second object represented by the second local point cloud data and the polishing posture of a polishing robot arm in the defect polishing device are combined to control the polishing robot arm to drive a power-controlled polishing head disposed on the polishing robot arm to polish the paint surface defect.

[0163] Specifically, when the target object is transported to the defect polishing station, the control device can control the polishing station 3D positioning camera to perform local point cloud acquisition of the target object at the defect polishing station to obtain second local point cloud data, and process the second local point cloud data using an image processor to obtain the second object position represented by the second local point cloud data. The control device obtains the detection posture of the polishing robot arm, and combines the second object position represented by the second local point cloud data with the polishing posture of the polishing robot arm to control the polishing robot arm to drive the power-controlled polishing head to polish the paint surface defects, effectively improving the polishing accuracy of the polishing process.

[0164] In some embodiments, as shown in FIG9 , based on the position of the second object represented by the second local point cloud data and the polishing posture of the polishing robot arm in the defect polishing device, controlling the polishing robot arm to drive the power-controlled polishing head to polish the paint surface defect includes:

[0165] S902 : Compare the second object position represented by the second partial point cloud data with the first object position represented by the first partial point cloud data.

[0166] Specifically, the control device compares the second object position represented by the second partial point cloud data with the first object position represented by the first partial point cloud data.

[0167] S904: When the second object position is consistent with the first object position, determine the grinding posture of the grinding robot arm according to the detection posture corresponding to the defect position.

[0168] Specifically, when the position of the second object is consistent with the position of the first object, it can be considered that the polishing robot arm has moved to the paint defect at this time, and only the position of the force-controlled polishing head on the polishing robot arm needs to be adjusted. Therefore, the control device determines the polishing posture of the polishing robot arm according to the detection posture corresponding to the defect position.

[0169] S906, based on the polishing posture control, the polishing robot arm drives the power-controlled polishing head to polish the paint surface defects.

[0170] Specifically, the control device controls the polishing robot arm based on the polishing posture to drive the power-controlled polishing head to polish the paint surface defects, and can accurately polish the paint surface defects.

[0171] In some embodiments, as shown in FIG10 , a paint surface defect detection and polishing method is provided, comprising:

[0172] Offline processing operations specifically include three steps: First, offline point planning for inspection stations and trajectory planning for multiple inspection robotic arms. Second, calibration of offline point calibration for inspection stations, including calibration of the paint imaging acquisition component and the extrinsic parameters of the inspection station's 3D positioning camera. Third, hand-eye calibration of the polishing robotic arm and the polishing station's 3D positioning camera.

[0173] The online processing operation specifically involves first detecting paint defects to obtain defect attributes and defect location; transferring the coordinates of the defect location to an automatic polishing component, which then polishes the paint defects.

[0174] In specific application examples, offline collection point planning for inspection stations includes:

[0175] Rough planning in the simulation environment: Import the actual vehicle body CAD model into the digital twin simulation system, specify the area to be inspected, and the simulation system automatically plans multiple acquisition points based on the vehicle body shape and the imaging component's field of view. Due to the certain discrepancy between simulation and reality, fine planning is required in the actual scenario.

[0176] In some embodiments, the actual scenario fine planning process may include the following steps:

[0177] First, the rough-planned points of the simulation scene are imported into the actual scene, and the detection robot arm equipped with an imaging acquisition component collects the point cloud data of the car body paint at each rough-planned point.

[0178] Second, all acquired point cloud data are spliced ​​based on the coarse planning point external parameters. Among them, the point external parameters of the actual scene fine planning are obtained by detecting the end posture of the robot arm and calculating the hand-eye calibration results.

[0179] Third, perform point assessment based on vehicle surface coverage and imaging quality.

[0180] Fourth, fine-tune the points, that is, evaluate the points according to the above steps, and repeat the point fine-tuning and evaluation process until the actual detection needs are met.

[0181] After offline point planning is complete, the trajectories of multiple inspection robotic arms need to be planned to meet two requirements: first, no interference between robotic arms and between robotic arms and the vehicle body, that is, no collision; second, optimal trajectories (minimizing time) to meet cycle requirements. In a specific application example, the trajectory planning process for multiple inspection robotic arms may include:

[0182] Rough planning in a simulation environment: Offline planned points are loaded into the digital twin simulation system. The system automatically plans interference areas based on these offline points, sets safety points, and interpolates path points between these points to complete trajectory planning for multiple inspection robotic arms. Due to the discrepancy between the simulation environment and the actual scene, fine planning in the actual scene is required.

[0183] Actual scenario fine planning: Import the rough planned trajectory of the simulation environment and fine-tune the trajectory according to the actual interference and operation conditions.

[0184] After the offline acquisition point planning is completed, in order to ensure the accuracy of the point external parameters, this application further uses visual calibration to perform calibration. In a specific application example, the process of offline acquisition point calibration at the inspection station may include:

[0185] Step 1: Divide the planned points under the jurisdiction of each detection robot into regions. Then, adjust the position of the base and the height and angle of the calibration plate according to the distribution of points so that as many points as possible can cover the calibration plate.

[0186] Step 2: Add multiple auxiliary points in the middle of the acquisition points to increase the common viewing area of ​​adjacent points and ensure the accuracy of calibration.

[0187] Step 3: Calibrate the camera intrinsic parameters of the paint surface imaging acquisition component based on the checkerboard calibration plate.

[0188] Step 4: The robotic arm carries the paint surface imaging acquisition component to acquire a two-dimensional image of the calibration plate 13 at the acquisition point and the auxiliary point.

[0189] Step 5: Extract features from the collected calibration plate image and detect the ID and center point information of each calibration block.

[0190] In step 6, based on the detected calibration block ID information, feature matching is performed on the calibration image of each point with the calibration images of other points, that is, calibration blocks with the same ID are regarded as a set of matching features.

[0191] Step 7: Based on the camera intrinsic parameters and feature matching information, the motion recovery structure algorithm is used to simultaneously estimate the three-dimensional coordinates of the feature points of the calibration plate and the pose information of each point.

[0192] Step 8: Estimate the global scale information of the scene based on the estimated three-dimensional coordinates of the feature points and the prior size information of the calibration plate.

[0193] Step 9: Calculate the relative pose of each acquisition point relative to the reference point based on the estimated phase pose of each point and the estimated global scale information.

[0194] Step 10, as shown in the calibration plate 108 in Figure 6, if the current calibration plate position A cannot be covered by all points, it is necessary to move the calibration plate to position B and ensure that the connecting points can cover both calibration plate positions A and B at the same time, repeat steps 4 to 9 to calculate the external parameters between the remaining points, and convert the external parameters of the remaining points to reference points based on the weighted average of multiple connecting points.

[0195] After completing the calibration of the external parameters of the offline acquisition points, the coordinates of the defects detected at each point can be converted to the reference point. In order to convert the defect coordinates to the coordinate system of the 3D positioning camera at the inspection station, it is necessary to calibrate the external parameters of the paint surface imaging acquisition component at the reference point and the 3D positioning camera at the inspection station offline. In a specific application example, as shown in FIG11 , the process may include the following: S1101, as shown in FIG7 , according to the common field of view of the 3D positioning camera at the inspection station and the paint surface imaging acquisition component at the reference point, adjust the angle of the double-sided calibration plate;

[0196] S1102: Move the double-sided calibration plate N times, and the 3D positioning camera at the inspection station and the paint surface imaging acquisition component synchronously capture N images of the calibration plate;

[0197] S1103, performing corner detection on the collected calibration plate image;

[0198] S1104, calculating the relative pose of the single-sided calibration plate relative to the acquisition component or the 3D positioning camera based on the detected corner points;

[0199] S1105, Estimating the geometry of a double-sided calibration plate based on bundle adjustment and image optimization;

[0200] S1106, based on the relative pose of the single-sided calibration plate with respect to the acquisition component or the 3D positioning camera and the estimated geometric structure of the double-sided calibration plate, estimate the external parameters of the inspection station 3D positioning camera and the paint surface imaging acquisition component at the reference point.

[0201] In a specific application example, the process of hand-eye calibration of the polishing station 3D positioning camera and the polishing robot arm may include: fixing the calibration plate to the end of the polishing robot arm, moving the polishing robot arm multiple times so that the polishing station 3D positioning camera can observe the calibration plate, recording the rectangular coordinates of the polishing robot arm and the corresponding calibration plate image, and calibrating the external parameters of the polishing station 3D positioning camera relative to the polishing robot arm base coordinate system based on the eye-in-hand external calibration algorithm.

[0202] In a specific application example, when performing paint defect inspection, after the vehicle body arrives at the inspection station, several (such as four) inspection robotic arms take photos and collect data according to the offline planned collection points, and use the paint surface inspection method to simultaneously perform defect detection and positioning, and output the defect attributes, including defect type, size, three-dimensional coordinates of the center point, and normal direction of the defect neighborhood surface.

[0203] In a specific application example, as shown in FIG12 , when transferring the coordinates of the defect location, the specific process may include:

[0204] When the vehicle arrives at the inspection station, the 3D positioning camera at the inspection station synchronously collects the local point cloud of the vehicle body for subsequent body posture correction;

[0205] After the vehicle body is inspected, the coordinate system C of each acquisition point is set. i The defect coordinates detected by offline calibration point external parameters Convert to reference point coordinate system C r Down;

[0206] The defect coordinates in the reference point coordinate system are calibrated by the external parameters of the offline calibration Convert to the inspection station 3D positioning camera coordinate system C d Down;

[0207] When the car body arrives at the polishing station, the 3D positioning camera at the polishing station collects the local point cloud of the car body, and obtains the corrected posture of the car body through online registration with the point cloud collected by the inspection station Then the defect coordinates in the 3D positioning camera coordinate system of the inspection station are corrected by the body posture Go to the grinding station 3D positioning camera coordinate system C p Down;

[0208] The defect coordinates in the 3D positioning camera coordinate system of the grinding station are calibrated by offline hand-eye calibration. Convert to the grinding robot arm base coordinate system O p Down.

[0209] In a specific application example, when the car body arrives at the polishing station and the defect coordinates are transferred, multiple polishing robotic arms begin online task planning, path planning, and trajectory planning, and then collaboratively polish the defects.

[0210] The paint defect detection and polishing method in this embodiment has a wide range of applications, a high degree of intelligence, and high detection and polishing efficiency. The use of a visual positioning solution can greatly improve the accuracy of defect coordinate transmission, and the visual calibration accuracy is much higher than the physical positioning accuracy.

[0211] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0212] Based on the same inventive concept, embodiments of the present application also provide a paint surface defect detection and polishing device for implementing the aforementioned paint surface defect detection and polishing method. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more paint surface defect detection and polishing device embodiments provided below can be found in the above-mentioned limitations of the paint surface defect detection and polishing method, and will not be repeated here.

[0213] In some embodiments, as shown in FIG13 , a paint surface defect detection and polishing device 1300 is provided, comprising: a defect detection module 1301 and a defect polishing module 1302 , wherein:

[0214] The defect detection module 1301 is used to control the defect detection device to perform paint surface defect detection on the target object, and obtain the paint surface defects of the target object and the defect locations of the paint surface defects.

[0215] The defect polishing module 1302 is used to control the defect polishing device to polish the paint surface defect based on the defect position.

[0216] The above-mentioned paint surface defect detection and polishing device is provided with a defect detection device at the defect detection station, and a defect polishing device at the downstream station of the defect detection station, i.e., the defect polishing station. Both the defect detection device and the defect polishing device are connected to a control device. The control device can control the defect detection device to perform paint surface defect detection on the target object, obtain the paint surface defects of the target object, and the defect location of the paint surface defects, and then control the defect polishing device to polish the paint surface defects based on the defect location. By coordinating the control of the defect detection device and the defect polishing device, a streamlined operation of the detection and polishing of the target object can be achieved. While improving the efficiency and accuracy of the paint surface defect detection of the target object, the detected paint surface defects can also be automatically polished, further improving the production efficiency of the target object.

[0217] In some embodiments, the defect detection module is also used to: control the detection robot arm in the defect detection device to drive the optical component in the defect detection device to move, collect the paint surface image of the target object, and the optical component is set on the detection robot arm; and perform image processing on the paint surface image to determine the paint surface defects of the target object.

[0218] In some embodiments, the paint defect detection and polishing device further includes: a guidance module for controlling the acquisition guidance device to acquire the posture of the target object; and controlling the defect detection device to perform paint surface inspection on the target object based on the posture of the target object.

[0219] In some embodiments, the defect detection module is also used to: control the 3D positioning camera of the inspection station in the defect detection device to perform local point cloud acquisition on the target object located at the defect detection station to obtain first local point cloud data; and determine the defect position of the paint defect in combination with the first object position represented by the first local point cloud data and the detection posture of the detection robot arm in the defect detection device.

[0220] In some embodiments, the defect polishing module is also used to: control the 3D positioning camera of the polishing station in the defect polishing device to perform local point cloud acquisition on the target object located at the defect polishing station to obtain second local point cloud data; and combine the second object position represented by the second local point cloud data and the polishing posture of the polishing robot arm in the defect polishing device to control the polishing robot arm to drive the force-controlled polishing head to polish the paint surface defects, and the force-controlled polishing head is set on the polishing robot arm.

[0221] In some embodiments, the defect polishing module is also used to: compare the second object position represented by the second local point cloud data with the first object position represented by the first local point cloud data; when the second object position is consistent with the first object position, determine the polishing posture of the polishing robot arm according to the detection posture corresponding to the defect position; and control the polishing robot arm to drive the force-controlled polishing head to polish the paint defect based on the polishing posture.

[0222] Each module in the paint defect detection and polishing device described above can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in hardware form, or can be stored in a computer device memory in software form, so that the processor can call and execute the corresponding operations of each module.

[0223] In some embodiments, a computer device is provided, which may be a control device, and its internal structure diagram may be as shown in FIG14 . The computer device includes a processor, a memory, and a network interface connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store paint defects of the target object and defect location data of the paint defects. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a paint defect detection and polishing method is implemented.

[0224] Those skilled in the art will understand that the structure shown in FIG14 is merely a block diagram of a portion of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0225] In some embodiments, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the specific implementation steps of the above-mentioned paint defect detection and polishing method are realized.

[0226] In some embodiments, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the specific implementation steps of the above-mentioned paint defect detection and polishing method are implemented.

[0227] In some embodiments, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the specific implementation steps of the above-mentioned paint defect detection and polishing method.

[0228] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0229] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processor involved in the various embodiments provided herein may be, but are not limited to, a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, and the like.

[0230] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0231] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A paint surface defect detection and polishing system, characterized in that: The system comprises: A defect detection device provided at a defect detection station; A defect polishing device is arranged at a defect polishing station; the defect polishing station is a downstream station of the defect detection station; A control device connecting the defect detection device and the defect grinding device; and The control device is used to control the defect detection device to perform paint defect detection on the target object to obtain the paint defect of the target object and the defect position of the paint defect; and is also used to control the defect polishing device to polish the paint defect based on the defect position.

2. The system according to claim 1, characterized in that The defect detection device comprises a first mechanical arm moving guide rail, a detection mechanical arm and a paint surface imaging component; The detection mechanical arm is arranged on the first mechanical arm moving guide rail; The paint surface imaging component is arranged on the detection robot arm and is used to collect the paint surface image of the target object; and The control device is connected to the detection robot arm and the paint surface imaging component respectively, and is used to control the detection robot arm to drive the paint surface imaging component to move, so that the paint surface imaging component collects the paint surface image of the target object, and performs image processing on the paint surface image to determine the paint surface defects of the target object.

3. The system according to claim 2, characterized in that The control device is also connected to the first mechanical arm moving guide rail, and is used to control the first mechanical arm moving guide rail to drive the detection mechanical arm to move.

4. The system according to any one of claims 1 to 3, characterized in that: The system further comprises: A collection and guidance device is provided at an object production station; the object production station is an upstream station of the defect detection station; and The acquisition guidance device is used to guide the defect detection device to acquire the posture of the target object; the control device specifically controls the defect detection device to perform paint defect detection on the target object based on the posture.

5. The system according to any one of claims 1 to 4, characterized in that: The defect grinding device comprises a second mechanical arm moving guide rail, a grinding mechanical arm and a force-controlled grinding head; The polishing mechanical arm is arranged on the second mechanical arm moving guide rail; The force-controlled grinding head is arranged on the grinding robot arm, and is used for grinding the paint surface defects; and The control device is connected to the grinding robot arm and the force-controlled grinding head respectively, and is used to control the grinding robot arm to drive the force-controlled grinding head to move, so that the force-controlled grinding head performs grinding processing on the paint surface defects.

6. The system according to claim 5, characterized in that The control device is also connected to the second mechanical movable guide rail, and is used to control the second mechanical movable guide rail to drive the grinding robot arm to move.

7. The system according to claim 5 or 6, characterized in that: The first mechanical arm moving guide rail is docked with the second mechanical arm moving guide rail.

8. The system according to any one of claims 2 to 7, characterized in that: The defect detection device also includes: A 3D positioning camera for the inspection station is used to collect local point cloud data of the target object located at the defect inspection station to obtain first local point cloud data; and The control device is connected to the 3D positioning camera of the inspection station, and is specifically used to determine the defect position of the paint surface defect in combination with the first object position represented by the first local point cloud data and the inspection posture of the inspection robot arm.

9. The system according to any one of claims 5 to 8, characterized in that: The defect polishing device also includes: A 3D positioning camera for a polishing station is used to collect local point cloud data of a target object located at the defect polishing station to obtain second local point cloud data; and The control device is connected to the 3D positioning camera of the polishing station, and is specifically used to control the polishing robot arm to drive the force-controlled polishing head to polish the paint surface defects in combination with the second object position represented by the second local point cloud data and the polishing posture of the polishing robot arm.

10. The system according to claim 9, characterized in that The installation layout and working space of the detection robot arm correspond one-to-one with the polishing robot arm, and the installation layout and acquisition area of ​​the detection station 3D positioning camera correspond one-to-one with the polishing station 3D positioning camera.

11. The system according to claim 9 or 10, characterized in that: The control device determines the grinding posture of the grinding robot arm according to the detection posture corresponding to the defect position when the second object position is consistent with the first object position; And based on the polishing posture, the polishing robot arm is controlled to drive the force-controlled polishing head to polish the paint surface defects.

12. A paint surface defect detection and polishing method, characterized in that: The method comprises: Controlling the defect detection device to perform paint surface defect detection on the target object to obtain the paint surface defect of the target object and the defect position of the paint surface defect; and Based on the defect position, the defect grinding device is controlled to grind the paint surface defect.

13. The method according to claim 12, characterized in that The control defect detection device performs paint surface defect detection on the target object to obtain the paint surface defect of the target object and the defect position of the paint surface defect, including: Controlling a detection mechanical arm in the defect detection device to drive an optical component in the defect detection device to move, and collecting a paint surface image of a target object, wherein the optical component is disposed on the detection mechanical arm; and The paint surface image is processed to determine the paint surface defect of the target object and the defect position of the paint surface defect.

14. The method according to claim 12 or 13, characterized in that The method further comprises: Based on the acquisition guidance device, the absence detection device is controlled to acquire the position and posture of the target object; and The defect detection device is controlled based on the position and posture of the target object to perform paint surface detection on the target object.

15. The method according to any one of claims 13 or 14, characterized in that: The controlling defect detection device performs paint surface defect detection on the target object to obtain the defect position of the paint surface defect, including: Controlling a 3D positioning camera of a detection station in a defect detection device to collect local point cloud data of a target object located at the defect detection station to obtain first local point cloud data; and The defect position of the paint surface defect is determined by combining the first object position represented by the first local point cloud data and the detection posture of the detection robot arm in the defect detection device.

16. The method according to any one of claims 12 to 15, characterized in that: The step of controlling the defect grinding device to grind the paint surface defect based on the defect position includes: Controlling a 3D positioning camera of a grinding station in the defect grinding device to collect local point cloud data of a target object located at the defect grinding station to obtain second local point cloud data; and In combination with the second object position represented by the second local point cloud data and the grinding posture of the grinding robot arm in the defect grinding device, the grinding robot arm is controlled to drive the force-controlled grinding head to grind the paint surface defects, and the force-controlled grinding head is arranged on the grinding robot arm.

17. The method according to claim 16, characterized in that The method combines the second object position represented by the second local point cloud data and the grinding posture of the grinding robot arm in the defect grinding device to control the grinding robot arm to drive the power-controlled grinding head to grind the paint surface defect, including: comparing a second object position represented by the second local point cloud data with a first object position represented by the first local point cloud data; In a case where the second object position is consistent with the first object position, determining the grinding posture of the grinding robot arm according to the detection posture corresponding to the defect position; and Based on the polishing posture, the polishing robot arm is controlled to drive the force-controlled polishing head to polish the paint surface defects.

18. A paint surface defect detection and polishing device, characterized in that: The device comprises: A defect detection module, used to control the defect detection device to perform paint surface defect detection on the target object, and obtain the paint surface defect of the target object and the defect position of the paint surface defect; and The defect polishing module is used to control the defect polishing device to polish the paint surface defect based on the defect position.

19. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 12 to 17 are implemented.

20. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 12 to 17 are implemented.

Images