A robotic arm trajectory planning method for fully automated laser cleaning of tire molds

Abstract

This disclosure provides a robotic arm trajectory planning method for fully automated laser cleaning of tire molds, comprising: using a 3D structured light camera to capture images of the tire mold to obtain regional point cloud data; using the camera's hand-eye calibration to obtain point cloud data of the tire mold in the robotic arm coordinate system; mounting a laser cleaning head at the end of the robotic arm; the laser cleaning head moving around an auxiliary axis at the end of the end according to the motion trajectory of the robotic arm; the auxiliary axis being a horizontal line located at the end of the laser cleaning head; performing feature recognition on the point cloud data to obtain the dimensions of the tire mold; the dimensions of the tire mold including at least one of the feature dimensions of the tread block mold and the cross-sectional dimensions of the side plate mold; and calculating the motion trajectory of the robotic arm and the rotation angle of the laser cleaning head around the auxiliary axis based on the dimensions of the tire mold to complete the laser cleaning trajectory planning. This disclosure also provides a robotic arm trajectory planning device for fully automated laser cleaning of tire molds.

Description

Technical Field

[0001] This disclosure relates to the field of laser cleaning, and more specifically to a robotic arm trajectory planning method for fully automated laser cleaning of tire molds. Background Technology

[0002] Tire molds are used in tire production. During the production process, surface residues such as rubber and sulfides are generated, necessitating regular cleaning. Traditional tire mold cleaning methods mainly involve manual hand-held dry ice equipment or chemical cleaning equipment, which are inefficient, ineffective, and environmentally unfriendly.

[0003] Because tire production requires a high cycle time, the efficiency of tire mold cleaning is a crucial indicator. Therefore, the degree of automation in tire mold cleaning equipment is extremely important. Existing tire mold cleaning equipment often requires manual measurement and teaching to plan the movement path of the robotic arm, making full automation impossible. Therefore, robotic arm trajectory planning is a vital step in tire mold laser cleaning. Summary of the Invention

[0004] In view of the above problems, this disclosure provides a robotic arm trajectory planning method for fully automated laser cleaning of tire molds, which combines 3D machine vision to perform trajectory planning for the robotic arm.

[0005] This disclosure provides a robotic arm trajectory planning method for fully automated laser cleaning of tire molds, comprising: using a 3D structured light camera to photograph the tire mold to obtain regional point cloud data; using the camera's hand-eye calibration of the regional point cloud data to obtain the tire mold's point cloud data in the robotic arm coordinate system; installing a laser cleaning head at the end of the robotic arm; the laser cleaning head moving around an auxiliary axis at the end of the end according to the robotic arm's motion trajectory; the auxiliary axis being a horizontal line located at the end of the laser cleaning head; performing feature recognition on the point cloud data to obtain the dimensions of the tire mold; the dimensions of the tire mold including at least one of the feature dimensions of the tread block mold and the cross-sectional dimensions of the side plate mold; and calculating the robotic arm's motion trajectory and the rotation angle of the laser cleaning head around the auxiliary axis based on the tire mold dimensions to complete the laser cleaning trajectory planning.

[0006] According to embodiments of this disclosure, feature recognition is performed on point cloud data to obtain the dimensions of a tire mold, including: extracting the edge contour of the tread block mold through straight line and rectangular feature recognition; identifying the feature dimensions of the tread block mold based on the edge contour of the tread block mold; the feature dimensions of the tread block mold include at least one of total length, total width, total height, cross-sectional width, and cross-sectional depth; and / or extracting the edge contour of the side plate mold through arc recognition; identifying the cross-sectional dimensions of the side plate mold based on the edge contour of the side plate mold; the cross-sectional dimensions of the side plate mold include at least one of radius and height.

[0007] According to embodiments of this disclosure, the edge contour of the pattern block mold is extracted by recognizing straight lines and rectangles, including extracting cross-sections of point cloud data along the first and second direction coordinate axes of the robotic arm coordinate system based on the laser linewidth of the laser cleaning head; the first and second direction coordinate axes are perpendicular; the horizontal plane containing the first and second direction coordinate axes is parallel to the ground of the tire mold; the distance between adjacent cross-sections is the laser linewidth.

[0008] According to embodiments of this disclosure, the edge contour of the side panel mold is extracted by arc recognition, including: recognizing the point cloud data of the side panel mold to obtain a series of full circular curves; for every two adjacent full circular curves, averaging the two adjacent full circular curves to obtain an average full circular curve for recognizing the cross-sectional dimensions of the side panel mold; wherein, averaging the two adjacent full circular curves to obtain the average full circular curve includes: calculating the average of the radii of the two adjacent full circular curves as the average radius; calculating the midpoint of the center of the two adjacent full circular curves as the average center; and obtaining the average full circular curve using the average radius and the average center.

[0009] According to embodiments of this disclosure, the motion trajectory of the robotic arm and the rotation angle of the laser cleaning head around the end-effector are calculated based on the dimensions of the tire mold, including: determining the rotation angle of the end-effector based on the edge contour of the tread block mold and / or the side plate mold according to the normal vector; and determining the motion trajectory of the robotic arm based on the cross-sectional dimensions and edge contour of the tread block mold and / or the side plate mold and the rotation angle of the end-effector, wherein the motion of the end-effector and the robotic arm are independent of each other.

[0010] According to an embodiment of this disclosure, using a 3D structured light camera to photograph a tire mold to obtain regional point cloud data includes: using a planar support tool and a conveyor belt to move the tire mold to a clean area where a robotic arm is located; dividing the planar support tool into a preset number of photographing areas; calling a 3D camera to photograph the planar support tool and the tire mold to obtain regional point cloud data; the union of the preset number of photographing areas includes the complete planar support tool and tire mold.

[0011] According to embodiments of this disclosure, point cloud data of a tire mold in the robotic arm coordinate system is obtained using point cloud data of a camera hand-eye calibration area. This includes: stitching together point cloud data of a preset number of photographed areas using the camera hand-eye calibration results to obtain overall point cloud data; obtaining a plane based on the overall point cloud data, and identifying the plane with the largest area as the plane bearing tool; filtering the point cloud data of the plane bearing tool to obtain point cloud data of all molds; and using clustering to divide the point cloud data of all molds to obtain individual point cloud data for each tire mold.

[0012] The second aspect of this disclosure provides a robotic arm trajectory planning device for fully automated laser cleaning of tire molds. The device, capable of implementing the aforementioned method, includes: a data acquisition module for capturing images of the tire mold using a 3D structured light camera to obtain regional point cloud data; a data processing module for calibrating the regional point cloud data using the camera's hand-eye coordinate system to obtain point cloud data of the tire mold in the robotic arm coordinate system; a laser cleaning head mounted at the end of the robotic arm; the laser cleaning head moving around an auxiliary axis at the end of the end of the robotic arm according to the robotic arm's motion trajectory; the auxiliary axis being a horizontal line located at the end of the laser cleaning head; a size recognition module for performing feature recognition on the point cloud data to obtain the dimensions of the tire mold; the dimensions of the tire mold include at least one of the feature dimensions of the tread block mold and the cross-sectional dimensions of the side plate mold; and a trajectory planning module for calculating the robotic arm's motion trajectory and the rotation angle of the laser cleaning head around the auxiliary axis based on the dimensions of the tire mold, thereby completing the laser cleaning trajectory planning.

[0013] A third aspect of this disclosure provides an electronic device comprising: one or more processors; and a memory for storing one or more programs, wherein, when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to perform the above-described robotic arm trajectory planning method for fully automated laser cleaning of tire molds.

[0014] A fourth aspect of this disclosure also provides a computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, cause the processor to perform the above-described robotic arm trajectory planning method for fully automated laser cleaning of tire molds.

[0015] According to the robotic arm trajectory planning method for fully automated laser cleaning of tire molds provided in this disclosure, a 3D camera carried by the robotic arm takes pictures of the tire mold on the tray to obtain 3D point cloud data. The motion trajectory of the robotic arm and the rotation angle of the end effector are obtained through point cloud processing algorithms. Since the motion trajectory planning and rotation angle calculation are fully automated, and the optimal rotation angle of the end effector is determined based on the surface normal, laser cleaning is performed in the optimal posture. Therefore, this method at least partially solves the technical problems of low automation and poor effect in traditional laser cleaning, achieving the technical effect of fully automated, high-precision laser cleaning of tire molds. Attached Figure Description

[0016] Figure 1 A flowchart illustrating a robotic arm trajectory planning method for fully automated laser cleaning of tire molds according to an embodiment of the present disclosure is shown schematically.

[0017] Figure 2 A schematic diagram of a laser cleaning head and an end auxiliary shaft according to an embodiment of the present disclosure is shown.

[0018] Figure 3 A schematic diagram illustrating the area division of a conveyor belt according to an embodiment of the present disclosure is shown.

[0019] Figure 4 This illustration schematically shows a diagram illustrating the division of the 3D camera's image capture area according to an embodiment of the present disclosure;

[0020] Figure 5 A partial coordinate system diagram of a patterned block mold according to an embodiment of the present disclosure is shown schematically;

[0021] Figure 6 This schematically illustrates a first cross-sectional extraction diagram of a patterned block mold according to an embodiment of the present disclosure;

[0022] Figure 7 This schematically illustrates a second cross-sectional extraction diagram of a patterned block mold according to an embodiment of the present disclosure;

[0023] Figure 8 A schematic diagram of a partial coordinate system of a side plate mold according to an embodiment of the present disclosure is shown.

[0024] Figure 9 This illustration schematically shows a diagram illustrating the calculation of the complete circular trajectory of a side plate mold according to an embodiment of the present disclosure;

[0025] Figure 10 A schematic diagram of a robotic arm trajectory planning device for fully automated laser cleaning of tire molds according to an embodiment of the present disclosure is shown.

[0026] Figure 11 A block diagram schematically illustrates an electronic device suitable for implementing a robotic arm trajectory planning method for fully automated laser cleaning of tire molds, according to an embodiment of the present disclosure. Detailed Implementation

[0027] The embodiments of the present disclosure will now be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the disclosure. In the following detailed description, numerous specific details are set forth to provide a thorough understanding of the embodiments of the present disclosure for ease of explanation. However, it will be apparent that one or more embodiments may be practiced without these specific details. Furthermore, descriptions of well-known structures and techniques are omitted in the following description to avoid unnecessarily obscuring the concepts of the present disclosure.

[0028] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit this disclosure. The terms “comprising,” “including,” etc., as used herein indicate the presence of the stated features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0029] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein are to be interpreted in a manner consistent with the context of this specification, and not in an idealized or overly rigid way.

[0030] When using expressions such as "at least one of A, B, and C", they should generally be interpreted in accordance with the meaning that is commonly understood by a person skilled in the art (e.g., "a system having at least one of A, B, and C" should include, but is not limited to, a system having A alone, a system having B alone, a system having C alone, a system having A and B, a system having A and C, a system having B and C, and / or a system having A, B, and C, etc.).

[0031] First, the technical terms used in this disclosure are explained as follows:

[0032] Camera hand-eye calibration: One of the core technologies of machine vision in robot guidance, it is mainly used to determine the transformation relationship between the robot arm and the camera, that is, to unify the relative pose relationship between the robot end effector (hand) and the camera, and complete the coordinate transformation from camera to robot, so that the robot can accurately locate the target in the camera's field of view.

[0033] Point cloud data: Point cloud data is a collection of a large number of points on the surface of an object obtained through scanning technology (such as laser scanning, camera shooting, etc.). Each point contains three-dimensional coordinates (X,Y,Z) and possible other attribute information (such as color, reflectivity, intensity, etc.).

[0034] 3D structured light cameras: The working principle of 3D structured light cameras is mainly based on structured light projection and binocular vision technology. First, a structured light projector illuminates the surface of the object being measured with a light source (usually a red or green laser light source), forming a series of light spots or stripes. These light spots or stripes change according to the shape of the object's surface. Then, the camera captures these changing images, and combined with computer algorithms, calculates the 3D point cloud data of the object's surface.

[0035] Figure 1 A flowchart illustrating a method according to an embodiment of this disclosure is shown schematically, such as Figure 1As shown, embodiments of this disclosure provide a robotic arm trajectory planning method for fully automated laser cleaning of tire molds, including: using a 3D structured light camera to capture images of the tire mold to obtain regional point cloud data; using the camera's hand-eye calibration of the regional point cloud data to obtain point cloud data of the tire mold in the robotic arm coordinate system; installing a laser cleaning head at the end of the robotic arm; the laser cleaning head moving around an auxiliary axis at the end of the robotic arm according to the motion trajectory of the robotic arm; the auxiliary axis at the end being a horizontal line located at the end of the laser cleaning head; performing feature recognition on the point cloud data to obtain the dimensions of the tire mold; the dimensions of the tire mold including at least one of the feature dimensions of the tread block mold and the cross-sectional dimensions of the side plate mold; and calculating the motion trajectory of the robotic arm and the rotation angle of the laser cleaning head around the auxiliary axis at the end based on the dimensions of the tire mold, thereby completing the laser cleaning trajectory planning.

[0036] In this embodiment, such as Figure 2 As shown, the laser cleaning head is mounted at the end of the robotic arm and includes a horizontal end-effector axis. The cleaning head can rotate around this axis under the drive of a motor, thus increasing the robotic arm's workspace. Therefore, the laser cleaning motion trajectory includes not only the robotic arm's 6-axis motion trajectory but also the motion trajectory of the laser cleaning head's end-effector axis, for a total of 7 degrees of freedom. For the end-effector axis, before planning the robotic arm's 6-axis trajectory, the optimal rotation angle of the end-effector axis is determined based on the surface normal, and then the robotic arm's trajectory is planned to perform laser cleaning in the optimal posture. The movement of the end-effector axis is independent of the robotic arm; the end-effector axis does not participate in the linkage during the robotic arm's movement.

[0037] Through the embodiments of this disclosure, multiple tire molds can be cleaned simultaneously and efficiently and accurately by planning the trajectory of an automated robotic arm and a laser cleaning head, thereby improving production efficiency. The high quality of the cleaning process is ensured by planning the motion trajectory of the robotic arm and the rotation angle of the laser cleaning head around the end auxiliary axis.

[0038] Based on the above embodiments, feature recognition is performed on the point cloud data to obtain the dimensions of the tire mold, including: extracting the edge contour of the tread block mold through straight line and rectangle feature recognition; identifying the feature dimensions of the tread block mold based on the edge contour of the tread block mold; the feature dimensions of the tread block mold include at least one of the following: total length, total width, total height, cross-sectional width, and cross-sectional depth; and / or extracting the edge contour of the side plate mold through arc recognition; identifying the cross-sectional dimensions of the side plate mold based on the edge contour of the side plate mold; the cross-sectional dimensions of the side plate mold include at least one of the following: radius and height.

[0039] Through embodiments of this disclosure, key features of tire molds, such as the dimensions and contours of tread blocks and side plates, are accurately extracted using line, rectangle, and arc recognition technologies. This provides precise dimensional data, offering a reliable basis for subsequent trajectory planning and laser cleaning. Furthermore, image processing and machine learning technologies enable automatic mold dimension recognition, improving the system's intelligence level.

[0040] Based on the above embodiments, the edge contour of the pattern block mold is extracted by recognizing straight lines and rectangles. This includes extracting a cross section of point cloud data along the first and second direction coordinate axes of the robotic arm coordinate system according to the laser linewidth of the laser cleaning head; the first and second direction coordinate axes are perpendicular; the horizontal plane containing the first and second direction axes is parallel to the ground of the tire mold; the distance between adjacent cross sections is the laser linewidth; the edge contour of the pattern block mold is extracted using the cross section.

[0041] In this embodiment, such as Figure 5 As shown, for the patterned block mold, edge contours are extracted through line and rectangle feature recognition to establish a local coordinate system. Then, the transformation relationship between the local coordinate system and the robotic arm coordinate system is calculated to obtain the three-axis coordinates and three-axis Euler angles of the patterned block mold in the robotic arm coordinate system. Then, two cross-sectional point set extractions are performed. The first extraction is as follows... Figure 6 As shown, based on the laser linewidth of the cleaning head, the point cloud data of the patterned block is segmented along the x-axis of the local coordinate system at intervals of one laser linewidth, resulting in several sets of point sets for the yz cross sections; the second extraction is as follows... Figure 7 As shown, based on the laser linewidth of the cleaning head, the point cloud data of the pattern block is segmented along the y-axis of the local coordinate system at intervals of one laser linewidth, resulting in several sets of point sets for the xz cross section.

[0042] Through the embodiments of this disclosure, the size and shape of the patterned block mold are accurately identified by extracting its edge contour, providing accurate data for cleaning trajectory planning; the interval of cross-sectional extraction is determined according to the laser linewidth to ensure the integrity and accuracy of the data.

[0043] Based on the above embodiments, the edge contour of the side plate mold is extracted by arc recognition, including: recognizing the point cloud data of the side plate mold to obtain a series of full circular curves; arranging the series of full circular curves according to their radius; averaging the two adjacent full circular curves to obtain an average full circular curve for recognizing the cross-sectional dimensions of the side plate mold; wherein, averaging the two adjacent full circular curves to obtain the average full circular curve includes: calculating the average of the radii of the two adjacent full circular curves as the average radius; calculating the midpoint of the center of the two adjacent full circular curves as the average center; and obtaining the average full circular curve using the average radius and the average center.

[0044] In this embodiment, such as Figure 8 As shown, for the side plate mold, the pose of the center of the circle can be identified by the arc feature recognition, thereby establishing a local coordinate system. Then, the transformation relationship between the local coordinate system and the robot arm coordinate system is calculated to obtain the three-axis coordinates and three-axis Euler angles of the side plate mold in the robot arm coordinate system.

[0045] In this embodiment, such as Figure 9 As shown, multiple circular curves can be extracted from the point cloud of the side plate. Arranging these circular curves according to their radius yields a series of circular curves. Then, for every two adjacent circular curves, the average is taken (the specific averaging method is: calculate the sum of the radii and divide by 2, and calculate the center of the circle according to the average of the centers of the two circular arcs) to obtain a new circular arc trajectory, which is the motion trajectory of the robotic arm.

[0046] Through the embodiments of this disclosure, the cross-sectional contour of the side plate mold is accurately extracted using arc recognition technology, providing a basis for subsequent dimensional measurement and trajectory planning; by averaging adjacent full-circle curves, data noise is reduced, and cleaning accuracy and efficiency are improved.

[0047] Based on the above embodiments, the motion trajectory of the robotic arm and the rotation angle of the laser cleaning head around the end auxiliary axis are calculated according to the size of the tire mold. This includes: calculating the motion trajectory of the robotic arm and the rotation angle of the laser cleaning head around the end auxiliary axis according to the size of the tire mold, including: determining the rotation angle of the end auxiliary axis based on the edge contour of the tread block mold and / or the side plate mold according to the normal vector; determining the motion trajectory of the robotic arm based on the cross-sectional dimensions and edge contour of the tread block mold and / or the side plate mold and the rotation angle of the end auxiliary axis. Wherein, the motion of the end auxiliary axis and the robotic arm are independent of each other.

[0048] In this embodiment, for the pattern block mold, the motion trajectory of the robotic arm is the trajectory fitted from the interface points extracted twice from the pattern block mold. Arranged in the order of shortest time, these trajectories form a complete robotic arm motion trajectory, thus completing the trajectory planning for a single pattern block mold. Further, firstly, the optimal rotation angle of the end-effector auxiliary axis needs to be obtained by calculating the plane normal vector near the pattern block trajectory point. Then, using this end-effector auxiliary axis rotation angle, the tool coordinate system (TCP) of the robotic arm is established. Next, the posture of the robotic arm at the trajectory point is calculated, ultimately obtaining the 6-axis coordinate data of that trajectory point.

[0049] In this embodiment, for the side plate mold, for this new circular arc trajectory, the closest end-effector rotation angle can be obtained based on the calculated point cloud surface normal vector. Then, the tool coordinate system (TCP) of the robotic arm is established using this end-effector rotation angle, and the posture of the robotic arm at the trajectory point is calculated, finally obtaining the 6-axis coordinate data of the trajectory. By arranging multiple trajectories calculated from adjacent full circles in descending order of radius, a complete robotic arm motion trajectory can be formed, thus completing the trajectory planning for a single side plate mold.

[0050] Through the embodiments of this disclosure, the optimal robotic arm motion trajectory is planned according to the mold size and contour to ensure that the laser cleaning head can cover the entire surface of the mold; the rotation angle of the laser cleaning head around the end auxiliary axis is determined by the normal vector to achieve precise cleaning angle control and improve the cleaning effect.

[0051] Based on the above embodiments, the tire mold is photographed using a 3D structured light camera to obtain regional point cloud data, including: using a planar support tool and a conveyor belt to move the tire mold to the clean area where the robotic arm is located; dividing the planar support tool into a preset number of photographing areas, calling the 3D camera to photograph the planar support tool and the tire mold to obtain regional point cloud data; the union of the preset number of photographing areas contains the complete planar support tool and tire mold.

[0052] In this embodiment, such as Figure 3 As shown, a conveyor belt consisting of sprockets and chains is installed on a support in front of the robotic arm. The conveyor belt has a loading area, a cleaning area, and a unloading area. Tire molds are placed on pallets, which are not fixed to the conveyor belt; they can be easily placed on and removed using a crane, facilitating loading and unloading. The conveyor belt can move horizontally, transporting pallets from the loading area to the cleaning area. After cleaning, it is transported to the unloading area, and simultaneously, the next pallet is transported from the loading area to the cleaning area. An infrared positioning device is installed within the cleaning area on the conveyor belt to ensure that the pallet moves to the appropriate cleaning zone. After the tire mold is cleaned using the robotic arm according to the trajectory planning method described in this disclosure within the cleaning area, the conveyor belt transports the pallet to the unloading area.

[0053] In this embodiment, such as Figure 4 As shown, in the 3D vision system disclosed herein, the imaging area of ​​the 3D structured light camera is a rectangle. Based on the size of the rectangle, the tray is divided into multiple imaging areas (in this example, 6 imaging areas are divided). There is an overlap between each imaging area, and the edge of the imaging area is outside the edge of the tray to ensure that the 3D point cloud information of all tire molds can be captured completely.

[0054] Through the embodiments of this disclosure, a tire mold is moved to a clean area using a planar support tool and a conveyor belt, thereby improving the level of automation; by overlapping the imaging areas, it is ensured that the complete tire mold and its surrounding environment are captured, providing complete data for subsequent point cloud data processing.

[0055] Based on the above embodiments, the point cloud data of the tire mold in the robotic arm coordinate system is obtained by using the point cloud data of the camera hand-eye calibration area, including: stitching the point cloud data of a preset number of photo areas using the camera hand-eye calibration results to obtain the overall point cloud data; obtaining a plane based on the overall point cloud data, and identifying the plane with the largest area as the plane bearing tool; filtering the point cloud data of the plane bearing tool to obtain the point cloud data of all molds; and using clustering to divide the point cloud data of all molds to obtain the individual point cloud data of each tire mold.

[0056] In this embodiment, the point cloud data obtained from each photographed area undergoes coordinate transformation, point cloud stitching, and downsampling based on the camera's hand-eye calibration results to obtain point cloud data containing all tire molds on the tray. The bottom surface of the tray is extracted according to the principle of maximizing area, and the point cloud data on the bottom surface is filtered out. Then, point cloud clustering is performed to achieve point cloud segmentation, extracting the individual point cloud data for each mold.

[0057] Through the embodiments of this disclosure, point cloud data from different shooting areas are stitched together into overall point cloud data by camera hand-eye calibration; the point cloud data of planar bearing tools are filtered out, and the remaining mold point cloud data are clustered to obtain individual point cloud data for each tire mold, which is convenient for subsequent processing.

[0058] Based on the above-described robotic arm trajectory planning method for fully automated laser cleaning of tire molds, this disclosure also provides a robotic arm trajectory planning device for fully automated laser cleaning of tire molds. The robotic arm trajectory planning device for fully automated laser cleaning of tire molds in this embodiment includes a data acquisition module, a data processing module, a size recognition module, and a trajectory planning module.

[0059] The data acquisition module is used to capture images of the tire mold using a 3D structured light camera to obtain regional point cloud data.

[0060] The data processing module is used to obtain the point cloud data of the tire mold in the coordinate system of the robotic arm by using the point cloud data of the camera's hand-eye calibration area; a laser cleaning head is installed at the end of the robotic arm; the laser cleaning head moves around the end auxiliary axis according to the movement trajectory of the robotic arm; the end auxiliary axis is a horizontal line located at the end of the laser cleaning head.

[0061] The size recognition module is used to perform feature recognition on point cloud data to obtain the size of the tire mold; the size of the tire mold includes at least one of the feature size of the tread block mold and the cross-sectional size of the side plate mold.

[0062] The trajectory planning module is used to calculate the motion trajectory of the robotic arm and the rotation angle of the laser cleaning head around the end auxiliary axis based on the size of the tire mold, thus completing the laser cleaning trajectory planning.

[0063] Furthermore, Figure 10 A schematic diagram of a robotic arm trajectory planning apparatus for fully automated laser cleaning of tire molds, according to an embodiment of this disclosure, is shown. Figure 10 As shown, the robotic arm trajectory planning method for fully automated laser cleaning of tire molds can be applied to a fully automated laser cleaning equipment for tire molds, which includes a robotic arm, a 3D camera, a laser cleaning head, a tray, a conveyor belt, and a positioning device.

[0064] The robotic arm is a 6-axis arm mounted on a horizontal base. A laser cleaning head and a 3D camera are both mounted at the end of the robotic arm. The 3D camera is a structured light camera, capable of capturing 3D point cloud data of objects within a rectangular area. The 3D camera and laser cleaning head are mounted at the end of the robotic arm, and the tire molds to be cleaned are placed on a tray. During the cleaning process, a conveyor belt transports the tray to the cleaning area. The robotic arm, carrying the 3D camera, photographs the tire molds on the tray, obtaining 3D point cloud data. Point cloud processing algorithms are used to perform coordinate transformation, stitching, downsampling, filtering, clustering, pose calculation, and straight-line / circular-arc fitting on the 3D point cloud data, resulting in the robotic arm's motion trajectory and end-effector rotation angle. The robotic arm then carries the laser cleaning head to execute the trajectory, achieving fully automated laser cleaning.

[0065] The main workflow of the fully automated laser cleaning equipment for tire molds is as follows: A pallet containing several tire molds to be cleaned (including several tread blocks and side plates) is transported to the cleaning area. A robotic arm carrying a 3D camera takes pictures at several points above the pallet. The number of photo points must ensure that the combined area of ​​the multiple photos covers the entire pallet. Next, the system takes several 3D point cloud data points obtained from the multiple photos, performs coordinate transformation based on the camera's hand-eye calibration results, and then stitches the point clouds together to obtain the overall 3D point cloud data of the tire molds on the pallet. Then, the system segments and registers this overall point cloud data to obtain the position and angle information of each mold. Next, feature recognition is performed on the 3D point cloud of each mold to obtain the feature dimensions of the tread blocks (including but not limited to total length, total width, total height, cross-sectional width, and cross-sectional depth) and the cross-sectional dimensions of the side plates (including radius and height). Finally, using the position, angle, and feature dimension data of each mold, the system calculates the motion trajectory points of the robotic arm and the angle of the end effector axis to achieve laser cleaning trajectory planning.

[0066] Figure 11A block diagram schematically illustrates an electronic device suitable for implementing a robotic arm trajectory planning method for fully automated laser cleaning of tire molds, according to an embodiment of the present disclosure.

[0067] like Figure 11 As shown, an electronic device 1100 according to an embodiment of the present disclosure includes a processor 1101, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1102 or a program loaded from a storage portion 1108 into a random access memory (RAM) 1103. The processor 1101 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or an associated chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 1101 may also include onboard memory for caching purposes. The processor 1101 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0068] RAM 1103 stores various programs and data required for the operation of electronic device 1100. Processor 1101, ROM 1102, and RAM 1103 are interconnected via bus 1104. Processor 1101 performs various operations of the method flow according to embodiments of the present disclosure by executing programs in ROM 1102 and / or RAM 1103. It should be noted that the programs may also be stored in one or more memories other than ROM 1102 and RAM 1103. Processor 1101 may also perform various operations of the method flow according to embodiments of the present disclosure by executing programs stored in said one or more memories.

[0069] According to embodiments of this disclosure, the electronic device 1100 may further include an input / output (I / O) interface 1105, which is also connected to a bus 1104. The electronic device 1100 may also include one or more of the following components connected to the I / O interface 1105: an input section 1106 including a keyboard, mouse, etc.; an output section 1107 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 1108 including a hard disk, etc.; and a communication section 1109 including a network interface card such as a LAN card, modem, etc. The communication section 1109 performs communication processing via a network such as the Internet. A drive 1110 is also connected to the I / O interface 1105 as needed. A removable medium 1111, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 1110 as needed so that computer programs read from it can be installed into the storage section 1108 as needed.

[0070] This disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or it may exist independently and not assembled into the device / apparatus / system. The computer-readable storage medium carries one or more programs that, when executed, implement the method according to the embodiments of this disclosure.

[0071] Embodiments of this disclosure also include a computer program product comprising a computer program containing program code for performing the methods shown in the flowchart. When the computer program product is run on a computer system, the program code is used to cause the computer system to implement the methods provided in the embodiments of this disclosure.

[0072] According to embodiments of this disclosure, program code for executing the computer programs provided in embodiments of this disclosure can be written in any combination of one or more programming languages. Specifically, these computational programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, languages ​​such as Java, C++, Python, "C", or similar programming languages. The program code can execute entirely on the user's computing device, partially on the user's device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0073] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0074] Those skilled in the art will understand that the features described in the various embodiments and / or claims of this disclosure can be combined or combined in various ways, even if such combinations or combinations are not explicitly described in this disclosure. In particular, the features described in the various embodiments and / or claims of this disclosure can be combined or combined in various ways without departing from the spirit and teachings of this disclosure. All such combinations and / or combinations fall within the scope of this disclosure.

[0075] The embodiments of this disclosure have been described above. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of this disclosure. Although various embodiments have been described above, this does not mean that the measures in the various embodiments cannot be used advantageously in combination. The scope of this disclosure is defined by the appended claims and their equivalents. Various substitutions and modifications can be made by those skilled in the art without departing from the scope of this disclosure, and all such substitutions and modifications should fall within the scope of this disclosure.

Claims

1. A robotic arm trajectory planning method for fully automated laser cleaning of tire molds, characterized in that, include: The tire mold was photographed using a 3D structured light camera to obtain regional point cloud data. The point cloud data of the region is calibrated using a camera to obtain the point cloud data of the tire mold in the robotic arm coordinate system; a laser cleaning head is installed at the end of the robotic arm; the laser cleaning head moves around the end auxiliary axis according to the motion trajectory of the robotic arm; the end auxiliary axis is a horizontal line located at the end of the laser cleaning head. The point cloud data is subjected to feature recognition to obtain the dimensions of the tire mold; the dimensions of the tire mold include at least one of the feature dimensions of the tread block mold and the cross-sectional dimensions of the side plate mold; Based on the dimensions of the tire mold, the motion trajectory of the robotic arm and the rotation angle of the laser cleaning head around the end auxiliary axis are calculated to complete the laser cleaning trajectory planning; The step of performing feature recognition on the point cloud data to obtain the dimensions of the tire mold includes: extracting the edge contour of the tread block mold through line and rectangle feature recognition; identifying the feature dimensions of the tread block mold based on the edge contour of the tread block mold; the feature dimensions of the tread block mold include at least one of the following: total length, total width, total height, cross-sectional width, and cross-sectional depth; and / or extracting the edge contour of the side plate mold through arc recognition; identifying the cross-sectional dimensions of the side plate mold based on the edge contour of the side plate mold; the cross-sectional dimensions of the side plate mold include at least one of the following: radius and height. The step of extracting the edge contour of the pattern block mold by recognizing straight lines and rectangles includes extracting cross-sections of point cloud data along the first and second direction coordinate axes of the robotic arm coordinate system based on the laser linewidth of the laser cleaning head; the first and second direction coordinate axes are perpendicular; the horizontal plane containing the first and second direction coordinate axes is parallel to the ground of the tire mold; the distance between adjacent cross-sections is the laser linewidth; and the edge contour of the pattern block mold is extracted using the cross-sections.

2. The method according to claim 1, wherein, The step of extracting the edge contour of the side plate mold through arc recognition includes: The point cloud data of the side plate mold is identified to obtain a series of complete circular curves; For every two adjacent full circular curves, the average of the two adjacent full circular curves is used to obtain the average full circular curve for identifying the cross-sectional dimensions of the side plate mold. The process of averaging two adjacent circular curves to obtain an average circular curve includes: Calculate the average of the radii of the two adjacent full circular curves, and use it as the average radius; Calculate the midpoint of the centers of the two adjacent full circular curves and use it as the average center. The average full circle curve is obtained using the average radius and the average center.

3. The method according to claim 1, wherein, The step of calculating the motion trajectory of the robotic arm and the rotation angle of the laser cleaning head around the end auxiliary axis based on the dimensions of the tire mold includes: Based on the edge contour of the patterned block mold and / or the side plate mold, the rotation angle of the end auxiliary shaft movement is determined according to the normal vector; The motion trajectory of the robotic arm is determined based on the cross-sectional dimensions and edge contours of the patterned block mold and / or the side plate mold, as well as the rotation angle of the end auxiliary shaft movement. The movements of the end effector and the robotic arm are independent of each other.

4. The method according to claim 1, wherein, The step of using a 3D structured light camera to photograph the tire mold to obtain regional point cloud data includes: Using a planar support tool and a conveyor belt, the tire mold is moved to the clean area where the robotic arm is located; The planar support tool is divided into a preset number of photographing areas, and a 3D camera is used to photograph the planar support tool and the tire mold to obtain point cloud data of the area; the union of the preset number of photographing areas contains the complete planar support tool and tire mold.

5. The method according to claim 4, wherein, The step of using a camera to calibrate the point cloud data of the region to obtain the point cloud data of the tire mold in the robotic arm coordinate system includes: The point cloud data of the preset number of photographed areas are stitched together using the camera hand-eye calibration results to obtain the overall point cloud data; Based on the overall point cloud data, a plane is obtained, and the plane with the largest area is identified as the plane carrying tool; Filter the point cloud data of the planar bearing tool to obtain the point cloud data of all molds; Clustering is used to divide the point cloud data of all the molds to obtain individual point cloud data for each tire mold.

6. A robotic arm trajectory planning device for fully automated laser cleaning of tire molds, characterized in that, The apparatus is capable of implementing the method as described in any one of claims 1 to 5, and the apparatus comprises: The data acquisition module is used to capture images of the tire mold using a 3D structured light camera to obtain regional point cloud data. The data processing module is used to calibrate the point cloud data of the region using a camera and hand-eye coordinate system to obtain the point cloud data of the tire mold in the robotic arm coordinate system; a laser cleaning head is installed at the end of the robotic arm; the laser cleaning head moves around the end auxiliary axis according to the motion trajectory of the robotic arm; the end auxiliary axis is a horizontal line located at the end of the laser cleaning head. A size recognition module is used to perform feature recognition on the point cloud data to obtain the size of the tire mold; the size of the tire mold includes at least one of the feature size of the tread block mold and the cross-sectional size of the side plate mold; The trajectory planning module is used to calculate the motion trajectory of the robotic arm and the rotation angle of the laser cleaning head around the end auxiliary axis based on the size of the tire mold, and to complete the laser cleaning trajectory planning. The step of performing feature recognition on the point cloud data to obtain the dimensions of the tire mold includes: extracting the edge contour of the tread block mold through line and rectangle feature recognition; identifying the feature dimensions of the tread block mold based on the edge contour of the tread block mold; the feature dimensions of the tread block mold include at least one of the following: total length, total width, total height, cross-sectional width, and cross-sectional depth; and / or extracting the edge contour of the side plate mold through arc recognition; identifying the cross-sectional dimensions of the side plate mold based on the edge contour of the side plate mold; the cross-sectional dimensions of the side plate mold include at least one of the following: radius and height. The step of extracting the edge contour of the pattern block mold by recognizing straight lines and rectangles includes extracting cross-sections of point cloud data along the first and second direction coordinate axes of the robotic arm coordinate system based on the laser linewidth of the laser cleaning head; the first and second direction coordinate axes are perpendicular; the horizontal plane containing the first and second direction coordinate axes is parallel to the ground of the tire mold; the distance between adjacent cross-sections is the laser linewidth; and the edge contour of the pattern block mold is extracted using the cross-sections.

7. An electronic device, comprising: One or more processors; Storage device for storing one or more programs. Wherein, when the one or more programs are executed by the one or more processors, the one or more processors perform the method according to any one of claims 1 to 5.

8. A computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, cause the processor to perform the method according to any one of claims 1 to 5.

Images