A polishing track automatic planning method and device based on 3D point cloud data

Abstract

The application discloses a polishing track automatic planning method and device based on 3D point cloud data, and the method comprises the following steps: collecting data of a large surface of a part surface through a 3D scanning device to obtain point clouds of the surface; obtaining a minimum circumscribed rectangular body of the point clouds, and generating a profile based on the minimum circumscribed rectangular body; projecting the point clouds onto the corresponding profile according to a preset distance threshold; performing polynomial fitting on the projected point set on the profile to obtain a path curve, and determining a polishing track according to the path curve; and generating an executable file according to the polishing track and transmitting the executable file to an executing mechanism for execution. The application solves the problem of low polishing efficiency of the large surface of the part surface.

Description

Technical Field

[0001] This invention relates to the field of intelligent manufacturing, and in particular to a method and apparatus for automatic planning of grinding trajectories based on 3D point cloud data. Background Technology

[0002] Currently, in the process of surface quality grinding of large surface parts, the main method is to plan the grinding trajectory and generate a grinding trajectory program based on the digital model of the part to be ground through offline programming; then, the part to be ground is positioned by various positioning methods (3-point positioning or visual positioning, etc.), and the generated grinding trajectory program is corrected according to the positioning information, thereby realizing automatic grinding of the part.

[0003] The above methods have the following main problems: the geometric deviation between the digital model of the part to be ground and the actual part will cause a mismatch between the surface of the grinding head and the part to be ground. Furthermore, after programming offline, the part still needs to be positioned for each grinding cycle, resulting in low grinding efficiency. Summary of the Invention

[0004] This invention provides an automatic grinding trajectory planning method and device based on 3D point cloud data, which solves the problem of low grinding efficiency for large surface parts.

[0005] An automatic planning method for polishing trajectories based on 3D point cloud data includes:

[0006] Data is collected from large surfaces of the part using 3D scanning equipment to obtain point clouds of the surface.

[0007] Obtain the minimum bounding rectangle of the point cloud, and generate a profile based on the minimum bounding rectangle;

[0008] The point cloud is projected onto the corresponding profile based on a preset distance threshold.

[0009] A polynomial fitting is performed on the projection point set on the cross section to obtain the path curve, and the grinding trajectory is determined based on the path curve.

[0010] An executable file is generated based on the grinding trajectory and sent to the execution mechanism for execution.

[0011] In one embodiment of the present invention, generating a cross-section based on the minimum bounding rectangle specifically includes: generating a main cross-section based on the minimum bounding rectangle; and determining N secondary cross-sections based on the main cross-section.

[0012] In one embodiment of the present invention, the step of performing polynomial fitting on the projection point set on the cross-section to obtain the path curve specifically includes: performing polynomial fitting on the projection point set on the main cross-section to obtain the main path curve; obtaining the intersection points of the main path curve and N secondary cross-sections according to the equation of the main path curve; performing polynomial fitting on the point set on each secondary cross-section to obtain N secondary path curves, wherein each secondary path curve passes through the intersection point on its respective secondary cross-section.

[0013] In one embodiment of the present invention, determining the grinding trajectory based on the path curve specifically includes: taking points at equal intervals on the corresponding secondary path curve based on the intersection of each secondary profile, and determining the number of each point; connecting points with the same number on different secondary profiles to obtain an equally spaced path; and connecting the beginning and end of the equally spaced path to obtain the grinding trajectory.

[0014] In one embodiment of the present invention, the main section plane passes through the center point of the minimum bounding rectangle, and the main section plane divides the minimum bounding rectangle along a direction parallel to the length of the rectangle; the secondary section plane divides the minimum bounding rectangle along a direction parallel to the width of the rectangle.

[0015] In one embodiment of the present invention, the secondary section plane is perpendicular to the primary section plane.

[0016] In one embodiment of the present invention, the information of each point in the point cloud is (x, y, z).

[0017] An automatic grinding trajectory planning device based on 3D point cloud data includes:

[0018] The data acquisition module is used to acquire data from large surfaces of the part using a 3D scanning device to obtain point clouds of the surface.

[0019] The profile generation module is used to obtain the minimum bounding rectangle of the point cloud and generate a profile based on the minimum bounding rectangle.

[0020] The projection module is used to project point clouds onto corresponding profiles according to a preset distance threshold.

[0021] The trajectory generation module performs polynomial fitting on the projection point set on the profile to obtain the path curve, and determines the grinding trajectory based on the path curve.

[0022] The execution module is used to generate an executable file based on the grinding trajectory and send it to the execution mechanism for execution.

[0023] An automatic grinding trajectory planning device based on 3D point cloud data includes:

[0024] At least one processor; and,

[0025] The memory is communicatively connected to the at least one processor via a bus; wherein,

[0026] The memory stores instructions that can be executed by the at least one processor to implement the method as described in any of the above embodiments.

[0027] A non-volatile storage medium storing computer-executable instructions, which are executed by a processor to implement the method as described in any of the above embodiments.

[0028] This invention provides a method and apparatus for automatic planning of polishing trajectories based on 3D point cloud data, which has at least the following beneficial effects: point cloud data is collected by a 3D scanning device, polishing trajectory is planned based on the point cloud data, and a polishing trajectory execution program is generated based on the planned polishing trajectory. This can directly guide the execution mechanism to achieve fully automatic polishing without the need for manual calibration and adjustment, thus freeing up manpower, reducing time and labor costs, and significantly improving polishing efficiency. Attached Figure Description

[0029] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this invention, illustrate exemplary embodiments of the invention and are used to explain the invention, but do not constitute an undue limitation of the invention. In the drawings:

[0030] Figure 1 This is a schematic diagram illustrating the steps of an automatic grinding trajectory planning method based on 3D point cloud data provided in an embodiment of the present invention.

[0031] Figure 2 This is a schematic diagram of the grinding system structure provided in an embodiment of the present invention;

[0032] Figure 3 This is a flowchart of automatic grinding trajectory planning provided in an embodiment of the present invention;

[0033] Figure 4 A schematic diagram of an automatic grinding trajectory planning device based on 3D point cloud data provided in an embodiment of the present invention;

[0034] Figure 5 This is a schematic diagram of an automatic grinding trajectory planning device based on 3D point cloud data, provided as an embodiment of the present invention. Detailed Implementation

[0035] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be described clearly and completely below in conjunction with specific embodiments. Obviously, the described embodiments are only a part of the embodiments of this invention, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0036] It should be noted that those skilled in the art will understand, explicitly and implicitly, that the embodiments described in this invention can be combined with other embodiments without conflict. Unless otherwise defined, the technical or scientific terms used in this invention should be understood in their ordinary sense by those skilled in the art. The terms "a," "an," "an," "the," etc., used in this invention do not indicate quantity limitation and can represent singular or plural. The terms "comprising," "including," "having," and any variations thereof used in this invention are intended to cover non-exclusive inclusion; the terms "first," "second," "third," etc., used in this invention are merely to distinguish similar objects and do not represent a specific ordering of objects.

[0037] The following explains some of the concepts involved in this application.

[0038] Molding: This is a method of obtaining a molded product by injecting fully molten plastic material, stirred by a screw at a certain temperature, into a mold cavity under high pressure, and then cooling and solidifying it.

[0039] A mechanism is a system of components used to transmit motion and force. It consists of a frame and is connected by kinematic pairs. Alternatively, a mechanism is a kinematic chain that uses a single component as a frame to transmit definite motion and force.

[0040] Kinematic pair: A movable connection consisting of two components in direct contact. It restricts some relative movements between the two components while allowing other relative movements.

[0041] A component can be a single part or multiple parts rigidly connected together; it is a moving unit in a mechanism; therefore, a component is a rigid body, but it can also be a resisting body (such as a liquid, belt, chain, etc.). Components are further divided into driving components, driving components, driven components, and frames.

[0042] Actuator: A drive device that provides linear or rotary motion, which utilizes a certain driving energy source and operates under the action of a certain control signal.

[0043] This invention addresses the problem of grinding the surface of large surface parts by proposing an automatic grinding trajectory planning method and device based on 3D point cloud data. A hand-eye calibrated 3D point cloud camera system is used to collect point cloud information of the large surface to be ground. By processing the point cloud information and based on the input grinding parameters, the grinding trajectory is automatically planned. This significantly improves grinding efficiency and is particularly suitable for applications where part placement requirements are not stringent and grinding is done in small batches. A detailed explanation follows.

[0044] Figure 1 A schematic diagram illustrating the steps of an automatic grinding trajectory planning method based on 3D point cloud data provided in this embodiment of the invention may include the following steps:

[0045] S110: Data is collected from large surfaces of the part using 3D scanning equipment to obtain point clouds of the surface.

[0046] In one embodiment of the present invention, the information of each point in the point cloud is (x, y, z).

[0047] Specifically, most point cloud data is generated by 3D scanning devices, such as LiDAR (2D / 3D), RGB binoculars, 3D structured light cameras, and ToF (time-of-flight) cameras. These 3D scanning devices automatically measure information about a large number of points on the surface of an object and then output point cloud data in some kind of data file. This point cloud data is what the scanning devices collect.

[0048] In this invention, a 3D camera calibrated with the hand-eye coordinate system of the motion mechanism is used to collect point cloud data of the large surface area of ​​the part to be polished, obtaining point cloud information based on the coordinate system of the motion mechanism. In this invention, the information for each point in the point cloud is (x, y, z). Generally, the coordinate values ​​of the point cloud of a large surface area are established in the base coordinate system of the actuator. If trajectory planning is performed based on the point cloud dataset, the generated trajectory program does not require calibration and can directly guide the actuator to perform polishing, significantly improving efficiency.

[0049] Furthermore, a 3D scanning device is used to scan the large surfaces of the part, collect point information of the surface, and finally output point cloud data, that is, the point cloud of the surface.

[0050] S120: Obtain the minimum bounding rectangle of the point cloud, and generate a profile based on the minimum bounding rectangle.

[0051] In one embodiment of the present invention, generating a cross-section based on the minimum bounding rectangle specifically includes: generating a main cross-section based on the minimum bounding rectangle; and determining N secondary cross-sections based on the main cross-section.

[0052] In one embodiment of the present invention, the main section plane passes through the center point of the minimum bounding rectangle, and the main section plane divides the minimum bounding rectangle along a direction parallel to the length of the rectangle; the secondary section plane divides the minimum bounding rectangle along a direction parallel to the width of the rectangle.

[0053] In one embodiment of the present invention, the secondary section plane is perpendicular to the primary section plane.

[0054] Specifically, the minimum bounding rectangle of the point cloud on the surface is obtained using a point cloud algorithm. Based on the obtained minimum bounding rectangle, the corresponding principal section plane is generated. The principal section plane is determined as follows: within the minimum bounding rectangle, the principal section plane passes through the center point of the minimum bounding rectangle, and the principal section plane divides the rectangle along its length.

[0055] Assume we establish a Cartesian coordinate system XYZ based on the minimum bounding rectangle, where the principal normal direction of the part's point cloud is assumed to be biased towards the Z-axis. Also, the length of the minimum bounding rectangle in the X-direction is greater than that in the Y-direction. Therefore, the principal section plane is parallel to both the X and Z axes and passes through the center point of the minimum bounding rectangle.

[0056] After obtaining the main section plane, N secondary section planes of rectangular bodies are generated at equal intervals, perpendicular to the main section plane and parallel to the Z-axis.

[0057] S130: Project the point cloud onto the corresponding profile according to the preset distance threshold.

[0058] Specifically, a threshold L is preset, and point clouds that are less than L away from each profile are projected onto the corresponding profile.

[0059] S140: Perform polynomial fitting on the projection point set on the profile to obtain the path curve, and determine the grinding trajectory based on the path curve.

[0060] In one embodiment of the present invention, the step of performing polynomial fitting on the projection point set on the cross-section to obtain the path curve specifically includes: performing polynomial fitting on the projection point set on the main cross-section to obtain the main path curve; obtaining the intersection points of the main path curve and N secondary cross-sections according to the equation of the main path curve; performing polynomial fitting on the point set on each secondary cross-section to obtain N secondary path curves, wherein each secondary path curve passes through the intersection point on its respective secondary cross-section.

[0061] Specifically, the main path curve L is obtained by performing polynomial-based fitting on the set of projection points on the main profile plane. 主 And based on the equation of the main path curve, the intersection points P1, P2, P3, P4........PN of the main path curve and N secondary profile planes are obtained.

[0062] Perform polynomial fitting on the point set on each secondary section plane, wherein the polynomial is required to pass through the point Pi on the current secondary section plane, so as to obtain N secondary path curves L1, L2, L3, L4, ..., LN.

[0063] In an embodiment of the present invention, the step of determining the grinding track according to the path curve specifically comprises: taking points at equal intervals on the corresponding secondary path curve based on the intersection point of each secondary section plane, and determining the number of each point; connecting points with the same number on different secondary section planes to obtain equal-interval paths, and connecting the head and tail of the equal-interval paths to obtain the grinding track.

[0064] Specifically, on the corresponding secondary path curve Li on each secondary section plane, starting from the corresponding intersection point Pi, points are taken at equal intervals (spacing refers to the length of the curve segment between two points on the curve), so as to obtain Pi1, Pi2, Pi3, Pi4, ..., Pi M .

[0065] Connections are made between different secondary section planes at corresponding points. For example:

[0066] P11, P21, P31, P41, ..., PN1 are connected to form path 1;

[0067] P12, P22, P32, P42, ..., PN2 are connected to form path 2;

[0068] According to the above rules, all points are connected, and finally a "chu" shaped equal-interval path is formed on the point cloud of the part surface.

[0069] By connecting the head to the tail of each of the above paths, that is, connecting the tail of the previous path to the head of the next path, the grinding track provided by the present invention is formed.

[0070] S150: generating an executable file according to the grinding track and transmitting it to an actuator for execution.

[0071] As Figure 2 shown a flow chart of a grinding track planning provided by an embodiment of the present invention, and the specific process is as follows:

[0072] 1. Acquiring a large-scale surface point cloud data set through a 3D scanning device, and acquiring a minimum bounding rectangle of the point cloud data set;

[0073] 2. Generating a main section plane along the length direction and height direction of the minimum bounding rectangle, wherein the main section plane passes through the center point of the minimum bounding rectangle;

[0074] 3. Generating N equally-spaced secondary section planes at a certain spacing along the width direction and height direction of the minimum bounding rectangle;

[0075] 4. Based on the combination of the main and secondary profile planes, the point cloud dataset is cut. A certain distance L is preset. Points within L of the corresponding profile are projected onto the corresponding profile.

[0076] 5. Perform polynomial fitting on the projection points on the sub-section to obtain N degree curve equations;

[0077] 6. Taking the i-th sub-curve as an example, the intersection of the sub-curve and the Zhu section plane is used as a reference. Based on the spacing H of the grinding trajectory strips, M points are drawn on the sub-curve, which are 1, 2, 3, 4...M points in sequence.

[0078] 7. Connecting the j-th points of all N sub-curves together will form M grinding tracks;

[0079] 8. Perform polynomial fitting on the projection points on the main section plane to obtain the main curve, which can be regarded as the 0th grinding trajectory;

[0080] 9. Connect the first and last polishing tracks of M+1 to form a complete polishing track.

[0081] like Figure 3 As shown, a grinding head mounted on the end of the robotic arm flange and a 3D scanning camera connected to the flange via a camera bracket are used as examples for illustration.

[0082] 1. Plan the scanning trajectory and use a 3D scanning camera to scan the large surface to obtain the point cloud dataset of the large surface.

[0083] 2. According to the point cloud dataset Figure 2 The process shown is used to process the data and obtain the grinding trajectory.

[0084] 3. Convert the data of the grinding trajectory into a program that the robotic arm can execute.

[0085] 4. Import the program into the robotic arm to control the grinding head and achieve automatic grinding.

[0086] The above process can be fully automated, requiring no manual calibration or standardization. Only hand-eye calibration is needed when mechanically installing the above mechanism.

[0087] The above describes an automatic grinding trajectory planning method based on 3D point cloud data provided by an embodiment of the present invention. Based on the same inventive concept, the present invention also provides a corresponding automatic grinding trajectory planning device based on 3D point cloud data, such as... Figure 4 As shown.

[0088] The data acquisition module 402 is used to acquire data from a large surface of a part using a 3D scanning device to obtain a point cloud of the surface.

[0089] The profile generation module 404 is used to obtain the minimum bounding rectangle of the point cloud and generate a profile based on the minimum bounding rectangle.

[0090] Projection module 406 is used to project point clouds onto corresponding profiles according to a preset distance threshold;

[0091] The trajectory generation module 408 performs polynomial fitting on the projection point set on the profile to obtain the path curve, and determines the grinding trajectory based on the path curve.

[0092] The execution module 410 is used to generate an executable file based on the grinding trajectory and send it to the execution mechanism for execution.

[0093] This invention also provides a corresponding automatic grinding trajectory planning device based on 3D point cloud data, such as... Figure 5 As shown, it includes:

[0094] The system includes at least one processor 502, a communication interface 504, a memory 506, and a communication bus 508; wherein the processor 502, the communication interface 504, and the memory 506 communicate with each other via the communication bus 508; the processor 502 can call logical instructions stored in the memory 506 to cause at least one processor 502 to execute the steps of the above embodiments, such as including:

[0095] Data is collected from large surfaces of the part using 3D scanning equipment to obtain point clouds of the surface.

[0096] Obtain the minimum bounding rectangle of the point cloud, and generate a profile based on the minimum bounding rectangle;

[0097] The point cloud is projected onto the corresponding profile based on a preset distance threshold.

[0098] A polynomial fitting is performed on the projection point set on the cross section to obtain the path curve, and the grinding trajectory is determined based on the path curve.

[0099] An executable file is generated based on the grinding trajectory and sent to the execution mechanism for execution.

[0100] Based on the same idea, some embodiments of the present invention also provide media corresponding to the above methods.

[0101] Some embodiments of the present invention provide a storage medium storing computer-executable instructions, which are executed by a processor to implement the steps of the above embodiments, including, for example:

[0102] Data is collected from large surfaces of the part using 3D scanning equipment to obtain point clouds of the surface.

[0103] Obtain the minimum bounding rectangle of the point cloud, and generate a profile based on the minimum bounding rectangle;

[0104] The point cloud is projected onto the corresponding profile based on a preset distance threshold.

[0105] A polynomial fitting is performed on the projection point set on the cross section to obtain the path curve, and the grinding trajectory is determined based on the path curve.

[0106] An executable file is generated based on the grinding trajectory and sent to the execution mechanism for execution.

[0107] On the other hand, this application also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can perform the steps of the automatic grinding trajectory planning method based on 3D point cloud data provided in the above embodiments, such as including:

[0108] Data is collected from large surfaces of the part using 3D scanning equipment to obtain point clouds of the surface.

[0109] Obtain the minimum bounding rectangle of the point cloud, and generate a profile based on the minimum bounding rectangle;

[0110] The point cloud is projected onto the corresponding profile based on a preset distance threshold.

[0111] A polynomial fitting is performed on the projection point set on the cross section to obtain the path curve, and the grinding trajectory is determined based on the path curve.

[0112] An executable file is generated based on the grinding trajectory and sent to the execution mechanism for execution.

[0113] The various embodiments in this invention are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the device and medium embodiments are relatively simple in description because they are fundamentally similar to the method embodiments; relevant parts can be referred to the descriptions in the method embodiments.

[0114] The devices, media, and methods provided in the embodiments of the present invention are one-to-one correspondences. Therefore, the devices and media also have similar beneficial technical effects as their corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be repeated here.

[0115] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process method or product that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process method or product. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process method or product that includes that element.

[0116] The above are merely embodiments of the present invention and are not intended to limit the invention. Although the present invention has been described in detail above with general descriptions and specific embodiments, modifications or improvements can be made to it, which will be obvious to those skilled in the art. Therefore, all such modifications or improvements made without departing from the spirit of the present invention fall within the scope of protection claimed by the present invention.

Claims

1. A method for automatically planning grinding trajectories based on 3D point cloud data, characterized in that, include: Data is collected from large surfaces of the part using 3D scanning equipment to obtain point clouds of the surface, which are point cloud information based on the coordinate system of the motion mechanism. Obtain the minimum bounding rectangle of the point cloud, and generate a profile based on the minimum bounding rectangle, specifically including: generating a main section plane based on the minimum bounding rectangle; and determining N secondary section planes based on the main section plane. The point cloud is projected onto the corresponding profile based on a preset distance threshold. A polynomial fitting is performed on the projection point set on the cross section to obtain the path curve, and the grinding trajectory is determined based on the path curve. An executable file is generated based on the grinding trajectory and sent to the execution mechanism for execution; The process of performing polynomial fitting on the projection point set on the profile to obtain the path curve specifically includes: performing polynomial fitting on the projection point set on the main profile plane to obtain the main path curve; obtaining the intersection points of the main path curve with N secondary profile planes according to the equation of the main path curve; performing polynomial fitting on the point set on each secondary profile plane to obtain N secondary path curves, wherein each secondary path curve passes through the intersection point on its respective secondary profile plane. The main section plane passes through the center point of the minimum bounding rectangle, and the main section plane divides the minimum bounding rectangle along a direction parallel to the length of the rectangle; the secondary section plane divides the minimum bounding rectangle along a direction parallel to the width of the rectangle.

2. The method according to claim 1, characterized in that, Determining the polishing trajectory based on the path curve specifically includes: Based on the intersection of each secondary profile plane, points are taken at equal intervals on the corresponding secondary path curve, and the number of each point is determined. Connecting points with the same number on different sub-planes yields equally spaced paths. Connecting the beginning and end of these equally spaced paths yields the grinding trajectory.

3. The method according to claim 1, characterized in that, The secondary section plane is perpendicular to the main section plane.

4. The method according to claim 1, characterized in that, The information of each point in the point cloud is (x, y, z).

5. An automatic grinding trajectory planning device based on 3D point cloud data, characterized in that, include: The data acquisition module is used to acquire data from large surfaces of the part using a 3D scanning device to obtain point clouds of the surface, wherein the point cloud is point cloud information based on the coordinate system of the motion mechanism. The profile generation module is used to obtain the minimum bounding rectangle of the point cloud and generate a profile based on the minimum bounding rectangle. Specifically, it includes: generating a main section plane based on the minimum bounding rectangle; and determining N secondary section planes based on the main section plane. The projection module is used to project point clouds onto corresponding profiles according to a preset distance threshold. The trajectory generation module performs polynomial fitting on the projection point set on the profile to obtain the path curve, and determines the grinding trajectory based on the path curve. The execution module is used to generate an executable file based on the grinding trajectory and send it to the execution mechanism for execution; To achieve the method as described in any one of claims 1-4.

6. An automatic grinding trajectory planning device based on 3D point cloud data, characterized in that, include: At least one processor; as well as, The memory is connected to the at least one processor via a bus; wherein, The memory stores instructions executable by the at least one processor, which are executed to implement the method as described in any one of claims 1-4.

7. A non-volatile storage medium storing computer-executable instructions, characterized in that, The computer-executable instructions are executed by a processor to implement the method as described in any one of claims 1-4.

Images