Aircraft painting method, device, equipment and medium

Abstract

The present application discloses an aircraft painting method, device, equipment and medium, which relates to the field of aircraft technology, including: obtaining an initial point cloud data set of each preset part in an aircraft to be painted; aligning an expected point cloud data set and the initial point cloud data set for the same preset part to eliminate unaligned data points in the initial point cloud data set to obtain a target point cloud data set; each expected point cloud data set is a data set respectively obtained from each preset part in the aircraft when the aircraft is located at an expected position; based on each target point cloud data set, the corresponding centroid coordinates are respectively determined to construct a target coordinate system using each centroid coordinate, and the actual position of the aircraft to be painted is determined based on the expected position and the position of the aircraft to be painted in the target coordinate system; based on the actual position and the expected position, an actual painting trajectory for the aircraft to be painted is generated to paint the aircraft to be painted, so that the aircraft can be painted more quickly and accurately.

Description

Technical Field

[0001] The present invention relates to the field of aircraft technology, and in particular to an aircraft painting method, device, equipment and medium. Background Art

[0002] At present, the common robot automatic spraying systems on the market can be divided into automatic spraying based on manual teaching, robot automatic spraying based on trajectory planning, and three-dimensional reconstruction, according to the difference between the spraying method and the calibration method. Among them, the automatic spraying based on manual teaching has low flexibility and cannot be used when the fuselage position deviates. Robot automatic spraying based on trajectory planning generally adopts a manually controlled robotic arm, and realizes automatic spraying by using a posture calibration method to collect data from horizontal measurement points on the surface of the fuselage through laser. However, this method generally requires two people to cooperate in collecting points and cannot be calibrated at the same time. When the number of collection points is about ten, it generally takes half a working day to calibrate the posture coordinates of the aircraft, which is time-consuming and inefficient. In addition, the robotic arm cannot perform interference simulation during the calibration process, and there is a risk of damage caused by collision between the robotic arm and the fuselage. Therefore, how to spray aircraft more quickly and accurately is a problem that needs to be solved at present. Summary of the invention

[0003] In view of this, the purpose of this application is to provide an aircraft painting method, device, equipment and medium, which can generate an actual painting trajectory for the aircraft through the actual position and the expected position, so as to achieve faster and more accurate painting of the aircraft. The specific scheme is as follows:

[0004] In a first aspect, the present application provides an aircraft painting method, which is applied to an aircraft painting device, comprising:

[0005] Obtaining an initial point cloud data set of each preset part of the aircraft to be painted;

[0006] The expected point cloud data set and the initial point cloud data set for the same preset position are registered to remove unregistered data points in the initial point cloud data set to obtain a corresponding target point cloud data set; each of the expected point cloud data sets is a data set obtained from each of the preset positions in the aircraft when the aircraft is at an expected position;

[0007] Determine the corresponding centroid coordinates based on each of the target point cloud data sets, respectively, to construct a target coordinate system using the centroid coordinates, and determine the actual position of the aircraft to be painted based on the expected position and the position of the aircraft to be painted in the target coordinate system;

[0008] An actual painting trajectory for the aircraft to be painted is generated according to the actual position and the expected position, so as to paint the aircraft to be painted.

[0009] Optionally, registering the expected point cloud dataset and the initial point cloud dataset for the same preset part to remove unregistered data points in the initial point cloud dataset to obtain a corresponding target point cloud dataset includes:

[0010] Determine the expected point cloud dataset and the initial point cloud dataset for the same preset part to obtain a current expected point cloud dataset and a current initial point cloud dataset, and transform the current initial point cloud dataset based on the current registration transformation matrix to obtain a transformed point cloud dataset;

[0011] Determine a target data point that meets a preset rejection condition from the transformed point cloud data set; the preset rejection condition includes that the minimum distance between the target data point and a data point in the current expected point cloud data set is greater than a preset distance;

[0012] Eliminate the unregistered data points corresponding to the target data points in the current initial point cloud dataset to update the current initial point cloud dataset, and when the preset termination condition is not currently met, update the current registration transformation matrix based on the minimum distance between each data point in the transformed point cloud dataset that does not meet the preset elimination condition and the data points in the expected point cloud dataset, and jump again to the step of transforming the current initial point cloud dataset based on the current registration transformation matrix until the preset termination condition is currently met, so as to determine the current initial point cloud dataset as the target point cloud dataset for the same preset part.

[0013] Optionally, the process of determining the initial value of the current registration transformation matrix includes:

[0014] Selecting a plurality of groups of data points from the expected point cloud data set and the initial point cloud data set for the same preset part, and determining an initial value of the current registration transformation matrix based on the plurality of groups of data points;

[0015] Among them, any group of data points among the plurality of groups of data points are data points corresponding to the same position in the expected point cloud data set and the initial point cloud data set for the same preset part.

[0016] Optionally, updating the current registration transformation matrix based on the minimum distance between each data point in the transformed point cloud data set that does not satisfy the preset rejection condition and the data points in the expected point cloud data set includes:

[0017] Determine the minimum distance between each data point in the transformed point cloud data set that does not meet the preset rejection condition and the data point in the expected point cloud data set, and determine the current error value based on each of the minimum distances;

[0018] A current descent gradient is determined based on the current error value using a gradient descent method, so as to update the current registration transformation matrix using the current descent gradient.

[0019] Optionally, the preset termination condition includes that the current descent gradient is less than a preset gradient threshold, and / or that the accumulated number of updates to the current registration transformation matrix reaches a preset number.

[0020] Optionally, determining corresponding centroid coordinates based on each of the target point cloud data sets includes:

[0021] Determine the centroid coordinates corresponding to each of the target point cloud data sets based on the coordinates of the data points in each of the target point cloud data sets;

[0022] Among them, the centroid coordinates include coordinate values ​​in three different directions, any coordinate value is a value determined based on the sum of the coordinate values ​​of the data points in the target point cloud data set in the target direction; the target direction is the same direction as the direction of any coordinate value.

[0023] Optionally, determining the actual position of the aircraft to be painted based on the expected position and the position of the aircraft to be painted in the target coordinate system includes:

[0024] Determine a first vector from the expected position to the position of the aircraft to be painted in the target coordinate system, determine a second vector from the position of the aircraft painting equipment to the expected position, and determine the actual position of the aircraft to be painted based on the first vector and the second vector;

[0025] Accordingly, generating an actual painting trajectory for the aircraft to be painted according to the actual position and the expected position includes:

[0026] A translation deviation and a rotation deviation are determined according to the actual position and the expected position, so as to generate an actual painting trajectory for the aircraft to be painted based on the translation deviation and the rotation deviation.

[0027] In a second aspect, the present application provides an aircraft painting device, which is applied to aircraft painting equipment, comprising:

[0028] A data set acquisition module is used to acquire an initial point cloud data set of each preset part of the aircraft to be painted;

[0029] A data set registration module, used for registering the expected point cloud data set for the same preset part with the initial point cloud data set, so as to remove the unregistered data points in the initial point cloud data set and obtain the corresponding target point cloud data set; each of the expected point cloud data sets is a data set respectively obtained from each of the preset parts in the aircraft when the aircraft is at the expected position;

[0030] an actual position determination module, configured to determine corresponding centroid coordinates based on each of the target point cloud data sets, respectively, to construct a target coordinate system using the centroid coordinates, and to determine the actual position of the aircraft to be painted based on the expected position and the position of the aircraft to be painted in the target coordinate system;

[0031] The aircraft painting module is used to generate an actual painting trajectory for the aircraft to be painted according to the actual position and the expected position, so as to paint the aircraft to be painted.

[0032] In a third aspect, the present application provides an electronic device, including:

[0033] Memory, used to store computer programs;

[0034] The processor is used to execute the computer program to implement the aforementioned aircraft painting method.

[0035] In a fourth aspect, the present application provides a computer-readable storage medium for storing a computer program, wherein the computer program implements the aforementioned aircraft painting method when executed by a processor.

[0036] In the present application, an initial point cloud dataset of each preset part in an aircraft to be painted is obtained; an expected point cloud dataset for the same preset part and the initial point cloud dataset are aligned to eliminate unaligned data points in the initial point cloud dataset to obtain a corresponding target point cloud dataset; each expected point cloud dataset is a dataset obtained from each preset part in the aircraft when the aircraft is located at an expected position; corresponding center of mass coordinates are determined based on each target point cloud dataset to construct a target coordinate system using each center of mass coordinate, and the actual position of the aircraft to be painted is determined based on the expected position and the position of the aircraft to be painted in the target coordinate system; an actual painting trajectory for the aircraft to be painted is generated according to the actual position and the expected position to paint the aircraft to be painted. As can be seen from the above, the present application first obtains the initial point cloud data set of the preset parts on the aircraft to be painted, and aligns these initial point cloud data sets with the expected point cloud data sets of the same parts when the aircraft is in the expected position; this alignment process is intended to remove the unaligned data points, that is, the noise data points, from the initial point cloud data set, so as to obtain the target point cloud data set. Then, based on the above target point cloud data sets, the centroid coordinates of each preset part of the aircraft are calculated, and the target coordinate system is constructed using the above centroid coordinates to obtain the position of the aircraft in the target coordinate system. Finally, the actual position of the aircraft relative to the aircraft painting equipment is determined according to the expected position and the position of the aircraft in the target coordinate system, so as to generate the actual painting trajectory for the aircraft through the actual position and the expected position, and paint the aircraft to be painted. This method avoids the problems of long time consumption and low efficiency caused by artificial means. At the same time, by selecting the point cloud data sets of different parts of the aircraft to construct the overall position of the aircraft in three-dimensional space, the actual position of the aircraft relative to the aircraft painting equipment is obtained to generate a more accurate actual painting trajectory, thereby achieving faster and more accurate painting of the aircraft. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0038] Figure 1 This is a flow chart of an aircraft painting method disclosed in this application;

[0039] Figure 2 A schematic diagram of a point cloud data set collection location disclosed in this application;

[0040] Figure 3This is a schematic diagram of the structure of an aircraft painting device disclosed in this application;

[0041] Figure 4 This is a structural diagram of an electronic device disclosed in this application. DETAILED DESCRIPTION

[0042] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0043] See also Figure 1 As shown, the embodiment of the present application discloses an aircraft painting method, which is applied to an aircraft painting device, comprising:

[0044] Step S11, obtaining an initial point cloud data set of each preset part of the aircraft to be painted.

[0045] In this embodiment, a preset part is first selected in the aircraft to be painted to collect an initial point cloud data set. The preset part can be a representative, easy-to-scan, and non-deformable part of the aircraft to avoid scanning difficulties caused by occlusion, reflection, or complex surfaces, such as Figure 2 As shown in the box, the end point of the left wing, the end point of the right wing and the engine air intake of the aircraft are selected as the collection points of the point cloud data set.

[0046] After determining the collection location of the point cloud data set, three-dimensional scanning equipment, such as 3D (3-dimensions) cameras, lidars, etc., can be used to perform a series of steps such as image acquisition, preprocessing, structured light reconstruction, point cloud generation and post-processing based on the collection location of the point cloud data set to obtain high-quality and smooth point cloud information, which can be used as the initial point cloud data set for each preset location in the aircraft to be painted.

[0047] Step S12, aligning the expected point cloud dataset and the initial point cloud dataset for the same preset position to eliminate the unaligned data points in the initial point cloud dataset to obtain a corresponding target point cloud dataset; each of the expected point cloud datasets is a dataset obtained from each of the preset positions in the aircraft when the aircraft is at an expected position.

[0048] In this embodiment, after determining the initial point cloud data set, it is necessary to align the initial point cloud data set and the expected point cloud data set for the same preset part, so as to remove the unaligned data points in the initial point cloud data set and obtain the aligned target point cloud data set. Among them, the expected point cloud data set is a data set obtained from each preset part of the aircraft when it is in the expected painting position. It should be noted that this embodiment adopts the ICP (Iterative Closest Point) point cloud registration algorithm to implement the above registration process.

[0049] Specifically, for the target point cloud dataset, the expected point cloud dataset and the initial point cloud dataset for the same preset part can be determined first to obtain the current expected point cloud dataset and the current initial point cloud dataset, and the current initial point cloud dataset is transformed based on the current registration transformation matrix to obtain the transformed point cloud dataset; then the target data point that meets the preset rejection condition is determined from the transformed point cloud dataset; wherein the preset rejection condition includes that the minimum distance between the target data point and the data point in the current expected point cloud dataset is greater than the preset distance. Further, after the target data point is determined, the unregistered data point corresponding to the target data point in the current initial point cloud dataset is eliminated to update the current initial point cloud dataset, and when the preset termination condition is not met at present, the current registration transformation matrix is ​​updated based on the minimum distance between each data point in the transformed point cloud dataset that does not meet the preset rejection condition and the data point in the expected point cloud dataset, and the step of transforming the current initial point cloud dataset based on the current registration transformation matrix is ​​jumped again, until the preset termination condition is met at present, so as to determine the current initial point cloud dataset as the target point cloud dataset for the same preset part.

[0050] It is understandable that the above-mentioned expected point cloud dataset is obtained through high-precision 3D scanning equipment, representing the 3D shape and position information of the aircraft in the expected painting state, so the accuracy is usually higher and the noise is less. The initial point cloud dataset is a dataset obtained from the same preset position when the aircraft is in the actual position. These datasets are also obtained through 3D scanning equipment, but because the aircraft may be in different postures or positions, the initial point cloud dataset may contain more noise, occlusion or deformation, and the accuracy may be lower, so it is necessary to remove the noise data points in the initial point cloud dataset.

[0051] As for the initial value of the current registration transformation matrix, a number of groups of data points can be selected from the expected point cloud data set and the initial point cloud data set for the same preset part, and the initial value of the current registration transformation matrix can be determined based on the number of data points. Among them, any group of data points in the number of groups of data points is the data points corresponding to the same position in the expected point cloud data set and the initial point cloud data set for the same preset part; and the number of the number of data points is generally not less than three groups.

[0052] It should be noted that the registration transformation matrices corresponding to different preset parts of the aircraft are different, but the method for determining the registration transformation matrices for different preset parts of the aircraft is the same. First, several groups of corresponding data points are selected from the expected point cloud data set and the initial point cloud data set for the same preset part. These data points are the points in the two data sets corresponding to the same aircraft part. For example, for the selection of several groups of corresponding data points, manual selection, feature matching algorithm or physical location-based methods, such as using known markers or structural features, can be used to determine which data points are corresponding in the two data sets; and the selected corresponding data points should be distributed as evenly as possible on the surface of the preset part to ensure the accuracy and robustness of the registration results. Furthermore, the initial value of the registration transformation matrix is ​​calculated based on several groups of corresponding data points. For example, the least squares method, iterative closest point algorithm, etc. can be used.

[0053] After determining the initial value of the registration transformation matrix, the initial value of the registration transformation matrix is ​​determined as the current registration transformation matrix, and then the current initial point cloud dataset is transformed by the current registration transformation matrix to obtain the transformed point cloud dataset; in this way, the current initial point cloud dataset can be roughly aligned to the position of the expected point cloud dataset.

[0054] Furthermore, for each data point in the transformed point cloud dataset, the minimum distance between each data point and the data point in the expected point cloud dataset is determined, and these minimum distances are compared with the preset distances respectively. If the above minimum distance is greater than the preset distance, the data point in the transformed point cloud dataset is confirmed as the target data point, and the data point corresponding to the above target data point in the current initial point cloud dataset is confirmed as an unregistered data point, that is, a noise data point, and then the unregistered data points in the current initial point cloud dataset are removed to update the current initial point cloud dataset.

[0055] For updating the current registration transformation matrix based on the minimum distance between each data point in the transformed point cloud data set that does not meet the preset elimination condition and the data point in the expected point cloud data set, it can include: first determining the minimum distance between each data point in the transformed point cloud data set that does not meet the preset elimination condition and the data point in the expected point cloud data set, and determining the current error value based on each minimum distance, and then using the gradient descent method and determining the current descent gradient based on the current error value, so as to update the current registration transformation matrix using the current descent gradient. Among them, the current error value can be determined based on each minimum distance. An algorithm such as mean square error can be used.

[0056] It should be noted that the preset termination condition may include that the current descending gradient is less than the preset gradient threshold, and / or the cumulative number of updates to the current registration transformation matrix reaches the preset number of times. Specifically, if the current descending gradient is less than the preset gradient threshold, and / or the cumulative number of updates to the current registration transformation matrix reaches the preset number of times, the update of the current initial point cloud dataset is terminated, and the current initial point cloud dataset is determined as the target point cloud dataset for the same preset part; if the current descending gradient is not less than the preset gradient threshold, and / or the cumulative number of updates to the current registration transformation matrix does not reach the preset number of times, then jump back to the above-mentioned step of transforming the current initial point cloud dataset based on the current registration transformation matrix to continue updating the current initial point cloud dataset until the preset termination condition is met. In addition, the preset termination condition may also include that the cumulative number of updates to the current initial point cloud dataset reaches the preset number of times, the cumulative number of transformations to the current initial point cloud dataset based on the current registration transformation matrix reaches the preset number of times, and of course, other situations may also be included, which will not be given in detail here.

[0057] It can be understood that the purpose of continuously updating the current initial point cloud dataset is to make the data points in the current initial point cloud dataset continuously approach the data points in the expected point cloud dataset. The current descent gradient is calculated through the updated current initial point cloud dataset, and whether the preset termination condition is met is determined based on whether the current descent gradient is less than the preset gradient threshold, and / or whether the cumulative update times of the current registration transformation matrix reaches the preset times. If the preset termination condition is met, it means that the data points in the current initial point cloud dataset are very close to the data points in the expected point cloud dataset, and the current initial point cloud dataset can be stopped from being updated, and the current initial point cloud dataset is determined as the target point cloud dataset for the same preset part; if the preset termination condition is not met, the current initial point cloud dataset is continuously updated to make the data points in the current initial point cloud dataset continuously approach the data points in the expected point cloud dataset.

[0058] Step S13, determining corresponding centroid coordinates based on each of the target point cloud data sets, constructing a target coordinate system using the centroid coordinates, and determining the actual position of the aircraft to be painted based on the expected position and the position of the aircraft to be painted in the target coordinate system.

[0059] In this embodiment, the centroid coordinates corresponding to the target point cloud data sets of each preset part are first determined to construct a target coordinate system based on the centroid coordinates; after the target coordinate system is constructed, the actual position of the aircraft to be painted can be determined based on the expected position and the position of the aircraft to be painted in the target coordinate system. Among them, for the actual position of the aircraft to be painted, a first vector from the expected position to the position of the aircraft to be painted in the target coordinate system can be determined first, and a second vector from the position of the aircraft painting equipment to the expected position can be determined, and then the actual position of the aircraft to be painted can be determined based on the first vector and the second vector. It should be noted that the actual position of the aircraft to be painted can be obtained by adding vectors, that is, the actual position of the aircraft to be painted is determined by adding the second vector to the first vector.

[0060] As for the centroid coordinates, the centroid coordinates corresponding to each target point cloud dataset can be determined based on the coordinates of the data points in each target point cloud dataset, that is, the centroid coordinates corresponding to any target point cloud dataset can be determined based on the coordinates of the data points in any target point cloud dataset in each target point cloud dataset, and one target point cloud dataset corresponds to one centroid coordinate. Among them, the centroid coordinates include coordinate values ​​in three different directions, any coordinate value is a value determined based on the sum of the coordinate values ​​of the data points in the target point cloud dataset in the target direction, and the target direction is the same direction as any coordinate value; that is, the coordinate value in any direction is a value determined based on the sum of the coordinate values ​​of the data points in the target point cloud dataset in any direction, for example, the average value of the sum of the coordinate values ​​of the data points in the target point cloud dataset in any direction can be determined as the coordinate value in any direction.

[0061] Taking three different directions including the x-axis, y-axis and z-axis as examples, according to the coordinate values ​​of the data points in each target point cloud data set in the x-axis, y-axis and z-axis directions respectively, the centroid coordinates including the coordinate values ​​in three different directions corresponding to each target point cloud data set can be calculated. For example, for any target point cloud data set in each target point cloud data set, first initialize the sum of x coordinate values, the sum of y coordinate values, and the sum of z coordinate values ​​to zero, then traverse each data point in any target point cloud data set, and for the currently traversed data point (x, y, z), add its x coordinate value, y coordinate value, and z coordinate value to the sum of x coordinate values, y coordinate value, and z coordinate value, respectively, to update the sum of x coordinate values, y coordinate value, and z coordinate value, and then after traversing all data points in any target point cloud data set, the final sum of x coordinate values, y coordinate value, and z coordinate value can be obtained, and the corresponding x coordinate average value, y coordinate average value, and z coordinate average value are calculated respectively, so that the calculated x coordinate average value, y coordinate average value, and z coordinate average value are used as the centroid coordinates corresponding to any target point cloud data set.

[0062] Further, the target coordinate system is constructed using the centroid coordinates. Taking the preset parts including the left wing end point, the right wing end point and the engine air inlet as examples, the centroid coordinates of the left wing end point, the right wing end point and the engine air inlet are represented as point O, point P and point Q respectively, and then point O is selected as the origin of the coordinate system, and the OP vector from the origin of the coordinate system O to point P and the OQ vector from the origin of the coordinate system O to point Q are determined, and the direction of the OP vector is taken as the x-axis direction, and the direction of the OQ vector is taken as the y-axis direction. In order to ensure that the OP vector and the OQ vector are non-zero and unitized, the OP vector and the OQ vector can be divided by their respective modulus lengths to obtain the unit vector {i} and the unit vector {j}. Further, after determining the x-axis direction and the y-axis direction, the cross product can be used to find the OZ vector orthogonal to both the OP vector and the OQ vector, and the direction of the OZ vector is determined as the z-axis direction, and then the OZ vector is unitized to obtain the unit vector {k}. Finally, the x-axis direction and the corresponding unit vector {i}, the y-axis direction and the corresponding unit vector {j}, the z-axis direction and the corresponding unit vector {k} are used to construct a target coordinate system with O as the origin of the coordinate system. At this time, the origin of the coordinate system O is the position of the aircraft to be painted in the target coordinate system. It should be noted that the above is only one specific implementation method of constructing a target coordinate system using the coordinates of each centroid. Of course, the target coordinate system can also be constructed with point P as the origin of the coordinate system or point Q as the origin of the coordinate system, etc., and no more examples will be given here.

[0063] Step S14: generating an actual painting trajectory for the aircraft to be painted according to the actual position and the expected position, so as to paint the aircraft to be painted.

[0064] In this embodiment, after obtaining the actual position of the aircraft to be painted, the translation deviation and rotation deviation of the aircraft to be painted can be determined according to the actual position and the expected position, so as to generate an actual painting trajectory for the aircraft to be painted based on the translation deviation and the rotation deviation, so as to paint the aircraft to be painted using the actual painting trajectory.

[0065] It can be understood that the translation deviation reflects the linear movement of the aircraft to be painted between the actual position and the expected position; wherein, in order to calculate the translation deviation, the coordinates of the aircraft at the actual position and the expected position can be obtained respectively, and then the translation vector is determined based on the coordinates of the aircraft at the actual position and the expected position to obtain the translation deviation. The rotation deviation describes the rotation change of the aircraft to be painted between the actual position and the expected position; wherein, in order to determine the rotation deviation, the attitude matrix of the aircraft can be determined for the actual position and the expected position respectively, and the attitude matrix describes the tilt state and rotation state of the aircraft in each direction, and then the rotation matrix is ​​determined based on the attitude matrix of the actual position and the attitude matrix of the expected position to obtain the rotation deviation.

[0066] As can be seen from the above, the present application first obtains the initial point cloud data set of the preset parts on the aircraft to be painted, and uses the current registration transformation matrix to register these initial point cloud data sets with the expected point cloud data set of the same part when the aircraft is in the expected position until the preset termination condition is met, and stops updating the current registration transformation matrix and using the current registration transformation matrix to register the current initial point cloud data set with the expected point cloud data set of the same part when the aircraft is in the expected position; this registration process is intended to remove unregistered data points, i.e., noise data points, from the initial point cloud data set, thereby obtaining the target point cloud data set. Then, based on the above target point cloud data sets, the centroid coordinates of each preset part of the aircraft are calculated, and the target coordinate system is constructed using the above centroid coordinates to obtain the position of the aircraft in the target coordinate system. Finally, the actual position of the aircraft relative to the aircraft painting equipment is determined based on the expected position and the position of the aircraft in the target coordinate system, so as to generate an actual painting trajectory for the aircraft through the actual position and the expected position, and paint the aircraft to be painted. This method avoids the time-consuming and inefficient problems caused by manual labor. At the same time, by selecting point cloud data sets of different parts of the aircraft to construct the overall position of the aircraft in three-dimensional space, the actual position of the aircraft relative to the aircraft painting equipment is obtained to generate a more accurate actual painting trajectory, thereby achieving faster and more accurate painting of the aircraft.

[0067] See also Figure 3As shown, the embodiment of the present application also discloses an aircraft painting device, which is applied to aircraft painting equipment, including:

[0068] The data set acquisition module 11 is used to acquire the initial point cloud data set of each preset part in the aircraft to be painted;

[0069] The data set registration module 12 is used to register the expected point cloud data set and the initial point cloud data set for the same preset part, so as to remove the unregistered data points in the initial point cloud data set to obtain the corresponding target point cloud data set; each of the expected point cloud data sets is a data set obtained from each of the preset parts in the aircraft when the aircraft is at the expected position;

[0070] an actual position determination module 13, for determining corresponding centroid coordinates based on each of the target point cloud data sets, respectively, to construct a target coordinate system using the centroid coordinates, and to determine the actual position of the aircraft to be painted based on the expected position and the position of the aircraft to be painted in the target coordinate system;

[0071] The aircraft painting module 14 is used to generate an actual painting trajectory for the aircraft to be painted according to the actual position and the expected position, so as to paint the aircraft to be painted.

[0072] As can be seen from the above, the present application first obtains the initial point cloud data set of the preset parts on the aircraft to be painted, and uses the current registration transformation matrix to register these initial point cloud data sets with the expected point cloud data set of the same part when the aircraft is in the expected position until the preset termination condition is met, and stops updating the current registration transformation matrix and using the current registration transformation matrix to register the current initial point cloud data set with the expected point cloud data set of the same part when the aircraft is in the expected position; this registration process is intended to remove unregistered data points, i.e., noise data points, from the initial point cloud data set, thereby obtaining the target point cloud data set. Then, based on the above target point cloud data sets, the centroid coordinates of each preset part of the aircraft are calculated, and the target coordinate system is constructed using the above centroid coordinates to obtain the position of the aircraft in the target coordinate system. Finally, the actual position of the aircraft relative to the aircraft painting equipment is determined based on the expected position and the position of the aircraft in the target coordinate system, so as to generate an actual painting trajectory for the aircraft through the actual position and the expected position, and paint the aircraft to be painted. This method avoids the time-consuming and inefficient problems caused by manual labor. At the same time, by selecting point cloud data sets of different parts of the aircraft to construct the overall position of the aircraft in three-dimensional space, the actual position of the aircraft relative to the aircraft painting equipment is obtained to generate a more accurate actual painting trajectory, thereby achieving faster and more accurate painting of the aircraft.

[0073] In some specific implementations, the data set registration module 12 may specifically include:

[0074] a data set transformation unit, configured to determine the expected point cloud data set and the initial point cloud data set for the same preset part to obtain a current expected point cloud data set and a current initial point cloud data set, and transform the current initial point cloud data set based on a current registration transformation matrix to obtain a transformed point cloud data set;

[0075] A data point determination unit, configured to determine a target data point that satisfies a preset elimination condition from the transformed point cloud data set; the preset elimination condition includes that a minimum distance between the target data point and a data point in the current expected point cloud data set is greater than a preset distance;

[0076] A data set determination unit is used to eliminate unregistered data points corresponding to the target data points in the current initial point cloud data set to update the current initial point cloud data set, and when the preset termination condition is not currently satisfied, update the current registration transformation matrix based on the minimum distance between each data point in the transformed point cloud data set that does not satisfy the preset elimination condition and the data points in the expected point cloud data set, and jump again to the step of transforming the current initial point cloud data set based on the current registration transformation matrix until the preset termination condition is currently satisfied, so as to determine the current initial point cloud data set as the target point cloud data set for the same preset part.

[0077] In some specific implementations, the process of determining the initial value of the current registration transformation matrix in the data set transformation unit may specifically include:

[0078] an initial value determination unit, configured to select a plurality of groups of data points from the expected point cloud data set and the initial point cloud data set for the same preset part, and determine an initial value of the current registration transformation matrix based on the plurality of groups of data points;

[0079] Among them, any group of data points among the plurality of groups of data points are data points corresponding to the same position in the expected point cloud data set and the initial point cloud data set for the same preset part.

[0080] In some specific implementations, the data set determination unit may specifically include:

[0081] an error value determination unit, configured to determine the minimum distance between each data point in the transformed point cloud data set that does not satisfy the preset rejection condition and each data point in the expected point cloud data set, and determine a current error value based on each of the minimum distances;

[0082] A matrix updating unit is used to determine a current descent gradient based on the current error value using a gradient descent method, so as to update the current registration transformation matrix using the current descent gradient.

[0083] In some specific implementations, the preset termination condition includes that the current descent gradient is less than a preset gradient threshold, and / or the cumulative number of updates to the current registration transformation matrix reaches a preset number.

[0084] In some specific implementations, the actual location determination module 13 may specifically include:

[0085] A centroid coordinate determining unit, configured to determine the centroid coordinates corresponding to each of the target point cloud data sets based on the coordinates of the data points in each of the target point cloud data sets;

[0086] Among them, the centroid coordinates include coordinate values ​​in three different directions, any coordinate value is a value determined based on the sum of the coordinate values ​​of the data points in the target point cloud data set in the target direction; the target direction is the same direction as the direction of any coordinate value.

[0087] In some specific implementations, the actual location determination module 13 may specifically include:

[0088] an actual position determination unit, configured to determine a first vector from the expected position to the position of the aircraft to be painted in the target coordinate system, determine a second vector from the position of the aircraft painting equipment to the expected position, and determine the actual position of the aircraft to be painted based on the first vector and the second vector;

[0089] Accordingly, the aircraft painting module 14 may specifically include:

[0090] The painting trajectory generating unit is used to determine the translation deviation and the rotation deviation according to the actual position and the expected position, so as to generate an actual painting trajectory for the aircraft to be painted based on the translation deviation and the rotation deviation.

[0091] Furthermore, the present application also discloses an electronic device. Figure 4This is a structural diagram of an electronic device 20 according to an exemplary embodiment, and the content in the figure cannot be regarded as any limitation on the scope of use of this application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 is used to store a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the aircraft painting method disclosed in any of the aforementioned embodiments. In addition, the electronic device 20 in this embodiment may specifically be an electronic computer.

[0092] In this embodiment, the power supply 23 is used to provide working voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and the external device, and the communication protocol it follows is any communication protocol that can be applied to the technical solution of the present application, and is not specifically limited here; the input and output interface 25 is used to obtain external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs and is not specifically limited here.

[0093] In addition, the memory 22, as a carrier for storing resources, can be a read-only memory, a random access memory, a disk or an optical disk, etc. The resources stored thereon can include an operating system 221, a computer program 222, etc., and the storage method can be temporary storage or permanent storage.

[0094] The operating system 221 is used to manage and control the hardware devices on the electronic device 20 and the computer program 222, which can be Windows Server, Netware, Unix, Linux, etc. In addition to including a computer program that can be used to complete the aircraft painting method performed by the electronic device 20 disclosed in any of the aforementioned embodiments, the computer program 222 can further include a computer program that can be used to complete other specific tasks.

[0095] Furthermore, the present application also discloses a computer-readable storage medium for storing a computer program; wherein the computer program, when executed by a processor, implements the aforementioned disclosed aircraft painting method. The specific steps of the method can refer to the corresponding contents disclosed in the aforementioned embodiments, and will not be repeated here.

[0096] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0097] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0098] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0099] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0100] The technical solution provided by the present application is introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for general technicians in this field, according to the idea of ​​the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for painting an aircraft, characterized in that: Applied to aircraft painting equipment, including: Obtaining an initial point cloud data set of each preset part of the aircraft to be painted; The expected point cloud data set and the initial point cloud data set for the same preset position are registered to remove unregistered data points in the initial point cloud data set to obtain a corresponding target point cloud data set; each of the expected point cloud data sets is a data set obtained from each of the preset positions in the aircraft when the aircraft is at an expected position; Determine the corresponding centroid coordinates based on each of the target point cloud data sets, respectively, to construct a target coordinate system using the centroid coordinates, and determine the actual position of the aircraft to be painted based on the expected position and the position of the aircraft to be painted in the target coordinate system; generating an actual painting trajectory for the aircraft to be painted according to the actual position and the expected position, so as to paint the aircraft to be painted; The registering of the expected point cloud dataset and the initial point cloud dataset for the same preset part to remove unregistered data points in the initial point cloud dataset to obtain a corresponding target point cloud dataset includes: Determine the expected point cloud dataset and the initial point cloud dataset for the same preset part to obtain a current expected point cloud dataset and a current initial point cloud dataset, and transform the current initial point cloud dataset based on the current registration transformation matrix to obtain a transformed point cloud dataset; Determine a target data point that meets a preset rejection condition from the transformed point cloud data set; the preset rejection condition includes that the minimum distance between the target data point and a data point in the current expected point cloud data set is greater than a preset distance; Eliminate the unregistered data points corresponding to the target data points in the current initial point cloud dataset to update the current initial point cloud dataset, and when the preset termination condition is not currently met, update the current registration transformation matrix based on the minimum distance between each data point in the transformed point cloud dataset that does not meet the preset elimination condition and the data points in the expected point cloud dataset, and jump again to the step of transforming the current initial point cloud dataset based on the current registration transformation matrix until the preset termination condition is currently met, so as to determine the current initial point cloud dataset as the target point cloud dataset for the same preset part.

2. The aircraft painting method according to claim 1, characterized in that: The process of determining the initial value of the current registration transformation matrix includes: Selecting a plurality of groups of data points from the expected point cloud data set and the initial point cloud data set for the same preset part, and determining an initial value of the current registration transformation matrix based on the plurality of groups of data points; Among them, any group of data points among the plurality of groups of data points are data points corresponding to the same position in the expected point cloud data set and the initial point cloud data set for the same preset part.

3. The aircraft painting method according to claim 1, characterized in that: The updating of the current registration transformation matrix based on the minimum distance between each data point in the transformed point cloud data set that does not meet the preset rejection condition and the data points in the expected point cloud data set comprises: Determine the minimum distance between each data point in the transformed point cloud data set that does not meet the preset rejection condition and the data point in the expected point cloud data set, and determine the current error value based on each of the minimum distances; A current descent gradient is determined based on the current error value using a gradient descent method, so as to update the current registration transformation matrix using the current descent gradient.

4. The aircraft painting method according to claim 3, characterized in that: The preset termination condition includes that the current descent gradient is less than a preset gradient threshold, and / or the accumulated number of updates to the current registration transformation matrix reaches a preset number.

5. The aircraft painting method according to claim 1, characterized in that: The determining of corresponding centroid coordinates based on each of the target point cloud data sets includes: Determine the centroid coordinates corresponding to each of the target point cloud data sets based on the coordinates of the data points in each of the target point cloud data sets; Among them, the centroid coordinates include coordinate values ​​in three different directions, any coordinate value is a value determined based on the sum of the coordinate values ​​of the data points in the target point cloud data set in the target direction; the target direction is the same direction as the direction of any coordinate value.

6. The aircraft painting method according to any one of claims 1 to 5, characterized in that: The determining the actual position of the aircraft to be painted based on the expected position and the position of the aircraft to be painted in the target coordinate system comprises: Determine a first vector from the expected position to the position of the aircraft to be painted in the target coordinate system, determine a second vector from the position of the aircraft painting equipment to the expected position, and determine the actual position of the aircraft to be painted based on the first vector and the second vector; Accordingly, generating an actual painting trajectory for the aircraft to be painted according to the actual position and the expected position includes: A translation deviation and a rotation deviation are determined according to the actual position and the expected position, so as to generate an actual painting trajectory for the aircraft to be painted based on the translation deviation and the rotation deviation.

7. An aircraft painting device, characterized in that: Applied to aircraft painting equipment, including: A data set acquisition module is used to acquire an initial point cloud data set of each preset part of the aircraft to be painted; A data set registration module, used for registering the expected point cloud data set for the same preset part with the initial point cloud data set, so as to remove the unregistered data points in the initial point cloud data set and obtain the corresponding target point cloud data set; each of the expected point cloud data sets is a data set respectively obtained from each of the preset parts in the aircraft when the aircraft is at the expected position; an actual position determination module, configured to determine corresponding centroid coordinates based on each of the target point cloud data sets, respectively, to construct a target coordinate system using the centroid coordinates, and to determine the actual position of the aircraft to be painted based on the expected position and the position of the aircraft to be painted in the target coordinate system; An aircraft painting module, used for generating an actual painting trajectory for the aircraft to be painted according to the actual position and the expected position, so as to paint the aircraft to be painted; Wherein, the data set registration module includes: a data set transformation unit, configured to determine the expected point cloud data set and the initial point cloud data set for the same preset part to obtain a current expected point cloud data set and a current initial point cloud data set, and transform the current initial point cloud data set based on a current registration transformation matrix to obtain a transformed point cloud data set; A data point determination unit, configured to determine a target data point that satisfies a preset elimination condition from the transformed point cloud data set; the preset elimination condition includes that a minimum distance between the target data point and a data point in the current expected point cloud data set is greater than a preset distance; A data set determination unit is used to eliminate unregistered data points corresponding to the target data points in the current initial point cloud data set to update the current initial point cloud data set, and when the preset termination condition is not currently satisfied, update the current registration transformation matrix based on the minimum distance between each data point in the transformed point cloud data set that does not satisfy the preset elimination condition and the data points in the expected point cloud data set, and jump again to the step of transforming the current initial point cloud data set based on the current registration transformation matrix until the preset termination condition is currently satisfied, so as to determine the current initial point cloud data set as the target point cloud data set for the same preset part.

8. An electronic device, characterized in that: include: Memory, used to store computer programs; A processor, configured to execute the computer program to implement the aircraft painting method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: Used to store a computer program; wherein, when the computer program is executed by a processor, the aircraft painting method according to any one of claims 1 to 6 is implemented.

Images