Intelligent coordinate conversion method, device and system and storage medium

Abstract

The invention discloses an intelligent coordinate conversion method, device and system and a storage medium, and relates to the technical field of vehicle and industrial robot application, and the method comprises the steps: obtaining a robot data file and a vehicle body coordinate system data file, first point set data under a robot base coordinate system and second point set data under a vehicle body coordinate system are obtained through file analysis; calculating a rotation matrix and a translation vector based on the first point set data and the second point set data; and calculating a first conversion result and / or a second conversion result based on the rotation matrix and the translation vector. According to the scheme, the calculation process for accurately solving the rotation matrix and the translation vector is designed, the high precision of coordinate conversion can be ensured, meanwhile, import and analysis of data of various mainstream brand robots can be supported, and the universality and flexibility of the system are enhanced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle and industrial robot application, and specifically provides an intelligent coordinate conversion method, device, system and storage medium. BACKGROUND

[0002] With the transformation and development of automation and intelligence in the automobile manufacturing industry, the application of robots in automobile manufacturing processes such as body assembly, welding and other processes is increasing. In the automobile manufacturing process, the precise operation of industrial robots is crucial to ensure product quality. However, due to the difference between the robot base coordinate system and the body coordinate system, traditional coordinate conversion methods rely on manual measurement and complex algorithms, which are tedious to operate and difficult to meet the increasing demand for production efficiency. Moreover, traditional methods may produce errors during conversion, thereby affecting the operation accuracy of the robot. Therefore, there is room for improvement in the efficiency and conversion accuracy of traditional coordinate conversion methods. Traditional coordinate conversion methods also have difficulty in adapting to the compatibility of the diversification of different brand robot data formats. SUMMARY

[0003] In order to overcome the above-mentioned defects, the present application provides an intelligent coordinate conversion method, device, system and storage medium which can effectively improve the conversion efficiency and conversion accuracy.

[0004] In a first aspect, the present application provides an intelligent coordinate conversion method, comprising:

[0005] obtaining a robot data file and a body coordinate system data file;

[0006] determining a first parsing component corresponding to the type of the robot data file based on the type of the robot data file, and parsing the robot data file based on the first parsing component to obtain first point set data in the robot base coordinate system;

[0007] parsing the body coordinate system data file based on a second parsing component corresponding to the body coordinate system data file to obtain second point set data in the body coordinate system;

[0008] calculating a rotation matrix and a translation vector based on the first point set data and the second point set data;

[0009] calculating a first conversion result and / or a second conversion result based on the rotation matrix and the translation vector;

[0010] The first conversion result corresponds to the conversion result of converting the first point set data from the robot base coordinate system to the body coordinate system; and the second conversion result corresponds to the conversion result of converting the second point set data from the body coordinate system to the robot base coordinate system.

[0011] Preferably, the method further comprises: performing error analysis based on the first transformation result and the second point set data or based on the second transformation result and the first point set data to obtain an error analysis result, the error analysis result comprising at least one of a minimum error, a maximum error, an average error, a root mean square error, and an error analysis chart.

[0012] Preferably, the method further comprises a step of converting the rotation matrix into Euler angles.

[0013] Preferably, the calculating the rotation matrix and the translation vector based on the first point set data and the second point set data comprises:

[0014] calculating a first centroid and a second centroid by respectively calculating a centroid of the first point set data and the second point set data;

[0015] de-centring the first point set data and the second point set data based on the first centroid and the second centroid;

[0016] constructing a covariance matrix based on the de-centred first point set data and the de-centred second point set data, and performing singular value decomposition on the covariance matrix to obtain the rotation matrix;

[0017] calculating a translation vector based on the rotation matrix, the first centroid and the second centroid. Preferably, the performing singular value decomposition on the covariance matrix to obtain the rotation matrix comprises:

[0018] performing singular value decomposition on the covariance matrix to obtain an initial estimation matrix, and performing reflection correction on the initial estimation matrix according to an orthogonality constraint condition to obtain the rotation matrix.

[0019] Preferably, the method further comprises, if the first parsing component corresponding to the type of the robot data file cannot be determined, parsing the robot data file based on a preset universal parsing component to extract all numerical values in the file, and obtaining the first point set data based on the extracted all numerical values.

[0020] Preferably, the parsing the robot data file based on the first parsing component to obtain the first point set data in the robot base coordinate system comprises: parsing the robot data file to obtain a first coordinate point set, and extracting a preset number of coordinate point data from the first coordinate point set to obtain the first point set data.

[0021] The parsing of the vehicle body coordinate system data file based on the second parsing component corresponding to the vehicle body coordinate system data file comprises: parsing the vehicle body coordinate system data file to obtain a second coordinate point set, and extracting a preset number of coordinate point data from the second coordinate point set to obtain the second point set data.

[0022] In a second aspect, the present application provides a computing device, comprising a processor and a memory, the memory being adapted to store a plurality of program codes, the program codes being adapted to be loaded and run by the processor to execute the intelligent coordinate conversion method described in any of the above technical solutions.

[0023] In a third aspect, the present application provides an intelligent coordinate conversion system, comprising a human-computer interaction module and the above computing device; the human-computer interaction module is used to obtain user input information, the user input information being used to select corresponding robot data files and vehicle body coordinate system data files; and is also used to show the first point set data and the second point set data obtained according to the user input information to the user, and show the result data obtained by the computing device according to the first point set data and the second point set data, the result data comprising a first conversion result, a second conversion result, an error analysis result and Euler angles.

[0024] In a fourth aspect, the present application provides a computer readable storage medium, wherein a plurality of program codes are stored, the program codes being adapted to be loaded and run by a processor to execute the intelligent coordinate conversion method described in any of the above technical solutions.

[0025] The above one or more technical solutions of the present application have at least one or more of the following beneficial effects: the present application uses advanced mathematical models and matrix operations, combines centroid calculation, singular value decomposition and other technologies, accurately solves the rotation matrix and the translation vector, ensures the high precision of coordinate conversion, and further improves the accuracy of robot operation. The present application can support the import and analysis of data of multiple mainstream brand robots, automatically identify and process different format files, extract key coordinate information, lay a foundation for subsequent unified calculation, and enhance the universality and flexibility of the system. BRIEF DESCRIPTION OF DRAWINGS

[0026] The disclosure of the present application will become more apparent with reference to the drawings. It is easy for those skilled in the art to understand that these drawings are only for illustrative purposes, and are not intended to limit the scope of protection of the present application. In addition, similar numbers in the figures are used to represent similar components, wherein:

[0027] Figure 1 is a main step flow diagram of an intelligent coordinate conversion method provided by an embodiment of the present application;

[0028] Figure 2 yes Figure 1 A flowchart illustrating the specific implementation steps of step S14;

[0029] Figure 3 is a schematic diagram of the working page of an intelligent coordinate transformation system provided in an embodiment of this application. Detailed Implementation

[0030] Some embodiments of this application are described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of this application and are not intended to limit the scope of protection of this application.

[0031] In the description of this application, "module" and "processor" can include hardware, software, or a combination of both. A module can include hardware circuitry, various suitable sensors, communication ports, memory, and can also include software components, such as program code, or a combination of software and hardware. A processor can be a central processing unit, microprocessor, image processor, digital signal processor, or any other suitable processor. The processor has data and / or signal processing capabilities. The processor can be implemented in software, in hardware, or a combination of both. Non-transitory computer-readable storage media includes any suitable medium capable of storing program code, such as magnetic disks, hard disks, optical disks, flash memory, read-only memory, random access memory, etc. The term "A and / or B" means all possible combinations of A and B, such as only A, only B, or A and B. The terms "at least one A or B" or "at least one of A and B" have a similar meaning to "A and / or B" and can include only A, only B, or A and B. The singular terms "a" or "this" can also include plural forms.

[0032] The technical terms used in the embodiments of this application are explained as follows:

[0033] Robot base coordinate system: refers to the coordinate system of the robot's installation position, which is the reference coordinate system for the robot's movement.

[0034] Vehicle body coordinate system: refers to the coordinate system of the vehicle body, used to determine the positional relationship of various parts of the vehicle body.

[0035] The execution subject of the intelligent coordinate transformation method proposed in this application includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in the embodiments of this application: a server, a terminal, etc. In other words, the method of this application can be executed by software or hardware installed on a terminal device or a server device. The terminal device includes, but is not limited to, a computer, a robot, a vehicle, etc. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster. The server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms.

[0036] like Figure 1 As shown, the intelligent coordinate transformation method provided in this application includes the following steps S11 to S16:

[0037] Step S11: Obtain the robot data file and the vehicle body coordinate system data file;

[0038] In this embodiment, the robot data file can be a data file of any brand or type of robot, and the type of data file corresponding to different types of robots is also different.

[0039] For example, the robot data files in this application can be data files of different brands of robots such as ABB, KUKA, and FANUC. Among them, the ABB robot data file is a .mod file, the KUKA robot data file is a .dat file, and the FANUC robot data file is a .ls file.

[0040] Step S12: Determine the first parsing component corresponding to the type of the robot data file, and parse the robot data file based on the first parsing component to obtain the first point set data in the robot base coordinate system;

[0041] In this embodiment, the type of the acquired robot data file can be determined by identifying its extension. For example, if the acquired robot data file is a *.mod file, it is identified as an ABB robot, and thus the first parsing component is specifically identified as the first parsing component corresponding to the ABB robot. In this embodiment, the first parsing component can be understood as a pre-defined regular expression engine that corresponds one-to-one with different types of robot data files. Optionally, a dynamic regular expression library can be pre-built, and the regular expression engines corresponding to different types of robot data files can be built into it. In actual use, the corresponding regular expression engine in the dynamic regular expression library is automatically called according to the file type for file parsing. The regular expression engine refers to a software component used to perform regular expression matching and operations, and its core functions include parsing regular expression patterns, processing input text, and performing matching or replacement operations.

[0042] For example, the dynamic regular expression library constructed in this embodiment is as follows: BRAND_REGEX = {"ABB":regex_abb,"FANUC":regex_fanuc,"KUKA":regex_kuka}. It automatically calls the corresponding regular expression engine according to the file extension (.mod / .ls / .dat) of the currently acquired robot data file. For example, if the file type is identified as .dat, the corresponding regular expression engine "KUKA":regex_kuka is called to parse the file.

[0043] Step S13: Based on the second parsing component corresponding to the vehicle coordinate system data file, parse the vehicle coordinate system data file to obtain the second point set data in the vehicle coordinate system;

[0044] In this embodiment, the vehicle body coordinate system data file can be a 3D coordinate system data file with a file type of .txt obtained based on a coordinate measuring system. The second parsing component in this embodiment can be understood as a pre-defined regularization engine corresponding to the 3D coordinate system data file.

[0045] Step S14: Calculate the rotation matrix and translation vector based on the first point set data and the second point set data;

[0046] In this embodiment, preferably, both the first point set data and the second point set data contain 4 coordinate point data, and the physical locations of the 4 coordinate point data corresponding to the 4 coordinate point data in the first point set data correspond one-to-one with the physical locations of the 4 coordinate point data corresponding to the 4 coordinate point data in the second point set data.

[0047] Step S15: Calculate the first transformation result and / or the second transformation result based on the rotation matrix and the translation vector.

[0048] Wherein, the first transformation result corresponds to the transformation result of transforming the first point set data from the robot base coordinate system to the vehicle body coordinate system; the second transformation result corresponds to the transformation result of transforming the second point set data from the vehicle body coordinate system to the robot base coordinate system.

[0049] For example, if the rotation matrix is ​​R and the translation vector is T, the first transformation result is... The second transformation result can be calculated further through inverse transformation.

[0050] In one specific embodiment, step S15 may be followed by step S16:

[0051] Step S16: Perform error analysis based on the first transformation result and the second point set data to obtain the error analysis result.

[0052] In this embodiment, based on the first or second transformation result, the error and root mean square error of each corresponding point in the first and second point sets can be calculated. Through error statistical analysis, the minimum error, maximum error, average error, and root mean square error can be obtained. Furthermore, the error statistical data can be plotted as an error analysis chart. Therefore, the error analysis result in this embodiment may include at least one of the minimum error, maximum error, average error, root mean square error, and an error analysis chart. It should be understood that this step can also be based on the second transformation result and the first point set to perform error analysis to obtain the error analysis result.

[0053] For example, transform the point set in the robot's base coordinate system to the vehicle's coordinate system using the obtained R and T coordinates:

[0054]

[0055] Calculate the error for each corresponding point. (i) :

[0056]

[0057] Calculate the root mean square error (RMS) for each group:

[0058]

[0059] The embodiments of this application can significantly improve the accuracy and reliability of coordinate transformation through key steps such as centroid denoising, robust SVD solution, reflection correction, consistent translation calculation, and closed-loop error verification. It is especially suitable for on-site calibration scenarios of industrial robots with extremely high accuracy requirements. That is, the robot's working point is adjusted based on the transformation results and error analysis results, thereby improving the accuracy of robot operation.

[0060] In practical applications of coordinate system transformation, the description of coordinate points usually includes angle values ​​in addition to coordinate values. Accordingly, after step S15 above, there may also be a step of converting the rotation matrix into Euler angles.

[0061] In practical applications, the intelligent coordinate transformation method provided in this application may further include: displaying the first transformation result and / or the second transformation result to the user based on a visual interface; or displaying the first transformation result and / or the second transformation result to the user based on a visual interface, and displaying at least one of the error analysis result and the Euler angles.

[0062] In one specific implementation, the step S12 above, which determines the corresponding first parsing component based on the type of the robot data file, may include:

[0063] If the robot data file is a .mod file, its characteristic is that coordinate values ​​are nested in motion instructions (MoveJ / MoveL) in the form of [[x,y,z],[q1,q2,q3,q4]]. In this case, a corresponding first parsing component can be identified, and this first parsing component uses a first regular expression matching rule. Based on this first regular expression matching rule, the .mod file is parsed to extract coordinate values ​​[x,y,z], with the unit set to mm by default. The extracted coordinates are stored in the following format: np.array([[x1,y1,z1],...]), and the brand label is marked as "ABB". Furthermore, the redundancy removal design during parsing automatically skips comment lines (starting with !) and lines that do not contain motion instructions.

[0064] For example, the first regular expression matching rule is as follows:

[0065] r'Move[JL]\s+.*? \[\[\s*(-?\d+\.?\d*)\s*,\s*(-?\d+\.?\d*)\s*,\s*(-?\d+\.?\d*)\s*\]'.

[0066] If the robot data file is a .mod file, and the file is characterized by coordinates scattered across multiple lines in the form of key-value pairs X=123.45mm, Y=234.56mm, Z=345.67mm, then the corresponding first parsing component can be determined. This first parsing component uses a second regular expression matching rule, which performs multi-line joint matching. Based on this second regular expression matching rule, the .ls file is parsed to extract coordinate values ​​[x,y,z], and the unit is unified to mm. The extracted coordinates are stored in the following format: np.array([[x1,y1,z1],...]), and the brand label is marked as "FUNUC".

[0067] For example, the second regular expression matching rule is as follows:

[0068] r'X\s*=\s*(-?\d+\.?\d*).*? Y\s*=\s*(-?\d+\.?\d*).*? Z\s*=\s*(-?\d+\.?\d*)'.

[0069] If the robot data file is a .dat file, its characteristic is that the coordinates are embedded in the KUKA robot file custom structure (DECL E6POS structure) in the form of X123.45, Y234.56, Z345.67, which may contain A / B / C Euler angles. In this case, the corresponding first parsing component can be determined, and the first parsing component adopts the third regular expression matching rule. During parsing, the DECL E6POS field is located first, and then the data of the .dat file is parsed based on the third regular expression matching rule, and the Euler angles are separated, that is, A / B / C are ignored and only the coordinate values ​​[x,y,z] are extracted, and the unit is unified to mm. The extracted coordinates are stored in the following format: np.array([[x1,y1,z1],...]), and the brand label is marked as "KUKA".

[0070] For example, the third regular expression matching rule is as follows:

[0071] r'X\s+(-?\d+\.?\d*).*? Y\s+(-?\d+\.?\d*).*? Z\s+(-?\d+\.?\d*)').

[0072] If the corresponding first parsing component cannot be determined, the robot data file can be parsed and all values ​​in the file can be extracted based on a preset general parsing component, and the first set of coordinate points can be obtained based on all the extracted values. For example, if the extension recognition of the currently acquired robot data file fails, the general text mode is triggered, that is, the preset general parsing component (for example, the regular expression matching rule used by this component is r'[-+]?\d*\.\d+|\d+') is called to perform text parsing to extract all values, and then the values ​​are forcibly parsed into three coordinate values ​​[x,y,z] in groups of three. Then, the first set of coordinate points is formed based on all the obtained three coordinate values. In practical applications, after the general text mode is triggered, all the parsed three coordinate values ​​can also be provided to the user for confirmation, and the first set of coordinate points is formed after the user confirms.

[0073] The step S12 above, which involves parsing the robot data file based on the first parsing component to obtain a first set of points in the robot's base coordinate system, specifically includes: parsing the robot data file to obtain a first set of coordinate points, and extracting a preset number of coordinate points from the first set of coordinate points to obtain the first set of points data; the step of parsing the vehicle coordinate system data file based on the second parsing component corresponding to the vehicle coordinate system data file to obtain a second set of points in the vehicle coordinate system includes: parsing the vehicle coordinate system data file to obtain a second set of coordinate points, and extracting a preset number of coordinate points from the second set of coordinate points to obtain the second set of points data. Preferably, the preset number is 4.

[0074] The step S12 above, which involves parsing the robot data file based on the first parsing component to obtain the first point set data in the robot base coordinate system, includes: parsing the robot data file to obtain the first coordinate point set, and extracting a preset number of coordinate point data from the first coordinate point set to obtain the first point set data; the step S12 above, which involves parsing the vehicle coordinate system data file based on the second parsing component corresponding to the vehicle coordinate system data file to obtain the second point set data in the vehicle coordinate system, includes: parsing the vehicle coordinate system data file to obtain the second coordinate point set, and extracting a preset number of coordinate point data from the second coordinate point set to obtain the second point set data.

[0075] In this embodiment, before extracting a preset number of coordinate point data, the method further includes: a step of unifying the units of the coordinate point data in the first coordinate point set and the second coordinate point set, for example, unifying the units using the units of the vehicle body coordinate system as the standard; and a step of sorting the data in the first coordinate point set and the data in the second coordinate point set according to the physical order of the coordinate points.

[0076] In one specific implementation, the specific method for calculating the rotation matrix and translation vector based on the first point set data and the second point set data in step S14 above is as follows: Figure 2 The specific steps shown are S141 and S144:

[0077] Step S141: Calculate the centroids of the first point set data and the second point set data respectively to obtain the first centroid and the second centroid;

[0078] For example, consider the point set P in the robot's base coordinate system. robot and the point set P in the vehicle body coordinate system car Calculate the centroid:

[0079]

[0080] Among them, C robot As the first center of mass, C car Let n be the second centroid, and n be a positive integer, preferably n = 4.

[0081] Step S142: Decentrifuge the first point set data and the second point set data based on the first centroid and the second centroid;

[0082] For example, after centroid-decentrating two point sets, the centered point set is as follows:

[0083]

[0084] in, This is the first set of data after centroid decentering. It is the second point set data after centroid decentering.

[0085] Step S143: Construct a covariance matrix based on the first point set data and the second point set data after centroid decentering, and perform singular value decomposition on the covariance matrix to obtain a rotation matrix;

[0086] For example, the constructed covariance matrix is ​​H:

[0087]

[0088] The covariance matrix contains information about the rotational relationships between point sets and is the core foundation for subsequent accurate solutions to the rotation matrix.

[0089] Perform singular value decomposition (SVD) on the covariance matrix H:

[0090] H=U∑V T

[0091] SVD decomposition can robustly extract the initial estimate matrix R of the rotation matrix.initial =VU T Compared to traditional methods (such as eigenvalue decomposition or direct least squares solution), SVD decomposition has stronger numerical stability, especially when dealing with noisy data or point sets that are nearly collinear / coplanar, effectively avoiding singularity or ill-conditioned problems in the solution.

[0092] In this embodiment, preferably, the initial estimation matrix R is obtained by performing singular value decomposition on the covariance matrix. initial Subsequently, the initial estimated matrix can be corrected by reflection according to the orthogonality constraint to obtain the rotation matrix, specifically as follows: Check the determinant of the rotation matrix: det(R) initial If the determinant is negative (i.e., the matrix V is negative), then invert the rightmost column of matrix V.

[0093] V corrected = [v1 v2 v3], thus obtaining the rotation matrix R = V corrected U T .

[0094] This correction ensures the physical validity of the rotation matrix (i.e., the determinant is positive 1), avoiding reflection transformations caused by data noise or uneven distribution of point sets, which is a key detail often overlooked in traditional methods.

[0095] Step S144: Calculate the translation vector based on the rotation matrix, the first centroid, and the second centroid.

[0096] For example, after obtaining the exact rotation matrix R, the translation vector T is recalculated using the centroid relation:

[0097] T = C car -R·C robot

[0098] This step utilizes an optimized rotation matrix to ensure that the translation vector is highly consistent with the rotation parameters, further improving the overall accuracy of the coordinate transformation.

[0099] Furthermore, this application provides a computing device including a processor and a memory, the memory being adapted to store a plurality of program codes, the program codes being adapted to be loaded and run by the processor to perform the intelligent coordinate transformation method of the above method embodiments.

[0100] Furthermore, this application also provides an intelligent coordinate transformation system, including a human-computer interaction module and a computing device, wherein:

[0101] The computing device is configured to perform the intelligent coordinate transformation method mentioned in any of the above embodiments.

[0102] The human-computer interaction module is used to acquire user input information, which is used to select the corresponding robot data file and vehicle coordinate system data file; it is also used to display the result data output by the computing device to the user, which includes at least one of a first transformation result, a second transformation result, an error analysis result, and Euler angles.

[0103] For example, during the operation of the intelligent coordinate transformation system in this embodiment, the interface diagram provided by the human-computer interaction module is shown in Figure 3. Figure 3(a) is the interface for user input information, such as station information and robot information (Robot and Robot Type). Figure 3(b) is the interface for displaying the first point set data and the second point set data obtained based on the user input information to the user. That is, the coordinate point data P1\P2\P3\P4 corresponding to the robot base coordinate system on the left and the coordinate point data P1\P2\P3\P4 corresponding to the vehicle coordinate system on the right as shown in the figure. Figure 3(c) is the interface for displaying the first transformation result, the second transformation result, Euler angles and error analysis results to the user. The Euler angles shown in the figure are represented by quaternions.

[0104] In practical applications, the intelligent coordinate transformation system of this application may also include a data export module for exporting the result data generated by the computing device. For example, the data may be directly exported and stored in a default file under the default storage path, or the exported data may be saved as an Excel file and a folder with the same name as the Excel file may be created to store screenshots for easy viewing, sharing and in-depth sharing by users.

[0105] Furthermore, this application provides a computer-readable storage medium storing a plurality of program codes adapted to be loaded and run by a processor to perform the intelligent coordinate transformation method of the above-described method embodiments.

[0106] It should be noted that although the steps in the above embodiments are described in a specific order, those skilled in the art will understand that in order to achieve the effect of this application, different steps do not necessarily have to be executed in such an order. They can be executed simultaneously (in parallel) or in other orders. These adjusted solutions are equivalent to the technical solutions described in this application and therefore will also fall within the protection scope of this application.

[0107] The technical solutions of this application have been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of this application is obviously not limited to these specific embodiments. Without departing from the principles of this application, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of this application.

Claims

1. An intelligent coordinate transformation method, characterized in that, The method includes: Obtain robot data files and vehicle body coordinate system data files; Based on the type of the robot data file, a first parsing component is determined, and the robot data file is parsed based on the first parsing component to obtain a first point set data in the robot base coordinate system. The second parsing component corresponding to the vehicle coordinate system data file parses the vehicle coordinate system data file to obtain the second point set data in the vehicle coordinate system; Calculate the rotation matrix and translation vector based on the first point set data and the second point set data; The first transformation result and / or the second transformation result are calculated based on the rotation matrix and the translation vector; Wherein, the first transformation result corresponds to the transformation result of transforming the first point set data from the robot base coordinate system to the vehicle body coordinate system; the second transformation result corresponds to the transformation result of transforming the second point set data from the vehicle body coordinate system to the robot base coordinate system.

2. The intelligent coordinate transformation method according to claim 1, characterized in that, The method further includes: Error analysis results are obtained by performing error analysis based on the first transformation result and the second point set data or based on the second transformation result and the first point set data. The error analysis results include at least one of the following: minimum error, maximum error, average error, root mean square error, and error analysis chart.

3. The intelligent coordinate transformation method according to claim 1 or 2, characterized in that, The method also includes the step of converting the rotation matrix into Euler angles.

4. The intelligent coordinate transformation method according to claim 1, characterized in that, The calculation of the rotation matrix and translation vector based on the first point set data and the second point set data includes: The first centroid and the second centroid are obtained by calculating the centroids of the first point set data and the second point set data, respectively. Based on the first centroid and the second centroid, the first point set data and the second point set data are decentroided; A covariance matrix is ​​constructed based on the first and second point set data after centroid decentering. Singular value decomposition is then performed on the covariance matrix to obtain a rotation matrix. The translation vector is calculated based on the rotation matrix, the first centroid, and the second centroid.

5. The intelligent coordinate transformation method according to claim 4, characterized in that, The step of performing singular value decomposition on the covariance matrix to obtain the rotation matrix includes: The initial estimation matrix is ​​obtained by performing singular value decomposition on the covariance matrix, and the rotation matrix is ​​obtained by reflection correction of the initial estimation matrix according to the orthogonality constraint.

6. The intelligent coordinate transformation method according to claim 1, characterized in that, The method further includes, if a first parsing component corresponding to the type of the robot data file cannot be determined, then the robot data file is parsed and all values ​​in the file are extracted based on a preset general parsing component, and the first set of coordinate points is obtained based on all the extracted values.

7. The intelligent coordinate transformation method according to claim 1, characterized in that, The step of parsing the robot data file based on the first parsing component to obtain the first point set data in the robot base coordinate system includes: parsing the robot data file to obtain the first coordinate point set, and extracting a preset number of coordinate point data from the first coordinate point set to obtain the first point set data; The step of parsing the vehicle coordinate system data file based on the second parsing component corresponding to the vehicle coordinate system data file to obtain the second point set data in the vehicle coordinate system includes: parsing the vehicle coordinate system data file to obtain the second coordinate point set, and extracting a preset number of coordinate point data from the second coordinate point set to obtain the second point set data.

8. A computing device comprising a processor and a memory, the memory being adapted to store a plurality of program codes, characterized in that, The program code is adapted to be loaded and run by the processor to perform the intelligent coordinate transformation method according to any one of claims 1 to 7.

9. An intelligent coordinate transformation system, characterized in that, The system includes a human-computer interaction module and the computing device as described in claim 8; The human-computer interaction module is used to acquire user input information, which is used to select the corresponding robot data file and vehicle coordinate system data file. It is also used to display to the user a first point set data and a second point set data obtained based on the user input information, as well as to display the result data calculated by the computing device based on the first point set data and the second point set data, wherein the result data includes a first transformation result, a second transformation result, an error analysis result, and Euler angles.

10. A computer-readable storage medium storing a plurality of program codes, characterized in that, The program code is adapted to be loaded and run by a processor to perform the intelligent coordinate transformation method according to any one of claims 1 to 7.

Images