Wheel diameter correction method, wheel speed coefficient correction method, vehicle and storage medium

Abstract

This application discloses a wheel diameter correction method, a wheel speed coefficient correction method, a vehicle, and a storage medium. The wheel diameter correction method obtains extrinsic parameter data of the vehicle along a driving path to obtain positioning data for multiple positioning points. Based on the positioning data and the vehicle's first wheel diameter, it obtains first coordinate data of the detected target at the corresponding positioning time at multiple positioning points. Based on the distance differences of all detected targets across all positioning time periods, it obtains second coordinate data belonging to the same detected target from the first coordinate data. A correction coefficient is calculated based on the second coordinate data, and the wheel diameter is corrected based on this correction coefficient. This wheel diameter correction method directly corrects the vehicle's wheel diameter based on extrinsic parameter data, eliminating the need for online signals such as GPS. This reduces or avoids problems such as inaccurate wheel diameter correction due to weak GPS signals, reduces the dependence of wheel diameter correction on the environment, and improves the accuracy and reliability of wheel diameter correction.

Description

Technical Field

[0001] This application relates to the field of automotive electronics technology, and in particular to wheel diameter correction methods, wheel speed coefficient correction methods, vehicles, and storage media. Background Technology

[0002] Generally speaking, as a vehicle operates, the tire pressure inside the tires will change to some extent. At the same time, in autonomous vehicles, the vehicle's speed is calculated based on pulse signals installed on the wheels, so as to recursively extrapolate the vehicle's trajectory and achieve relative positioning of the vehicle.

[0003] However, changes in tire pressure alter the relative relationship between the pulse and the actual wheel speed. When tire pressure decreases, the distance between the wheel's center point and the contact point with the ground (i.e., the vehicle's contact wheel diameter) decreases, leading to a decline in the accuracy of relative positioning. Existing wheel diameter correction methods typically utilize GPS to identify the wheel's contact wheel diameter in real time, using the GPS's absolute position to correct the wheel speed coefficient.

[0004] However, existing wheel diameter correction methods rely on GPS signals when using GPS for wheel diameter correction. This requires a relatively open area to obtain a good GPS signal, enabling accurate correction of the wheel speed coefficient. However, in special scenarios such as tunnels, forests, and parking lots, GPS signals are weak or unstable, which may cause GPS-based wheel diameter correction methods to fail or lose accuracy. Summary of the Invention

[0005] To address the aforementioned technical problems, this application provides a wheel diameter correction method, a wheel speed coefficient correction method, a vehicle, and a storage medium.

[0006] To address the aforementioned problems, this application provides a first technical solution: a method for correcting the wheel diameter of a vehicle, comprising: obtaining extrinsic parameter data of the vehicle along a driving path, and obtaining positioning data of multiple positioning points based on the extrinsic parameter data; obtaining first coordinate data of a detected target at the positioning time corresponding to the multiple positioning points based on the positioning data and the first wheel diameter of the vehicle; obtaining second coordinate data belonging to the same detected target from the first coordinate data based on the distance differences of all detected targets within all the positioning time periods; and calculating a correction coefficient based on the second coordinate data, and correcting the first wheel diameter based on the correction coefficient.

[0007] Optionally, the aforementioned extrinsic data includes trajectory data of multiple aforementioned positioning points, and semantic data of each of the aforementioned positioning points during semantic detection; obtaining positioning data of multiple positioning points based on the aforementioned extrinsic data includes: performing interpolation calculation on the trajectory data of the aforementioned positioning points based on the detection time of the aforementioned semantic data to obtain the aforementioned positioning data.

[0008] Optionally, after the step of interpolating the trajectory data of the positioning point based on the detection time of the semantic data to obtain the positioning data, the wheel diameter correction method further includes: converting the positioning data under all the positioning times to the initial detection time of the semantic data; or, after the step of obtaining the second coordinate data belonging to the same detection target from the first coordinate data based on the distance difference of all the detection targets under all the positioning times, the wheel diameter correction method further includes: converting the second coordinate data under all the positioning times to the initial detection time of the semantic data.

[0009] Optionally, the above-mentioned calculation of correction coefficients based on the second coordinate data to correct the first wheel diameter includes: calculating an objective function between the fluctuation values ​​of all the above-mentioned detection targets at different positioning times and the ground wheel diameter of the vehicle based on the second coordinate data of all the above-mentioned detection targets; solving the objective function to correct the first wheel diameter based on the solution value of the objective function.

[0010] Optionally, the objective function calculated based on the second coordinate data of all the above-mentioned detection targets at different positioning times and the ground contact wheel diameter of the vehicle includes: calculating the covariance data of the second coordinate data of the same detection target; and summing the covariance data of all the above-mentioned detection targets to obtain the objective function.

[0011] Optionally, obtaining the first coordinate data of the detected target at the positioning time corresponding to the above-mentioned multiple positioning points based on the above-mentioned positioning data and the first wheel diameter of the vehicle includes: obtaining the third coordinate data of the detected target at each of the above-mentioned positioning points based on the above-mentioned positioning data, wherein the third coordinate data is coordinate data in a second coordinate system; and converting the detected target of the third coordinate data from the second coordinate system to the first coordinate system based on the first wheel diameter to obtain the first coordinate data.

[0012] Optionally, the first coordinate data of the positioning point under each of the above-mentioned positioning times includes the corner coordinates of at least one of the above-mentioned detection targets; the above-mentioned acquisition of second coordinate data belonging to the same detection target from the first coordinate data based on the distance difference of all the above-mentioned detection targets in all the above-mentioned positioning times includes: acquiring the first coordinate data of two above-mentioned positioning times in a first adjacent time; calculating the difference between the corner coordinates corresponding to the detection targets in the two above-mentioned first coordinate data in the first adjacent time; when the distance of the corner coordinates corresponding to the difference is less than a preset threshold and the direction of the difference between the corresponding corner coordinates is the same, determining that the two above-mentioned detection targets corresponding to the first adjacent time belong to the same detection target, so as to obtain the associated coordinate data of the first adjacent time; continuing to calculate the difference between the first coordinate data of two above-mentioned positioning times in a second adjacent time and obtaining the associated coordinate data of the second adjacent time, until the calculation of the first coordinate data of all adjacent above-mentioned positioning times is completed, so as to obtain the second coordinate data belonging to the same detection target.

[0013] To address the aforementioned problems, this application provides a second technical solution: a method for correcting wheel speed coefficient, comprising: obtaining a corrected first wheel diameter of the vehicle according to the above wheel diameter correction method; correcting the wheel speed coefficient of the vehicle based on the corrected first wheel diameter; and controlling the driving trajectory of the vehicle based on the corrected wheel speed coefficient.

[0014] To address the aforementioned problems, this application provides a third technical solution: a vehicle comprising a processor and a memory, wherein the processor is connected to the memory, and the memory stores program instructions; the processor is used to execute the program instructions stored in the memory to implement the method described above.

[0015] To address the aforementioned problems, this application provides a fourth technical solution: a computer-readable storage medium storing program instructions that can be executed by a processor to implement the above-described method.

[0016] This application provides a wheel diameter correction method, a wheel speed coefficient correction method, a vehicle, and a storage medium. The wheel diameter correction method includes: obtaining extrinsic parameter data of the vehicle along a driving path, and obtaining positioning data of multiple positioning points based on the extrinsic parameter data; obtaining first coordinate data of a detected target at the positioning time corresponding to the multiple positioning points based on the positioning data and the vehicle's first wheel diameter; obtaining second coordinate data belonging to the same detected target from the first coordinate data based on the distance differences of all detected targets at all positioning times; and calculating a correction coefficient based on the second coordinate data to correct the first wheel diameter. Through this method, the present application can directly locate the first coordinate data of a detected target at multiple positioning points based on the extrinsic parameter data, obtain the second coordinate data belonging to the same detected target based on the first coordinate data, and calculate the correction coefficient for the first wheel diameter to correct the vehicle's wheel diameter. This eliminates the need for wheel diameter correction via online signals such as GPS, reducing or avoiding problems such as inaccurate wheel diameter correction due to weak GPS signals, reducing the dependence of wheel diameter correction on the environment, and thus improving the accuracy and reliability of wheel speed calculation. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Wherein:

[0018] Figure 1 This is a flowchart illustrating the first embodiment of the wheel diameter correction method provided in this application;

[0019] Figure 2 This is a flowchart illustrating the second embodiment of the wheel diameter correction method provided in this application;

[0020] Figure 3 This is a flowchart illustrating the third embodiment of the wheel diameter correction method provided in this application;

[0021] Figure 4 This is a flowchart illustrating the fourth embodiment of the wheel diameter correction method provided in this application;

[0022] Figure 5 This is a flowchart illustrating an embodiment of the wheel speed correction method provided in this application;

[0023] Figure 6 This is a schematic diagram of the structure of one embodiment of the vehicle provided in this application;

[0024] Figure 7 This is a schematic diagram of an embodiment of the computer-readable storage medium provided in this application. Detailed Implementation

[0025] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0026] It should be noted that if the embodiments of this application involve directional indicators (such as up, down, left, right, front, back, etc.), the directional indicators are only used to explain the relative positional relationship and movement of the components in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indicators will also change accordingly.

[0027] Furthermore, if the embodiments of this application involve descriptions such as "first" or "second," these descriptions are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, features defined with "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the technical solutions of various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. If the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed in this application.

[0028] This application first provides a method for correcting the wheel diameter of a vehicle. This method is used to correct the ground contact wheel diameter so that the corrected ground contact wheel diameter is close to the actual wheel diameter. This facilitates the subsequent calculation of the vehicle's wheel speed based on the corrected wheel diameter, thereby achieving the relative positioning of the vehicle and improving the accuracy of vehicle positioning.

[0029] Please see Figure 1 , Figure 1 This is a schematic flowchart of the first embodiment of the wheel diameter correction method provided in this application. Figure 1 As shown, in this embodiment, the wheel diameter correction method includes the following steps:

[0030] Step S11: Obtain extrinsic parameter data of the vehicle along a driving path, and obtain positioning data of multiple positioning points based on the extrinsic parameter data.

[0031] Specifically, the extrinsic parameter data of a vehicle along a driving path can be, but is not limited to, external position parameters and other related data obtained by external devices such as sensors, LiDAR, and cameras while the vehicle is traveling along a certain driving path. The extrinsic parameter data can describe the vehicle's position relative to the world coordinate system along that driving path. After obtaining the extrinsic parameter data, positioning data for multiple positioning points can be obtained based on it. Here, a positioning point can be understood as multiple location trajectory points selected by the vehicle within that driving path. The vehicle has corresponding positioning data for each location trajectory point, which describes the relative positional relationship between the vehicle and ground objects within a certain positioning point along the driving path.

[0032] Step S12: Based on the positioning data and the first wheel diameter of the vehicle, obtain the first coordinate data of the detected target at the positioning time corresponding to multiple positioning points.

[0033] Each positioning point has a corresponding positioning time, which describes the temporal relationship of the positioning point within the driving path. For example, when the driving path includes multiple positioning points, each positioning point has a corresponding positioning time, and the multiple positioning points are arranged sequentially according to the chronological order of their positioning times. The vehicle's first wheel diameter can be understood as the current wheel diameter determined by the vehicle's control system. The first wheel diameter can be the wheel diameter under ideal tire pressure, the current wheel diameter defined by the control system, or the wheel diameter after wheel diameter correction in the previous stage; no specific limitation is made here.

[0034] Specifically, after obtaining the positioning data and the vehicle's first wheel diameter, the positional relationship of a ground object relative to the vehicle at each positioning point can be calculated based on the positioning data of all positioning points and the vehicle's first wheel diameter. To enhance the accuracy of the wheel diameter correction method in a specific application scenario, this embodiment can set a detection target. The detection target can be a common object in different application scenarios. For example, when a vehicle enters a parking lot, parking space corners, parking bollards, and positioning poles of entry / exit gates can be set as detection targets. The coordinate data of a detection target at the corresponding positioning time, i.e., the first coordinate data, can be obtained based on the positioning data of all positioning points. It is understood that the positioning data corresponding to each positioning point may include one or more detection targets, or may not have a corresponding detection target.

[0035] Step S13: Based on the distance differences of all detected targets within all positioning time periods, obtain the second coordinate data belonging to the same detected target from the first coordinate data.

[0036] After obtaining the first coordinate data of a specific detected target at each positioning point for a given positioning time, the distances between all detected targets can be calculated from the first coordinate data of all detected targets across all positioning time periods to obtain the distance differences among all detected targets. Based on these distance differences, the second coordinate data belonging to the same detected target at different positioning time periods can be determined.

[0037] For example, the extrinsic data for a driving path may include a first positioning point, a second positioning point, and a third positioning point. The first positioning point corresponds to a first positioning time, and its positioning data contains the first coordinate data of detection target 1 and detection target 2. The second positioning point corresponds to a second positioning time, and its positioning data contains the first coordinate data of detection target 2 and detection target 3. The third positioning point corresponds to a third positioning time, and its positioning data contains the first coordinate data of detection target 3 and detection target 1. At this time, by calculating the distance difference between the detection targets at the first and second positioning times, the distance difference between the detection targets at the second and third positioning times, and the distance difference between the detection targets at the first and third positioning times respectively, it can be determined from the above scheme that the first coordinate data of detection target 1 at the first positioning point corresponds to the first coordinate data of detection target 1 at the third positioning point, the first coordinate data of detection target 2 at the first positioning point corresponds to the first coordinate data of detection target 2 at the second positioning point, and the first coordinate data of detection target 3 at the second positioning point corresponds to the first coordinate data of detection target 3 at the third positioning point. Therefore, coordinate data belonging to the same detection target can be determined from the above content to obtain the second coordinate data.

[0038] Step S14: Calculate the correction coefficient based on the second coordinate data, and correct the first wheel diameter based on the correction coefficient.

[0039] After obtaining the second coordinate data of all positioning points belonging to the same detection target, the positional change relationship of the same three-dimensional object (i.e., the detection target) at different positioning times in the above driving path can be determined based on the second coordinate data. A correction coefficient can then be calculated based on this positional change relationship, and the first wheel diameter can be corrected based on the correction coefficient. The correction coefficient ensures that the corrected first wheel diameter maintains a stable value at different positioning times, reducing wheel diameter fluctuations caused by factors such as tire pressure, and improving the reliability and stability of wheel diameter correction.

[0040] In this embodiment, the wheel diameter correction method includes: obtaining extrinsic parameter data of the vehicle along a driving path, and obtaining positioning data of multiple positioning points based on the extrinsic parameter data; obtaining first coordinate data of a detected target at the positioning time corresponding to the multiple positioning points based on the positioning data and the vehicle's first wheel diameter; obtaining second coordinate data belonging to the same detected target from the first coordinate data based on the distance difference of all detected targets at all positioning times; calculating a correction coefficient based on the second coordinate data, and correcting the first wheel diameter based on the correction coefficient. Through the above method, the method of this embodiment can directly locate the first coordinate data of the detected target among multiple positioning points based on the extrinsic parameter data, obtain the second coordinate data belonging to the same detected target based on the first coordinate data, and calculate the correction coefficient of the first wheel diameter to correct the vehicle's wheel diameter. This eliminates the need for wheel diameter correction via GPS signals, reducing or avoiding problems such as inaccurate wheel diameter correction due to weak GPS signals, reducing the dependence of wheel diameter correction on the environment, and thus improving the accuracy and reliability of wheel speed calculation.

[0041] In one embodiment, the extrinsic data includes trajectory data from multiple positioning points, and semantic data for semantic detection at each positioning point. Please refer to [link to relevant documentation]. Figure 2 , Figure 2 This is a flowchart illustrating the second embodiment of the wheel diameter correction method provided in this application. Figure 2 As shown, in this embodiment, the wheel diameter correction method includes the following steps:

[0042] Step S21: Obtain the extrinsic data of the vehicle along a driving path. The extrinsic data includes trajectory data of multiple positioning points and semantic data of each positioning point when performing semantic detection.

[0043] Specifically, the extrinsic parameter data of a vehicle along a driving path includes, but is not limited to, trajectory data obtained through parameter acquisition by external devices such as sensors, LiDAR, and image acquisition units. The extrinsic parameter data may also include image data obtained by image acquisition units positioned around the vehicle's circumference, such as fisheye cameras or industrial cameras mounted on either side of the vehicle. After obtaining the image data, the semantic information of the image data is segmented to obtain speech data. The semantic data may include the detection time during semantic segmentation and the pixel coordinates of the segmented image data. For example, the trajectory data may include path = {pose1, pose2, ... pose}. n}; at a detection time of ts i At time t, the pixel coordinates can be represented as

[0044] Step S22: Interpolate the trajectory data of the positioning point based on the detection time of the semantic data to obtain the positioning data.

[0045] The trajectory data of the positioning points is interpolated based on the detection time of semantic data. Each detection time corresponds to a positioning point. After interpolating the trajectory data of this positioning point based on the detection time of semantic data, the trajectory data at each detection time can be obtained, which is the positioning data for each positioning time mentioned above. The detection time of semantic data can be defined as ts. i The detection time of semantic data corresponds to the positioning time of the location points. Interpolation based on the detection time of the semantic data yields the following positioning data:

[0046] Step S23: Based on the positioning data and the first wheel diameter of the vehicle, obtain the first coordinate data of the detected target at the positioning time corresponding to multiple positioning points.

[0047] Step S24: Based on the distance differences of all detected targets within all positioning time periods, obtain the second coordinate data belonging to the same detected target from the first coordinate data.

[0048] Step S25: Calculate the correction coefficient based on the second coordinate data, and correct the first wheel diameter based on the correction coefficient.

[0049] Steps S23-S25 are similar to steps S12-S14 above, and will not be repeated here.

[0050] In this embodiment, the wheel diameter correction method obtains extrinsic data of the vehicle along a driving path. This extrinsic data includes trajectory data from multiple positioning points and semantic data from each positioning point during semantic detection. Based on the detection time of the semantic data, the trajectory data of the positioning points is interpolated to obtain positioning data. Based on the positioning data and the vehicle's first wheel diameter, first coordinate data of the detected target at the corresponding positioning time at multiple positioning points is obtained. Based on the distance differences of all detected targets across all positioning times, second coordinate data belonging to the same detected target is obtained from the first coordinate data. A correction coefficient is calculated based on the second coordinate data, and the first wheel diameter is corrected accordingly. Therefore, the method of this embodiment can achieve wheel diameter correction using relatively stable semantic data, eliminating the need for GPS signal correction. This reduces or avoids problems such as inaccurate wheel diameter correction due to weak GPS signals, reduces the dependence of wheel diameter correction on the environment, and thus improves the accuracy and reliability of wheel speed calculation.

[0051] In an optional implementation, after step S22, the wheel diameter correction method further includes: converting all positioning data at all positioning times to the initial detection time of the semantic data.

[0052] Specifically, the trajectory data of all positioning points has corresponding semantic data, and the semantic data has corresponding detection time. After interpolating the trajectory data of the positioning points and obtaining the positioning data, the positioning data at each corresponding positioning time is obtained. The positioning data at each positioning time is then converted to the initial detection time of the semantic data. That is, the positioning data of all positioning points is expanded at the initial detection time to obtain the positioning data of the positioning points at different times at the initial detection time.

[0053] In another alternative implementation, after step S24, the wheel diameter correction method further includes: converting all second coordinate data at the positioning time to the initial detection time of the semantic data.

[0054] Specifically, after obtaining the second coordinate data belonging to the same detection target in all positioning times, the second coordinate data can be transformed to the initial detection time of the semantic data, so that the second coordinate data of all positioning points are expanded in the initial detection time, that is, the second coordinate data of positioning points belonging to the same detection target at different times in the initial detection time are obtained.

[0055] Furthermore, the above steps for converting the second coordinate data to the initial detection time of the semantic data can be performed using the following formula:

[0056]

[0057] Where ts1 is the initial detection time, ts i For a given positioning time, i = 1, 2, 3, ...; For ts i The translation vector of the image acquisition time when it is converted to the initial detection time. Let be the actual translation vector of the image acquisition device at the initial detection time of ts1. For image acquisition components in ts i The actual translation vector at time, Let be the actual rotation matrix of the image acquisition device at the initial detection time of ts1. For image acquisition components in ts i The actual matrix at time, For ts i The rotation matrix of the image acquisition device at the time of the time is converted to the initial detection time.

[0058] In the above manner, the wheel diameter correction method of this embodiment can convert the positioning data or the second coordinate data to the initial detection time of the semantic data, so that the data of all positioning points are unfolded at the initial detection time, which facilitates the subsequent fusion of the data of all positioning points to highlight the positional change relationship of the same detection target at different positioning times, thereby obtaining the correction coefficient.

[0059] In one embodiment, please refer to Figure 3 , Figure 3 This is a flowchart illustrating the third embodiment of the wheel diameter correction method provided in this application. Figure 3 As shown, step S14 or step S25 may further include the following steps:

[0060] Step S31: Based on the second coordinate data of all detected targets, calculate the objective function between the fluctuation value of all detected targets at different positioning times and the ground contact wheel diameter of the vehicle.

[0061] Specifically, after obtaining the second coordinate data belonging to the same detection target, an objective function is calculated based on all the second coordinate data to determine the relationship between the detection target at all positioning points and the vehicle's ground wheel diameter. Understandably, after obtaining the second coordinate data for all detection targets, the mapping relationship between the pixel position of the detection target in the image data and the actual position of the detection target relative to the vehicle at different positioning times can be obtained based on the second coordinate data. This mapping relationship is then used to determine the position fluctuation value of the detection target at different positioning times under the current first wheel diameter, thus obtaining the objective function. Here, the aforementioned position fluctuation value of the detection target at different positioning times represents the difference in coordinate position fluctuation of the same detection target at multiple positioning times along the same driving path.

[0062] Step S32: Solve the objective function and correct the first wheel diameter based on the solution value of the objective function.

[0063] Specifically, after obtaining the objective function, the objective function is solved to find its minimum value as the solution. Ideally, the vehicle's wheel diameter remains constant, meaning the coordinates of the same detection target should remain unchanged at different positioning times. However, due to factors such as tire pressure and road conditions, the coordinates of the vehicle belonging to the same detection target will fluctuate at different positioning times in real-world applications.

[0064] Therefore, this embodiment can calculate an objective function, which represents the fluctuation difference in coordinate position across multiple positioning times within the current first wheel diameter. By solving the objective function, the actual wheel diameter parameters within the driving path can be determined, thus obtaining the corrected first wheel diameter. In this way, the wheel diameter correction method of this embodiment can utilize extrinsic parameter data to identify the actual wheel diameter during driving, thereby achieving wheel diameter correction. This reduces or avoids problems such as inaccurate wheel diameter correction due to weak GPS signals, reduces the dependence of wheel diameter correction on the environment, and thus improves the accuracy and reliability of wheel speed calculation.

[0065] Optionally, step S31 includes: calculating the covariance data of the second coordinate data of the same detection target; summing the covariance data of all detection targets to obtain the objective function.

[0066] Each detection target may include several corner points that make up the detection target; that is, the second coordinate data may include the coordinates of corner points belonging to the same detection target. After obtaining the second coordinate data belonging to the same detection target, the coordinates of the corner points corresponding to each detection target can be aggregated and calculated. For example, if the detection target includes a first corner point and a second corner point, the first covariance data of the first corner point and the second covariance data of the coordinate data of the second corner point can be calculated at different positioning times to obtain the covariance data corresponding to the detection target.

[0067] After calculating the covariance data of the second coordinate data of the same detection target, the covariance data of all detection targets are summed to obtain the objective function. It can be understood that since the corner coordinates corresponding to each detection target have corresponding covariance data, the summation can be performed by first summing the covariance data of different corner points belonging to the same detection target, and then summing the covariance data of different detection targets to obtain the objective function.

[0068] For example, the objective function can be represented as follows:

[0069]

[0070] Where N is the number of detected targets, std ij Let be the covariance data of the j-th corner point of the i-th detected target.

[0071] In this embodiment, the wheel diameter correction method calculates the covariance data of the second coordinate data of the same detection target, sums the covariance data of all detection targets to obtain the objective function, and realizes wheel diameter correction. This can reduce or avoid problems such as inaccurate wheel diameter correction caused by weak GPS signals, reduce the dependence of wheel diameter correction on the environment, and thus improve the accuracy and reliability of wheel speed calculation.

[0072] In one embodiment, step S12 or step S23 may further include: obtaining third coordinate data of the detected target at each positioning point based on the positioning data, wherein the third coordinate data is coordinate data in the second coordinate system; and converting the detected target of the third coordinate data from the second coordinate system to the first coordinate system based on the first wheel diameter to obtain the first coordinate data.

[0073] After obtaining the positioning data at the corresponding positioning time, the third coordinate data of the detected target at each positioning point is acquired. The third coordinate data can be understood as the coordinate data of the detected target in a second coordinate system, which can be understood as a vehicle coordinate system set based on an origin at a certain position on the vehicle. For example, the second coordinate system can be set with an origin at the rear seat or trunk of the vehicle, with the vehicle's forward direction as the Y-axis, the right-hand direction facing the forward direction as the X-axis, and the vertically upward direction as the Z-axis. The first coordinate system can be understood as a relative positioning coordinate system established with the acquisition point of the external parameter data as its origin. After converting the detected target from the second coordinate system to the first coordinate system and obtaining the first coordinate data, it is easier to subsequently fuse data from different positioning points to obtain second coordinate data belonging to the same detected target.

[0074] Optionally, step S12 or step S23 further includes: based on the positioning data and the first wheel diameter of the vehicle, transforming the pixel coordinates of the detected target at each positioning point to a second coordinate system to obtain third coordinate data in the second coordinate system.

[0075] Specifically, the positioning data includes pixel coordinates corresponding to the detected target in the image data, which are coordinate point data in the camera coordinate system. When the image acquisition device is installed on the vehicle body, the installation extrinsic parameters of the image acquisition device can be defined as follows: and It is a translation vector used to describe the positional relationship between the second coordinate system of the image acquisition device and the first coordinate system; This is a rotation matrix used to describe the rotation relationship between the second coordinate system of the image acquisition device and the first coordinate system. It represents the pixel coordinates p in the camera coordinate system. c Transform to coordinates p in the second coordinate system b The conversion formula is as follows:

[0076]

[0077] When the origin of the second coordinate system is set at the projection of the vehicle's rear axle onto the ground, the extrinsic parameters of the image acquisition unit to the ground coordinate system need to be adjusted by adding the actual distance from the center of the vehicle's rear axle to the ground, i.e., the vehicle's ground contact radius, to the translation amount. The formula is as follows:

[0078]

[0079] Where r is the actual contact radius of the vehicle tires. Let be the translation vector of the image acquisition device. Therefore, combining the above formulas (3) and (4), the transformation formula for converting the coordinate points in the camera coordinate system to the ground in the vehicle coordinate system is as follows:

[0080]

[0081] Since the detection target is usually on the ground in most application scenarios, the semantic data in the aforementioned extrinsic data is represented on the ground. For example, when the detection target is a parking line, it is necessary to detect the parking lines and parking corners on the ground. When the pixel coordinates of the semantic detection result on the original image data in the extrinsic data are (u i ,v i When calculating pixel coordinates, the position of the point on the image normalization plane can be determined based on the camera's intrinsic and extrinsic parameters, using the following formula:

[0082]

[0083] in, pixel coordinates (u i ,v i The point on the normalized plane corresponding to ) is d, where d is the depth of that point.

[0084] Therefore, the wheel diameter correction method in this embodiment can calculate the above formulas (5) and (6) based on the current first wheel diameter and positioning data after obtaining the positioning data, so as to map the pixel positions obtained in the extrinsic parameter data to the three-dimensional points on the actual ground. It is understood that since semantic detection of image data is usually performed by identifying the corner coordinates of each detected target to locate the detected target, the coordinate expression of the detected target can be represented by the pixel position of the corner coordinates. This embodiment can obtain the third coordinate data of the detected target at different positioning times under the current first wheel diameter in the above manner, so as to facilitate the subsequent conversion of the third coordinate data from the second coordinate system to the first coordinate system and obtain the first coordinate data.

[0085] Optionally, please see Figure 4 , Figure 4This is a flowchart illustrating the fourth embodiment of the wheel diameter correction method provided in this application. Figure 4 As shown, the first coordinate data of the positioning point at each positioning time includes the corner coordinates of at least one detected target. Specifically, step S13 or step S24 may include:

[0086] Step S41: Obtain the first coordinate data of the two positioning times of the first adjacent time.

[0087] Specifically, the first coordinate data of the aforementioned multiple positioning points each has a corresponding positioning time. Arranged in chronological order, the first coordinate data of two adjacent positioning times can be obtained. The aforementioned first adjacent time specifically refers to the first coordinate data of two adjacent positioning times that are in the first sequence in chronological order. For example, including the first coordinate data of positioning points 1, 2, 3, and 4 arranged in chronological order, the two first coordinate data of the first adjacent time could refer to the first coordinate data of positioning points 1 and 2, the two first coordinate data of the second adjacent time could refer to the first coordinate data of positioning points 2 and 3, and the two first coordinate data of the third adjacent time could refer to the first coordinate data of positioning points 3 and 4.

[0088] Step S42: Calculate the difference between the corner coordinates of the detected target in the two first coordinate data in the first adjacent time interval.

[0089] After obtaining two sets of first coordinate data from adjacent time points, the difference between the corner coordinates corresponding to the detected targets in the two sets of first coordinate data is calculated. Specifically, the difference calculation involves subtracting the corner coordinates of a detected target from the first coordinate data of location point 1 from the corner coordinates of a detected target from the first coordinate data of location point 2. Here, the detected targets can be understood as relevant markers used to identify scenes, areas, and locations during vehicle operation, and the corner coordinates can be understood as the coordinates of the corner points constituting the detected target in the first coordinate system.

[0090] When the detection target is a parking space, the parking space is typically composed of four corner coordinates, and each corner coordinate has a corresponding direction, such as the upper left, lower left, upper right, and lower right corner coordinates. In this case, the first coordinate data at each positioning time can include one or more detection targets, and the first coordinate data of the first detection target in the first coordinate system can be represented as follows: The first coordinate data of n detected targets can be represented as: Where p1 is the coordinate of the lower left corner point, p2 is the coordinate of the lower right corner point, p3 is the coordinate of the upper right corner point, and p4 is the coordinate of the upper left corner point.

[0091] When calculating the difference between the corner coordinates of two detected targets in two adjacent time periods, if the first coordinate data includes multiple detected targets, the difference in corner coordinates can be calculated by selecting one detected target from the first coordinate data of positioning point 1 and another detected target from the first coordinate data of positioning point 2, and combining them. The difference in the coordinates of the corresponding corner points of the two detected targets is then calculated based on the combined result. For example, selecting a detected target from positioning point 1... Select the detection target in positioning point 2 The difference between corresponding corner points of detection target A and detection target B is calculated, i.e., the difference is calculated. The difference. And / or, after determining that a certain detection target at location point 1 and a certain detection target at location point 2 are the same detection target, the detection targets at the corresponding location points 1 and 2 can be removed from the above combination to reduce redundant calculations and improve the speed of association calculation.

[0092] Step S43: When the distance between the corner coordinates corresponding to the difference indicator is less than a preset threshold and the direction of the difference between the corresponding corner coordinates is the same, it is determined that the two detection targets corresponding to the first adjacent time belong to the same detection target, so as to obtain the associated coordinate data of the first adjacent time.

[0093] After obtaining the difference in the corner coordinates corresponding to two detected targets, since this difference is the difference between coordinates, the difference can include vector distance and vector direction. If the vector distance of the difference indicates that the distance between the corresponding corner coordinates is less than a preset threshold, and the vector directions of the four corner coordinates corresponding to the two detected targets are all in the same direction, it means that the two detected targets correspond to the same detected target on the actual ground. Therefore, the corresponding detected targets at two adjacent positioning times can be associated to obtain the associated coordinate data of the first adjacent time.

[0094] Step S44: Continue to calculate the difference between the first coordinate data of the two positioning times of the second adjacent time and obtain the associated coordinate data of the second adjacent time until the first coordinate data of all adjacent positioning times are calculated, so as to obtain the second coordinate data belonging to the same detection target.

[0095] Continue acquiring the first coordinate data of the two positioning times of the second adjacent time, and repeat steps S41-S43 above to calculate the difference to obtain the associated coordinate data of the second adjacent time. After calculating the associated coordinate data of the second adjacent time, continue calculating the associated coordinate data of the third associated time, the fourth associated time, and so on, until the first coordinate data of all adjacent positioning times has been calculated. After the first coordinate data of all adjacent positioning times has been calculated, information fusion is performed on the associated coordinate data of all adjacent times to determine which positioning time corresponding image frames observed a certain detection target, and obtain the second coordinate data of the same detection target in all positioning times under the driving path. Here, the second adjacent time specifically refers to the first coordinate data of the two adjacent positioning times that are located after the sequence of the first adjacent time in terms of time sequence, and the third adjacent time is the first coordinate data of the two adjacent positioning times that are located after the sequence of the second adjacent time, etc., which will not be elaborated here.

[0096] In this embodiment, the wheel diameter correction method obtains the first coordinate data of two adjacent positioning times, calculates the difference between the corner coordinates of the detected target in the two first coordinate data within the first adjacent time, and determines that the two detected targets corresponding to the first adjacent time belong to the same detected target when the difference indicates that the distance between the corresponding corner coordinates is less than a preset threshold and the direction of the difference between the corresponding corner coordinates is the same. This obtains the associated coordinate data of the first adjacent time. The method continues to calculate the difference between the first coordinate data of two adjacent positioning times and obtain the associated coordinate data of the second adjacent time, until the calculation of the first coordinate data of all adjacent positioning times is completed, thus obtaining the second coordinate data belonging to the same detected target. Therefore, it is possible to obtain the positional change of a certain three-dimensional object on the actual ground from the extrinsic parameter data under a driving path, so that the objective function between the fluctuation value of all detected targets at different positioning times and the ground wheel diameter of the vehicle can be calculated based on the second coordinate data. While achieving wheel diameter correction, it does not require identification using online signals such as GPS, reducing the dependence of wheel diameter correction on the environment and thus improving the accuracy and reliability of wheel speed calculation.

[0097] Please see Figure 5 , Figure 5 This is a flowchart illustrating an embodiment of the wheel speed correction method provided in this application. Figure 5 As shown in the embodiments of this application, a method for correcting wheel speed coefficient is also proposed, which includes the following steps:

[0098] Step S51: Obtain the corrected first wheel diameter of the vehicle according to the wheel diameter correction method of any of the above embodiments.

[0099] According to the wheel diameter correction method in the above embodiments, a corrected first wheel diameter can be obtained. Specifically, the correction can be made using the vehicle's external parameter data without the need for online signals such as GPS. This reduces the dependence of wheel diameter correction on the environment, thereby improving the accuracy and reliability of wheel speed calculation.

[0100] Step S52: Based on the corrected first wheel diameter, correct the wheel speed coefficient of the vehicle.

[0101] After obtaining the corrected first wheel diameter, the vehicle's wheel speed coefficient is adjusted based on this first wheel diameter. Specifically, the corrected first wheel diameter can be used as the rolling radius to calculate the wheel circumference, and the corresponding wheel speed coefficient can be calculated based on the vehicle's actual speed and the tire's wheel circumference to obtain the corrected wheel speed coefficient.

[0102] Step S53: Control the vehicle's trajectory based on the corrected wheel speed coefficient.

[0103] After obtaining the corrected wheel speed coefficient, based on the corrected wheel speed coefficient and external parameter data, the vehicle's driving trajectory can be recursively calculated using the wheel rotation speed (RPM) and the onboard inertial measurement unit (IMU). This allows for IPM projection of the vehicle's actual position on the ground to achieve relative positioning, facilitating subsequent control of the vehicle's driving trajectory and autonomous driving.

[0104] Therefore, the wheel speed correction method in this embodiment corrects the wheel speed coefficient of the vehicle based on the corrected first wheel diameter, and controls the vehicle's driving trajectory based on the corrected wheel speed coefficient. This allows the wheel diameter to be identified and corrected using extrinsic parameter data under a driving path, making full use of stable extrinsic and extrinsic parameter data to identify the wheel speed coefficient. It eliminates the dependence on GPS and does not require the use of online signals such as GPS for identification, reducing the dependence of wheel speed correction on the environment and ensuring the accuracy and reliability of wheel speed calculation in various scenarios.

[0105] Please see Figure 6 , Figure 6 This is a structural schematic diagram of one embodiment of the vehicle provided in this application. Figure 6 As shown, the vehicle 50 in this embodiment includes a memory 52 and a processor 51, with the processor 51 connected to the memory 52. ​​The memory 52 stores program instructions. The processor 51 executes the program instructions stored in the memory 52 to implement the method described in any of the above embodiments.

[0106] The processor 51 can also be referred to as a CPU (Central Processing Unit). The processor 51 may be an integrated circuit chip with signaling processing capabilities. The processor 51 can also be a general-purpose processor, a digital signaling processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. A general-purpose processor can be a microprocessor or any conventional processor.

[0107] The memory 52 can be a memory module, TF card, etc., and can store all information in the vehicle 50, including the input raw data, computer program, intermediate running results, and final running results. It stores and retrieves information according to the location specified by the controller. With the memory, the string matching prediction device has a memory function and can ensure normal operation. The memory of the string matching prediction device can be classified according to its purpose into main memory (RAM) and auxiliary memory (external storage), or it can be classified into external memory and internal memory. External storage is usually magnetic media or optical discs, which can store information for a long time. RAM refers to the storage components on the motherboard, used to store currently executing data and programs, but it is only used for temporary storage of programs and data; the data will be lost when the power is turned off.

[0108] In the embodiments provided in this application, it should be understood that the disclosed methods and apparatus can be implemented in other ways. For example, the inverter control method described above is merely illustrative; for instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0109] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0110] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0111] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, system server, or network device, etc.) or processor to execute all or part of the steps of the methods of the various embodiments of this application.

[0112] Please see Figure 7 , Figure 7 This is a schematic diagram of the structure of an embodiment of the computer-readable storage medium provided in this application. Figure 7 As shown, the computer-readable storage medium of this application stores program instructions 61 capable of implementing all the above methods. These program instructions 61 can be stored in the storage medium in the form of a software product, including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods of each embodiment of this application. The aforementioned storage devices include various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks, or electronic devices such as computers, servers, mobile phones, and tablets.

[0113] The above description is merely an embodiment of this application and does not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A method for correcting the wheel diameter of a vehicle, characterized in that, include: Obtain the extrinsic parameter data of the vehicle along a driving path, and obtain the positioning data of multiple positioning points based on the extrinsic parameter data; Based on the positioning data and the first wheel diameter of the vehicle, the first coordinate data of the detected target is obtained at the positioning time corresponding to the plurality of positioning points; Based on the distance differences of all detected targets within all the positioning time periods, second coordinate data belonging to the same detected target are obtained from the first coordinate data; The correction coefficient is calculated based on the second coordinate data, and the first wheel diameter is corrected based on the correction coefficient; The extrinsic data includes trajectory data of multiple positioning points, as well as semantic data of each positioning point during semantic detection. The process of obtaining positioning data for multiple positioning points based on the extrinsic parameter data includes: Based on the detection time of the semantic data, the trajectory data of the positioning point is interpolated to obtain the positioning data; After the step of interpolating the trajectory data of the positioning point based on the detection time of the semantic data to obtain the positioning data, the wheel diameter correction method further includes: Convert all the location data under the aforementioned location time to the initial detection time of the semantic data; or... After the step of obtaining second coordinate data belonging to the same detected target from the first coordinate data based on the distance difference of all detected targets within all the positioning time periods, the wheel diameter correction method further includes: The second coordinate data under all the positioning times are converted to the initial detection time of the semantic data.

2. The wheel diameter correction method according to claim 1, characterized in that, The step of calculating a correction coefficient based on the second coordinate data, and then correcting the first wheel diameter based on the correction coefficient, includes: Based on the second coordinate data of all the detected targets, a target function is calculated between the fluctuation value of all the detected targets at different positioning times and the ground wheel diameter of the vehicle; The objective function is solved to correct the first wheel diameter based on the solution value of the objective function.

3. The wheel diameter correction method according to claim 2, characterized in that, The objective function calculated based on the second coordinate data of all the detected targets and the ground contact wheel diameter of the vehicle at different positioning times includes: Calculate the covariance data of the second coordinate data of the same detected target; The covariance data of all the detected targets are summed to obtain the objective function.

4. The wheel diameter correction method according to claim 1, characterized in that, The step of obtaining the first coordinate data of the detected target at the positioning time corresponding to the plurality of positioning points based on the positioning data and the first wheel diameter of the vehicle includes: Based on the positioning data, the third coordinate data of the detected target at each positioning point is obtained, wherein the third coordinate data is the coordinate data in the second coordinate system; Based on the first wheel diameter, the detection target of the third coordinate data is converted from the second coordinate system to the first coordinate system to obtain the first coordinate data.

5. The wheel diameter correction method according to claim 4, characterized in that, The first coordinate data of the positioning point at each positioning time includes the corner coordinates of at least one of the detected targets; The step of obtaining second coordinate data belonging to the same detected target from the first coordinate data based on the distance difference of all detected targets within all the positioning time periods includes: Obtain the first coordinate data of the two positioning times that are in the first adjacent time; Calculate the difference between the corner coordinates of the detected target in the two first coordinate data in the first adjacent time interval; When the distance between the corner coordinates corresponding to the difference indication is less than a preset threshold and the direction of the difference between the corresponding corner coordinates is the same, it is determined that the two detection targets corresponding to the first adjacent time belong to the same detection target, so as to obtain the associated coordinate data of the first adjacent time. Continue to calculate the difference between the first coordinate data of the two positioning times of the second adjacent time and obtain the associated coordinate data of the second adjacent time, until the first coordinate data of all adjacent positioning times are calculated, so as to obtain the second coordinate data belonging to the same detection target.

6. A method for correcting wheel speed coefficient, characterized in that, include: The corrected first wheel diameter of the vehicle is obtained according to the wheel diameter correction method as described in any one of claims 1-5; Based on the corrected first wheel diameter, the wheel speed coefficient of the vehicle is corrected; The vehicle's trajectory is controlled based on the corrected wheel speed coefficient.

7. A vehicle, characterized in that, It includes a processor and a memory, wherein the processor is connected to the memory, wherein, The memory stores program instructions; The processor is configured to execute program instructions stored in the memory to implement the method as described in any one of claims 1-6.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores program instructions that can be executed by a processor to implement the method as described in any one of claims 1-6.

Images