Object localization method, device, autonomous vehicle, and edge computing platform

Abstract

This disclosure provides an object localization method, relating to the field of artificial intelligence technology, and particularly to the fields of autonomous driving, assisted driving, localization technology, and high-precision mapping technology. The specific implementation scheme is as follows: based on the pose information of the target object and the first localization data of the target object in a first coordinate system, second localization data of the target object in a second coordinate system is obtained; based on the second localization data, the information to be processed of the target object in the second coordinate system is determined; the information to be processed is filtered to obtain target localization data; and based on the target localization data, the position of the target object is determined. This disclosure also provides an object localization device, an autonomous vehicle, and an edge computing platform.

Description

Technical Field

[0001] This disclosure relates to the field of artificial intelligence technology, and more particularly to the fields of autonomous driving, driver assistance, positioning technology, and high-precision mapping technology. More specifically, this disclosure provides an object localization method, apparatus, electronic device, storage medium, computer program product, edge computing platform, and autonomous vehicle. Background Technology

[0002] With the development of artificial intelligence and high-precision mapping technologies, the application scenarios for autonomous driving and driver assistance technologies are constantly increasing. In autonomous driving or driver assistance modes, the vehicle's movement can be controlled based on its location. Summary of the Invention

[0003] This disclosure provides an object location method, apparatus, electronic device, storage medium, computer program product, edge computing platform, and autonomous vehicle.

[0004] According to one aspect of this disclosure, an object localization method is provided, the method comprising: obtaining second localization data of the target object in a second coordinate system based on the pose information of the target object and first localization data of the target object in a first coordinate system; determining information to be processed of the target object in the second coordinate system based on the second localization data; performing filtering processing on the information to be processed to obtain target localization data; and determining the position of the target object based on the target localization data.

[0005] According to another aspect of this disclosure, an object positioning device is provided, the device comprising: an acquisition module, configured to obtain second positioning data of the target object in a second coordinate system based on the pose information of the target object and first positioning data of the target object in a first coordinate system; a first determination module, configured to determine information to be processed of the target object in the second coordinate system based on the second positioning data; a filtering processing module, configured to perform filtering processing on the information to be processed to obtain target positioning data; and a second determination module, configured to determine the position of the target object based on the target positioning data.

[0006] According to another aspect of this disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform a method provided according to this disclosure.

[0007] According to another aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions for causing a computer to perform the methods provided according to this disclosure.

[0008] According to another aspect of this disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the method provided according to this disclosure.

[0009] According to another aspect of this disclosure, an edge computing platform is provided, including a plurality of edge computing units, the edge computing units including the electronic devices provided in this disclosure.

[0010] According to another aspect of this disclosure, an autonomous vehicle is provided, including the electronic equipment provided in this disclosure.

[0011] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0012] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0013] Figure 1 This is an exemplary system architecture diagram of an object location method and apparatus applicable according to an embodiment of the present disclosure;

[0014] Figure 2 This is a flowchart of an object location method according to an embodiment of the present disclosure;

[0015] Figure 3 This is a flowchart illustrating the process of obtaining second positioning data according to an embodiment of the present disclosure;

[0016] Figure 4 This is a flowchart illustrating the process of obtaining target location data according to an embodiment of the present disclosure;

[0017] Figure 5A This is an exemplary scenario diagram according to an embodiment of the present disclosure;

[0018] Figure 5B This is an exemplary schematic diagram showing the location of a target object according to an embodiment of the present disclosure;

[0019] Figure 6 This is an exemplary schematic diagram showing the location of a target object according to another embodiment of the present disclosure;

[0020] Figure 7 This is a block diagram of an object positioning device according to an embodiment of the present disclosure; and

[0021] Figure 8 This is a block diagram of an electronic device to which an object positioning method can be applied, according to an embodiment of the present disclosure. Detailed Implementation

[0022] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0023] In autonomous driving or assisted driving scenarios, the positioning system needs to output continuous, high-frequency, and accurate positioning results in real time to ensure the normal operation of related modules such as path planning and perception. The positioning system can be a multi-sensor fusion system, fully utilizing the absolute and relative positioning results from various sensors such as GNSS (Global Navigation Satellite System), LiDAR (Laser Radar), Camera, and IMU (Inertial Measurement Unit) to obtain high-precision fused positioning results. The fusion positioning method used by the positioning system can be based on Kalman filtering technology.

[0024] In some embodiments, the fusion positioning method may include, for example,: using data collected by the IMU to predict (recursively) and update the position, velocity, attitude and corresponding covariance to obtain the prediction result; using data collected by sensors such as GNSS, LiDAR, and Camera to perform measurements to obtain the measurement result; and using the measurement result to update and correct the error of the prediction result to ensure that the positioning system can continuously output high-precision positioning results in real time.

[0025] Fusion positioning methods can involve two coordinate systems. One is the navigation coordinate system, namely the ENU (East-North-Up) coordinate system. The other is the vehicle coordinate system, which can be defined by the horizontal and vertical axes of the object (e.g., a vehicle) as the X and Y axes, respectively. The Z-axis of the vehicle coordinate system, together with the X and Y axes, forms a right-handed Cartesian coordinate system. For example, the direction from the rear of the vehicle to the front of the vehicle can be considered the positive direction of the Y-axis.

[0026] To achieve high-precision positioning results globally, predictions and measurements in fusion positioning methods are generally performed in a navigation coordinate system. However, for special positioning scenarios involving tunnels or roadside barriers, LiDAR-acquired data can be used for positioning. Other special positioning scenarios may include those requiring lane markings.

[0027] In these special positioning scenarios, the accuracy of measurements may be correlated with the horizontal and vertical coordinates of the carrier coordinate system. In this case, the horizontal constraints are strong and the accuracy is high, while the vertical constraints are weak and the accuracy is poor. If the above measurements are used for updates in the navigation coordinate system, since both the horizontal and vertical coordinates are projected onto the northeast direction, they will interfere with each other, making it impossible to fully utilize the high-precision horizontal measurements. This leads to deviations in the positioning results and a decrease in positioning accuracy.

[0028] In some embodiments, in the specific positioning scenarios described above, the fusion positioning method described above can be adjusted. The adjusted fusion positioning method may, for example, include: converting the first positioning data in the navigation coordinate system into intermediate positioning data in the carrier coordinate system.

[0029] For example, the first positioning data may include a first innovation vector, which can be determined by the following formula.

[0030]

[0031] pos sins The location information pushed out by the IMU includes the first latitude and longitude data and the first elevation data; pos sensor Location information determined by sensors such as GNSS, LiDAR, and cameras includes second latitude and longitude data and second elevation data. The first and second latitude and longitude data are in radians, and the first and second elevation data are in meters. lon d lat and d h These are the differences in longitude data, latitude data, and elevation data, respectively.

[0032] D n The inverse matrix, D n This is the transformation parameter matrix for converting meters to radians in the navigation coordinate system. This is the rotation matrix from the vehicle coordinate system to the navigation coordinate system. b This is the lever arm value.

[0033] The transformation parameter matrix D in the navigation coordinate system can be determined using the following formula. n :

[0034]

[0035] R M R is the radius of curvature of the meridian. N Let B be the radius of curvature of the tropomorphic circle. B is the latitude data in radians. cos() is the cosine function.

[0036] For example, intermediate positioning data may include intermediate innovation vectors, and the first innovation vector can be converted into an intermediate innovation vector in the carrier coordinate system using the following formula.

[0037]

[0038] d is the rotation matrix from the navigation coordinate system to the vehicle coordinate system. x d y and d z This includes differences in horizontal data, vertical data, and height data.

[0039] For example, the first positioning data may include a first covariance matrix. First covariance matrix Corresponding to the first innovation vector. In one example, the first covariance matrix A column of data can include: d lon variance, d lon With d lat The covariance and d between lon With d h The covariance between them.

[0040] The intermediate covariance matrix of intermediate positioning data can be determined using the following formula.

[0041]

[0042] In some embodiments, the adjusted fusion positioning method may include, for example, adjusting intermediate positioning data using preset values ​​to obtain adjusted intermediate positioning data.

[0043] For example, the vertical data of the intermediate innovation vector can be adjusted to a preset vertical data value (e.g., 0), and the adjusted intermediate innovation vector... It can be:

[0044]

[0045] For example, the intermediate covariance matrix can be adjusted using a preset standard deviation (e.g., 0.05*0.05) and a preset covariance (e.g., 0). The adjusted intermediate covariance matrix can be:

[0046]

[0047] "same" means that the result is the same before and after the adjustment.

[0048] In some embodiments, the adjusted fusion positioning method may include, for example, converting the adjusted intermediate positioning data in the carrier coordinate system into the adjusted first positioning data in the navigation coordinate system.

[0049] For example, the adjusted first innovation vector can be determined using the following formula.

[0050]

[0051] For example, the adjusted first covariance matrix can be determined using the following formula.

[0052]

[0053] The radius of curvature of a target object can differ in different coordinate systems. This difference was overlooked when using Formulas 5 and 6 above for data transformation, resulting in the adjusted fusion positioning method failing to completely avoid the influence of low-precision longitudinal data.

[0054] Furthermore, the use of a preset standard deviation in determining the adjusted intermediate covariance matrix can easily lead to positioning drift. This is because the adjusted fusion positioning method described above cannot avoid the influence of low-precision longitudinal data on the positioning results. The data generated by the IMU recursion itself also has a certain degree of error, causing the longitudinal data in the positioning results of this method to converge to an incorrect state. In addition, the preset standard deviation is difficult to set accurately. If the preset standard deviation is too small, it can cause the Kalman filter to converge excessively, while if the preset standard deviation is too large, it will not have a constraint effect.

[0055] Figure 1 This is a schematic diagram of an exemplary system architecture for applying object location methods and apparatus according to an embodiment of this disclosure. It should be noted that... Figure 1 The examples shown are merely examples of system architectures that can be applied to the embodiments of this disclosure, in order to help those skilled in the art understand the technical content of this disclosure, but do not mean that the embodiments of this disclosure cannot be used in other devices, systems, environments or scenarios.

[0056] like Figure 1 As shown, the system architecture 100 according to this embodiment may include sensors 101, 102, and 103, a network 120, a server 130, and a roadside unit 140. The network 120 serves as a medium for providing communication links between the sensors 101, 102, and 103 and the server 130. The network 120 may include various connection types, such as wired and / or wireless communication links, etc.

[0057] Sensors 101, 102, and 103 can interact with server 130 via network 120 to receive or send messages, etc.

[0058] Sensors 101, 102, and 103 can be functional components integrated on vehicle 110, such as infrared sensors, ultrasonic sensors, millimeter-wave radar, information acquisition devices, etc. Sensors 101, 102, and 103 can be used to collect status data of objects around vehicle 110 (such as pedestrians, vehicles, obstacles, etc.) and surrounding road data.

[0059] Vehicle 110 can communicate with Road Side Unit (RSU) 140, receive information from Road Side Unit 140, or send information to Road Side Unit.

[0060] Server 130 can be set at a remote location that can establish communication with the vehicle terminal. It can be implemented as a distributed server cluster consisting of multiple servers or as a single server.

[0061] Server 130 can be a server that provides various services. Applications such as map applications and data processing applications can be installed on server 130. Taking server 130 running a data processing application as an example: it receives obstacle status data and road data transmitted from sensors 101, 102, and 103 via network 120. One or more of the obstacle status data and road data can be used as data to be processed. This data is then processed to obtain the target data.

[0062] It should be noted that the object positioning method provided in this embodiment can generally be executed by server 130. Correspondingly, the object positioning device provided in this embodiment can also be located in server 130. However, it is not limited to this. The object positioning method provided in this embodiment can also generally be executed by sensors 101, 102, or 103. Correspondingly, the object positioning device provided in this embodiment can also be located in sensors 101, 102, or 103.

[0063] Understandable. Figure 1 The number of sensors, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of sensors, networks, and servers can be included.

[0064] It should be noted that the sequence numbers of the operations in the following methods are for descriptive purposes only and should not be considered as indicating the execution order of the operations. Unless explicitly stated otherwise, the method does not need to be executed in the exact order shown.

[0065] Figure 2 This is a flowchart of an object location method according to an embodiment of the present disclosure.

[0066] like Figure 2As shown, the method 200 may include operations S210 to S240.

[0067] In operation S210, based on the target object's posture information and the target object's first positioning data in the first coordinate system, the target object's second positioning data in the second coordinate system is obtained.

[0068] For example, the target object could be a vehicle, a pedestrian holding a mobile device, etc.

[0069] For example, the first coordinate system could be the navigation coordinate system described above. As another example, the second coordinate system could be the vehicle coordinate system.

[0070] For example, the attitude information of the target object may include the target object's yaw, roll, and pitch.

[0071] For example, the first positioning data can be correlated with the longitude, latitude, and elevation data of the target object. Similarly, the second positioning data can be correlated with the horizontal, vertical, and height data of the target object.

[0072] For example, during data transformation, a set of transformation parameters can be determined using attitude information. This set of transformation parameters can then be used to perform data transformations between different coordinate systems.

[0073] In operation S220, based on the second positioning data, the information to be processed for the target object in the second coordinate system is determined.

[0074] For example, as described above, the second positioning data may include the target object's horizontal, vertical, and height data. The second positioning data can indicate the target object's position in a second coordinate system. In one example, the second positioning data can be used as information to be processed.

[0075] In operation S230, the information to be processed is filtered to obtain target positioning data.

[0076] For example, a Kalman filter can be used to filter the information to be processed to obtain target location data. It is understandable that other filters can also be used for filtering.

[0077] In operation S240, the location of the target object is determined based on the target positioning data.

[0078] For example, various calculations can be performed using the target location data to determine the location of the target object, and this disclosure does not limit this.

[0079] Through the embodiments of this disclosure, when performing positioning data conversion between different coordinate systems, the pose information of the target object is utilized, which can focus on the difference in the radius of curvature of the target object between different coordinate systems, reduce the influence of longitudinal data on lateral data, and more accurately determine the position of the target object.

[0080] In some embodiments, the first positioning data is related to the first position information of the target object in the first coordinate system, the first position information including longitude data, latitude data and altitude data; the second positioning data is related to the second position information of the target object in the second coordinate system, the second position information including lateral data, longitudinal data and altitude data; the first positioning data includes a first innovation vector and a first covariance matrix, and the second positioning data includes a second innovation vector and a second covariance matrix.

[0081] For example, the first innovation vector can be determined using the following formula.

[0082]

[0083] Similar to Formula 1, pos sins The location information pushed out by the IMU includes the first latitude and longitude data and the first elevation data; pos sensor Location information determined by sensors such as GNSS, LiDAR, and cameras includes second latitude and longitude data and second elevation data. The first and second latitude and longitude data are in radians, and the first and second elevation data are in meters. lon d lat and d h These are the differences in longitude data, latitude data, and elevation data, respectively. D n The inverse matrix, D n This is the transformation parameter matrix for converting meters to radians in the navigation coordinate system. This is the rotation matrix from the vehicle coordinate system to the navigation coordinate system. b This is the lever arm value. Regarding D... n For a detailed description, please refer to Formula 2 mentioned above; this disclosure will not repeat it here.

[0084] For example, the first covariance matrix Corresponding to the first innovation vector. In one example, the first covariance matrix A column of data can include: d lon variance, d lon With d lat The covariance and d between lon With d h The covariance between them.

[0085] The following will combine Figure 3 Let us now provide a more detailed explanation of the operation S210 described above.

[0086] Figure 3 This is a flowchart of obtaining second positioning data according to an embodiment of the present disclosure.

[0087] like Figure 3 As shown, method 310 can obtain the second positioning data of the target object in the second coordinate system based on the pose information of the target object and the first positioning data of the target object in the first coordinate system. The following will be explained in detail in conjunction with operations S311 to S313.

[0088] In operation S311, based on the orientation information of the target object, the first radius of curvature and the second radius of curvature of the target object in the second coordinate system are determined.

[0089] For example, the first radius of curvature R can be determined using the following formula. X Second radius of curvature R Y :

[0090]

[0091]

[0092] R M R is the radius of curvature of the meridian. N Let be the radius of curvature of the ramusoidal coordinate system. cos() is the cosine function. sin() is the sine function. yaw is the heading angle of the second coordinate system relative to the first coordinate system, in radians.

[0093] In operation S312, the set of transformation parameters of the target object in the second coordinate system is determined based on the first radius of curvature and the second radius of curvature.

[0094] For example, the set of transformation parameters of the target object in the second coordinate system can be implemented as a transformation parameter matrix D. b The transformation parameter matrix D can be determined using the following formula. b :

[0095]

[0096] In operation S313, the second positioning data is obtained based on the set of conversion parameters and the first positioning data.

[0097] For example, the first positioning data can be transformed to obtain the intermediate positioning data of the target object in the second coordinate system.

[0098] For example, intermediate location data may include intermediate information vectors and intermediate covariance matrices.

[0099] In one example, Formula 3 described above can be used to pair the first innovation vector. The transformation is performed to obtain the intermediate information vector. In one example, Formula 4 described above can be used to pair the first covariance matrix. The transformation yields the intermediate covariance matrix.

[0100] For example, second positioning data is obtained based on the set of transformation parameters and intermediate positioning data.

[0101] For example, the transformation parameter matrix D can be obtained using the following formula. b By combining the intermediate innovation vector, we obtain the second innovation vector.

[0102]

[0103] For the transformation parameter matrix D b The inverse matrix, This is the rotation matrix from the navigation coordinate system to the vehicle coordinate system.

[0104] For example, the transformation parameter matrix D can be obtained using the following formula. b The second covariance matrix is ​​obtained by combining the intermediate covariance matrix and the intermediate covariance matrix.

[0105]

[0106] for The transpose of . Know The unit is radians.

[0107] It is understood that the above description uses the heading angle in attitude information as an example to illustrate the implementation method for obtaining the second positioning data. In the embodiments of this disclosure, the second positioning data can also be obtained based on the roll angle or pitch angle, which will not be elaborated here.

[0108] As can be understood, the above text has described in detail some implementation methods for obtaining the second positioning data. The following will describe in detail the information to be processed to determine the target object in the second coordinate system.

[0109] In some embodiments, determining the information to be processed of the target object in the second coordinate system based on the second positioning data includes: determining filtering parameter data based on the second innovation vector; and determining the information to be processed based on the second positioning data and the filtering parameter data.

[0110] In this embodiment of the disclosure, the partial derivative of the second innovation vector can be calculated to obtain the partial derivative matrix, which is used as the filtering parameter data.

[0111] For example, based on position information, velocity information, attitude information, gyroscope parameter information, and accelerometer parameter information, the partial derivative of the second innovation vector is calculated to obtain the partial derivative matrix, which is used as the filtering parameter data.

[0112] In one example, combining Equations 9 and 13 mentioned above, the partial derivative matrix... For example, it could be:

[0113]

[0114] It can be a 3×15 matrix. 0 3×3 Includes three columns of data where all three elements are 0.

[0115] In this embodiment of the disclosure, the filter parameter data includes multiple first column data, at least one of the multiple first column data is the rate of change of the position information of the target object, and at least one of the multiple first column data is the rate of change of the pose information of the target object.

[0116] For example, in middle, The data in the first column (from the first to the third column) can represent the rate of change of the target object's location information.

[0117] For example, in middle, The data in columns 7 through 9 can represent the rate of change of the target object's pose information. The "×" symbol is used to convert single-column data into multi-column data, or to convert multi-row data into multi-row data.

[0118] In some embodiments, the filter parameter data and the second positioning data can be adjusted to determine the information to be processed.

[0119] In this embodiment of the disclosure, the filter parameter data further includes a plurality of first row data. Determining the information to be processed based on the second positioning data and the filter parameter data may include: determining adjusted filter parameter data based on at least one of the plurality of first row data; and determining the information to be processed based on the second positioning data and the adjusted filter parameter data.

[0120] For example, multiple first-row data include: first-row data related to the horizontal data of the target object, first-row data related to the vertical data of the target object, and first-row data related to the height data of the target object.

[0121] For example, at least one first row of data is associated with at least one of the target object's lateral data and the target object's height data. In one example, adjusted parameter-filtered data can be obtained based on the first row of data associated with the target object's lateral data and the first row of data associated with the target object's height data. Through embodiments of this disclosure, the influence of longitudinal data on lateral data can be reduced when the target object travels on a road with varying heights.

[0122] In one example, as described above, the partial derivative matrix It can be a 3×15 matrix. Partial derivative matrix. It can include three data points in the first row. In the partial derivative matrix... In the diagram, the first row of data can be correlated with the horizontal data of the target object, the second row with the vertical data, and the third row with the height data. This can be determined based on the partial derivative matrix. The adjusted partial derivative matrix is ​​obtained by taking the first and third rows of data in the first data set.

[0123] In one example, the adjusted partial derivative matrix can be obtained using the following formula.

[0124]

[0125] (1, 3;:) represents the first and third rows of the matrix. It can be a 2×15 matrix.

[0126] Furthermore, in this embodiment of the disclosure, the second covariance matrix includes multiple second row data and multiple second column data. Determining the information to be processed based on the second positioning data and the adjusted filter parameter data includes: obtaining the adjusted second covariance matrix based on at least one second row data and at least one second column data from the multiple second row data; and determining the information to be processed based on the adjusted second covariance matrix and the adjusted filter parameter data.

[0127] For example, multiple second-row data include: second-row data related to the horizontal data of the target object, second-row data related to the vertical data of the target object, and second-row data related to the height data of the target object.

[0128] For example, multiple second column data include: second column data related to the horizontal data of the target object, second column data related to the vertical data of the target object, and second column data related to the height data of the target object.

[0129] For example, at least one second row of data is associated with at least one of the horizontal data and the height data of the target object; at least one second column of data is associated with at least one of the horizontal data and the height data of the target object. In one example, the adjusted second covariance matrix can be obtained based on the second row of data associated with the horizontal data of the target object, the second row of data associated with the height data of the target object, the second column of data associated with the horizontal data of the target object, and the second column of data associated with the height data of the target object.

[0130] In one example, the second covariance matrix It can be a 3×3 matrix. The second covariance matrix. This includes three rows of data and three columns of data. The second covariance matrix... In the second covariance matrix, the first row of data can be correlated with the horizontal data of the target object, the second row with the vertical data, and the third row with the height data. Furthermore, in the second covariance matrix... In the second column, the first set of data can be correlated with the horizontal data of the target object, the second set with the vertical data, and the third set with the height data. This can be determined based on the second covariance matrix. The adjusted second covariance matrix is ​​obtained by taking the first row of data, the third row of data, the first column of data, and the third column of data in the second column.

[0131] In one example, the adjusted second covariance matrix can be obtained using the following formula.

[0132]

[0133] (1, 3; 1, 3) represents: first, taking the first and third rows of the matrix, then extracting the first and third columns from the first and third rows to obtain the processed matrix. The adjusted second covariance matrix. It can be a 2×2 matrix.

[0134] Furthermore, in this embodiment of the disclosure, the second innovation vector includes multiple third row data. Determining the information to be processed based on the adjusted second covariance matrix and the adjusted filter parameter data includes: determining the adjusted second innovation vector based on at least one third row data among the multiple third row data; and determining the adjusted second innovation vector, the adjusted second covariance matrix, and the adjusted filter parameter data as the information to be processed.

[0135] For example, multiple third-row data include: third-row data related to the horizontal data of the target object, third-row data related to the vertical data of the target object, and third-row data related to the height data of the target object.

[0136] For example, at least one third row of data is related to at least one of the horizontal data and the height data of the target object.

[0137] In one example, the adjusted second information vector can be obtained based on the third row of data related to the horizontal data of the target object and the third row of data related to the height data of the target object.

[0138] In one example, the second innovation vector It can be a 3×1 matrix. The second innovation vector. This can include three third rows of data. In the second news vector... In the data, the first row of data can be correlated with the horizontal data of the target object, the second row can be correlated with the vertical data of the target object, and the third row can be correlated with the height data of the target object. This can be determined based on the second information vector. The adjusted second information vector is obtained by taking the first and third rows of data from the first and third rows of data.

[0139] In one example, the adjusted second innovation vector can be obtained using the following formula.

[0140]

[0141] It can be a 2×1 matrix.

[0142] For example, the adjusted second innovation vector Adjusted partial derivative matrix and the adjusted second covariance matrix As information to be processed.

[0143] In other embodiments, at least one first row of data is associated with the horizontal data of the target object. At least one second row of data is associated with the horizontal data of the target object; at least one second column of data is associated with the horizontal data of the target object. At least one third row of data is associated with the horizontal data of the target object.

[0144] For example, it can be determined based on the partial derivative matrix. The first row of data in the matrix yields the adjusted partial derivative matrix. Based on the second covariance matrix The adjusted second covariance matrix is ​​obtained by taking the first row and second column of data from the first data set. According to the second innovation vector The adjusted second information vector is obtained from the first row of data in the third row. Through the embodiments of this disclosure, when the target object is traveling on a road with no change in elevation, the influence of longitudinal data on lateral data can be reduced.

[0145] After obtaining the information to be processed, the information can be filtered, which will be described in detail below.

[0146] Figure 4 This is a flowchart of obtaining target location data according to an embodiment of the present disclosure.

[0147] like Figure 4 As shown, method 430 can filter the information to be processed to obtain target positioning data. The following will be explained in detail in conjunction with operations S431 to S434.

[0148] In operation S431, the target gain matrix is ​​obtained based on the adjusted second covariance matrix and the adjusted filter parameter data.

[0149] For example, the target gain matrix K can be determined using the following formula. k :

[0150]

[0151] Target gain matrix K k Let K be the gain matrix at time k. The target gain matrix is ​​K. k It can be a 15×2 matrix. P k / k-1 P is the covariance matrix of the Kalman filter state prediction at time k, derived from the IMU's Kalman filter state prediction at time k-1. k / k-1 It can be a 15×15 matrix.

[0152] In operation S432, the target state data is obtained based on the target gain matrix, the adjusted second innovation vector, and the adjusted filter parameter data.

[0153] For example, the target state data X can be obtained using the following formula. k :

[0154]

[0155] X k / k-1 X is the Kalman filter state prediction value at time k derived from the IMU's Kalman filter state prediction value at time k-1. k It can be a 15×1 matrix. Xk / k-1 It can be a 15×1 matrix.

[0156] In operation S433, the target covariance matrix is ​​obtained based on the target gain matrix and the adjusted filter parameter data.

[0157] For example, the target covariance matrix P can be obtained using the following formula. k :

[0158]

[0159] I is the identity matrix. P k It can be a 15×15 matrix.

[0160] In operation S434, target positioning data is determined based on target state data and target covariance matrix.

[0161] For example, it can be based on the target covariance matrix P. k and target state data X k Determine the target location data.

[0162] In some embodiments, target state data X k It can be a 15×1 matrix. Target state data X k This includes row data related to the location of the target object, based on which the location of the target object can be determined.

[0163] Figure 5A This is an exemplary scenario diagram according to an embodiment of the present disclosure.

[0164] As shown in Figure 5, in scenario 500, vehicle 510 can drive into tunnel 520. After exiting tunnel 520, vehicle 510 can drive through intersection 530. Inside tunnel 520, it is difficult to obtain accurate location information based on data collected by vehicle 510's GNSS, LiDAR, camera, and other sensors.

[0165] Figure 5B This is an exemplary schematic diagram showing the location of a target object according to an embodiment of the present disclosure.

[0166] like Figure 5B As shown, at the first moment of travel within the tunnel, using the object positioning method provided in this disclosure, it can be determined that vehicle 510 is at position 510_1. At the second moment of travel within the tunnel, using the object positioning method provided in this disclosure, it can be determined that vehicle 510 is at position 510_2. At the third moment of travel within the tunnel, using the object positioning method provided in this disclosure, it can be determined that vehicle 510 is at position 510_3. It is understood that... Figure 5BThe wireframes indicating positions (e.g., position 510_1) are for illustrative purposes only.

[0167] Figure 6 This is an exemplary schematic diagram of the position of a target object adjusted according to another embodiment of the present disclosure.

[0168] like Figure 6 As shown, vehicle 610 can drive in scenario 600. The detailed description of scenario 500 described above also applies to scenario 600 in this embodiment, and will not be repeated here.

[0169] like Figure 6 As shown, at the first moment of travel within the tunnel in scenario 600, using the adjusted fusion positioning method, it can be determined that vehicle 610 is at position 610_1'. At the second moment of travel within the tunnel, it can be determined that vehicle 610 is at position 610_2'. At the third moment of travel within the tunnel, it can be determined that vehicle 610 is at position 610_3'. Figure 6 As shown, when driving in the tunnel, the adjusted fusion positioning method cannot accurately determine the position of vehicle 610, resulting in position drift. This can cause the autonomous driving system of vehicle 610 to generate incorrect instructions and change lanes back and forth in the tunnel.

[0170] Understandable. Figure 6 The wireframe indicating a location (e.g., location 610_1') is for illustrative purposes only.

[0171] like Figure 5B and Figure 6 As shown, through the embodiments of this disclosure, the position of vehicle 510 can be accurately determined by using the object positioning method (e.g., method 200) provided by this disclosure, thus mitigating the position drift phenomenon.

[0172] Figure 7 This is a block diagram of an object positioning device according to an embodiment of the present disclosure.

[0173] like Figure 7 As shown, the device 700 may include an acquisition module 710, a first determination module 720, a filtering module 730, and a second determination module 740.

[0174] The module 710 is used to obtain the second positioning data of the target object in the second coordinate system based on the pose information of the target object and the first positioning data of the target object in the first coordinate system.

[0175] The first determining module 720 is used to determine the information to be processed of the target object in the second coordinate system based on the second positioning data.

[0176] The filtering module 730 is used to filter the information to be processed to obtain target positioning data.

[0177] The second determining module 740 is used to determine the position of the target object based on the target positioning data.

[0178] In some embodiments, the first positioning data is associated with first location information of the target object in a first coordinate system, the first location information including longitude data, latitude data, and elevation data. The second positioning data is associated with second location information of the target object in a second coordinate system, the second location information including lateral data, longitudinal data, and height data. The first positioning data includes a first innovation vector and a first covariance matrix, and the second positioning data includes a second innovation vector and a second covariance matrix.

[0179] In some embodiments, the obtaining module includes: a first determining submodule, configured to determine a first radius of curvature of the target object in a second coordinate system and a second radius of curvature of the target object in a second coordinate system based on the pose information of the target object; a second determining submodule, configured to determine a set of transformation parameters of the target object in a second coordinate system based on the first radius of curvature and the second radius of curvature; and a first obtaining submodule, configured to obtain second positioning data based on the set of transformation parameters and the first positioning data.

[0180] In some embodiments, the first determining module includes: a third determining submodule, configured to determine filtering parameter data based on the second innovation vector, wherein the filtering parameter data includes a plurality of first column data, at least one of the plurality of first column data being the rate of change of the position information of the target object, and at least one of the plurality of first column data being the rate of change of the attitude information of the target object; and a fourth determining submodule, configured to determine information to be processed based on the second positioning data and the filtering parameter data.

[0181] In some embodiments, the filter parameter data further includes a plurality of first row data, and the fourth determining submodule includes: a first determining unit, configured to determine adjusted filter parameter data based on at least one of the plurality of first row data, wherein at least one first row data is related to at least one of the horizontal data of the target object and the height data of the target object; and a second determining unit, configured to determine the information to be processed based on the second positioning data and the adjusted filter parameter data.

[0182] In some embodiments, the second covariance matrix includes a plurality of second row data and a plurality of second column data. The second determining unit includes: a first determining subunit, configured to determine an adjusted second covariance matrix based on at least one of the plurality of second row data and at least one of the plurality of second column data, wherein at least one second row data is correlated with at least one of the horizontal data and the height data of the target object, and at least one second column data is correlated with at least one of the horizontal data and the height data of the target object; and a second determining subunit, configured to determine the information to be processed based on the adjusted second covariance matrix and the adjusted filter parameter data.

[0183] In some embodiments, the second innovation vector includes a plurality of third row data, and the second determining subunit is further configured to: determine an adjusted second innovation vector based on at least one of the plurality of third row data, wherein the at least one third row data is related to at least one of the horizontal data of the target object and the height data of the target object; and determine the adjusted second innovation vector, the adjusted second covariance matrix, and the adjusted filter parameter data as information to be processed.

[0184] In some embodiments, the filtering processing module includes: a second obtaining submodule, configured to obtain a target gain matrix based on the adjusted second covariance matrix and the adjusted filtering parameter data; a third obtaining submodule, configured to obtain target state data based on the target gain matrix, the adjusted second innovation vector, and the adjusted filtering parameter data; a fourth obtaining submodule, configured to obtain a target covariance matrix based on the target gain matrix and the adjusted filtering parameter data; and a fifth obtaining submodule, configured to obtain target positioning data based on the target state data and the target covariance matrix.

[0185] The collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0186] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0187] Figure 8A schematic block diagram of an example electronic device 800 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0188] like Figure 8 As shown, device 800 includes a computing unit 801, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 802 or a computer program loaded from storage unit 808 into random access memory (RAM) 803. RAM 803 may also store various programs and data required for the operation of device 800. The computing unit 801, ROM 802, and RAM 803 are interconnected via bus 804. Input / output (I / O) interface 805 is also connected to bus 804.

[0189] Multiple components in device 800 are connected to I / O interface 805, including: input unit 806, such as keyboard, mouse, etc.; output unit 807, such as various types of monitors, speakers, etc.; storage unit 808, such as disk, optical disk, etc.; and communication unit 809, such as network card, modem, wireless transceiver, etc. Communication unit 809 allows device 800 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0190] The computing unit 801 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 801 performs the various methods and processes described above, such as object location methods. For example, in some embodiments, the object location method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed on device 800 via ROM 802 and / or communication unit 809. When the computer program is loaded into RAM 803 and executed by the computing unit 801, one or more steps of the object location method described above may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to perform object location methods by any other suitable means (e.g., by means of firmware).

[0191] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0192] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0193] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0194] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0195] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0196] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other.

[0197] According to embodiments of this disclosure, this disclosure also provides an autonomous driving vehicle that may include the electronic equipment provided in this disclosure. For example, the autonomous driving vehicle may include the electronic equipment 800 described above.

[0198] According to embodiments of this disclosure, this disclosure also provides an edge computing platform including a plurality of edge computing units, which may include the electronic devices provided in this disclosure. For example, the edge computing unit may include the electronic device 800 described above.

[0199] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0200] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. An object location method, comprising: Based on the attitude information of the target object and the first positioning data of the target object in the first coordinate system, the second positioning data of the target object in the second coordinate system is obtained. The first positioning data is related to the first position information of the target object in the first coordinate system, which includes longitude data, latitude data, and elevation data. The second positioning data is related to the second position information of the target object in the second coordinate system, which includes lateral data, longitudinal data, and height data. The first positioning data includes a first innovation vector and a first covariance matrix, and the second positioning data includes a second innovation vector and a second covariance matrix. The first coordinate system is a navigation coordinate system, and the second coordinate system is a carrier coordinate system. Based on the second information vector, filter parameter data is determined, wherein the filter parameter data includes multiple first column data and multiple first row data, at least one of the multiple first column data is the rate of change of the position information of the target object, and at least one of the multiple first column data is the rate of change of the pose information of the target object; Based on at least one of the plurality of first row data, the adjusted filter parameter data is determined, wherein the at least one first row data is related to at least one of the horizontal data of the target object and the height data of the target object; Based on the second positioning data and the adjusted filter parameter data, the information to be processed is determined; The information to be processed is filtered to obtain target location data; and The location of the target object is determined based on the target positioning data.

2. The method according to claim 1, wherein, The step of obtaining the second positioning data of the target object in the second coordinate system based on the pose information of the target object and the first positioning data of the target object in the first coordinate system includes: Based on the pose information of the target object, determine the first radius of curvature of the target object in the second coordinate system and the second radius of curvature of the target object in the second coordinate system; Based on the first radius of curvature and the second radius of curvature, determine the set of transformation parameters of the target object in the second coordinate system; and The second positioning data is obtained based on the set of conversion parameters and the first positioning data.

3. The method according to claim 1, wherein, The second covariance matrix includes multiple second rows of data and multiple second columns of data. The step of determining the information to be processed based on the second positioning data and the adjusted filter parameter data includes: An adjusted second covariance matrix is ​​determined based on at least one second row of data and at least one second column of data from the plurality of second rows, wherein the at least one second row of data is correlated with at least one of the horizontal data and the height data of the target object, and the at least one second column of data is correlated with at least one of the horizontal data and the height data of the target object; and Based on the adjusted second covariance matrix and the adjusted filter parameter data, the information to be processed is determined.

4. The method according to claim 3, wherein, The second information vector includes multiple third rows of data. The step of determining the information to be processed based on the adjusted second covariance matrix and the adjusted filter parameter data includes: Based on at least one of the plurality of third-row data, an adjusted second information vector is determined, wherein the at least one third-row data is correlated with at least one of the horizontal data and the height data of the target object; and The adjusted second innovation vector, the adjusted second covariance matrix, and the adjusted filter parameter data are determined as the information to be processed.

5. The method according to claim 4, wherein, The filtering process performed on the information to be processed to obtain the target location data includes: The target gain matrix is ​​obtained based on the adjusted second covariance matrix and the adjusted filter parameter data; The target state data is obtained based on the target gain matrix, the adjusted second innovation vector, and the adjusted filter parameter data; Based on the target gain matrix and the adjusted filter parameter data, the target covariance matrix is ​​obtained; and The target positioning data is obtained based on the target state data and the target covariance matrix.

6. An object positioning device, comprising: The acquisition module is used to obtain second positioning data of the target object in a second coordinate system based on the attitude information of the target object and the first positioning data of the target object in a first coordinate system. The first positioning data is related to the first position information of the target object in the first coordinate system, which includes longitude data, latitude data, and elevation data. The second positioning data is related to the second position information of the target object in the second coordinate system, which includes lateral data, longitudinal data, and height data. The first positioning data includes a first innovation vector and a first covariance matrix, and the second positioning data includes a second innovation vector and a second covariance matrix. The first coordinate system is a navigation coordinate system, and the second coordinate system is a carrier coordinate system. The third determining submodule is used to determine filtering parameter data based on the second information vector, wherein the filtering parameter data includes multiple first column data and multiple first row data, at least one of the multiple first column data is the rate of change of the position information of the target object, and at least one of the multiple first column data is the rate of change of the pose information of the target object; The first determining unit is configured to determine adjusted filter parameter data based on at least one of the plurality of first row data, wherein the at least one first row data is related to at least one of the horizontal data of the target object and the height data of the target object; The second determining unit is used to determine the information to be processed based on the second positioning data and the adjusted filter parameter data; A filtering module is used to filter the information to be processed to obtain target positioning data; and The second determining module is used to determine the location of the target object based on the target positioning data.

7. The apparatus according to claim 6, wherein, The obtaining module includes: The first determining submodule is used to determine the first radius of curvature of the target object in the second coordinate system and the second radius of curvature of the target object in the second coordinate system based on the pose information of the target object; The second determining submodule is used to determine the set of transformation parameters of the target object in the second coordinate system based on the first radius of curvature and the second radius of curvature; and The first obtaining submodule is used to obtain the second positioning data based on the set of conversion parameters and the first positioning data.

8. The apparatus according to claim 6, wherein, The second covariance matrix includes multiple second rows of data and multiple second columns of data. The second determining unit includes: A first determining subunit is configured to determine an adjusted second covariance matrix based on at least one second row of data and at least one second column of data from the plurality of second row data, wherein the at least one second row of data is correlated with at least one of the horizontal data and the height data of the target object, and the at least one second column of data is correlated with at least one of the horizontal data and the height data of the target object; and The second determining subunit is used to determine the information to be processed based on the adjusted second covariance matrix and the adjusted filter parameter data.

9. The apparatus according to claim 8, wherein, The second information vector includes multiple third rows of data. The second determining subunit is further configured to: Based on at least one of the plurality of third-row data, an adjusted second information vector is determined, wherein the at least one third-row data is correlated with at least one of the horizontal data and the height data of the target object; and The adjusted second innovation vector, the adjusted second covariance matrix, and the adjusted filter parameter data are determined as the information to be processed.

10. The apparatus according to claim 9, wherein, The filtering module includes: The second acquisition submodule is used to obtain the target gain matrix based on the adjusted second covariance matrix and the adjusted filter parameter data; The third acquisition submodule is used to obtain target state data based on the target gain matrix, the adjusted second innovation vector, and the adjusted filter parameter data; The fourth submodule is used to obtain the target covariance matrix based on the target gain matrix and the adjusted filter parameter data; and The fifth submodule is used to obtain the target positioning data based on the target state data and the target covariance matrix.

11. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 5.

12. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1 to 5.

13. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1 to 5.

14. An edge computing platform comprising a plurality of edge computing units, wherein the edge computing units comprise the electronic device of claim 11.

15. An autonomous vehicle comprising the electronic device of claim 11.

Images