Vehicle positioning reliability evaluation method and device

Abstract

The embodiment of the invention provides a vehicle positioning reliability evaluation method and device, and relates to the technical field of vehicles. The method comprises the following steps: firstly, acquiring first positioning information of a vehicle under a current frame determined by a plurality of preset modes, first verification results respectively corresponding to the plurality of pieces of first positioning information, and target positioning information of the vehicle, and then determining the target positioning information of the vehicle according to the first positioning information corresponding to the plurality of preset modes and the plurality of first verification results, and determining a reliability evaluation result of the target positioning information. According to the invention, the accuracy of reliability evaluation of the vehicle positioning information can be improved, and the precision and safety of vehicle positioning are effectively improved.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to a reliability assessment method and device for vehicle positioning. Background Art

[0002] With the rapid development of intelligence, vehicle technology has entered a new era. As an important part of vehicle technology, vehicle positioning technology is mainly used to obtain and track the location of vehicles in real time, supporting functions such as navigation, autonomous driving, and Internet of Vehicles. With the continuous development of intelligent transportation, Internet of Vehicles, and autonomous driving technologies, accurate positioning has become the basis for the efficient operation of these systems. Therefore, how to evaluate the reliability of vehicle positioning systems has become an urgent problem to be solved.

[0003] At present, the reliability assessment of positioning systems usually relies on data from a single or a few information sources, such as the Global Positioning System (GPS), Inertial Navigation System (INS) or visual sensors, etc. The reliability of the system is assessed by comparing the error between the position output by the positioning system and the reference position output by the known information source.

[0004] However, due to the data limitations of a single or a few data sources, when the information source is disturbed or fails, the reliability of the output reference position will be significantly reduced, resulting in insufficient assessment accuracy. Summary of the invention

[0005] The embodiments of the present application provide a method and device for evaluating the reliability of vehicle positioning, so as to achieve the effect of accurately evaluating whether the positioning information is reliable.

[0006] In a first aspect, an embodiment of the present application provides a method for evaluating the reliability of vehicle positioning, comprising:

[0007] Obtaining first positioning information of the vehicle in the current frame determined by multiple preset methods, first verification results respectively corresponding to the multiple first positioning information, and target positioning information of the vehicle, wherein the multiple preset methods include: determining based on chassis information of the vehicle, determining based on first position information of a global navigation satellite system GNSS, determining based on lane line information of the vehicle, determining based on curb information of a road where the vehicle is located, and determining based on at least two of second position information of laser positioning, and the target positioning information is obtained by fusing the first positioning information respectively corresponding to the multiple preset methods;

[0008] A reliability evaluation result of the target positioning information is determined according to the first positioning information corresponding to the plurality of preset modes and the plurality of first verification results.

[0009] In a possible implementation, determining a reliability evaluation result of the target positioning information according to the first positioning information corresponding to the plurality of preset modes and the plurality of first verification results includes:

[0010] When the number of dependent methods among the multiple preset methods is greater than the preset number threshold, determining the reliability evaluation result of the target positioning information according to the first positioning information corresponding to the multiple preset methods and the multiple first verification results, the dependent method is the method with the highest degree of trust among the multiple preset methods;

[0011] When the number of dependent methods is not greater than a preset number threshold, it is determined that the reliability evaluation results of the plurality of preset methods are all abnormal and the positioning information is unreliable.

[0012] In a possible implementation, determining a reliability evaluation result of the target positioning information according to the first positioning information corresponding to the plurality of preset modes and the plurality of first verification results includes:

[0013] If the first verification result corresponding to the dependent mode is abnormal, determining the reliability assessment result of the target positioning information is that all the tests are abnormal and the positioning information is unreliable, and the abnormality includes at least one of the following: abnormal verification result, unstable verification, and verification timeout;

[0014] If the difference between the first positioning information corresponding to the dependent mode and the target positioning information is greater than the first preset positioning threshold, it is determined that the reliability assessment result of the target positioning information is that all inspections are abnormal and the positioning information is unreliable;

[0015] If the difference between the first positioning information corresponding to the dependent method and the target positioning information is not greater than the first preset positioning threshold, the reliability assessment result of the target positioning information is determined according to the first verification result corresponding to the auxiliary method in multiple preset methods and the first positioning information corresponding to the auxiliary method, and the auxiliary method is a method among the multiple preset methods that has a lower degree of trust than the dependent method.

[0016] In a possible implementation, determining a reliability evaluation result of the target positioning information according to a first verification result corresponding to an auxiliary mode in a plurality of preset modes and first positioning information corresponding to the auxiliary mode includes:

[0017] If the first verification result corresponding to the auxiliary mode is abnormal, determining that the reliability assessment result of the target positioning information is that the inspection part is normal and the positioning information is reliable;

[0018] If the difference between the first positioning information corresponding to the auxiliary mode and the target positioning information is greater than the second preset positioning threshold, it is determined that the reliability assessment result of the target positioning information is that the inspection part is normal and the positioning information is reliable.

[0019] In a possible implementation manner, the preset manner is determined based on chassis information of the vehicle;

[0020] Accordingly, obtaining the first positioning information of the vehicle in the current frame determined in a preset manner and the first verification result corresponding to the first positioning information includes:

[0021] Determine the first positioning information according to the chassis information of the vehicle and the second positioning information of the vehicle in the previous frame;

[0022] If the difference between the first positioning information and the second positioning information is greater than a first preset verification threshold, determining that the first verification result is an abnormal verification result;

[0023] If the difference between the timestamp corresponding to the chassis information and the system timestamp is greater than a first preset time threshold, it is determined that the first verification result is a verification timeout.

[0024] In a possible implementation manner, the preset manner is determined based on the first location information of the GNSS;

[0025] Accordingly, obtaining the first positioning information of the vehicle in the current frame determined in a preset manner and the first verification result corresponding to the first positioning information includes:

[0026] Determine first positioning information of the vehicle according to the first position information of the GNSS;

[0027] If the difference between the first positioning information and the second positioning information of the vehicle in the previous frame is greater than a second preset verification threshold, determining that the first verification result is an abnormal verification result;

[0028] If the difference between the timestamp corresponding to the GNSS and the system timestamp is greater than a second preset time threshold, determining that the first verification result is a verification timeout;

[0029] If the result of the GNSS status bit and information self-consistency check exceeds a third preset check threshold, it is determined that the first check result is unstable.

[0030] In a possible implementation manner, the preset manner is determined based on lane line information in which the vehicle is located;

[0031] Accordingly, obtaining the first positioning information of the vehicle in the current frame determined in a preset manner and the first verification result corresponding to the first positioning information includes:

[0032] Inputting the image data including the lane line into the lane line detection model to obtain the third position information of the lane line;

[0033] Determine first positioning information according to the third position information and the orientation information of the vehicle relative to the lane line in the previous frame;

[0034] If the difference between the first positioning information and the second positioning information of the vehicle in the previous frame is greater than a fourth preset verification threshold, determining that the first verification result is an abnormal verification result;

[0035] If the difference between the timestamp corresponding to the image data of the lane line and the system timestamp is greater than a third preset time threshold, it is determined that the first verification result is a verification timeout.

[0036] In a possible implementation manner, the preset manner is determined based on the curb information of the road on which the vehicle is located;

[0037] Accordingly, obtaining the first positioning information of the vehicle in the current frame determined in a preset manner and the first verification result corresponding to the first positioning information includes:

[0038] Obtain the first point cloud information of the scene where the vehicle is located;

[0039] Filtering the first point cloud information to obtain second point cloud information corresponding to the roadside interest area;

[0040] Determining the orientation information of the curb relative to the vehicle based on the second point cloud information;

[0041] Determining first positioning information according to the orientation information of the curb relative to the vehicle;

[0042] If the difference between the position information of the curb relative to the vehicle and the position information of the lower curb relative to the vehicle in the previous frame is greater than a fifth preset verification threshold, determining that the first verification result is an abnormal verification result;

[0043] If the difference between the timestamp corresponding to the first point cloud information and the system timestamp is greater than a fourth preset time threshold, it is determined that the first verification result is a verification timeout.

[0044] In a possible implementation manner, the preset manner is determined based on the second position information of laser positioning;

[0045] Accordingly, obtaining the first positioning information of the vehicle in the current frame determined in a preset manner and the first verification result corresponding to the first positioning information includes:

[0046] Determine the first positioning information according to the second position information of the laser positioning;

[0047] If the difference between the second position information and the fourth position information of the laser positioning in the previous frame is greater than a sixth preset verification threshold, determining that the first verification result is an abnormal verification result;

[0048] If the difference between the timestamp corresponding to the second location information and the system timestamp is greater than a fifth preset time threshold, determining that the first verification result is a verification timeout;

[0049] If the result of the state bit of the laser positioning and the information self-consistency check exceeds a seventh preset check threshold, it is determined that the first check result is an unstable check.

[0050] In a second aspect, an embodiment of the present application provides a reliability assessment device for vehicle positioning, comprising:

[0051] an acquisition module, used to acquire first positioning information of the vehicle in the current frame determined by multiple preset methods, first verification results respectively corresponding to the multiple first positioning information, and target positioning information of the vehicle, wherein the multiple preset methods include: determining based on chassis information of the vehicle, determining based on first position information of a global navigation satellite system GNSS, determining based on lane line information of the vehicle, determining based on curb information of a road where the vehicle is located, and determining based on at least two of second position information of laser positioning;

[0052] The determination module is used to determine the reliability evaluation result of the target positioning information according to the first positioning information corresponding to multiple preset methods and multiple first verification results.

[0053] In a possible implementation, the determination module is specifically configured to:

[0054] When the number of dependent methods among the multiple preset methods is greater than the preset number threshold, determining the reliability evaluation result of the target positioning information according to the first positioning information corresponding to the multiple preset methods and the multiple first verification results, the dependent method is the method with the highest degree of trust among the multiple preset methods;

[0055] When the number of dependent methods is not greater than a preset number threshold, it is determined that the reliability evaluation results of the plurality of preset methods are all abnormal and the positioning information is unreliable.

[0056] In a possible implementation, the determination module determines the reliability evaluation result of the target positioning information according to the first positioning information corresponding to the plurality of preset modes and the plurality of first verification results, specifically for:

[0057] If the first verification result corresponding to the dependent mode is abnormal, determining the reliability assessment result of the target positioning information is that all the tests are abnormal and the positioning information is unreliable, and the abnormality includes at least one of the following: abnormal verification result, unstable verification, and verification timeout;

[0058] If the difference between the first positioning information corresponding to the dependent mode and the target positioning information is greater than the first preset positioning threshold, it is determined that the reliability assessment result of the target positioning information is that all inspections are abnormal and the positioning information is unreliable;

[0059] If the difference between the first positioning information corresponding to the dependent method and the target positioning information is not greater than the first preset positioning threshold, the reliability assessment result of the target positioning information is determined according to the first verification result corresponding to the auxiliary method in multiple preset methods and the first positioning information corresponding to the auxiliary method, and the auxiliary method is a method among the multiple preset methods that has a lower degree of trust than the dependent method.

[0060] In a possible implementation, the determination module determines the reliability evaluation result of the target positioning information according to the first verification result corresponding to the auxiliary mode in multiple preset modes and the first positioning information corresponding to the auxiliary mode, specifically for:

[0061] If the first verification result corresponding to the auxiliary mode is abnormal, determining that the reliability assessment result of the target positioning information is that the inspection part is normal and the positioning information is reliable;

[0062] If the difference between the first positioning information corresponding to the auxiliary mode and the target positioning information is greater than the second preset positioning threshold, it is determined that the reliability assessment result of the target positioning information is that the inspection part is normal and the positioning information is reliable.

[0063] In a possible implementation manner, the preset manner is determined based on chassis information of the vehicle;

[0064] Correspondingly, the determination module obtains the first positioning information of the vehicle in the current frame determined in a preset manner and the first verification result corresponding to the first positioning information, specifically for:

[0065] Determine the first positioning information according to the chassis information of the vehicle and the second positioning information of the vehicle in the previous frame;

[0066] If the difference between the first positioning information and the second positioning information is greater than a first preset verification threshold, determining that the first verification result is an abnormal verification result;

[0067] If the difference between the timestamp corresponding to the chassis information and the system timestamp is greater than a first preset time threshold, it is determined that the first verification result is a verification timeout.

[0068] In a possible implementation manner, the preset manner is determined based on the first location information of the GNSS;

[0069] Correspondingly, the determination module obtains the first positioning information of the vehicle in the current frame determined in a preset manner and the first verification result corresponding to the first positioning information, specifically for:

[0070] Determine first positioning information of the vehicle according to the first position information of the GNSS;

[0071] If the difference between the first positioning information and the second positioning information of the vehicle in the previous frame is greater than a second preset verification threshold, determining that the first verification result is an abnormal verification result;

[0072] If the difference between the timestamp corresponding to the GNSS and the system timestamp is greater than a second preset time threshold, determining that the first verification result is a verification timeout;

[0073] If the result of the GNSS status bit and information self-consistency check exceeds a third preset check threshold, it is determined that the first check result is unstable.

[0074] In a possible implementation manner, the preset manner is determined based on lane line information of the vehicle;

[0075] Correspondingly, the determination module obtains the first positioning information of the vehicle in the current frame determined in a preset manner and the first verification result corresponding to the first positioning information, specifically for:

[0076] Inputting the image data including the lane line into the lane line detection model to obtain the third position information of the lane line;

[0077] Determine first positioning information according to the third position information and the orientation information of the vehicle relative to the lane line in the previous frame;

[0078] If the difference between the first positioning information and the second positioning information of the vehicle in the previous frame is greater than a fourth preset verification threshold, determining that the first verification result is an abnormal verification result;

[0079] If the difference between the timestamp corresponding to the image data of the lane line and the system timestamp is greater than a third preset time threshold, it is determined that the first verification result is a verification timeout.

[0080] In a possible implementation manner, the preset manner is determined based on the curb information of the road on which the vehicle is located;

[0081] Correspondingly, the determination module obtains the first positioning information of the vehicle in the current frame determined in a preset manner and the first verification result corresponding to the first positioning information, specifically for:

[0082] Obtain the first point cloud information of the scene where the vehicle is located;

[0083] Filtering the first point cloud information to obtain second point cloud information corresponding to the roadside interest area;

[0084] Determining the orientation information of the curb relative to the vehicle based on the second point cloud information;

[0085] Determining first positioning information according to the orientation information of the curb relative to the vehicle;

[0086] If the difference between the position information of the curb relative to the vehicle and the position information of the lower curb relative to the vehicle in the previous frame is greater than a fifth preset verification threshold, determining that the first verification result is an abnormal verification result;

[0087] If the difference between the timestamp corresponding to the first point cloud information and the system timestamp is greater than a fourth preset time threshold, it is determined that the first verification result is a verification timeout.

[0088] In a possible implementation manner, the preset manner is determined based on the second position information of laser positioning;

[0089] Correspondingly, the determination module obtains the first positioning information of the vehicle in the current frame determined in a preset manner and the first verification result corresponding to the first positioning information, specifically for:

[0090] Determining first positioning information according to second position information of laser positioning;

[0091] If the difference between the second position information and the fourth position information of the laser positioning in the previous frame is greater than a sixth preset verification threshold, determining that the first verification result is an abnormal verification result;

[0092] If the difference between the timestamp corresponding to the second location information and the system timestamp is greater than a fifth preset time threshold, determining that the first verification result is a verification timeout;

[0093] If the result of the state bit of the laser positioning and the information self-consistency check exceeds a seventh preset check threshold, it is determined that the first check result is an unstable check.

[0094] In a third aspect, an embodiment of the present application provides an electronic device, including: a memory, a processor;

[0095] Memory stores computer-executable instructions;

[0096] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the above first aspect and / or various possible implementations of the first aspect.

[0097] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the first aspect above and / or various possible implementations of the first aspect.

[0098] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the above first aspect and / or various possible implementation methods of the first aspect.

[0099] The reliability assessment method and device of vehicle positioning provided in the embodiment of the present application obtain the first positioning information of the vehicle in the current frame through multiple preset methods, which include: based on the chassis information of the vehicle, based on the location information of the global navigation satellite system, based on the lane line information of the vehicle, based on the roadside information, and based on the information of laser positioning. These methods include at least two, and then, the first positioning information obtained by each preset method is verified to obtain the corresponding first verification result, and the first positioning information of multiple preset methods is fused to obtain the target positioning information of the vehicle, and then the reliability assessment result of the target positioning information is determined according to the first positioning information of multiple preset methods and their corresponding verification results. Since each information source has its advantages and disadvantages, the accuracy and robustness of the positioning information can be improved by combining data from different sensors and information sources. On this basis, each positioning information is verified to identify and filter out unreliable information sources, ensuring that the reliability of the target positioning information can be more accurately assessed. In summary, the method of the present application can accurately assess whether the positioning information is reliable through the fusion and verification of multi-source information, thereby effectively improving the accuracy and safety of vehicle positioning. BRIEF DESCRIPTION OF THE DRAWINGS

[0100] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0101] Figure 1 Schematic diagram of the process of the reliability assessment method of vehicle positioning provided in this application Figure 1 ;

[0102] Figure 2 Schematic diagram of the process of the reliability assessment method of vehicle positioning provided in this application Figure 2 ;

[0103] Figure 3 Schematic diagram of the process of the reliability assessment method of vehicle positioning provided in this application Figure 3 ;

[0104] Figure 4 Schematic diagram of the process of the reliability assessment method of vehicle positioning provided in this application Figure 4 ;

[0105] Figure 5 Schematic diagram of the process of the reliability assessment method of vehicle positioning provided in this application Figure 5 ;

[0106] Figure 6 Schematic diagram of the process of the reliability assessment method of vehicle positioning provided in this application Figure 6 ;

[0107] Figure 7Schematic diagram of the process of the reliability assessment method of vehicle positioning provided in this application Figure 7 ;

[0108] Figure 8 A schematic diagram of the structure of the reliability assessment device for vehicle positioning provided in this application;

[0109] Fig. 9 A schematic diagram of the structure of the electronic device provided in this application.

[0110] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0111] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0112] It should be noted that in the embodiments of the present application, certain software, components, models and other existing solutions in the industry may be mentioned, and they should be regarded as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of the present application, but it does not mean that the applicant has or will necessarily use the solution.

[0113] With the rapid development of intelligent and autonomous driving technologies, the importance of vehicle positioning technology has become increasingly prominent. Accurate vehicle positioning is the basis for realizing functions such as navigation, autonomous driving and vehicle networking. However, traditional positioning systems usually rely on a single or a few information sources, such as GPS, inertial navigation systems or visual sensors. This approach may face challenges in some cases, especially when the information source is interfered with or fails. The accuracy and reliability of positioning may be significantly reduced. If its reliability cannot be accurately quantified and evaluated, it may affect the vehicle driving process.

[0114] Based on this, the present application proposes a reliability assessment method and device for vehicle positioning. The method is based on consideration of the limitations of a single data source. If data from different information sources are combined and verified separately to obtain a first verification result, even if a certain information source fails, other information sources can still provide support. Since the error characteristics of different data sources are different, then, if the target positioning information of the vehicle is obtained based on multi-source data fusion, they can compensate for each other and reduce the overall error. Then, the first positioning information and the first verification result corresponding to the multi-source data can be used to make a difference judgment on the target positioning information, thereby achieving the effect of accurately assessing the reliability of the target positioning information.

[0115] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0116] Figure 1 Schematic diagram of the process of the reliability assessment method of vehicle positioning provided in this application Figure 1 .like Figure 1 As shown, the method may include:

[0117] S101, obtaining first positioning information of a vehicle in a current frame determined by multiple preset methods, first verification results respectively corresponding to the multiple first positioning information, and target positioning information of the vehicle.

[0118] Among them, the preset method may refer to different technical means for obtaining positioning information, including but not limited to: determination based on vehicle chassis information, first position information determination based on the Global Navigation Satellite System (GNSS), determination based on the lane line information of the vehicle, determination based on the curb information of the road on which the vehicle is located, and at least two of the second position information determination based on laser positioning.

[0119] The first positioning information may refer to the position information of the vehicle in the current frame obtained by a plurality of preset methods, and each preset method provides an independent positioning information.

[0120] The first verification result may refer to a result after verifying the first positioning information obtained in each preset manner, and the verification process is used to evaluate the accuracy and reliability of the positioning information.

[0121] The target positioning information is obtained by fusing the first positioning information corresponding to the multiple preset modes respectively, and is the current positioning information of the vehicle, that is, the input information source.

[0122] In this embodiment, firstly, the first positioning information of the vehicle in the current frame determined by a plurality of preset methods is obtained, and then each type of positioning information is verified to obtain a first verification result, and then these positioning information are fused to generate target positioning information.

[0123] It should be noted that the current frame may refer to the data set at the moment being processed or analyzed in a continuous data stream (such as video, lidar point cloud, sensor data, etc.), that is, relative to the previously processed frame (previous frame) and the frame to be processed (next frame).

[0124] Exemplarily, the current frame may refer to the current image captured from the camera, which is used to identify lane lines, traffic signs, pedestrians, etc.; or the lidar point cloud data at the current moment, which is used to build a three-dimensional environment model around the vehicle; or the current data from other sensors, which is used to infer the vehicle's motion state and position.

[0125] It should be noted that the category of the information source is not limited to the preset method disclosed in this application, and the first positioning information, the first verification result and the target positioning information can be adjusted accordingly according to the actual method of obtaining the information source in the specific scenario.

[0126] S102: Determine a reliability evaluation result of the target positioning information according to the first positioning information corresponding to the plurality of preset modes and the plurality of first verification results.

[0127] In this embodiment, the target positioning information of the vehicle is used as an input information source, and then the target positioning information is checked and verified in combination with the first positioning information and the first verification result of the vehicle in the current frame determined by other preset methods to evaluate the reliability of the target positioning information.

[0128] Specifically, when the first verification information indicates that the verification is normal, it means that the first positioning information obtained by the preset method is reliable, and then the reliability of the target positioning information is evaluated in combination with multiple first positioning information. If the target positioning information is all normal or partially normal based on the verification of each first positioning information, the positioning result of the target positioning information is reliable, otherwise the positioning result of the target positioning information is unreliable.

[0129] In the following implementation, the initial reliability evaluation result is assumed to be reliable.

[0130] The reliability assessment method for vehicle positioning provided in the embodiment of the present application reduces the error caused by the failure of a single information source by means of multi-source information fusion and verification mechanism, and then verifies the current positioning information according to the processing results of each information source, and obtains the verification results respectively. The reliability of the current target positioning information is evaluated through the verification results, thereby improving the accuracy of the reliability evaluation of the positioning result.

[0131] Based on the above embodiments, Figure 2 Schematic diagram of the process of the reliability assessment method of vehicle positioning provided in this application Figure 2 .like Figure 2 As shown, a possible implementation of the above step S102 includes the following steps:

[0132] S201. When the number of dependent methods among multiple preset methods is greater than a preset number threshold, determine a reliability evaluation result of the target positioning information according to the first positioning information corresponding to the multiple preset methods and the multiple first verification results.

[0133] Among them, the dependent method is the most trusted method among multiple preset methods, which provides the most reliable positioning information under specific environments or conditions.

[0134] The preset quantity threshold refers to a threshold used to determine whether the number of dependency methods is sufficient. Its value can be adjusted according to the actual application scenario. Exceeding the threshold means that the information of the dependency methods is sufficient to perform reliability assessment.

[0135] It should be noted that the initial values ​​of the first verification results corresponding to the first positioning information are all VALID, that is, the positioning results are all normal based on the verification of each information source, and the positioning results are reliable.

[0136] In this embodiment, the dependent methods are checked according to their number. When the number of dependent methods is greater than a preset number threshold, the reliability of the target positioning information is evaluated based on the first verification result and the first positioning information corresponding to the dependent method. Specifically, if the first verification result of the dependent method is abnormal, the first positioning information is considered unreliable; if the difference between the first positioning information of the dependent method and the target positioning information is greater than the first preset positioning threshold, the positioning information is also considered unreliable; on the contrary, if the difference is not greater than the first preset positioning threshold, the reliability is further evaluated based on the information of the auxiliary method. On this basis, if the verification result of the auxiliary method is abnormal, but the difference is not greater than the second preset positioning threshold, the positioning information is considered reliable.

[0137] In one achievable manner, S201 is specifically implemented through the following steps:

[0138] If the first verification result corresponding to the dependent mode is abnormal, determining the reliability assessment result of the target positioning information is that all the tests are abnormal and the positioning information is unreliable, and the abnormality includes at least one of the following: abnormal verification result, unstable verification, and verification timeout;

[0139] If the difference between the first positioning information corresponding to the dependent mode and the target positioning information is greater than the first preset positioning threshold, it is determined that the reliability assessment result of the target positioning information is that all inspections are abnormal and the positioning information is unreliable;

[0140] If the difference between the first positioning information corresponding to the dependent method and the target positioning information is not greater than the first preset positioning threshold, the reliability assessment result of the target positioning information is determined according to the first verification result corresponding to the auxiliary method in multiple preset methods and the first positioning information corresponding to the auxiliary method.

[0141] Among them, the auxiliary method is a method with a lower trust level than the dependent method among multiple preset methods, and is used to provide supplementary information when the dependent method information is unreliable.

[0142] The preset positioning threshold is a threshold used to determine whether the positioning information difference is within an acceptable range. The first preset positioning threshold can be dynamically adjusted according to actual application scenario conditions or historical data.

[0143] It should be noted that the difference between the first positioning information and the target positioning information may vary depending on the preset method (including dependent method and auxiliary method), such as the difference in the orientation angle of the vehicle position, the lateral difference distance of the vehicle positioning information, the longitudinal difference distance, etc.

[0144] In this embodiment, the first verification result corresponding to the dependent method in multiple preset methods is first checked. If the result is abnormal, such as abnormal, unstable, or timed out, the reliability assessment result of the target positioning information is ERROR, that is, all checks are abnormal and the positioning information is unreliable.

[0145] In addition, it is also necessary to calculate the difference between the first positioning information of the dependent mode and the target positioning information. If the difference is greater than the first preset positioning threshold, the target positioning information is also evaluated as ERROR.

[0146] Further, if the difference is not greater than a first preset positioning threshold, the reliability of the target positioning information is further evaluated using a first verification result and first positioning information corresponding to an auxiliary method in a plurality of preset methods.

[0147] Specifically, verification is performed on various types of information sources in the preset method to obtain a first verification result, including: VALID, indicating that the verification of the source information result is normal and the information is reliable; INVALID, indicating that the verification of the source information result is abnormal and the information is unavailable; UNSTABLE, indicating that the verification of the source information result is unstable and the information is unreliable; TIMEOUT, indicating that the source information result has timed out and the information is unreliable.

[0148] Correspondingly, after the target positioning information is verified and processed by various information sources, the determined reliability assessment results include: VALID, indicating that the positioning result is normal based on the verification of each information source, and the positioning result is reliable; WARN, indicating that the positioning result is partially normal based on the verification of each information source, and the positioning result is reliable; ERROR, indicating that the positioning result is abnormal based on the verification of each information source, and the positioning result is unreliable.

[0149] It can be understood that by setting the dependent method and based on the first positioning information and the first verification result corresponding to the target positioning information and the dependent method, it can be ensured that the final evaluation result combines the verification result of the dependent method itself and the verification of the target positioning information and the dependent method, thereby ensuring that the final evaluation result has high accuracy and reliability.

[0150] Further, according to the first verification result corresponding to the auxiliary mode in the plurality of preset modes and the first positioning information corresponding to the auxiliary mode, determining the reliability evaluation result of the target positioning information includes:

[0151] If the first verification result corresponding to the auxiliary mode is abnormal, determining that the reliability assessment result of the target positioning information is that the inspection part is normal and the positioning information is reliable;

[0152] If the difference between the first positioning information corresponding to the auxiliary mode and the target positioning information is greater than the second preset positioning threshold, it is determined that the reliability assessment result of the target positioning information is that the inspection part is normal and the positioning information is reliable.

[0153] The second preset positioning threshold is used to determine whether the difference between the first positioning information in the auxiliary mode and the target positioning information is within an acceptable range.

[0154] In this embodiment, similar to the dependent method, the first verification result corresponding to the auxiliary method is first checked. If the result is abnormal, such as abnormal, unstable, or timed out, the reliability assessment result of the target positioning information is WARN, that is, the inspection part is normal and the positioning information is reliable.

[0155] Then, a difference evaluation is performed based on the first positioning information of the auxiliary mode, and the difference between the first positioning information of the auxiliary mode and the target positioning information is calculated. If the difference is greater than the second preset positioning threshold, the reliability evaluation result of the target positioning information is also WARN.

[0156] It can be understood that, on the basis of inspection and verification based on the dependent method, further combining the first positioning information and the first verification result corresponding to the auxiliary method can provide a more comprehensive reliability assessment. At the same time, the combination of the two verification methods and results can make up for the errors that may exist in a single verification method, thereby improving the accuracy of the reliability assessment of the target positioning information.

[0157] In some embodiments, more levels of assistance may be introduced, with the degree of trust in each level gradually decreasing, to provide a more detailed reliability assessment.

[0158] S202: When the number of dependent methods is not greater than a preset number threshold, determine that the reliability evaluation results of multiple preset methods are all abnormal and the positioning information is unreliable.

[0159] It can be understood that multiple preset methods refer to multiple available positioning or verification methods, including dependent methods and auxiliary methods. When their number is not greater than the preset number threshold, it means that the current information source is insufficient. Therefore, the reliability assessment results of multiple preset methods are determined to be "all inspections are abnormal, and positioning information is unreliable", so as to avoid wasting computing resources and prevent the spread of erroneous information, ensuring that reliability assessment calculations are performed only when there is sufficient information support, thereby improving the accuracy of the assessment.

[0160] The reliability assessment method for vehicle positioning provided in the embodiment of the present application can more accurately assess the reliability of positioning information by distinguishing between dependent modes and auxiliary modes and combining multiple verification results. When some information sources are abnormal, the reliability assessment results of the target positioning information can be quickly determined. In addition, according to the different dependent modes and auxiliary modes that are distinguished, the reliability assessment results obtained by evaluating the difference between the first positioning information and the target positioning information respectively not satisfying the first preset positioning threshold and the second preset positioning threshold are also different, that is, the trust and threshold of the preset mode are dynamically adjusted, so that the positioning system can adapt to various complex environments and improve the reliability of the positioning information and the accuracy of the assessment.

[0161] Based on the above embodiments, Figure 3 Schematic diagram of the process of the reliability assessment method of vehicle positioning provided in this application Figure 3 .like Figure 3 As shown, the preset method is determined based on the chassis information of the vehicle; accordingly, a possible implementation of the step of obtaining the first positioning information of the vehicle in the current frame determined by the preset method and the first verification result corresponding to the first positioning information includes the following steps:

[0162] S301. Determine first positioning information according to chassis information of the vehicle and second positioning information of the vehicle in a previous frame.

[0163] Among them, chassis information refers to the data provided by the vehicle chassis sensor, including vehicle position and posture information, which can be used to calculate the current positioning information of the vehicle, that is, the first positioning information, which includes vehicle speed, side slip angle, vehicle movement type (i.e., vehicle forward or backward), timestamp and other information. The second positioning information is the vehicle positioning information of the previous frame, which is used to compare with the first positioning information to determine the first positioning information of the current frame. The side slip angle refers to the angle between the longitudinal axis of the vehicle and its actual direction of movement, reflecting the lateral dynamic characteristics of the vehicle.

[0164] In this embodiment, the second positioning information of the vehicle in the previous frame and the chassis information of the vehicle in the current frame can be input into the kinematic model for deduction to describe the movement behavior of the vehicle between two time points, and obtain the first positioning information loc_chassis.

[0165] It should be noted that the initial value of the first verification result for the first positioning information is set to VALID (the verification result of the source information is normal and the information is reliable), indicating that the deduction result is considered valid in the initial state.

[0166] S302: If the difference between the first positioning information and the second positioning information is greater than a first preset verification threshold, determine that the first verification result is an abnormal verification result.

[0167] The first preset check threshold is used to determine whether the difference between the positioning information of the current frame and the previous frame is within an acceptable range, and the first preset time threshold is used to determine whether the difference between the positioning information of the current frame and the previous frame is within an acceptable range.

[0168] It should be noted that all thresholds preset in the embodiments of the present application, including verification thresholds and time thresholds, can be dynamically adjusted according to actual conditions.

[0169] In this embodiment, the difference between the first positioning information and the second positioning information is compared. If the difference is greater than a first preset verification threshold, the first verification result is determined to be abnormal (INVALID), that is, the vehicle's motion calculation result is inconsistent with expectations, there may be a positioning error, and the information is not available.

[0170] As an example, vehicle-related information in the first positioning information, such as speed, sideslip angle, and vehicle motion type, can be compared with historical information (i.e., the second positioning information), and based on the comparison result and the first preset verification threshold, it is determined whether the threshold is exceeded. If exceeded, the first verification result corresponding to the first positioning information is INVALID, indicating that the source information result verification is abnormal and the information is unavailable.

[0171] S303: If the difference between the timestamp corresponding to the chassis information and the system timestamp is greater than a first preset time threshold, determine that the first verification result is a verification timeout.

[0172] In this embodiment, the difference between the timestamp of the chassis information and the system timestamp (i.e., standard time) is checked. If the difference is greater than the first preset time threshold, the first verification result is determined to be a timeout, indicating that the chassis information may not be updated in a timely manner, affecting the accuracy of positioning. The corresponding first verification result is a verification timeout, i.e., TIMEOUT, indicating that the source information result has timed out and the information is unreliable.

[0173] The vehicle positioning reliability assessment method provided in the embodiment of the present application determines the first verification result corresponding to the first positioning information by combining chassis information and historical positioning data, so as to more accurately infer the current position of the vehicle and improve the positioning accuracy. Through the verification mechanism, positioning anomalies can be identified and processed in a timely manner, thereby enhancing the reliability of the system.

[0174] Based on the above embodiments, Figure 4 Schematic diagram of the process of the reliability assessment method of vehicle positioning provided in this application Figure 4 .like Figure 4 As shown, the preset method is to determine the first position information based on GNSS; accordingly, a possible implementation of the step of obtaining the first positioning information of the vehicle in the current frame determined by the preset method and the first verification result corresponding to the first positioning information includes the following steps:

[0175] S401. Determine first positioning information of a vehicle according to first position information of a GNSS.

[0176] Among them, GNSS refers to a system that provides global positioning services through satellites, including GPS, etc., and is used to obtain the first positioning information loc_gnss of the vehicle, and the first verification result is VALID.

[0177] In this embodiment, a sensor combined navigation is installed on the vehicle. By performing coordinate transformation, the data of the sensor can be converted to a certain coordinate system fixed to the vehicle. For example, the front of the vehicle is the positive direction of the x-axis of the coordinate system, the left of the vehicle is the positive direction of the y-axis of the coordinate system, and the top of the vehicle is the positive direction of the z-axis of the coordinate system. Thus, the first position information provided by the GNSS is used to perform coordinate transformation calculation to determine the first positioning information of the vehicle in the current frame.

[0178] S402: If the difference between the first positioning information and the second positioning information of the vehicle in the previous frame is greater than a second preset verification threshold, determine that the first verification result is an abnormal verification result.

[0179] In this embodiment, the difference between the first positioning information and the second positioning information of the previous frame is compared. If the difference is greater than the second preset verification threshold, the first verification result is determined to be abnormal INVALID, indicating that the vehicle's position change exceeds the expected range, there may be a positioning error, and the information is unavailable.

[0180] S403: If the difference between the timestamp corresponding to the GNSS and the system timestamp is greater than a second preset time threshold, determine that the first verification result is a verification timeout.

[0181] In this embodiment, the difference between the GNSS timestamp and the system timestamp is checked. If the difference is greater than the second preset time threshold, the first verification result is determined to be a timeout, which means that the GNSS data may not be updated in a timely manner, affecting the accuracy of positioning, and the first verification result is TIMEOUT.

[0182] S404: If the result of the GNSS status bit and information self-consistency check exceeds a third preset check threshold, determine that the first check result is unstable.

[0183] Among them, the GNSS status bit is one or more basic units used to represent the current state of the system, which can be used to indicate status, error detection, and control process. Information self-consistency verification refers to verifying the consistency and integrity of data to ensure that it is logically reasonable and conflict-free.

[0184] Specifically, the information self-consistency check needs to check the consistency of the data, such as whether the data in the first positioning information is consistent, the logical consistency, such as whether the state of the vehicle represented by the first positioning information conforms to the logic of normal driving of the vehicle, and the integrity of the data, such as whether the first positioning information can represent the complete vehicle location information, thereby judging whether the first positioning information of the vehicle is reliable.

[0185] In this embodiment, the status bit of the GNSS and the information self-consistency check result are checked. If the result exceeds the third preset check threshold, the first check result is determined to be unstable, indicating that the GNSS data may be internally inconsistent or unreliable, and the first positioning information may have errors, and the corresponding first check result is UNSTABLE, indicating that the source information result verification is unstable and the information is unreliable.

[0186] The vehicle positioning reliability assessment method provided in the embodiment of the present application can more accurately determine the vehicle position through precise calculation and multi-level verification of GNSS data, thereby improving the accuracy of reliability assessment of the positioning system. For GNSS data, through a variety of verification mechanisms, GNSS positioning anomalies can be identified and processed in a timely manner, thereby enhancing the reliability of the system.

[0187] Based on the above embodiments, Figure 5Schematic diagram of the process of the reliability assessment method of vehicle positioning provided in this application Figure 5 .like Figure 5 As shown, the preset method is determined based on the lane line information of the vehicle; accordingly, a possible implementation of the step of obtaining the first positioning information of the vehicle in the current frame determined by the preset method and the first verification result corresponding to the first positioning information includes the following steps:

[0188] S501. Input image data including lane lines into a lane line detection model to obtain third position information of the lane lines.

[0189] Among them, the lane detection model is a computer vision model that usually uses deep learning technology to identify and extract lane information from image data.

[0190] The third position information may refer to the position information of the lane line extracted from the image data by the lane line detection model.

[0191] In this embodiment, the sensor camera can be installed on the vehicle, and the installation position and angle cover the ground area directly in front of the vehicle. Then, the sensor data is converted to a coordinate system fixed to the tractor through coordinate conversion, where the front of the tractor is the positive direction of the x-axis of the coordinate system, the left of the tractor is the positive direction of the y-axis of the coordinate system, and the top of the tractor is the positive direction of the z-axis of the coordinate system. Then, the sensor image data is used as input, and the lane line detection model is used to determine the angle and lateral position of the ground lane line in front of the vehicle relative to the vehicle, that is, the third position information. At the same time, according to the movement state of the vehicle and the changes in the sensor data, the position of the vehicle in the lane is updated in real time.

[0192] S502: Determine first positioning information according to the third position information and the orientation information of the vehicle relative to the lane line in the previous frame.

[0193] In this embodiment, the orientation information of the vehicle relative to the lane line in the previous frame refers to the absolute position of the vehicle in the previous frame, that is, the longitude and latitude position, and can be combined with map information to determine the absolute direction and lateral position of the lane line in the map in the area ahead of the vehicle.

[0194] Then, based on the third position information, that is, the angle and lateral position of the ground lane line in front of the vehicle relative to the vehicle and the orientation information of the vehicle relative to the lane line in the previous frame, that is, the absolute direction and lateral position of the lane line in the map of the area in front of the vehicle, the absolute direction and lateral position of the vehicle are calculated, which is the first positioning information loc_lane of the current frame. Similarly, the initial value of the first verification result is VALID.

[0195] S503: If the difference between the first positioning information and the second positioning information of the vehicle in the previous frame is greater than a fourth preset verification threshold, determine that the first verification result is an abnormal verification result.

[0196] In this embodiment, the difference between the first positioning information of the current frame and the second positioning information of the previous frame is compared. If the difference is greater than the fourth preset verification threshold, the first verification result is determined to be abnormal, which indicates that the vehicle's position change exceeds the expected range and there may be an error, then the first verification result is INVALID.

[0197] Exemplarily, while comparing the first positioning information with the second positioning information of the vehicle in the previous frame, the third position information is compared with the historical information, and then the difference obtained by the comparison is compared with the fourth preset verification threshold for verification, so as to determine whether the verification of the visual lane line related information is abnormal and whether the information is available.

[0198] S504: If the difference between the timestamp corresponding to the image data of the lane line and the system timestamp is greater than a third preset time threshold, determine that the first verification result is a verification timeout.

[0199] In this embodiment, the difference between the timestamp of the lane line image data and the system timestamp is checked. If the difference is greater than the third preset time threshold, the first verification result is determined to be a timeout, which means that the image data may not be updated in a timely manner during the camera shooting process, and there is a shooting time error, which affects the accuracy of positioning, and the first verification result is TIMEOUT.

[0200] The vehicle positioning reliability assessment method provided in the embodiment of the present application can ensure the high reliability of the vehicle positioning system in different environments and improve the positioning assessment accuracy by determining the first positioning information based on the lane line information of the vehicle and then verifying the first positioning information.

[0201] Based on the above embodiments, Figure 6 Schematic diagram of the process of the reliability assessment method of vehicle positioning provided in this application Figure 6 .like Figure 6 As shown, the preset method is determined based on the curb information of the road where the vehicle is located; accordingly, a possible implementation of the step of obtaining the first positioning information of the vehicle in the current frame determined by the preset method and the first verification result corresponding to the first positioning information includes the following steps:

[0202] S601: Acquire first point cloud information of a scene in which a vehicle is located.

[0203] The first point cloud information may refer to a set of three-dimensional data points generated by a laser radar or other sensors, which is used to describe the spatial structure of the vehicle's surroundings. In this embodiment, a sensor laser radar may be installed on the vehicle, and the installation position and angle need to cover the side area of ​​the vehicle. Similar to the above embodiment, the sensor data is converted to a certain coordinate system fixed to the vehicle through coordinate transformation to obtain the first point cloud information.

[0204] S602: Filter the first point cloud information to obtain second point cloud information corresponding to the roadside interest area.

[0205] Among them, the curb region of interest (RoI) refers to a specific point cloud data area related to the road edge or curb in the first point cloud information, which is used to identify road boundaries, lane lines or other road features. The obtained second point cloud information focuses on the curb region of interest and removes other irrelevant points. In this embodiment, it can be determined whether there is a curb within the threshold range based on the previous frame positioning information and the map curb information. If there is a curb, the area is determined to be the curb region of interest, and then the point cloud is filtered based on the curb region of interest to obtain the second point cloud information falling on the curb.

[0206] S603: Determine the orientation information of the curb relative to the vehicle based on the second point cloud information.

[0207] In this embodiment, the normal vector of each point is estimated based on the point cloud of the RoI region. Then, project the normal vector onto the xy plane parallel to the ground to obtain a two-dimensional vector (n x ,n y ), and then, using the relationship Filter the point cloud to obtain points in the point cloud whose normal vectors are approximately parallel to the xy plane, that is, points on the vertical plane of the curb. Wherein, T is the set threshold, which can be adjusted according to actual conditions, for example, 0.99.

[0208] Next, the random sampling consensus (RANSAC) method can be used to perform plane fitting on the points on the vertical plane of the curb, thereby eliminating the influence of noise on the fitting. The fitted vertical plane equation of the curb is ax+by+cz+d=0. At the same time, the internal points in the fitting process are obtained, that is, the points in the fitting process that are finally used to determine the vertical plane equation of the curb.

[0209] Afterwards, according to the points inside the vertical plane equation of the roadside, all z values ​​of the point cloud are assigned to 0, so that all the point clouds are compressed to the xy plane to obtain a two-dimensional point cloud.

[0210] Then, the random sampling consensus (RANSAC) method is used to perform straight line fitting on the two-dimensional point cloud to eliminate the influence of noise on the fitting, and the straight line equation of the curb in the xy plane is obtained by fitting: ax+by+c=0.

[0211] Finally, according to the straight line equation of the curb in the xy plane, the angle and lateral position of the curb relative to the vehicle, that is, the orientation information of the curb relative to the vehicle, is obtained.

[0212] S604: Determine first positioning information according to the orientation information of the curb relative to the vehicle.

[0213] In this embodiment, by combining the orientation information of the curb relative to the vehicle with the known position relationship of the vehicle, the absolute orientation and lateral position of the curb in the vehicle side area map can be determined. Then, based on the orientation and lateral position of the vehicle relative to the curb (that is, the orientation information of the curb relative to the vehicle) and the absolute orientation and lateral position of the curb, the absolute orientation and lateral position of the vehicle can be calculated, that is, the first positioning information loc_line of the current frame, and the initial value of the first verification result is VALID.

[0214] S605: If the difference between the position information of the curb relative to the vehicle and the position information of the curb relative to the vehicle in the previous frame is greater than a fifth preset verification threshold, determine that the first verification result is an abnormal verification result.

[0215] In this embodiment, the orientation information of the curb relative to the vehicle is compared with the orientation information of the curb relative to the vehicle in the previous frame (i.e., historical information), and the difference is then compared with the fifth preset verification threshold for verification. If the threshold is exceeded, the first verification result is an abnormal verification result, which is INVALID.

[0216] S606: If the difference between the timestamp corresponding to the first point cloud information and the system timestamp is greater than a fourth preset time threshold, determine that the first verification result is a verification timeout.

[0217] Similarly, if the difference between the timestamp corresponding to the first point cloud information and the system timestamp is greater than the fourth preset time threshold, it means that the point cloud data is not updated in time, and the first verification result is determined to be a verification timeout, which is TIMEOUT.

[0218] The reliability assessment method for vehicle positioning provided in the embodiment of the present application determines the first positioning information based on the curb information of the road on which the vehicle is located, and obtains the first verification result by verifying the first positioning information. It can quickly determine whether there is an abnormality in the verification and whether the identification information is reliable.

[0219] Based on the above embodiments, Figure 7 Schematic diagram of the process of the reliability assessment method of vehicle positioning provided in this application Figure 7 .like Figure 7 As shown, the preset method is to determine the second position information based on laser positioning; accordingly, a possible implementation of the step of obtaining the first positioning information of the vehicle in the current frame determined by the preset method and the first verification result corresponding to the first positioning information includes the following steps:

[0220] S701. Determine first positioning information according to second position information obtained by laser positioning.

[0221] In this embodiment, laser radar technology is used to obtain three-dimensional information of the vehicle's surroundings to determine the second position information of the vehicle, and then the second position information is converted and calculated to determine the first positioning information loc_lidar, and the initial value of the first verification result is VALID.

[0222] S702: If the difference between the second position information and the fourth position information of the laser positioning in the previous frame is greater than a sixth preset verification threshold, determine that the first verification result is abnormal.

[0223] In this embodiment, the second position information is compared with the historical information, and then the difference is compared with a sixth preset verification threshold for verification. If the difference exceeds the threshold, the first verification result is INVALID.

[0224] S703: If the difference between the timestamp corresponding to the second location information and the system timestamp is greater than a fifth preset time threshold, determine that the first verification result is a verification timeout.

[0225] In this embodiment, if the difference between the timestamp corresponding to the second position information and the system timestamp is greater than the fifth preset time threshold, it indicates that the laser positioning data may not be updated in time, and the first verification result is a verification timeout, which is TIMEOUT.

[0226] S704: If the result of the laser positioning status bit and the information self-consistency check exceeds a seventh preset check threshold, it is determined that the first check result is an unstable check.

[0227] In this embodiment, if the result of the status bit and information self-consistency check of the laser positioning exceeds the seventh preset check threshold, indicating that the laser positioning data may be internally inconsistent or unreliable, the first check result is UNSTABLE.

[0228] The reliability assessment method for vehicle positioning provided in the embodiment of the present application determines the first positioning information by performing multi-level verification on the second position information based on laser positioning to obtain a first verification result, which can timely identify and handle positioning anomalies and enhance the accuracy of reliability assessment of vehicle positioning.

[0229] Figure 8 The schematic diagram of the reliability assessment device for vehicle positioning provided in this application is as follows: Figure 8 As shown, the vehicle positioning reliability assessment device 80 provided in this embodiment includes:

[0230] The acquisition module 801 is used to acquire the first positioning information of the vehicle in the current frame determined by multiple preset methods, the first verification results respectively corresponding to the multiple first positioning information, and the target positioning information of the vehicle, wherein the multiple preset methods include: determining based on the chassis information of the vehicle, determining based on the first position information of the global navigation satellite system GNSS, determining based on the lane line information of the vehicle, determining based on the curb information of the road where the vehicle is located, and determining based on at least two of the second position information of laser positioning;

[0231] The determination module 802 is used to determine the reliability evaluation result of the target positioning information according to the first positioning information corresponding to multiple preset methods and multiple first verification results.

[0232] In a possible implementation, the determination module 802 is specifically configured to:

[0233] When the number of dependent methods among the multiple preset methods is greater than the preset number threshold, determining the reliability evaluation result of the target positioning information according to the first positioning information corresponding to the multiple preset methods and the multiple first verification results, the dependent method is the method with the highest degree of trust among the multiple preset methods;

[0234] When the number of dependent methods is not greater than a preset number threshold, it is determined that the reliability evaluation results of the plurality of preset methods are all abnormal and the positioning information is unreliable.

[0235] In a possible implementation, the determination module 802 determines the reliability evaluation result of the target positioning information according to the first positioning information corresponding to the plurality of preset modes and the plurality of first verification results, specifically for:

[0236] If the first verification result corresponding to the dependent mode is abnormal, determining the reliability assessment result of the target positioning information is that all the tests are abnormal and the positioning information is unreliable, and the abnormality includes at least one of the following: abnormal verification result, unstable verification, and verification timeout;

[0237] If the difference between the first positioning information corresponding to the dependent mode and the target positioning information is greater than the first preset positioning threshold, it is determined that the reliability assessment result of the target positioning information is that all inspections are abnormal and the positioning information is unreliable;

[0238] If the difference between the first positioning information corresponding to the dependent method and the target positioning information is not greater than the first preset positioning threshold, the reliability assessment result of the target positioning information is determined according to the first verification result corresponding to the auxiliary method in multiple preset methods and the first positioning information corresponding to the auxiliary method, and the auxiliary method is a method among the multiple preset methods that has a lower degree of trust than the dependent method.

[0239] In a possible implementation, the determination module 802 determines the reliability evaluation result of the target positioning information according to the first verification result corresponding to the auxiliary mode in multiple preset modes and the first positioning information corresponding to the auxiliary mode, specifically for:

[0240] If the first verification result corresponding to the auxiliary mode is abnormal, determining that the reliability assessment result of the target positioning information is that the inspection part is normal and the positioning information is reliable;

[0241] If the difference between the first positioning information corresponding to the auxiliary mode and the target positioning information is greater than the second preset positioning threshold, it is determined that the reliability assessment result of the target positioning information is that the inspection part is normal and the positioning information is reliable.

[0242] In a possible implementation manner, the preset manner is determined based on chassis information of the vehicle;

[0243] Correspondingly, the determination module 802 obtains the first positioning information of the vehicle in the current frame determined in a preset manner and the first verification result corresponding to the first positioning information, specifically for:

[0244] Determine the first positioning information according to the chassis information of the vehicle and the second positioning information of the vehicle in the previous frame;

[0245] If the difference between the first positioning information and the second positioning information is greater than a first preset verification threshold, determining that the first verification result is an abnormal verification result;

[0246] If the difference between the timestamp corresponding to the chassis information and the system timestamp is greater than a first preset time threshold, it is determined that the first verification result is a verification timeout.

[0247] In a possible implementation manner, the preset manner is determined based on the first location information of the GNSS;

[0248] Correspondingly, the determination module 802 obtains the first positioning information of the vehicle in the current frame determined in a preset manner and the first verification result corresponding to the first positioning information, specifically for:

[0249] Determine first positioning information of the vehicle according to the first position information of the GNSS;

[0250] If the difference between the first positioning information and the second positioning information of the vehicle in the previous frame is greater than a second preset verification threshold, determining that the first verification result is an abnormal verification result;

[0251] If the difference between the timestamp corresponding to the GNSS and the system timestamp is greater than a second preset time threshold, determining that the first verification result is a verification timeout;

[0252] If the result of the GNSS status bit and information self-consistency check exceeds a third preset check threshold, it is determined that the first check result is unstable.

[0253] In a possible implementation manner, the preset manner is determined based on lane line information in which the vehicle is located;

[0254] Correspondingly, the determination module 802 obtains the first positioning information of the vehicle in the current frame determined in a preset manner and the first verification result corresponding to the first positioning information, specifically for:

[0255] Inputting the image data including the lane line into the lane line detection model to obtain the third position information of the lane line;

[0256] Determine first positioning information according to the third position information and the orientation information of the vehicle relative to the lane line in the previous frame;

[0257] If the difference between the first positioning information and the second positioning information of the vehicle in the previous frame is greater than a fourth preset verification threshold, determining that the first verification result is an abnormal verification result;

[0258] If the difference between the timestamp corresponding to the image data of the lane line and the system timestamp is greater than a third preset time threshold, it is determined that the first verification result is a verification timeout.

[0259] In a possible implementation manner, the preset manner is determined based on the curb information of the road on which the vehicle is located;

[0260] Correspondingly, the determination module 802 obtains the first positioning information of the vehicle in the current frame determined in a preset manner and the first verification result corresponding to the first positioning information, specifically for:

[0261] Obtain the first point cloud information of the scene where the vehicle is located;

[0262] Filtering the first point cloud information to obtain second point cloud information corresponding to the roadside interest area;

[0263] Determining the orientation information of the curb relative to the vehicle based on the second point cloud information;

[0264] Determining first positioning information according to the orientation information of the curb relative to the vehicle;

[0265] If the difference between the position information of the curb relative to the vehicle and the position information of the lower curb relative to the vehicle in the previous frame is greater than a fifth preset verification threshold, determining that the first verification result is an abnormal verification result;

[0266] If the difference between the timestamp corresponding to the first point cloud information and the system timestamp is greater than a fourth preset time threshold, it is determined that the first verification result is a verification timeout.

[0267] In a possible implementation manner, the preset manner is determined based on the second position information of laser positioning;

[0268] Correspondingly, the determination module 802 obtains the first positioning information of the vehicle in the current frame determined in a preset manner and the first verification result corresponding to the first positioning information, specifically for:

[0269] Determine the first positioning information according to the second position information of the laser positioning;

[0270] If the difference between the second position information and the fourth position information of the laser positioning in the previous frame is greater than a sixth preset verification threshold, determining that the first verification result is an abnormal verification result;

[0271] If the difference between the timestamp corresponding to the second location information and the system timestamp is greater than a fifth preset time threshold, determining that the first verification result is a verification timeout;

[0272] If the result of the laser positioning status bit and the information self-consistency check exceeds a seventh preset check threshold, it is determined that the first check result is an unstable check.

[0273] The reliability assessment device for vehicle positioning provided in this embodiment can execute the method provided in the above method embodiment, and its implementation principle and technical effect are similar, which will not be described in detail in this embodiment.

[0274] Fig. 9 This is a schematic diagram of the structure of the electronic device provided in this application. Fig. 9 As shown, the electronic device 90 provided in this embodiment includes: at least one processor 901 and a memory 902. Optionally, the device 90 further includes a communication component 903. The processor 901, the memory 902 and the communication component 903 are connected via a bus 904.

[0275] In a specific implementation process, at least one processor 901 executes the computer execution instructions stored in the memory 902, so that at least one processor 901 executes the above method.

[0276] The specific implementation process of the processor 901 can be found in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be repeated here.

[0277] In the above embodiments, it should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the invention may be directly implemented as being executed by a hardware processor, or may be executed by a combination of hardware and software modules in the processor.

[0278] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (Non-volatile Memory, NVM), such as at least one disk memory.

[0279] The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of the present application is not limited to only one bus or one type of bus.

[0280] The present application also provides a computer program product, including a computer program, which implements the above method when executed by a processor.

[0281] The present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the above method is implemented.

[0282] The above-mentioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.

[0283] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (Application Specific Integrated Circuits, referred to as: ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0284] The division of units is only a logical function division, and there may be other divisions in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0285] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0286] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0287] If the function is implemented in the form of 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 the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0288] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0289] Finally, it should be noted that those skilled in the art will readily conceive of other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present invention, which follow the general principles of the present invention and include common knowledge or customary technical means in the art not disclosed by the present invention, are not limited to the precise structure described above and shown in the drawings, and may be modified and changed in various ways without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A reliability assessment method for vehicle positioning, characterized in that: include: Obtaining first positioning information of the vehicle in the current frame determined by multiple preset methods, first verification results respectively corresponding to the multiple first positioning information, and target positioning information of the vehicle, the multiple preset methods including: determining based on chassis information of the vehicle, determining based on first position information of a global navigation satellite system GNSS, determining based on lane line information of the vehicle, determining based on curb information of a road where the vehicle is located, and determining based on at least two of second position information of laser positioning, the target positioning information being obtained by fusing the first positioning information respectively corresponding to the multiple preset methods; A reliability evaluation result of the target positioning information is determined according to the first positioning information corresponding to the multiple preset modes and the multiple first verification results.

2. The method according to claim 1, characterized in that The determining, according to the first positioning information corresponding to the plurality of preset modes and the plurality of first verification results, a reliability evaluation result of the target positioning information comprises: When the number of dependent methods in the multiple preset methods is greater than a preset number threshold, determining a reliability evaluation result of the target positioning information according to the first positioning information corresponding to the multiple preset methods and the multiple first verification results, the dependent method being the method with the highest degree of trust among the multiple preset methods; When the number of the dependent methods is not greater than the preset number threshold, it is determined that the reliability evaluation results of the multiple preset methods are all abnormal and the positioning information is unreliable.

3. The method according to claim 1 or 2, characterized in that: The determining, according to the first positioning information corresponding to the plurality of preset modes and the plurality of first verification results, a reliability evaluation result of the target positioning information comprises: If the first verification result corresponding to the dependent mode is abnormal, determining the reliability evaluation result of the target positioning information is that all the inspections are abnormal and the positioning information is unreliable, wherein the abnormality includes at least one of the following: abnormal verification result, unstable verification, and verification timeout; If the difference between the first positioning information corresponding to the dependent mode and the target positioning information is greater than a first preset positioning threshold, determining that the reliability assessment result of the target positioning information is that all inspections are abnormal and the positioning information is unreliable; If the difference between the first positioning information corresponding to the dependent method and the target positioning information is not greater than the first preset positioning threshold, the reliability assessment result of the target positioning information is determined according to the first verification result corresponding to the auxiliary method among the multiple preset methods and the first positioning information corresponding to the auxiliary method, and the auxiliary method is a method among the multiple preset methods whose trust level is lower than that of the dependent method.

4. The method according to claim 3, characterized in that The determining, according to the first verification result corresponding to the auxiliary mode in the plurality of preset modes and the first positioning information corresponding to the auxiliary mode, a reliability evaluation result of the target positioning information comprises: If the first verification result corresponding to the auxiliary mode is abnormal, determining that the reliability evaluation result of the target positioning information is that the inspection part is normal and the positioning information is reliable; If the difference between the first positioning information corresponding to the auxiliary method and the target positioning information is greater than a second preset positioning threshold, it is determined that the reliability assessment result of the target positioning information is that the inspection part is normal and the positioning information is reliable.

5. The method according to claim 3, characterized in that: The preset method is determined based on chassis information of the vehicle; Correspondingly, obtaining the first positioning information of the vehicle in the current frame determined by the preset method and a first verification result corresponding to the first positioning information includes: Determine the first positioning information according to the chassis information of the vehicle and the second positioning information of the vehicle in the previous frame; If the difference between the first positioning information and the second positioning information is greater than a first preset verification threshold, determining that the first verification result is an abnormal verification result; If the difference between the timestamp corresponding to the chassis information and the system timestamp is greater than a first preset time threshold, it is determined that the first verification result is a verification timeout.

6. The method according to claim 3, characterized in that The preset method is determined based on the first position information of the GNSS; Correspondingly, obtaining the first positioning information of the vehicle in the current frame determined by the preset method and a first verification result corresponding to the first positioning information includes: Determining first positioning information of the vehicle according to the first position information of the GNSS; If the difference between the first positioning information and the second positioning information of the vehicle in the previous frame is greater than a second preset verification threshold, determining that the first verification result is an abnormal verification result; If the difference between the timestamp corresponding to the GNSS and the system timestamp is greater than a second preset time threshold, determining that the first verification result is a verification timeout; If the result of the GNSS status bit and information self-consistency check exceeds a third preset check threshold, it is determined that the first check result is unstable.

7. The method according to claim 3, characterized in that The preset method is determined based on the lane line information of the vehicle; Correspondingly, obtaining the first positioning information of the vehicle in the current frame determined by the preset method and a first verification result corresponding to the first positioning information includes: Inputting the image data including the lane line into the lane line detection model to obtain the third position information of the lane line; Determine the first positioning information according to the third position information and the orientation information of the vehicle relative to the lane line in the previous frame; If the difference between the first positioning information and the second positioning information of the vehicle in the previous frame is greater than a fourth preset verification threshold, determining that the first verification result is an abnormal verification result; If the difference between the timestamp corresponding to the image data of the lane line and the system timestamp is greater than a third preset time threshold, it is determined that the first verification result is a verification timeout.

8. The method according to claim 3, characterized in that The preset method is determined based on the curb information of the road where the vehicle is located; Correspondingly, obtaining the first positioning information of the vehicle in the current frame determined by the preset method and a first verification result corresponding to the first positioning information includes: Acquire first point cloud information of the scene in which the vehicle is located; Filtering the first point cloud information to obtain second point cloud information corresponding to the curb area of ​​interest; Determining the orientation information of the curb relative to the vehicle according to the second point cloud information; Determining the first positioning information according to the orientation information of the curb relative to the vehicle; If the difference between the position information of the curb relative to the vehicle and the position information of the curb relative to the vehicle in the previous frame is greater than a fifth preset verification threshold, determining that the first verification result is an abnormal verification result; If the difference between the timestamp corresponding to the first point cloud information and the system timestamp is greater than a fourth preset time threshold, it is determined that the first verification result is a verification timeout.

9. The method according to claim 3, characterized in that: The preset method is determined based on the second position information of laser positioning; Correspondingly, obtaining the first positioning information of the vehicle in the current frame determined by the preset method and a first verification result corresponding to the first positioning information includes: Determining the first positioning information according to the second position information of the laser positioning; If the difference between the second position information and the fourth position information of the laser positioning in the previous frame is greater than a sixth preset verification threshold, determining that the first verification result is an abnormal verification result; If the difference between the timestamp corresponding to the second location information and the system timestamp is greater than a fifth preset time threshold, determining that the first verification result is a verification timeout; If the result of the state bit of the laser positioning and the information self-consistency check exceeds a seventh preset check threshold, it is determined that the first check result is an unstable check.

10. A reliability assessment device for vehicle positioning, characterized in that: include: an acquisition module, used to acquire first positioning information of the vehicle in the current frame determined by multiple preset methods, first verification results respectively corresponding to the multiple first positioning information, and target positioning information of the vehicle, wherein the multiple preset methods include: determining based on chassis information of the vehicle, determining based on first position information of a global navigation satellite system GNSS, determining based on lane line information of the vehicle, determining based on curb information of a road where the vehicle is located, and determining based on at least two of second position information of laser positioning; A determination module is used to determine the reliability evaluation result of the target positioning information according to the first positioning information corresponding to the multiple preset methods and the multiple first verification results.

Images