Method and apparatus for detecting accuracy of vehicle positioning algorithm, computing device, and medium

Abstract

This application provides a method, apparatus, computing device, and medium for detecting the accuracy of a vehicle positioning algorithm. This application acquires test data packets containing driving data collected during vehicle operation. Based on the driving data included in each test data packet and a pre-established map, a first positioning information for the vehicle is determined. Then, using the positioning algorithm to be tested, a second positioning information for the vehicle is determined based on each test data packet, resulting in multiple first and second positioning information. Finally, based on each first and corresponding second positioning information, a positioning error is determined. This allows the positioning accuracy of the positioning algorithm to be tested to meet positioning requirements if the positioning error information corresponding to multiple test data packets satisfies set conditions. This enables the evaluation of the accuracy of the positioning algorithm for autonomous vehicles, ensuring the accuracy of the autonomous vehicle's positioning location.

Description

Technical Field

[0001] This specification relates to the field of autonomous driving technology, and in particular to a method, apparatus, computing device, and medium for detecting the accuracy of a vehicle positioning algorithm. Background Technology

[0002] With the rapid development of technologies such as mobile communication, the Internet of Things, and computer vision, new technologies such as autonomous driving have also experienced rapid development, and autonomous vehicles are being used more and more widely in real life.

[0003] The first step for autonomous vehicles is knowing their location. In the complex and ever-changing urban environment, the positioning accuracy of autonomous vehicles must be within 10cm. If the positioning deviation is too large, the driving video determined by the software algorithm based on the positioning will be significantly off, making the autonomous vehicle prone to scraping or colliding with roadside facilities during operation. Therefore, in autonomous driving technology, positioning accuracy is crucial from both hardware and software perspectives. Thus, there is an urgent need for a method to detect the accuracy of vehicle positioning algorithms to evaluate the accuracy of autonomous vehicle positioning algorithms and ensure the accuracy of the vehicle's location. Summary of the Invention

[0004] To overcome the problems existing in related technologies, this application provides a method, apparatus, computing device and medium for detecting the accuracy of a vehicle positioning algorithm.

[0005] According to a first aspect of the embodiments of this application, a method for detecting the accuracy of a vehicle positioning algorithm is provided, the method comprising:

[0006] Acquire multiple test data packets, which include driving data collected during vehicle operation;

[0007] Based on the driving data included in each test data packet and the pre-established map, a first positioning information of the vehicle is determined, and a second positioning information of the vehicle is determined based on each test data packet using the positioning algorithm to be tested.

[0008] Based on each first positioning information and the corresponding second positioning information, a positioning error information is determined;

[0009] If the positioning error information corresponding to multiple test data packets meets the set conditions, it is determined that the positioning accuracy of the positioning algorithm to be tested meets the positioning requirements.

[0010] In some embodiments of this application, multiple test data packets are prepared in advance. These test data packets are labeled with a location problem tag and an environment tag. The location problem tag indicates the cause of the vehicle positioning error, and the environment tag indicates the environmental conditions during vehicle operation. The preparation process for the multiple test data packets includes:

[0011] Acquire driving data collected from at least one vehicle during its operation;

[0012] Based on the timestamps of the driving data, the collected driving data is segmented to obtain multiple candidate data packets;

[0013] Based on the visualization results of each candidate data packet, obtain the location problem label and environment label for each candidate data packet;

[0014] Candidate data packets whose location problem labels and environment labels meet the target conditions will be used as test data packets.

[0015] In some embodiments of this application, the driving data includes at least initial positioning information, point cloud data, and wheel speed data;

[0016] Based on the driving data included in each test data packet and the pre-built map, a first location information for the vehicle is determined, including:

[0017] For any test data packet, the vehicle's location area on the map is determined based on the initial positioning information and wheel speed data in the driving data included in the test data packet.

[0018] From the candidate point cloud data corresponding to each candidate positioning information in the positioning area, determine the candidate point cloud data that matches the point cloud data, and determine the candidate positioning information corresponding to the candidate point cloud data as the first positioning information.

[0019] In some embodiments of this application, the positioning information includes position information and attitude information. The position information includes the vehicle's position coordinates in a set coordinate system, and the attitude information is used to indicate the angular relationship between the vehicle's position and the coordinate axes of the set coordinate system. The positioning error information includes relative pose error and absolute trajectory error.

[0020] Based on each first positioning information and the corresponding second positioning information, a positioning error information is determined, including:

[0021] For any first positioning information and the corresponding second positioning information, the absolute trajectory error is determined based on the first position information included in the first positioning information and the second position information included in the second positioning information, and the relative pose error is determined based on the first attitude information included in the first positioning information and the second attitude information included in the second positioning information.

[0022] In some embodiments of this application, when the positioning error information corresponding to multiple test data packets meets set conditions, determining that the positioning accuracy of the positioning algorithm to be tested meets the positioning requirements includes:

[0023] If the positioning error information corresponding to multiple test data packets is less than the set error threshold, it is determined that the positioning accuracy of the positioning algorithm to be tested meets the positioning requirements.

[0024] In some embodiments of this application, after determining a positioning error information based on each first positioning information and the corresponding second positioning information, the method further includes:

[0025] If the positioning error information corresponding to multiple test data packets does not meet the set conditions, it is determined that the positioning accuracy of the positioning algorithm to be tested does not meet the positioning requirements.

[0026] In some embodiments of this application, the method further includes:

[0027] Output test result information, which indicates the pass / fail status of multiple test data packets, as well as the test comparison between the location algorithm to be tested and at least one location algorithm that has been tested.

[0028] According to a second aspect of the embodiments of this specification, an accuracy detection device for a vehicle positioning algorithm is provided, the device comprising:

[0029] The acquisition module is used to acquire multiple test data packets, which include driving data collected during vehicle operation.

[0030] The determination module is used to determine a first location information of the vehicle based on the driving data included in each test data packet and a pre-established map;

[0031] The determination module is also used to determine a second location information of the vehicle based on each test data packet using the positioning algorithm to be detected;

[0032] The determination module is also used to determine a positioning error information based on each first positioning information and the corresponding second positioning information;

[0033] The determination module is also used to determine whether the positioning accuracy of the positioning algorithm to be tested meets the positioning requirements, provided that the positioning error information corresponding to multiple test data packets meets the set conditions.

[0034] In some embodiments of this application, multiple test data packets are prepared in advance. These test data packets are labeled with a location problem tag and an environment tag. The location problem tag indicates the cause of the vehicle positioning error, and the environment tag indicates the environmental conditions during vehicle operation. The preparation process for the multiple test data packets includes:

[0035] Acquire driving data collected from at least one vehicle during its operation;

[0036] Based on the timestamps of the driving data, the collected driving data is segmented to obtain multiple candidate data packets;

[0037] Based on the visualization results of each candidate data packet, obtain the location problem label and environment label for each candidate data packet;

[0038] Candidate data packets whose location problem labels and environment labels meet the target conditions will be used as test data packets.

[0039] In some embodiments of this application, the driving data includes at least initial positioning information, point cloud data, and wheel speed data;

[0040] The determination module, when used to determine a first location of the vehicle based on the driving data included in each test data packet and a pre-built map, is used for:

[0041] For any test data packet, the vehicle's location area on the map is determined based on the initial positioning information and wheel speed data in the driving data included in the test data packet.

[0042] From the candidate point cloud data corresponding to each candidate positioning information in the positioning area, determine the candidate point cloud data that matches the point cloud data, and determine the candidate positioning information corresponding to the candidate point cloud data as the first positioning information.

[0043] In some embodiments of this application, the positioning information includes position information and attitude information. The position information includes the vehicle's position coordinates in a set coordinate system, and the attitude information is used to indicate the angular relationship between the vehicle's position and the coordinate axes of the set coordinate system. The positioning error information includes relative pose error and absolute trajectory error.

[0044] The determination module, when determining a positioning error based on each first positioning information and the corresponding second positioning information, is used for:

[0045] For any first positioning information and the corresponding second positioning information, the absolute trajectory error is determined based on the first position information included in the first positioning information and the second position information included in the second positioning information, and the relative pose error is determined based on the first attitude information included in the first positioning information and the second attitude information included in the second positioning information.

[0046] In some embodiments of this application, the determining module, when determining that the positioning accuracy of the positioning algorithm to be tested meets the positioning requirements when the positioning error information corresponding to multiple test data packets meets set conditions, is configured to:

[0047] If the positioning error information corresponding to multiple test data packets is less than the set error threshold, it is determined that the positioning accuracy of the positioning algorithm to be tested meets the positioning requirements.

[0048] In some embodiments of this application, the determining module is further configured to determine that the positioning accuracy of the positioning algorithm to be tested does not meet the positioning requirements when the positioning error information corresponding to multiple test data packets does not meet the set conditions.

[0049] In some embodiments of this application, the device further includes:

[0050] The output module is used to output test result information, which indicates the pass / fail status of multiple test data packets and the test comparison between the positioning algorithm to be tested and at least one previously tested positioning algorithm.

[0051] According to a third aspect of the embodiments of this application, a computing device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the operations performed by the accuracy detection method of the vehicle positioning algorithm described above.

[0052] According to a fourth aspect of the embodiments of this application, a computer-readable storage medium is provided, on which a program is stored, and the program is executed by a processor to perform the operations performed by the accuracy detection method of the vehicle positioning algorithm described above.

[0053] According to a fifth aspect of the present application, a computer program product is provided, including a computer program that, when executed by a processor, implements the operations performed by the accuracy detection method of the vehicle positioning algorithm described above.

[0054] The technical solutions provided by the embodiments of this application may include the following beneficial effects:

[0055] This application acquires test data packets containing driving data collected during vehicle operation. Based on the driving data included in each test data packet and a pre-established map, it determines a first positioning information for the vehicle. Then, using a positioning algorithm to be tested, it determines a second positioning information for the vehicle based on each test data packet, thus obtaining multiple first and second positioning information. Based on each first and corresponding second positioning information, it determines a positioning error information. This allows the positioning accuracy of the positioning algorithm to be tested to meet positioning requirements, provided that the positioning error information corresponding to multiple test data packets meets set conditions. This enables the evaluation of the accuracy of the positioning algorithm for autonomous vehicles, ensuring the accuracy of the autonomous vehicle's positioning location.

[0056] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this specification. Attached Figure Description

[0057] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this specification and, together with the description, serve to explain the principles of this specification.

[0058] Figure 1 This is a flowchart illustrating an accuracy detection method for a vehicle positioning algorithm according to an exemplary embodiment of this application.

[0059] Figure 2 This is a schematic diagram illustrating a display format of test result information according to an exemplary embodiment of this application.

[0060] Figure 3 This is a framework diagram illustrating the accuracy detection process of a vehicle positioning algorithm according to an exemplary embodiment of this application.

[0061] Figure 4 This is a block diagram of a vehicle positioning algorithm accuracy detection device according to an exemplary embodiment of this application.

[0062] Figure 5 This is a schematic diagram of the structure of a computing device according to an exemplary embodiment of this application. Detailed Implementation

[0063] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this specification. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this specification as detailed herein.

[0064] The terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to be limiting of this specification. The singular forms “a,” “described,” and “the” as used herein are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any and all possible combinations of one or more of the associated listed items.

[0065] It should be understood that although the terms first, second, third, etc., may be used in this specification to describe various information, this information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this specification, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0066] This application provides a method for detecting the accuracy of a vehicle positioning algorithm, used to detect the accuracy of the positioning algorithm to be tested. The positioning algorithm to be tested can be the positioning algorithm currently used by the vehicle, and can be any type of positioning algorithm. For example, the positioning algorithm to be tested can be a Bayesian filtering-based fusion positioning algorithm, an Ultra-wideband (UWB) Least Square Method (LSM) Taylor cascaded vehicle positioning algorithm, etc. This application does not limit the specific type of positioning algorithm to be tested.

[0067] The above is merely an illustrative description of the application scenarios of this application and does not constitute a limitation on the application scenarios of this application. In many other possible implementations, this application can be applied to various other scenarios involving the accuracy detection process of vehicle positioning algorithms.

[0068] The accuracy detection method of the above-mentioned vehicle positioning algorithm can be executed by a computing device, which can be a server, such as a single server, multiple servers, a server cluster, a cloud computing platform, etc. Optionally, the computing device can also be a terminal device, such as a desktop computer, a portable computer, an advertising machine, an all-in-one machine, etc. This application does not limit the specific type of computing device.

[0069] The above is a description of the application scenarios of this application. Next, in conjunction with the embodiments of this application, the accuracy detection method of the vehicle positioning algorithm provided in this application will be described in detail.

[0070] like Figure 1 As shown, Figure 1This is a flowchart illustrating an accuracy detection method for a vehicle positioning algorithm according to an exemplary embodiment of this application. The method includes the following steps:

[0071] Step 101: Obtain multiple test data packets, which include driving data collected during vehicle operation.

[0072] Step 102: Based on the driving data included in each test data packet and the pre-established map, determine a first positioning information of the vehicle, and determine a second positioning information of the vehicle based on each test data packet using the positioning algorithm to be tested.

[0073] Step 103: Based on each first positioning information and the corresponding second positioning information, determine a positioning error information.

[0074] Step 104: If the positioning error information corresponding to multiple test data packets meets the set conditions, determine that the positioning accuracy of the positioning algorithm to be tested meets the positioning requirements.

[0075] This application acquires test data packets containing driving data collected during vehicle operation. Based on the driving data included in each test data packet and a pre-established map, it determines a first positioning information for the vehicle. Then, using a positioning algorithm to be tested, it determines a second positioning information for the vehicle based on each test data packet, thus obtaining multiple first and second positioning information. Based on each first and corresponding second positioning information, it determines a positioning error information. This allows the positioning accuracy of the positioning algorithm to be tested to meet positioning requirements, provided that the positioning error information corresponding to multiple test data packets meets set conditions. This enables the evaluation of the accuracy of the positioning algorithm for autonomous vehicles, ensuring the accuracy of the autonomous vehicle's positioning location.

[0076] After introducing the basic implementation process of this application, the various optional implementation methods of this application will be introduced below.

[0077] In some embodiments, the test data packets obtained in step 101 may be pre-prepared. In one possible implementation, the preparation of multiple test data packets can be achieved through the following steps:

[0078] Step 1: Obtain driving data collected from at least one vehicle during its operation.

[0079] The model, driving scenario, and driving speed of at least one vehicle may be the same or different, and this application does not limit this.

[0080] Each vehicle collects various types of data during its operation. For example, any given vehicle may be equipped with various types of data acquisition devices, such as onboard cameras (e.g., dashcams), lidar, wheel speed sensors (e.g., wheel speedometers), etc. This application does not limit the specific type of data acquisition device.

[0081] Taking a data acquisition device including an in-vehicle camera, a lidar, and a wheel speed sensor as an example, the driving data collected by the in-vehicle camera can be image data, the driving data collected by the lidar can be point cloud data, and the driving data collected by the wheel speed sensor can be the vehicle speed.

[0082] Step 2: Based on the timestamps of the driving data, the collected driving data is segmented to obtain multiple candidate data packets.

[0083] It should be noted that for any vehicle, the timestamps of the driving data collected are continuous. The continuous driving data collected by the vehicle can be segmented according to a set duration to divide the driving data into multiple candidate data packets with a set duration.

[0084] Taking the vehicle's driving data as a continuous 100-second driving data as an example, with a set duration of 10 seconds, this 100-second driving data can be divided into 10 candidate data packets. Each candidate data packet includes driving data collected within a 10-second time period.

[0085] Step 3: Based on the visualization results of each candidate data packet, obtain the location problem label and environment label for each candidate data packet.

[0086] In one possible implementation, data visualization tools can be used to visualize the data of each candidate data packet, so that relevant technicians can see the vehicle's driving process in a clear and intuitive way. Based on the relevant information of the vehicle's driving process, corresponding location problem labels and environment labels can be set for the candidate data packets, so that the computing device can obtain the location problem labels and environment labels set by the relevant technicians for each candidate data packet.

[0087] The positioning problem label indicates the reason for the vehicle positioning error, while the environment label indicates the environmental conditions during vehicle operation. Optionally, the positioning problem label may include initial positioning failure, positioning deviation during operation, or positioning error caused by data corruption. The environment label may indicate weather conditions, road conditions, number of pedestrians, etc., during vehicle operation. For example, the environment label may be an Operational Design Domain (ODD) label, or it may be other types of labels. This application does not limit the specific types of positioning problem labels and environment labels.

[0088] Step 4: Select candidate data packets whose location problem labels and environment labels meet the target conditions as test data packets.

[0089] In one possible implementation, the computing device can determine the candidate data packets corresponding to the location problem label and environment label that meet the target conditions based on the location problem label and environment label of each candidate data packet, and use the candidate data packets corresponding to the location problem label and environment label that meet the target conditions as test data packets.

[0090] The target conditions can be a first setting type for locating the problem label, and / or a second setting type for the environment label. This application does not limit the specific content of the first setting type and the second setting type.

[0091] It should be noted that the first setting type may include at least one location problem label type, and the second setting type may include at least one environment label type. This application does not limit the number of label types included in the first and second setting types. Based on this, in order to ensure that the test data packets can cover as many location error scenarios as possible, the number of label types included in the first and second setting types can be maximized. This ensures that candidate data packets collected under various location error scenarios can be used as test data packets, thereby guaranteeing that the test data packets can cover as many location error scenarios as possible.

[0092] In addition, it should be emphasized that since there can be multiple vehicles used to collect driving data, and these vehicles may have different models, driving speeds, etc., in order to ensure the generalization of the localization algorithm to be tested, when selecting test data packets, the candidate test data packets can be collected from different vehicles. This allows the localization algorithm to be tested based on test data packets collected from different vehicles, thereby improving the generalization of the localization algorithm to be tested.

[0093] Through the above process, multiple test data packets that meet the testing requirements can be obtained, so that the accuracy of the positioning algorithm to be tested can be tested based on the multiple test data packets.

[0094] It should be noted that since multiple candidate data packets are labeled with location problem tags and environment tags, the test data packets determined from the multiple candidate data packets are also labeled with location problem tags and environment tags.

[0095] Optionally, after identifying test data packets from multiple candidate data packets, these test data packets can be recorded in a dataset to construct a test dataset containing multiple test data packets. This dataset can then be used to test the accuracy of the localization algorithm to be detected. The test dataset records the localization problem label and environment label for each test data packet.

[0096] In other possible implementations, new driving data may be obtained from the identified multiple test data packets. In this case, new test data packets can be determined based on the newly obtained driving data. The process of determining new test data packets based on the newly obtained driving data can be found in the above embodiments, and will not be repeated here.

[0097] It should be noted that after the new test data packet is determined, it can be used together with the previously determined test data packets as the test data packet for the localization algorithm to be detected. This can expand the test data packet and improve the accuracy of the localization algorithm.

[0098] Furthermore, when constructing a test dataset based on multiple test data packets, after determining new test data packets based on newly acquired driving data, the determined new test data packets can be added to the test dataset so that the computing device can obtain the new test data packets and previously determined test data packets by acquiring the test dataset.

[0099] After determining multiple test data packets through the above process, the computing device can obtain multiple test data packets through step 101, so as to detect the accuracy of the positioning algorithm to be detected based on the obtained test data packets.

[0100] In some embodiments, driving data may include point cloud data and wheel speed data. Optionally, driving data may also include more types of data. This application does not limit the data types included in the driving data. Taking driving data including point cloud data and wheel speed data as an example, for step 102, when determining a first positioning information of the vehicle based on the driving data included in each test data packet and the pre-established map, it can be achieved through the following steps:

[0101] Step 102-1-1: For any test data packet, determine the vehicle's location area on the map based on the initial positioning information and wheel speed data in the driving data included in the test data packet.

[0102] It should be noted that the initial positioning information can be Global Navigation Satellite System (GNSS) information. Optionally, the initial positioning information can also be other types of positioning information. This application does not limit the specific type of initial positioning information.

[0103] By setting initial positioning information in the test data packet, positioning information can be determined through loopback based on the initial positioning information. Since the error will continue to accumulate during driving, the loopback can distribute the error evenly to each positioning point when the vehicle passes the previous position again, so as to ensure that the position and attitude information of each point is more accurate.

[0104] In one possible implementation, when determining the vehicle's location area on the map based on the initial positioning information and wheel speed data in the driving data included in the test data packet, the vehicle's travel distance can be determined based on the wheel speed data and the vehicle's travel time, and then the vehicle's location area on the map can be determined based on the vehicle's travel distance and the initial positioning information.

[0105] Optionally, when determining the vehicle's location area on the map based on the vehicle's driving distance and initial positioning information, the vehicle's predicted positioning information in multiple directions can be determined first based on the sum of the vehicle's driving distance and initial positioning information, resulting in multiple predicted positioning information. Then, a set distance value is added to and subtracted from each predicted positioning information to obtain a positioning area centered on the predicted positioning information. In this case, the vehicle's positioning area on the map can be a ring-shaped area.

[0106] In more possible implementations, the vehicle's driving data can also include the vehicle's driving direction. Then, when determining the vehicle's location area on the map based on the initial positioning information and wheel speed data in the driving data included in the test data package, the vehicle's driving distance can be determined based on the wheel speed data and the vehicle's driving time. Then, based on the vehicle's driving distance, driving direction, and initial positioning information, the vehicle's location area on the map can be determined.

[0107] In determining the vehicle's location area on the map based on the vehicle's driving distance, driving direction, and initial positioning information, a predicted positioning information can be determined first based on the sum of the vehicle's driving distance in the driving direction and the initial positioning information. Then, a set distance value is added to and subtracted from the predicted positioning information to obtain a positioning area centered on the predicted positioning information. At this time, the vehicle's positioning area on the map can be a line segment.

[0108] Step 102-1-2: From the candidate point cloud data corresponding to each candidate positioning information in the positioning area, determine the candidate point cloud data that matches the point cloud data, and determine the candidate positioning information corresponding to the candidate point cloud data as the first positioning information.

[0109] It should be noted that the positioning area includes multiple candidate positioning information, and each candidate positioning information corresponds to point cloud data (denoted as candidate point cloud data). Therefore, the computing device can compare the point cloud data included in the driving data with each candidate point cloud data to determine the candidate point cloud data that matches the point cloud data, and thus use the candidate positioning information corresponding to the candidate point cloud data as the first positioning information.

[0110] It should be noted that the positioning information may include position information and attitude information. Position information may include the vehicle's position coordinates in the set coordinate system, and attitude information may be used to indicate the angular relationship between the vehicle's position and the coordinate axes of the set coordinate system. Optionally, the set coordinate system may be any type of coordinate system, for example, the set coordinate system may be the Earth coordinate system.

[0111] The first positioning information can be denoted as ground truth(x, y, yaw). Here, x represents the vehicle's position coordinates along the x-axis of the set coordinate system, y represents the vehicle's position coordinates along the x-axis of the set coordinate system, and x and y together constitute the position information; yaw is the angle between the line connecting the vehicle's position and the origin of the coordinate system and the y-axis of the set coordinate system, also known as the yaw angle, and yaw represents the attitude information. The above is merely an exemplary form of positioning information. In more possible implementations, the positioning information can take other forms. For example, the position information can also be three-dimensional coordinates, and the attitude information can also include pitch and roll angles. This application does not limit the specific form of the positioning information.

[0112] For step 102, when determining a second location information of the vehicle based on each test data packet using the location algorithm to be tested, each test data packet can be input into the location algorithm to be tested. By running the location algorithm to be tested, the second location information corresponding to each test data packet is output, and multiple second location information of the vehicle is obtained. One second location information can be obtained based on one test data packet.

[0113] It should be noted that the description of the second positioning information can be found in the above embodiments, and will not be repeated here. Additionally, it should be noted that the format of the second positioning information must be consistent with that of the first positioning information to ensure the smooth progress of subsequent processes.

[0114] Additionally, it should be noted that the second location information and the first location information are in one-to-one correspondence. That is, a first location information and a second location information can be obtained based on a test data packet.

[0115] After obtaining the first positioning information and the second positioning information through the above process, a positioning error information can be determined in step 103 based on each first positioning information and the corresponding second positioning information.

[0116] It should be noted that, since positioning information can include position information and attitude information, positioning error information can include relative pose error and absolute trajectory error. The absolute trajectory error can include lateral absolute trajectory error (i.e., the error in the x-coordinate) and longitudinal absolute trajectory error (i.e., the error in the y-coordinate). Furthermore, when positioning information includes other types of information, positioning error information can also include other types of information, which this application does not limit.

[0117] Taking the positioning error information, which includes relative pose error and absolute trajectory error, as an example, for step 103, when determining a positioning error information based on each first positioning information and the corresponding second positioning information, it can be achieved in the following way:

[0118] For any first positioning information and the corresponding second positioning information, the absolute trajectory error is determined based on the first position information included in the first positioning information and the second position information included in the second positioning information, and the relative pose error is determined based on the first attitude information included in the first positioning information and the second attitude information included in the second positioning information.

[0119] In one possible implementation, when determining the absolute trajectory error based on the first position information included in the first positioning information and the second position information included in the second positioning information, the difference between the first position information and the second position information can be used as the absolute trajectory error. Similarly, when determining the relative pose error based on the first attitude information included in the first positioning information and the second attitude information included in the second positioning information, the difference between the first attitude information and the second attitude information can be used as the relative attitude error.

[0120] Through the above process, an absolute trajectory error and a relative attitude error can be determined based on each first positioning information and the corresponding second positioning information, which can be used as a positioning error information. Thus, multiple positioning error information can be obtained, and each test data packet can correspond to a positioning error information.

[0121] After determining the positioning error information corresponding to multiple test data packets through the above process, it is possible to determine whether the positioning accuracy of the positioning algorithm to be tested meets the positioning requirements based on the positioning error information corresponding to multiple test data packets.

[0122] In some embodiments, if the positioning error information corresponding to multiple test data packets meets a set condition, it can be determined that the positioning accuracy of the positioning algorithm to be tested meets the positioning requirements. For example, if the positioning error information corresponding to multiple test data packets is all less than a set error threshold, it can be determined that the positioning accuracy of the positioning algorithm to be tested meets the positioning requirements.

[0123] In other embodiments, if the positioning error information corresponding to the plurality of test data packets does not meet the set conditions, it is determined that the positioning accuracy of the positioning algorithm to be tested does not meet the positioning requirements. For example, if there is a positioning error information among the positioning error information corresponding to the plurality of test data packets that is greater than or equal to a set error threshold, it can be determined that the positioning accuracy of the positioning algorithm to be tested does not meet the positioning requirements.

[0124] The set error thresholds can include a first error threshold and a second error threshold. The first error threshold can correspond to the absolute trajectory error, and the second error threshold can correspond to the relative attitude error. Therefore, when determining whether the positioning error information corresponding to multiple test data packets meets the set conditions, it can be determined whether the absolute trajectory error of the multiple test data packets is less than the first error threshold and whether the relative attitude error of the multiple test data packets is less than the second error threshold. If the absolute trajectory error of the multiple test data packets is less than the first error threshold and the relative attitude error of the multiple test data packets is less than the second error threshold, then the positioning error information of the multiple test data packets can be determined to meet the set conditions. Conversely, if there is an absolute trajectory error greater than or equal to the first error threshold, or a relative attitude error greater than or equal to the second error threshold, then the positioning error information of the multiple test data packets does not meet the set conditions.

[0125] Through the above embodiments, the vehicle positioning algorithm accuracy detection method provided in this application can provide a full-link solution from analyzing the positioning problem of each candidate data packet, to finding a suitable test data packet for positioning algorithm accuracy detection, and then using the test data packet to detect the positioning accuracy of the vehicle positioning algorithm, so as to realize the evaluation of the accuracy of the positioning algorithm of autonomous vehicles, thereby ensuring the accuracy of the positioning position of autonomous vehicles.

[0126] In more possible implementations, after determining whether each test data packet passes the test based on the positioning error information of each test data packet, test result information can also be output. This test result information can be used to indicate the pass / fail status of multiple test data packets, as well as the test comparison between the positioning algorithm to be tested and at least one previously tested positioning algorithm.

[0127] The "test pass status" refers to whether the test data packet passes the test. If the test data packet passes the test, it means that the positioning error information corresponding to the test data packet is less than the set error threshold. Conversely, if the positioning error information corresponding to the test data packet is greater than or equal to the set error threshold, it can be determined that the test data packet fails the test.

[0128] By outputting test result information indicating the pass / fail status of multiple test data packets and the test comparison between the positioning algorithm to be tested and at least one previously tested positioning algorithm, the test result information output by the computing device or other devices that can provide visualization functions can be visualized. This allows relevant technicians to make a horizontal comparison of multiple positioning algorithms based on the displayed test result information, thereby identifying the positioning algorithm with better positioning performance.

[0129] Optionally, the test results information can also be categorized and displayed based on the location problem tags and environment tags of each test data package. For example, the test pass status of the same type of location problem tags and the test pass status of the same type of environment tags can be summarized so that relevant technical personnel can determine what kind of location problems are likely to occur in what kind of environment based on the categorized display results, thereby enabling targeted improvements to be made in the future.

[0130] See Figure 2 , Figure 2 This is a schematic diagram illustrating a display format of test result information according to an exemplary embodiment of this application, such as... Figure 2 As shown, taking the localization algorithm used in this detection as Algorithm No. 3 as an example, as follows... Figure 2The test results information shown includes the number of test data packets (i.e., the number of test bags) used to test the positioning accuracy of Algorithm 3, the test process time (i.e., the total test bag time, including the total time for acquiring test data packets and the test process), the overall test situation, and the classification display results of the test situation.

[0131] The overall test result refers to the pass / fail status of the multiple test data packets as a whole. Figure 2 As shown, the overall test results include test time, perfect pass rate (i.e., the proportion of the number of test data packets that pass the test to the total number of test data packets), average frequency (i.e., the test speed of the data packets), maximum lateral error (i.e., the maximum value among the lateral absolute trajectory errors of multiple absolute trajectory errors), maximum longitudinal error (i.e., the maximum value among the longitudinal absolute trajectory errors of multiple absolute trajectory errors), maximum angular deviation (i.e., the maximum value among the relative pose errors of multiple absolute trajectory errors), minimum lateral error (i.e., the minimum value among the lateral absolute trajectory errors of multiple absolute trajectory errors), minimum longitudinal error (i.e., the minimum value among the longitudinal absolute trajectory errors of multiple absolute trajectory errors), and minimum angular deviation (i.e., the minimum value among the relative pose errors of multiple absolute trajectory errors).

[0132] The test results can be categorized and displayed based on location problem tags and environment tags. The location problem tag-based results show the algorithm test status, including the data packet test pass rate for five location problem tags: perfect pass, initial location failure, automatic recovery after location deviation during movement, location failure during operation and no recovery, and location timeout during operation. This includes the number of test packets that passed the test and the pass rate for each of these five location problem tags. The environment tag-based results show the data packet test pass rate for five environment tags: sunny-daytime, sunny-nighttime, rainy-daytime, rainy-nighttime, and snowy-daytime. This also includes the number of test packets that passed the test and the pass rate for each of these five environment tags.

[0133] In addition, such as Figure 2 The test results also show a comparison between the current localization algorithm and at least one previously tested localization algorithm. For example... Figure 2 The test results information shown includes an algorithm selection control (i.e., a selection box labeled "Please select the algorithm to compare"). Technical personnel can use this control to select the algorithm from the selection box. Figure 2The device includes an algorithm selection control to select a positioning algorithm to be compared with the currently detected positioning algorithm. A technician can trigger the algorithm selection control so that the device can respond to the technician's trigger operation and display at least one detected positioning algorithm so that the technician can select from it.

[0134] in, Figure 2 The tested positioning algorithm used for comparison with algorithm 3 is algorithm 2. The test comparison between algorithm 3 and algorithm 2 includes the data packet test pass rate corresponding to the five positioning problem labels of algorithm 3 and algorithm 2, namely, the number of test data packets that passed the test and the test data packet pass rate corresponding to the five positioning problem labels.

[0135] In addition, such as Figure 2 The test results information shown includes a label selection control (i.e., a selection box with the text "Please select the cases to include"). Technical personnel can use this control to... Figure 2 The label selection control is set up to select the specific situation to be compared when comparing different algorithms (that is, the specific location problem label to be compared). The relevant technician can trigger the label selection control so that the device can respond to the trigger operation of the relevant technician and display at least one optional location problem label so that the relevant technician can select from it.

[0136] Figure 2 The location issue label selected by the relevant technical personnel was "location timeout during operation," therefore, Figure 2 The data displayed shows the average longitudinal error, average lateral error, and average offset angle of test data packets that were labeled as having location problems and had timed out during the test but had successfully passed the test.

[0137] Optionally, such as Figure 2 The test results also show the basic information of the data packets for Algorithm 3 and the environmental label information. The basic data packet information includes the localization problem label (i.e., problem description), test start time, test end time, average longitudinal error, average lateral error, longitudinal error offset, lateral error offset, average angle error, and angle error offset. The environmental label information includes weather conditions, vehicle position, site conditions, road surface conditions, and obstacle conditions (including whether there are static obstacles, what the static obstacles are, whether there are dynamic obstacles, and what the dynamic obstacles are).

[0138] Through such Figure 2The test results shown allow technical personnel to compare the algorithm 3 tested this time with previously tested algorithms (i.e., algorithm 2). This allows them to intuitively understand which test data packets passed the test successfully after the improvement algorithm, and which previously passed test data packets failed. Furthermore, environmental tags can be used to statistically analyze which scenarios are prone to which types of localization problems.

[0139] The accuracy detection method for the vehicle positioning algorithm provided in the above embodiments can be found in [reference needed]. Figure 3 , Figure 3 This is a framework diagram illustrating the accuracy detection process of a vehicle positioning algorithm according to an exemplary embodiment of this application, such as... Figure 3 As shown, the accuracy detection process of the vehicle positioning algorithm provided in the above embodiments can be divided into three main stages: data packet labeling, dataset collection, and algorithm evaluation. In the data packet labeling stage, driving data after data visualization processing is used to analyze each data packet. Based on the analysis results, each data packet is labeled. By traversing the labeled data packets, some representative or unique labels are identified, and these data packets are used as test data packets. Then, in the dataset construction stage, the positioning problem labels and environment labels of the test data packets are recorded. In the algorithm evaluation stage, the algorithm is evaluated based on multiple test data packets to generate an algorithm evaluation report.

[0140] Figure 3 The illustration shown is merely a procedural description of this application. For details on the specific implementation of each step in each stage, please refer to the above embodiments, which will not be repeated here.

[0141] Corresponding to the embodiments of the foregoing methods, this application also provides embodiments of the apparatus and the computing device on which it is applied.

[0142] like Figure 4 As shown, Figure 4 This is a block diagram illustrating an accuracy detection device for a vehicle positioning algorithm according to an exemplary embodiment of this application. The device includes:

[0143] The acquisition module 401 is used to acquire multiple test data packets, which include driving data collected during vehicle operation.

[0144] The determination module 402 is used to determine a first location information of the vehicle based on the driving data included in each test data packet and a pre-established map;

[0145] The determination module 402 is also used to determine a second positioning information of the vehicle based on each test data packet using the positioning algorithm to be detected;

[0146] The determining module 402 is also used to determine a positioning error information based on each first positioning information and the corresponding second positioning information;

[0147] The determination module 402 is also used to determine whether the positioning accuracy of the positioning algorithm to be tested meets the positioning requirements when the positioning error information corresponding to multiple test data packets meets the set conditions.

[0148] In some embodiments of this application, multiple test data packets are prepared in advance. These test data packets are labeled with a location problem tag and an environment tag. The location problem tag indicates the cause of the vehicle positioning error, and the environment tag indicates the environmental conditions during vehicle operation. The preparation process for the multiple test data packets includes:

[0149] Acquire driving data collected from at least one vehicle during its operation;

[0150] Based on the timestamps of the driving data, the collected driving data is segmented to obtain multiple candidate data packets;

[0151] Based on the visualization results of each candidate data packet, obtain the location problem label and environment label for each candidate data packet;

[0152] Candidate data packets whose location problem labels and environment labels meet the target conditions will be used as test data packets.

[0153] In some embodiments of this application, the driving data includes at least initial positioning information, point cloud data, and wheel speed data;

[0154] The determination module 402, when determining a first location information of the vehicle based on the driving data included in each test data packet and a pre-established map, is used to:

[0155] For any test data packet, the vehicle's location area on the map is determined based on the initial positioning information and wheel speed data in the driving data included in the test data packet.

[0156] From the candidate point cloud data corresponding to each candidate positioning information in the positioning area, determine the candidate point cloud data that matches the point cloud data, and determine the candidate positioning information corresponding to the candidate point cloud data as the first positioning information.

[0157] In some embodiments of this application, the positioning information includes position information and attitude information. The position information includes the vehicle's position coordinates in a set coordinate system, and the attitude information is used to indicate the angular relationship between the vehicle's position and the coordinate axes of the set coordinate system. The positioning error information includes relative pose error and absolute trajectory error.

[0158] The determining module 402, when determining a positioning error information based on each first positioning information and the corresponding second positioning information, is used to:

[0159] For any first positioning information and the corresponding second positioning information, the absolute trajectory error is determined based on the first position information included in the first positioning information and the second position information included in the second positioning information, and the relative pose error is determined based on the first attitude information included in the first positioning information and the second attitude information included in the second positioning information.

[0160] In some embodiments of this application, the determining module 402, when determining that the positioning accuracy of the positioning algorithm to be tested meets the positioning requirements when the positioning error information corresponding to multiple test data packets meets the set conditions, is used for:

[0161] If the positioning error information corresponding to multiple test data packets is less than the set error threshold, it is determined that the positioning accuracy of the positioning algorithm to be tested meets the positioning requirements.

[0162] In some embodiments of this application, the determining module 402 is further configured to determine that the positioning accuracy of the positioning algorithm to be tested does not meet the positioning requirements when the positioning error information corresponding to multiple test data packets does not meet the set conditions.

[0163] In some embodiments of this application, the device further includes:

[0164] The output module is used to output test result information, which indicates the pass / fail status of multiple test data packets and the test comparison between the positioning algorithm to be tested and at least one previously tested positioning algorithm.

[0165] The specific implementation process of the functions and roles of each module in the above device can be found in the implementation process of the corresponding steps in the above method, and will not be repeated here.

[0166] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of the solution in this specification according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0167] This application also provides a computing device, see [link to relevant documentation] Figure 5 , Figure 5This is a schematic diagram illustrating the structure of a computing device according to an exemplary embodiment of this application. Figure 5 As shown, the computing device includes a processor 510, a memory 520, and a network interface 530. The memory 520 stores computer instructions that can run on the processor 510. The processor 510 is used to implement the accuracy detection method of the vehicle positioning algorithm provided in any embodiment of this application when executing the computer instructions. The network interface 530 is used to implement input / output functions. In more possible implementations, the computing device may also include other hardware, which is not limited in this application.

[0168] This application also provides a computer-readable storage medium, which can take many forms, such as RAM (Random Access Memory), volatile memory, non-volatile memory, flash memory, storage drives (e.g., hard disk drives), solid-state drives, any type of storage disk (e.g., optical discs, DVDs), or similar storage media, or combinations thereof. Specifically, the computer-readable medium can also be paper or other suitable media capable of printing programs. A computer program is stored on the computer-readable storage medium, and when executed by a processor, the computer program implements the accuracy detection method of the vehicle positioning algorithm provided in any embodiment of this application.

[0169] This application also provides a computer program product, including a computer program that, when executed by a processor, implements a method for detecting the accuracy of a vehicle positioning algorithm provided in any embodiment of this application.

[0170] Those skilled in the art will understand that one or more embodiments of this specification can be provided as a method, apparatus, computing device, computer-readable storage medium, or computer program product. Therefore, one or more embodiments of this specification can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, one or more embodiments of this specification can take the form of a computer program product implemented on one or more computer-readable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-readable program code.

[0171] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments corresponding to computing devices are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0172] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of this application. In some cases, the actions or steps described in this application may be performed in a different order than those shown in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0173] The embodiments of the subject matter and functional operation described in this specification can be implemented in the following ways: digital electronic circuits, tangibly embodied computer software or firmware, computer hardware including the structures disclosed in this specification and their structural equivalents, or combinations thereof. Embodiments of the subject matter described in this specification can be implemented as one or more computer programs, i.e., one or more modules of computer program instructions encoded on a tangible, non-transitory program carrier for execution by a data processing device or for controlling the operation of a data processing device. Alternatively or additionally, the program instructions can be encoded on artificially generated propagation signals, such as machine-generated electrical, optical, or electromagnetic signals, which are generated to encode information and transmit it to a suitable receiving device for execution by an accuracy detection device of a vehicle positioning algorithm. The computer storage medium can be a machine-readable storage device, a machine-readable storage substrate, a random or serial access memory device, or combinations thereof.

[0174] The processing and logic flow described in this specification can be executed by one or more programmable computers that execute one or more computer programs to perform corresponding functions by operating on input data and generating output. The processing and logic flow can also be executed by dedicated logic circuitry—such as FPGAs (Field-Programmable Gate Arrays) or ASICs (Application-Specific Integrated Circuits), and the device can also be implemented as dedicated logic circuitry.

[0175] Suitable computers for executing computer programs include, for example, general-purpose and / or special-purpose microprocessors, or any other type of central processing unit. Typically, the central processing unit receives instructions and data from read-only memory and / or random access memory. The basic components of a computer include a central processing unit for implementing or executing instructions and one or more memory devices for storing instructions and data. Typically, a computer will also include one or more mass storage devices for storing data, such as disks, magneto-optical disks, or optical disks, or the computer will be operatively coupled to such mass storage devices to receive data from or transfer data to them, or both. However, a computer is not required to have such devices. Furthermore, a computer can be embedded in another device, such as a mobile phone, a personal digital assistant (PDA), a mobile audio or video player, a game console, a global positioning system (GPS) receiver, or a portable storage device such as a universal serial bus (USB) flash drive, to name a few.

[0176] Computer-readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media, and memory devices, such as semiconductor memory devices (e.g., EPROM, EEPROM, and flash memory devices), magnetic disks (e.g., internal hard disks or removable disks), magneto-optical disks, and CD-ROM and DVD-ROM disks. Processors and memory may be supplemented by or incorporated into dedicated logic circuitry.

[0177] While this specification contains numerous specific implementation details, these should not be construed as limiting the scope of any invention or the scope of the claims, but rather are primarily intended to describe features of specific embodiments of a particular invention. Certain features described in the various embodiments herein may also be implemented in combination in a single embodiment. Conversely, various features described in a single embodiment may also be implemented separately in various embodiments or in any suitable sub-combination. Furthermore, while features may function in certain combinations as described above and even initially claimed in this way, one or more features from a claimed combination may be removed from that combination in some cases, and a claimed combination may refer to a sub-combination or a variation thereof.

[0178] Similarly, although the operations are depicted in a specific order in the accompanying drawings, this should not be construed as requiring these operations to be performed in the specific order shown or sequentially, or requiring all illustrated operations to be performed to achieve the desired result. In some cases, multitasking and parallel processing may be advantageous. Furthermore, the separation of various system modules and components in the above embodiments should not be construed as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product or packaged into multiple software products.

[0179] Thus, specific embodiments of the subject matter have been described. Other embodiments are within the scope of this application. In some cases, the actions described in this application may be performed in a different order and still achieve the desired result. Furthermore, the processes depicted in the drawings are not necessarily shown in a specific order or sequence to achieve the desired result. In some implementations, multitasking and parallel processing may be advantageous.

[0180] Other embodiments of this specification will readily occur to those skilled in the art upon consideration of the specification and practice of the invention claimed herein. This specification is intended to cover any variations, uses, or adaptations that follow the general principles of this specification and include common knowledge or customary techniques in the art not claimed herein. That is, this specification is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope.

[0181] The above description is merely an optional embodiment of this specification and is not intended to limit this specification. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this specification shall be included within the scope of protection of this specification.

Claims

1. A method for detecting the accuracy of a vehicle positioning algorithm, characterized in that, The method includes: Acquire multiple test data packets, the test data packets including driving data collected during vehicle operation; Based on the driving data included in each test data packet and the pre-established map, a first positioning information of the vehicle is determined, and a second positioning information of the vehicle is determined based on each test data packet using the positioning algorithm to be detected. Based on each first positioning information and the corresponding second positioning information, a positioning error information is determined; If the positioning error information corresponding to the multiple test data packets meets the set conditions, it is determined that the positioning accuracy of the positioning algorithm to be tested meets the positioning requirements. The driving data includes at least initial positioning information, point cloud data, wheel speed data, the vehicle's driving time, and the vehicle's driving direction; determining a first positioning information of the vehicle based on the driving data included in each test data packet and a pre-established map includes: For any test data packet, the predicted positioning information of the vehicle is determined based on the initial positioning information, wheel speed data, vehicle travel time and vehicle travel direction in the driving data included in the test data packet. Based on the predicted positioning information and the set distance value, a positioning area is determined, wherein the positioning area is a line segment centered on the predicted positioning information; From the candidate point cloud data corresponding to each candidate positioning information in the positioning area, determine the candidate point cloud data that matches the point cloud data, and determine the candidate positioning information corresponding to the candidate point cloud data as the first positioning information; The multiple test data packets are pre-prepared and are labeled with location problem tags and environment tags. The location problem tags indicate the cause of the vehicle positioning error, and the environment tags indicate the environmental conditions during vehicle operation. The preparation process of the multiple test data packets includes: Acquire driving data collected from at least one vehicle during its operation; Based on the timestamps of the driving data, the collected driving data is segmented to obtain multiple candidate data packets; Based on the visualization results of each candidate data packet, obtain the location problem label and environment label for each candidate data packet; Candidate data packets whose location problem label and environment label satisfy the target conditions are used as test data packets.

2. The method according to claim 1, characterized in that, The positioning information includes position information and attitude information. The position information includes the vehicle's position coordinates in a set coordinate system. The attitude information is used to indicate the angular relationship between the vehicle's position and the coordinate axes of the set coordinate system. The positioning error information includes relative pose error and absolute trajectory error. The step of determining a positioning error information based on each first positioning information and the corresponding second positioning information includes: For any first positioning information and the corresponding second positioning information, the absolute trajectory error is determined based on the first position information included in the first positioning information and the second position information included in the second positioning information, and the relative pose error is determined based on the first attitude information included in the first positioning information and the second attitude information included in the second positioning information.

3. The method according to claim 1, characterized in that, The step of determining that the positioning accuracy of the positioning algorithm to be tested meets the positioning requirements when the positioning error information corresponding to the multiple test data packets meets the set conditions includes: If the positioning error information corresponding to the multiple test data packets is less than the set error threshold, it is determined that the positioning accuracy of the positioning algorithm to be tested meets the positioning requirements.

4. The method according to claim 1, characterized in that, After determining a positioning error based on each first positioning information and the corresponding second positioning information, the method further includes: If the positioning error information corresponding to the multiple test data packets does not meet the set conditions, it is determined that the positioning accuracy of the positioning algorithm to be tested does not meet the positioning requirements.

5. The method according to claim 1, characterized in that, The method further includes: Output test result information, which is used to indicate the pass status of the multiple test data packets and the test comparison between the positioning algorithm to be tested and at least one positioning algorithm that has been tested.

6. A device for detecting the accuracy of a vehicle positioning algorithm, characterized in that, The device includes: The acquisition module is used to acquire multiple test data packets, which include driving data collected during vehicle operation. The determination module is used to determine a first location information of the vehicle based on the driving data included in each test data packet and a pre-established map; The determining module is further configured to determine a second positioning information of the vehicle based on each test data packet using the positioning algorithm to be detected; The determining module is further configured to determine a positioning error information based on each first positioning information and the corresponding second positioning information; The determining module is further configured to determine, when the positioning error information corresponding to the plurality of test data packets meets the set conditions, whether the positioning accuracy of the positioning algorithm to be tested meets the positioning requirements. The driving data includes at least initial positioning information, point cloud data, wheel speed data, the vehicle's driving time, and the vehicle's driving direction; The determining module, when determining a first location information of the vehicle based on the driving data included in each test data packet and a pre-established map, is used to: For any test data packet, the predicted positioning information of the vehicle is determined based on the initial positioning information, wheel speed data, vehicle travel time and vehicle travel direction in the driving data included in the test data packet. Based on the predicted positioning information and the set distance value, a positioning area is determined, wherein the positioning area is a line segment centered on the predicted positioning information; From the candidate point cloud data corresponding to each candidate positioning information in the positioning area, determine the candidate point cloud data that matches the point cloud data, and determine the candidate positioning information corresponding to the candidate point cloud data as the first positioning information; The multiple test data packets are pre-prepared and are labeled with location problem tags and environment tags. The location problem tags indicate the cause of the vehicle positioning error, and the environment tags indicate the environmental conditions during vehicle operation. The preparation process of the multiple test data packets includes: Acquire driving data collected from at least one vehicle during its operation; Based on the timestamps of the driving data, the collected driving data is segmented to obtain multiple candidate data packets; Based on the visualization results of each candidate data packet, obtain the location problem label and environment label for each candidate data packet; Candidate data packets whose location problem label and environment label satisfy the target conditions are used as test data packets.

7. A computing device, characterized in that, The computing device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, it performs the operations performed by the accuracy detection method of the vehicle positioning algorithm as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a program that is executed by a processor as described in any one of claims 1 to 5, according to the accuracy detection method of the vehicle positioning algorithm.

Images