Positioning information processing method and device, electronic equipment and storage medium

Abstract

The invention provides a positioning information processing method and device, electronic equipment and a storage medium, and relates to the technical field of artificial intelligence, in particular to the field of computer vision, image processing and automatic driving. According to the specific implementation scheme, the method comprises the steps of determining road-level positioning information and a to-be-verified layer of a target vehicle; wherein the to-be-verified layer is a hierarchy of a road corresponding to the road-level positioning information in a multi-layer map; determining at least one verification result for the to-be-verified layer based on the sensing data and / or the positioning height of the target vehicle; and determining the validity of the road-level positioning information based on the at least one verification result of the to-be-verified layer.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, and in particular to the fields of computer vision, image processing and autonomous driving. Background Art

[0002] In recent years, autonomous driving technology has been widely improved, among which auxiliary functions such as automatic lane change have received widespread attention. At the same time, high-precision positioning, as a very critical part of assisted driving functions, can be roughly divided into the following two types according to assisted driving needs: one is to clarify the road where the main vehicle is traveling, and the second is to confirm the position of the main vehicle on the high-precision road; and among them, confirming the road position of the main vehicle is a basic work in high-precision positioning, and it is also a key factor to ensure that the vehicle can drive smoothly on the road, change lanes, and pass intersections in the high-precision map. Summary of the invention

[0003] The present disclosure provides a method, device, electronic device and storage medium for processing positioning information.

[0004] According to one aspect of the present disclosure, a method for processing positioning information is provided, including:

[0005] Determine the road-level positioning information and the layer to be verified of the target vehicle; wherein the layer to be verified is the layer of the road corresponding to the road-level positioning information in the multi-layer map;

[0006] Determine at least one verification result for the layer to be verified based on the sensing data and / or positioning height of the target vehicle;

[0007] Based on at least one verification result of the layer to be verified, the validity of the road-level positioning information is determined.

[0008] According to another aspect of the present disclosure, a device for processing positioning information is provided, including:

[0009] The module for determining information to be verified is used to determine the road-level positioning information and the layer to be verified of the target vehicle; wherein the layer to be verified is the layer of the road corresponding to the road-level positioning information in the multi-layer map;

[0010] A verification module, configured to determine at least one verification result for the layer to be verified based on the sensing data and / or positioning height of the target vehicle;

[0011] The validity determination module is used to determine the validity of the road-level positioning information based on at least one verification result of the layer to be verified.

[0012] According to another aspect of the present disclosure, there is provided an electronic device, comprising:

[0013] at least one processor; and

[0014] a memory communicatively connected to the at least one processor; wherein,

[0015] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute any method in the embodiments of the present disclosure.

[0016] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute any method according to the embodiments of the present disclosure.

[0017] According to another aspect of the present disclosure, a computer program product is provided, including a computer program, which implements any method according to the embodiments of the present disclosure when executed by a processor.

[0018] According to the technical solution of the embodiment of the present disclosure, after determining the road-level positioning information of the target vehicle, it is necessary to verify the level of the road corresponding to the road-level positioning information according to the perception data and / or positioning height, and determine the validity of the road-level positioning information based on the verification result. Based on this, the technical solution of the embodiment of the present disclosure can be applied in multi-layer map scenarios to avoid the situation where the road-level positioning information is misplaced, thereby improving the accuracy of the road-level positioning information.

[0019] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0021] Figure 1 is a schematic diagram of a method for processing positioning information provided by an embodiment of the present disclosure;

[0022] Figure 2 is a schematic diagram of an application example of the present disclosure;

[0023] Figure 3 is a schematic diagram of another application example of the present disclosure;

[0024] Figure 4 is a schematic diagram of another application example of the present disclosure;

[0025] Figure 5 is a schematic diagram of another application example of the present disclosure;

[0026] Figure 6 is a schematic block diagram of a positioning information processing device provided by an embodiment of the present disclosure;

[0027] Figure 7 is a schematic block diagram of a positioning information processing device provided by another embodiment of the present disclosure;

[0028] Figure 8 The present invention is a block diagram of an electronic device for implementing the method for processing positioning information according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0029] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope of the present disclosure. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0030] As the basic information element of current high-precision positioning output, road-level positioning mainly uses high-precision topological information and lane perception information to track high-precision roads to confirm the location of the vehicle. This positioning method that relies on high-precision map topology will inevitably be affected by the accuracy and completeness of high-precision maps. Especially in complex and ambiguous scenarios such as multi-layer roads, misjudgment of road-level positioning will lead to safety issues such as abnormal vehicle speed and wrong lane change.

[0031] Specifically, most of the current road-level positioning algorithms are based on probability inference based on high-precision map topology, such as end-to-end road-level based on Hidden Markov Model (HMM) algorithm. These solutions have high accuracy and generalization in single-layer road scenarios, but for complex road scenarios, especially multi-layer scenarios and scenarios where high-precision maps are restored after interruption, the recursive algorithm based on high-precision topology cannot accurately estimate the layer number of the main vehicle, or when the current main vehicle position is offset, it is easy to have a mismatch. Once the layer is mismatched, the lack of a fault detection module cannot promptly identify whether the vehicle is in an abnormal state, resulting in autonomous driving driving along the wrong map, especially in scenarios with high distinction between upper and lower layers. Incorrect high-precision map guidance may lead to incorrect lane changes within the high-precision, ultimately leading to serious driving problems.

[0032] The disclosed embodiment provides a method for processing positioning information, which can be used to verify the layer where the vehicle is located in complex scenarios to output valid road-level positioning information. Unlike other road-level positioning solutions that rely solely on high-precision maps, the disclosed embodiment uses one or more of altitude information, perception information, and map matching information to distinguish different layers to ensure the accuracy of the output road-level positioning information. For example, the accuracy of the output road positioning in the initialization state can be guaranteed, and the road-level positioning can be actively restarted when a layer mismatch occurs, to further improve the road-level accuracy.

[0033] Figure 1 A schematic diagram of a method for processing positioning information provided by an embodiment of the present disclosure is shown. The method can be applied to a positioning information processing device, which can be deployed in an electronic device. The electronic device is, for example, a single-machine or multi-machine terminal, server or other processing device. Optionally, the electronic device can be a device in a target vehicle, wherein the target vehicle is a vehicle that applies a road-level positioning service, which can be referred to as a main vehicle in some examples. In some possible implementations, the method can also be implemented by a processor calling computer-readable instructions stored in a memory. Figure 1 As shown, the method may include the following steps S110 to S130.

[0034] S110, determining the road-level positioning information of the target vehicle and the layer to be verified; wherein the layer to be verified is the layer of the road corresponding to the road-level positioning information in the multi-layer map;

[0035] S120, determining at least one verification result for the layer to be verified based on the sensing data and / or positioning height of the target vehicle;

[0036] S130. Determine the validity of the road-level positioning information based on at least one verification result of the layer to be verified.

[0037] For example, in the above step S110, the road-level positioning information may be calculated based on the road topology information provided by the high-precision map using a preset road-level positioning algorithm. For example, the road-level positioning information may be determined using an HMM algorithm. Optionally, the road-level positioning information may be the ID (Link-ID) of a road segment in the road.

[0038] Exemplarily, in a multi-layer road scenario, the high-precision map includes multiple layers of maps, and the road-level positioning information is used to characterize a road section on a road in one of the layers of the multi-layer map. In the disclosed embodiment, the layer of the road in the multi-layer map, that is, the layer corresponding to the road-level positioning information, is used as the layer to be verified. For example, the multi-layer road scenario includes two layers of roads, namely, urban roads and highways. When the road-level positioning information of the target vehicle is determined to be the ID of a section of the urban road based on the road-level positioning algorithm, the urban road can be used as the layer to be verified for subsequent verification.

[0039] In the disclosed embodiment, the perception data of the target vehicle may include data collected by a sensor device on the target vehicle, wherein the sensor device is, for example, an image acquisition device (such as a camera), a radar, etc. Exemplarily, the perception data may include a perception image and / or a 3D point cloud.

[0040] In the disclosed embodiment, the positioning height of the target vehicle can be determined based on a positioning system, such as GNSS. For example, the global positioning posture of the target vehicle can be obtained based on one or more information such as the positioning system, the posture sensor on the target vehicle, the perception data, and the posture of the sensor device that collects the perception data. The global positioning posture can include information such as the longitude, latitude, heading angle, and altitude of the target vehicle, and the altitude information is the above-mentioned positioning height.

[0041] Optionally, in the above step S120, the layer to be verified can be verified in combination with the map of the layer to be verified. Exemplarily, one or more verification results of the layer to be verified can be determined based on the perception data of the target vehicle and the map of the layer to be verified. Alternatively, one or more verification results of the layer to be verified can be determined based on the positioning height of the target vehicle and the map of the layer to be verified. Alternatively, one or more verification results of the layer to be verified can be determined based on the perception data, positioning height and map of the layer to be verified of the target vehicle.

[0042] For example, step S120 may include two parts of verification, one part of which uses the perception data of the target vehicle and the map of the layer to be verified to determine one or more verification results, and obtains the verification result of this part based on the one or more verification results; the other part uses the positioning height of the target vehicle and the map of the layer to be verified to determine the verification result of this part.

[0043] For another example, step S120 may include a three-part verification, wherein the first part uses the perception data of the target vehicle and the map of the layer to be verified to determine one or more verification results; the second part uses the perception data of the target vehicle and the map of the layer to be verified to determine the verification result of this part; and the third part uses the perception data of the target vehicle and multiple layers of maps to determine a verification result.

[0044] Optionally, in the above step S130, any method may be adopted to perform a comprehensive judgment based on various verification results to determine the validity of the road-level positioning information.

[0045] For example, a numerical value (such as 0 or 1) can be used to represent each verification result, and a weight can be set for each partial verification in step S120. The comprehensive verification result is obtained by weighted averaging. When the value of the comprehensive verification result is greater than or equal to a preset threshold, the road-level positioning information is determined to be valid; when the value of the comprehensive verification result is less than the preset threshold, the road-level positioning information is determined to be invalid.

[0046] For another example, a multi-source voting system may be used, and when the majority of verification results in at least one verification result indicate that the verification is passed, the road-level positioning information is determined to be valid, otherwise the road-level positioning information is determined to be invalid.

[0047] In some exemplary application scenarios, road positioning information can be applied to downstream modules such as navigation and autonomous driving decision-making. The validity of road-level positioning information is determined according to the embodiments of the present disclosure. If the road-level positioning information is valid, the road-level positioning information can be output to the downstream module; if the road-level positioning information is invalid, the road-level positioning information will not be output to the downstream module.

[0048] Optionally, the road-level positioning information is calculated in real time. Each determination of the road-level positioning information can be based on a frame of data (e.g., a frame of perception data, a frame of 3D point cloud) or determined for a moment. When the road-level positioning information corresponding to a single frame of data fails, the downstream module can continue processing based on the previous decision information, thereby avoiding the use of erroneous information to affect the processing of the downstream module. When multiple consecutive road positioning information corresponding to multiple consecutive frames of data fail, the downstream module can optionally issue an alarm; and / or, the road-level positioning algorithm can be restarted to reinitialize the algorithm and obtain accurate road positioning information.

[0049] It can be seen that according to the above method of the embodiment of the present disclosure, after determining the road-level positioning information of the target vehicle, it is necessary to verify the level of the road corresponding to the road-level positioning information according to the perception data or positioning height, and determine the validity of the road-level positioning information based on the verification result. Based on this, the technical solution of the embodiment of the present disclosure can be applied in multi-layer map scenarios to avoid the situation where the road-level positioning information is misplaced, thereby improving the accuracy of the road-level positioning information. In some application scenarios, the decision-making accuracy of downstream modules such as navigation and autonomous driving can be improved accordingly.

[0050] In some embodiments, the above step S120, determining at least one verification result for the layer to be verified based on the sensing data and / or positioning height of the target vehicle, includes:

[0051] Based on the raster map corresponding to the perception data and the raster map corresponding to each layer of the multi-layer map, determining the comparison features between the perception data and each layer of the map;

[0052] Based on the comparison features between the perception data and each layer of the map, determine the layer in the multi-layer map that matches the perception data;

[0053] When the layer matching the perception data is the layer to be verified, it is determined that the first verification result of the layer to be verified is verification passed.

[0054] In the disclosed embodiments, a raster map is an image represented by a pixel array, and may also be referred to as a dot map, a bitmap, etc. In practical applications, the perception data may be in the form of a vector map or a point cloud, and by rasterizing the perception data, a raster map corresponding to the perception data may be obtained. For each layer of a multi-layer map, the map may be converted into a raster map based on the global positioning posture of the target vehicle. For example, based on the longitude, latitude, and heading angle in the global positioning posture, partial area information in the map may be projected into the image space to obtain a corresponding raster map. By obtaining the perception data and the raster map corresponding to each layer of the map, the perception data and each layer of the map may be compared based on data in the same form.

[0055] Exemplarily, the comparison feature between the perception data and each layer of the map may be related to the difference information, offset, etc. between the perception data and each layer of the map, so that the comparison feature may characterize whether the perception data and each layer of the map match. Exemplarily, the comparison feature may be a statistical feature (such as mean, variance, maximum value, minimum value, etc.) obtained based on multiple difference information after calculating the difference information between the perception data and each layer of the map multiple times.

[0056] Exemplarily, the level that matches the perception data can be the level that is most similar to the perception data or has the smallest difference based on the comparison features. In the case that the level that matches the perception data is the layer to be verified, it indicates that the road information represented by the map of the layer to be verified matches the road environment observed by the perception data. Therefore, the layer to be verified is reliable, and the first verification result can be determined to be passed. Optionally, in the case that the level that matches the perception data is not the layer to be verified, it indicates that the road information represented by the map of the layer to be verified does not match the road environment observed by the perception data, and the first verification result of the layer to be verified can be determined to be verification failed.

[0057] According to the above embodiment, by converting the perception data and each layer of the map into a raster map, the perception data and each layer of the map can be compared based on data in the same form, and the layer matching the perception data can be determined, so that the perception data can be fully utilized to verify the layer to be verified, thereby improving the accuracy of the verification results and correspondingly improving the accuracy of the road-level positioning information finally outputted.

[0058] In some embodiments, based on the grid map corresponding to the perception data and the grid map corresponding to each layer of the multi-layer map, determining the comparison features between the perception data and each layer of the map includes:

[0059] Calculate the difference information between the raster map corresponding to the perception data and the raster map corresponding to the i-th layer map in the multi-layer map under different offset modes; where i is a positive integer, and i is less than or equal to the number of layers of the multi-layer map;

[0060] Based on the difference information between the raster map corresponding to the perception data and the raster map corresponding to the i-th layer map under different offset modes, the variance of the difference information between the perception data and the i-th layer map is determined.

[0061] The i-th layer map can be any layer map in the multi-layer map, or any level map. Optionally, for each layer map in the multi-layer map, the comparison features between the perception data and the map can be obtained in a similar manner to the i-th layer map, that is, the value of i can be any value from 1 to the number of layers.

[0062] In the above embodiment, the raster image corresponding to the perception data and the raster image corresponding to the map can be offset based on different offset methods to determine the correspondence between the pixels in the two raster images, and the difference information is calculated based on the correspondence. The difference in pixel values ​​of the corresponding pixels in the two raster images is superimposed to obtain the difference information between the two raster images.

[0063] Optionally, different offset methods can be based on different offsets to offset the raster map. Exemplarily, when the offset between the raster map corresponding to the perception data and the raster map corresponding to the map is (x, y), the two are offset horizontally by x and vertically by y, and the pixel point with coordinates (i, j) in the raster map corresponding to the perception data and the pixel point with coordinates (i-x, j-y) in the raster map corresponding to the map have a corresponding relationship. For example, the first offset method is to offset the raster map corresponding to the perception data and the raster map corresponding to the map based on the offset (1, 0), and the second offset method is to offset the raster map corresponding to the perception data and the raster map corresponding to the map based on the offset (2, 0). By analogy, 10 offset methods can be used to establish the offset relationship between the raster map corresponding to the perception data and the raster map corresponding to the map, thereby calculating 10 times of difference information, and based on the 10 times of difference information, determine the variance of the difference information, and use the variance as the comparison feature.

[0064] In summary, the above-mentioned difference information variance can reflect the stability of the similarity between the raster map corresponding to the perception data and the raster map corresponding to the map under different offset modes. When the difference information variance is small, it indicates that there is a stable similarity under different offset modes, that is, the two raster maps may have more corresponding information. In this way, using the difference information variance as a comparison feature can accurately measure whether the perception data matches the map, so as to use the perception data to accurately verify the layer to be verified, improve the accuracy of the verification results, and correspondingly improve the accuracy of the final output road-level positioning information.

[0065] In some embodiments, based on the comparison features between the perception data and each layer of the map, determining the layer in the multi-layer map that matches the perception data includes:

[0066] Based on the comparison features between the perception data and each layer of the map, the maximum and minimum values ​​of the comparison features are determined;

[0067] If the maximum and minimum values ​​of the compared features meet the preset gap requirement, the level corresponding to the minimum value in the multi-layer map is determined as the level that matches the perception data.

[0068] Taking the comparison feature including difference information variance as an example, if the multi-layer map includes a layer of urban road map and a layer of highway map, and the difference information variance corresponding to the urban road map is the smallest, and the difference information variance corresponding to the highway map is the largest, and the gap requirements are met between the two, then the layer to which the urban road map belongs is taken as the layer that matches the perception data.

[0069] For example, the gap requirement is that the distance between the maximum value and the minimum value (or the difference between the maximum value and the minimum value) is greater than a preset threshold. Thus, when the gap requirement is met, it indicates that there is a clear distinction between the multi-layer maps.

[0070] Optionally, if the maximum and minimum values ​​of the compared features meet a preset gap requirement, the level matching the sensed data is not output, and accordingly, the verification method is invalid and the verification result is not output. In this way, the accuracy of the verification result can be guaranteed.

[0071] According to the above embodiment, when there is a clear distinction between multiple layers of maps, the layer with smaller comparison features is used as the layer that matches the perception data, so that the layer that matches the perception data can be accurately determined, and then the layer to be verified can be accurately verified, thereby improving the accuracy of the verification results and correspondingly improving the accuracy of the road-level positioning information finally outputted.

[0072] In order to facilitate understanding of the above technical solution, a specific application example is provided below. In this application example, a verification method for the verification layer includes:

[0073] S21: Obtain all high-precision maps near the global positioning of the main vehicle, and stratify them according to topology or road level.

[0074] S22: Based on the global positioning posture of the main vehicle, high-precision maps of different layers are converted into raster maps respectively. For example, high-precision maps of different layers include urban road maps and highway maps, so raster maps hd_grid1 representing urban roads and raster maps hd_hrid2 representing highways are obtained respectively.

[0075] S23: rasterize the perception data to obtain a grid map percep_grid corresponding to the perception data.

[0076] S24: Calculate the histogram distribution in layers to obtain the deviation values ​​and variances of different layers.

[0077] Specifically, the histogram traversal is used to obtain the histogram distribution corresponding to percep_grid and hd_hrid1, and the histogram distribution corresponding to percep_grid and hd_grid2. The histogram distribution here contains the difference information calculated at different offsets between the raster image representing the map and the raster image of the perception data. Specifically, the histogram distribution includes multiple SSD information, each SSD corresponds to an offset. For example, when the offset is (x, y), the SSD is calculated as follows:

[0078]

[0079] in, is the pixel value of pixel point (i, j) in the grid map percep_grid of the perception data, is the credibility of the point (which can be understood as weight); It is the pixel value of the pixel point (i - x, i - y) in the raster map hd_grid representing the map, which is the credibility (which can be understood as weight) of this point. Among them, and can be preset or calculated according to the algorithm.

[0080] Based on this histogram distribution, the deviation value hd offset1 between the urban road map and the perception data, as well as the SSD variance hd cov1 can be obtained, and the deviation value hd offset2 between the highway road map and the perception data, as well as the SSD variance hd_cov2 can be obtained. Among them, the deviation value hd offset1 between the urban road map and the perception data can be the maximum SSD value in the histogram distribution corresponding to percep_grid and hd_grid1; the deviation value hd offset2 between the highway road map and the perception data can be the maximum SSD value in the histogram distribution corresponding to percep_grid and hd_grid2.

[0081] S25: Split - level check.

[0082] Specifically, obtain the minimum value min_cov and the maximum value max_cov in the variances hd cov1 and hd cov2 , and determine the corresponding map levels of the two, denoted as max_roadtype and min_roadtype respectively;

[0083] If min_cov < max_cov * ε (ε is a decimal) and the layer to be checked is min_roadtype, then the layer to be checked passes the check;

[0084] If min_cov < max_cov * ε and the layer to be checked is min_roadtype, then the layer to be checked fails the check or is said to fail the check;

[0085] If min_cov ≥ max_cov * ε, then this check method fails and there is no output.

[0086] S26: Store the check result in the buffer.

[0087] The above example provides a check method. Other check methods are provided through more embodiments below.

[0088] In some embodiments, based on the perception data and / or positioning height of the target vehicle, at least one check result for the layer to be checked is determined, including:

[0089] Based on the perception data of the target vehicle, determining a first measurement result of the current target information; wherein the target information includes a road width and / or a distance from the target vehicle to a single side of the roadside;

[0090] Determine a second measurement result for the target information based on a map corresponding to the layer to be verified;

[0091] Based on the difference between the current first measurement result for the target information and the current second measurement result for the target information, a second verification result for the layer to be verified is determined.

[0092] In the disclosed embodiment, the first measurement result indicates the measurement result obtained based on the perception data. The second measurement result indicates the measurement result obtained based on the map. That is, for target information related to the road surface, such as road width and the distance from the vehicle to the curb, the perception data and the map corresponding to the layer to be verified are used to perform measurements respectively, and the first measurement result corresponding to the perception data and the second measurement result corresponding to the layer to be verified are obtained, and the difference between the two is used to determine the second verification result. For example, if the difference is less than a preset threshold, the second verification result is determined to be a passed verification; if the difference is greater than the preset threshold, the second verification result is determined to be a failed verification.

[0093] According to the above embodiment, by using the perception data and the map corresponding to the layer to be verified to respectively measure the target information, and using the difference between the measurement results to determine the second verification result, it is possible to fully utilize the perception data to verify the layer to be verified, thereby improving the accuracy of the verification results and correspondingly improving the accuracy of the road-level positioning information finally outputted.

[0094] In some embodiments, based on the perception data of the target vehicle, determining a first measurement result currently for the target information includes:

[0095] Based on the perception data of the target vehicle, determine the distance from the target vehicle to the left boundary of the road and the distance from the target vehicle to the right boundary of the road;

[0096] Based on the distance from the target vehicle to the left boundary of the road and the distance from the target vehicle to the right boundary of the road, a first measurement result of the current road width is determined.

[0097] Exemplarily, the left boundary and the right boundary of the road can be identified based on the perception data of the target vehicle, such as the perception image, and the coordinate conversion relationship between the perception image and the real world can be used to obtain the position of the left boundary and the right boundary of the road in the real world. Based on the position and the positioning information of the target vehicle, the distance from the target vehicle to the left boundary of the road and the distance from the target vehicle to the right boundary of the road can be determined, and then the first measurement result of the road width can be obtained based on the sum of the two.

[0098] According to the above embodiments, the problem that the perception data does not contain road width information can be overcome, and the road width can be calculated using the perception data to provide more diverse target information, support the verification of the layer to be verified, improve the accuracy of the verification results, and correspondingly improve the accuracy of the road-level positioning information finally outputted.

[0099] In some embodiments, based on the perception data of the target vehicle, determining the current first measurement result for the target information also includes: based on the perception data of the target vehicle (such as a perception image), identifying a single-side curb in the road (such as a left-side curb) to obtain the position information of the single-side curb, and determining the distance from the target vehicle to the single-side curb based on the position and the positioning information of the target vehicle.

[0100] In some embodiments, determining a second verification result for the layer to be verified based on a difference between a current first measurement result for the target information and a current second measurement result for the target information includes:

[0101] Determine, based on the data in the buffer, whether a difference between a first measurement result for the target information at a historical moment and a second measurement result for the target information at a historical moment is less than a first threshold;

[0102] If the difference between the first measurement result for the target information at a historical moment and the second measurement result for the target information at a historical moment is less than a first threshold, and the difference between the current first measurement result for the target information and the current second measurement result for the target information is less than a second threshold, then the second verification result for the layer to be verified is determined to be passed.

[0103] Optionally, the number of the above historical moments can be multiple. If in n-1 historical moments (corresponding to n-1 frames of data in the buffer), the difference between the first measurement result based on the perception data and the second measurement result based on the map is less than the first threshold, and the difference between the current (corresponding to the current frame data) first measurement result and the second measurement result based on the map is less than the second threshold, that is, the difference between the first measurement result and the second measurement result of n consecutive frames is less than the preset threshold, then the verification passes.

[0104] Optionally, the first threshold and the second threshold may be the same or different.

[0105] According to the above embodiment, combined with the historical moment data stored in the buffer, it is possible to accurately identify whether there is a continuous deviation between the perception data and the map data, so that the verification layer can be accurately verified, thereby improving the accuracy of the verification results and correspondingly improving the accuracy of the road-level positioning information finally outputted.

[0106] In some embodiments, based on the sensing data and / or positioning height of the target vehicle, determining at least one verification result for the layer to be verified includes:

[0107] Detect stop line based on the perception data of the target vehicle;

[0108] Based on the distance between the target vehicle and the stop line and the road type of the layer to be verified, a third verification result for the layer to be verified is determined.

[0109] Exemplarily, the perception data includes a perception image, and the stop line can be detected by image detection to obtain the position information of the stop line in the image. The position information of the stop line in the real world is determined based on the position information of the stop line in the image and the coordinate conversion relationship between the image and the real world. Based on the position information and the global positioning of the target vehicle, the distance between the target vehicle and the stop line can be determined.

[0110] Since different road types correspond to different stop line features, the above embodiment determines the third verification result for the layer to be verified based on the distance between the target vehicle and the stop line and the road type of the layer to be verified, and can provide a variety of verification methods, thereby utilizing the combination of multiple verification methods to improve the accuracy of the verification results, and correspondingly improve the accuracy of the road-level positioning information finally outputted.

[0111] In some embodiments, based on the distance between the target vehicle and the stop line and the road type of the layer to be verified, determining a third verification result for the layer to be verified includes:

[0112] If the distance between the target vehicle and the stop line is less than the third threshold value, and the road type of the layer to be verified is an urban road, the third verification result for the layer to be verified is verification passed;

[0113] and / or,

[0114] If the distance between the target vehicle and the stop line is greater than the fourth threshold value, and the road type of the layer to be verified is a highway, the third verification result for the layer to be verified is verification passed.

[0115] Optionally, the third threshold value and the fourth threshold value may be the same, for example, both are 400 meters. Alternatively, the third threshold value and the fourth threshold value may be different, for example, the third threshold value is 400 meters and the fourth threshold value is 800 meters.

[0116] Optionally, if the distance between the target vehicle and the stop line is greater than or equal to a third threshold value, and the road type of the layer to be verified is an urban road, the third verification result for the layer to be verified is verification failure.

[0117] Optionally, if the distance between the target vehicle and the stop line is less than or equal to a fourth threshold value, and the road type of the layer to be verified is a highway, the third verification result for the layer to be verified is verification failure.

[0118] Since the distance between vehicles and stop lines in urban roads is not too far, while the distance between vehicles and stop lines in highways is often far or even non-existent, if the distance between the target vehicle and the stop line is less than the third threshold and the layer to be verified is an urban road, the verification passes; if the distance between the target vehicle and the stop line is greater than the fourth threshold and the layer to be verified is a highway, the verification passes. This can guarantee the accuracy of the verification results to a certain extent, and accordingly improve the accuracy of the road-level positioning information finally outputted.

[0119] In some embodiments, based on the sensing data and / or positioning height of the target vehicle, determining at least one verification result for the layer to be verified includes:

[0120] Determine, based on the map corresponding to the layer to be verified, a mean height value of at least one map element within a preset range of the road-level positioning information;

[0121] Based on the difference between the height average and the positioning height of the target vehicle, a fourth verification result for the layer to be verified is determined.

[0122] Exemplarily, the at least one map element within a preset range of the road-level positioning information may include a stop line, a curb, a sidewalk, or other map elements near the target vehicle that are close to the height of the road surface.

[0123] Exemplarily, if the difference between the height average and the positioning height of the target vehicle is less than a certain value, the fourth verification result can be determined as a passed verification; otherwise, the fourth verification result is determined as a failed verification.

[0124] According to the above embodiment, the global positioning information (including positioning height) can be fully utilized to verify the layer to be verified, thereby improving the accuracy of the verification result and correspondingly improving the accuracy of the road-level positioning information finally outputted.

[0125] In some embodiments, based on the difference between the height average and the positioning height of the target vehicle, determining a fourth verification result for the layer to be verified includes:

[0126] When the difference between the height mean and the positioning height of the target vehicle is less than a fifth threshold, the fourth verification result for the layer to be verified is determined to be passed; wherein the fifth threshold is determined based on the variance of the heights of each map element.

[0127] Exemplarily, the fifth threshold may be a multiple of the variance of the height.

[0128] Optionally, when the difference between the height mean and the positioning height of the target vehicle is greater than a sixth threshold, the fourth verification result for the layer to be verified is determined to be a verification failure. The sixth threshold may be the same as the fifth threshold, or greater than the fifth threshold. Exemplarily, the sixth threshold may also be a multiple of the variance.

[0129] Optionally, when the height mean is greater than or equal to the fifth threshold and less than or equal to the sixth threshold, it is determined that the verification has failed, that is, no verification result is output.

[0130] For example, the fifth threshold is 3 times the variance of the height, and the sixth threshold is 5 times the variance of the height. The average height of the map elements around the road segment located by the road-level positioning information is height_avg, the variance is σ, and the positioning height of the target vehicle is fusion_height; then the verification result frame status is determined as follows:

[0131] frame status =GOOD,if height diff <3*σ;

[0132] frame status =BAD,if height diff >5*σ;

[0133] frame status =NONE,if height diff >3*σand height diff <5*σ;

[0134] where height diff =‖fusion height ―height avg ‖;

[0135] Among them, frame status =GOOD means the verification is passed; frame status =BAD means verification failed; frame status =NONE means verification failed and no result is output.

[0136] According to the above embodiment, the fifth threshold is determined based on the variance of the heights of each map element, and the fifth threshold can be adjusted according to actual conditions, so that the verification based on the fifth threshold is more accurate, and the accuracy of the road-level positioning information finally outputted is correspondingly improved.

[0137] A variety of verification methods are introduced above through multiple embodiments. It should be noted that the above-mentioned multiple verification methods can be implemented independently or in combination. For example, two, three or four of the verification methods can be used at the same time. As described above, there can also be multiple comprehensive judgment methods based on multiple verification results, such as weighted averaging, multi-source voting mechanism, etc., which will not be elaborated here. For ease of understanding, a specific application example is provided below.

[0138] Figure 3 This is a schematic diagram of the application example. In this application example, multi-source elements such as perceptual visual elements, high-precision height, and global positioning height are used to monitor the input of different layers of the current complex scene. The final monitoring result adopts a multi-source voting system, and the winner is the winner. That is, when most monitoring results (verification results) are passed, it indicates that the layer to be verified and the corresponding road-level positioning information are correct, and are output to the downstream path planning.

[0139] Specifically, Figure 3 The verification methods shown include sensing state monitoring (sensing width, sensing left boundary, stop line element), high-precision height state monitoring, and multi-layer histogram state monitoring. Each state monitoring has three states (GOOD, NONE, BAD), which respectively indicate verification pass, failure, and failure.

[0140] Specifically, the perception state monitoring is mainly composed of three parts of perception, namely, the perception width, the perception left boundary, and the stop line element. The three parts output the corresponding verification results respectively, that is, three corresponding verification results are obtained. If more than two of them pass the verification, the verification result of the perception state monitoring is GOOD. If all three verification results fail, the verification result of the perception state monitoring is BAD. If only one condition succeeds, the verification result of the perception state monitoring is NONE. The following is a detailed explanation of the usage of each element:

[0141] 1. Comparison of perceived and high-precision width differences: Calculate the sum of the distances from the vehicle to the left and right boundaries of the perception and the difference in road width from the high-precision. If the width difference of n frames in the buffer is less than 2.5m, the verification is considered successful.

[0142] 2. Comparison of distance from left curb: Calculate the difference between the distance from the vehicle to the perceived left curb and the distance from the vehicle to the high-precision left road boundary. If the distance difference is less than 3.0m for n frames in the buffer, the verification is considered successful.

[0143] 3. Stop line distance: Calculate the distance from the main vehicle to the perceived stop line. If the distance from the main vehicle to the stop line in the current frame is greater than 400m, the current frame count is GOOD, otherwise the count is bad; (the definition of good and bad is set according to the highway standard). At the same time, if the current verification result is an urban scene, if the distance from the main vehicle to the stop line is less than 400 meters for n consecutive frames of perception, the stop line status is set to GOOD. The BAD state judgment corresponding to the perception state is relatively loose in urban scenes. There is no need to check the stop line. Only the perception width and left edge verification are required; because there are obstructions in the city, it may not be possible to accurately detect the stop line.

[0144] The height status monitoring mainly obtains the height mean height_avg and variance σ of the map elements (stop lines, sidewalks, etc.) around the road section where the road-level positioning result is located, as well as the fusion positioning height fusion_height; the verification result is obtained based on the difference between the height mean and the fusion positioning height. For details, please refer to the description of the above embodiment.

[0145] Multi-layer histogram status monitoring is to calculate the variance of multi-layer maps. If the layer with a smaller variance is consistent with the layer to be verified, the verification result is passed; if the single-layer variance is large or the multi-layer discrimination is not high, the verification result is invalid; if the multi-layer discrimination is high and inconsistent with the layer to be verified, the verification result is failed.

[0146] One or more application scenarios of the above verification method are described below through specific embodiments.

[0147] In some embodiments, determining the road-level positioning information of the target vehicle and the layer to be verified includes:

[0148] Based on a preset road-level positioning algorithm, determine the current road-level positioning information of the target vehicle;

[0149] Perform road-level loop detection based on current road-level positioning information and road-level positioning information at historical moments to obtain a road-level loop detection result;

[0150] When the road-level loop detection result does not meet the preset detection requirements, the layer of the road corresponding to the current road-level positioning information in the multi-layer map is used as the layer to be verified.

[0151] The road-level loop detection result is used to detect whether the current road-level positioning information is associated with the road-level positioning information at a historical moment. If so, the detection requirement is met; if not, the detection result is not met.

[0152] According to the above embodiment, when the road-level loopback result does not meet the detection requirements, the layer of the road corresponding to the current road-level positioning information in the multi-layer map is used as the layer to be verified, that is, the verification step of the layer to be verified is entered, and whether the road-level positioning information is valid is determined based on the detection result of the layer to be verified. In this way, when there is a risk of misalignment, timely monitoring can be carried out to ensure the accuracy of the road-level positioning information.

[0153] In some embodiments, the above method further comprises:

[0154] When the road-level loop detection result meets the preset detection requirements, it is determined that the road-level positioning information is valid.

[0155] According to this embodiment, if the road-level loop detection result meets the detection requirements, it can be directly determined that the road-level positioning information is valid, and the road-level positioning information can be output to the downstream module.

[0156] In order to facilitate understanding of the above technical solution, Figure 4 An application example is shown. Figure 4 As shown, the method for processing positioning information includes:

[0157] S41: Obtaining road-level positioning information, that is, road-level positioning output result;

[0158] S42: Determine whether the loopback check passes; if so, jump to step S44; if not, jump to step S43;

[0159] S43: Perform availability check on the to-be-checked layer corresponding to the road-level positioning information; this includes the height check status, the perception check status, and the histogram check status; if the result of more than two statuses indicates that the check is passed, jump to step S44; otherwise jump to step 45;

[0160] S44: Road-level positioning information is output normally;

[0161] S45: Road level positioning output is invalid.

[0162] According to the above embodiment, the validity of the road-level positioning information can be judged through loop detection, so as to avoid introducing too many verification processes, thereby avoiding unnecessary consumption of computing resources and improving the utilization rate of computing resources.

[0163] In some embodiments, determining the road-level positioning information of the target vehicle and the layer to be verified includes:

[0164] When the preset road-level positioning algorithm is in the running initialization state, first road-level positioning information and second road-level positioning information of the target vehicle are determined based on the road-level positioning algorithm; wherein the first road-level positioning information is the road-level positioning information with the highest probability predicted by the road-level positioning algorithm, and the second road-level positioning information is the road-level positioning information with the second highest probability predicted by the road-level positioning algorithm;

[0165] The level of the road corresponding to the first road-level positioning information in the multi-layer map and the level of the road corresponding to the second road-level positioning information in the multi-layer map are respectively used as layers to be verified.

[0166] That is to say, when the road-level positioning algorithm is in the running initialization state, for example, after the road-level positioning algorithm is started, only the first N frames of data are obtained, and not enough historical time data is cached, two inference results are output based on the road-level positioning algorithm, including the first road-level positioning information with the highest probability and the second road-level positioning information with the second highest probability. The layers corresponding to the two road-level positioning information are taken as the layers to be verified, and are verified according to the above-mentioned verification method, so as to judge the validity of the two road-level positioning information respectively.

[0167] Optionally, the second road-level positioning information may be the road-level positioning information with the second highest probability determined after excluding the road section having a topological relationship with the road section indicated by the first road-level positioning information. Exemplarily, based on the road-level positioning algorithm, multiple road-level positioning information and the probability corresponding to each road-level positioning information may be determined; first, the road-level positioning information with the highest probability is selected as the first road-level positioning information, and after excluding the road section having a topological relationship with the road section corresponding to the first road-level positioning information, the road-level positioning information with the highest probability (i.e., the road-level positioning information with the second highest global probability) is selected from at least one road-level positioning information corresponding to the remaining road sections, and the road-level positioning information is used as the second road-level positioning information.

[0168] Accordingly, the method for processing positioning information further includes:

[0169] If the first road-level positioning information is valid, outputting the first road-level positioning information to a downstream module;

[0170] In the case where the first road-level positioning information is invalid, if the second road-level positioning information is valid, the second road-level positioning information is output to a downstream module.

[0171] Optionally, when the first road-level positioning information fails and the second road-level positioning information fails, the road-level positioning algorithm is restarted.

[0172] According to the above embodiment, if the road-level positioning result with the second highest probability meets the availability judgment condition, it can also be output to the downstream as the final result. By verifying the newly added second highest probability result in the initialization state, multiple output sources can be provided for road-level positioning in multi-layer scenarios, avoiding the problem of long-term failure of road-level positioning due to a single maximum a posteriori probability.

[0173] It should be noted that the above-mentioned multiple embodiments can be implemented in combination.

[0174] Figure 5 A schematic diagram showing an application example is shown in FIG. Figure 5 As shown, the method for processing positioning information includes:

[0175] S51: In the initialization state of the operation of the road-level positioning algorithm, based on the road-level positioning algorithm, multiple road-level positioning information and the probability corresponding to each road-level positioning information are determined; wherein the first road-level positioning information with the highest probability and the second road-level positioning information with the second highest probability can be selected. For example, for each frame of data in the first N frames of data processed after the road-level positioning algorithm is started (N is a preset integer), the first road-level positioning information and the second road-level positioning information are determined based on the road-level positioning algorithm;

[0176] S52: Verify the to-be-verified layer corresponding to the first road-level positioning information and the to-be-verified layer corresponding to the second road-level positioning information respectively to determine the validity of the first road-level positioning information and the second road-level positioning information.

[0177] S52: Based on the first road-level positioning information and the second road-level positioning information, output a valid result of the initialization state stage and store it in a buffer.

[0178] S53: In the calculation update state of the road-level positioning algorithm, that is, when the road-level positioning algorithm can perform calculations based on the data in the buffer and the current frame data collected in real time, a plurality of road-level positioning information and the probability corresponding to each road-level positioning information can be determined based on the road-level positioning algorithm. At this time, the road-level positioning information with the largest probability is output to enter the subsequent verification step.

[0179] S54: Perform road-level loop detection based on the data in the buffer.

[0180] S55: Perform staggered verification on the road-level positioning information based on multiple verification methods. Specifically, multiple verification methods based on sensory data and positioning height may be included. For example, sensory data, roadside matching, GNSS observation, etc. may be introduced to make full use of multi-source information for verification.

[0181] S56: When a layer mismatch is detected in multiple consecutive frames, the road-level positioning algorithm is restarted and the process returns to step S51.

[0182] The above application examples significantly solve the problems of road-level positioning misalignment, positioning drift, and inability to drive in multi-layer scenarios caused by missing maps by introducing perception, curb matching, GNSS and other observations, as well as the problem of hitting the shoulder caused by road-level positioning misalignment when the whole vehicle is restarted in multi-layer scenarios.

[0183] The disclosed embodiment also provides a device for processing positioning information. Figure 5 FIG. 1 is a schematic block diagram of the device. Figure 6 As shown, the device comprises:

[0184] The module 610 for determining information to be verified is used to determine the road-level positioning information of the target vehicle and the layer to be verified; wherein the layer to be verified is the layer of the road corresponding to the road-level positioning information in the multi-layer map;

[0185] A verification module 620, configured to determine at least one verification result for the layer to be verified based on the sensing data and / or positioning height of the target vehicle;

[0186] The validity determination module 630 is used to determine the validity of the road-level positioning information based on at least one verification result of the layer to be verified.

[0187] According to the positioning information processing device of the embodiment of the present disclosure, after determining the road-level positioning information of the target vehicle, it is necessary to verify the level of the road corresponding to the road-level positioning information according to the perception data or the positioning height, and determine the validity of the road-level positioning information based on the verification result. Based on this, the technical solution of the embodiment of the present disclosure can be applied in a multi-layer map scenario to avoid the situation where the road-level positioning information is misplaced, thereby improving the accuracy of the road-level positioning information.

[0188] In some embodiments, Figure 7 As shown, the verification module 620 includes a multi-layer map verification unit 621, which is used to:

[0189] Based on the raster map corresponding to the perception data and the raster map corresponding to each layer of the map, the comparison features between the perception data and each layer of the map are determined;

[0190] Based on the comparison features between the perception data and each layer of the map, determine the layer in the multi-layer map that matches the perception data;

[0191] When the layer matching the perception data is the layer to be verified, it is determined that the first verification result of the layer to be verified is verification passed.

[0192] In some embodiments, the multi-layer map verification unit 621 is further used to:

[0193] Calculate the difference information between the raster map corresponding to the perception data and the raster map corresponding to the i-th layer map in the multi-layer map under different offset modes; where i is a positive integer, and i is less than or equal to the number of layers of the multi-layer map;

[0194] Based on the difference information between the raster map corresponding to the perception data and the raster map corresponding to the i-th layer map under different offset modes, the variance of the difference information between the perception data and the i-th layer map is determined.

[0195] In some embodiments, the multi-layer map verification unit 621 is further used to:

[0196] Based on the comparison features between the perception data and each layer of the map, the maximum and minimum values ​​of the comparison features are determined;

[0197] If the maximum and minimum values ​​of the compared features meet the preset gap requirement, the level corresponding to the minimum value in the multi-layer map is determined as the level that matches the perception data.

[0198] In some embodiments, Figure 7 As shown, the verification module 620 includes a first perception state monitoring unit 622, which is used to:

[0199] Based on the perception data of the target vehicle, determining a first measurement result of the current target information; wherein the target information includes a road width and / or a distance from the target vehicle to a single side of the roadside;

[0200] Determine a second measurement result for the target information based on a map corresponding to the layer to be verified;

[0201] Based on the difference between the current first measurement result for the target information and the current second measurement result for the target information, a second verification result for the layer to be verified is determined.

[0202] In some embodiments, the first perception state monitoring unit 622 is further configured to:

[0203] Based on the perception data of the target vehicle, determine the distance from the target vehicle to the left boundary of the road and the distance from the target vehicle to the right boundary of the road;

[0204] Based on the distance from the target vehicle to the left boundary of the road and the distance from the target vehicle to the right boundary of the road, a first measurement result of the current road width is determined.

[0205] In some embodiments, the first perception state monitoring unit 622 is further configured to:

[0206] Determine, based on the data in the buffer, whether a difference between a first measurement result for the target information at a historical moment and a second measurement result for the target information at a historical moment is less than a first threshold;

[0207] If the difference between the first measurement result for the target information at a historical moment and the second measurement result for the target information at a historical moment is less than a first threshold, and the difference between the current first measurement result for the target information and the current second measurement result for the target information is less than a second threshold, then the second verification result for the layer to be verified is determined to be passed.

[0208] In some embodiments, the verification module 620 includes a second perception state monitoring unit 623, which is used to:

[0209] Detect stop line based on the perception data of the target vehicle;

[0210] Based on the distance between the target vehicle and the stop line and the road type of the layer to be verified, a third verification result for the layer to be verified is determined.

[0211] In some embodiments, the second perception state monitoring unit 623 is further configured to:

[0212] If the distance between the target vehicle and the stop line is less than the third threshold value, and the road type of the layer to be verified is an urban road, the third verification result for the layer to be verified is verification passed;

[0213] and / or,

[0214] If the distance between the target vehicle and the stop line is greater than the fourth threshold value, and the road type of the layer to be verified is a highway, the third verification result for the layer to be verified is verification passed.

[0215] In some embodiments, the verification module includes an altitude status monitoring unit 624 for:

[0216] Determine, based on the map corresponding to the layer to be verified, a mean height value of at least one map element within a preset range of the road-level positioning information;

[0217] Based on the difference between the height average and the positioning height of the target vehicle, a fourth verification result for the layer to be verified is determined.

[0218] In some embodiments, the altitude status monitoring unit 624 is further configured to:

[0219] When the difference between the height mean and the positioning height of the target vehicle is less than a fifth threshold, the fourth verification result for the layer to be verified is determined to be passed; wherein the fifth threshold is determined based on the variance of the heights of each map element.

[0220] In some embodiments, Figure 7 As shown, the to-be-verified information determination module 610 includes a real-time monitoring unit 611, which is used to:

[0221] Based on a preset road-level positioning algorithm, determine the current road-level positioning information of the target vehicle;

[0222] Perform road-level loop detection based on current road-level positioning information and road-level positioning information at historical moments to obtain a road-level loop detection result;

[0223] When the road-level loop detection result does not meet the preset detection requirements, the layer of the road corresponding to the current road-level positioning information in the multi-layer map is used as the layer to be verified.

[0224] In some embodiments, the apparatus further comprises:

[0225] The loop detection module 710 is used to determine that the road-level positioning information is valid when the road-level loop detection result meets the preset detection requirements.

[0226] In some embodiments, the to-be-verified information determination module 610 includes an initialization monitoring unit 612, which is used to:

[0227] When the preset road-level positioning algorithm is in the running initialization state, first road-level positioning information and second road-level positioning information of the target vehicle are determined based on the road-level positioning algorithm; wherein the first road-level positioning information is the road-level positioning information with the highest probability predicted by the road-level positioning algorithm, and the second road-level positioning information is the road-level positioning information with the second highest probability predicted by the road-level positioning algorithm;

[0228] The level of the road corresponding to the first road-level positioning information in the multi-layer map and the level of the road corresponding to the second road-level positioning information in the multi-layer map are respectively used as layers to be verified;

[0229] The device further includes an output module 720, configured to:

[0230] If the first road-level positioning information is valid, outputting the first road-level positioning information to a downstream module;

[0231] In the case where the first road-level positioning information is invalid, if the second road-level positioning information is valid, the second road-level positioning information is output to a downstream module.

[0232] For the description of specific functions and examples of each module and submodule of the device in the embodiment of the present disclosure, reference can be made to the relevant description of the corresponding steps in the above method embodiment, which will not be repeated here.

[0233] In the technical solution disclosed herein, the acquisition, storage and application of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0234] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0235] Figure 8 A schematic block diagram of an example electronic device 800 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0236] like Figure 8 As shown, the electronic device 800 includes a computing unit 801, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 802 or a computer program loaded from a storage unit 808 into a random access memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the device 800 can also be stored. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0237] A number of components in the device 800 are connected to the I / O interface 805, including: an input unit 806, such as a keyboard, a mouse, etc.; an output unit 807, such as various types of displays, speakers, etc.; a storage unit 808, such as a disk, an optical disk, etc.; and a communication unit 809, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 809 allows the device 800 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0238] The computing unit 801 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 801 performs the various methods and processes described above, such as a processing method for positioning information. For example, in some embodiments, the processing method for positioning information may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 800 via ROM 802 and / or communication unit 809. When the computer program is loaded into RAM 803 and executed by the computing unit 801, one or more steps of the processing method for positioning information described above may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to perform the processing method for positioning information in any other appropriate manner (e.g., by means of firmware).

[0239] According to the technical solution of the embodiment of the present disclosure, after determining the road-level positioning information of the target vehicle, it is necessary to verify the level of the road corresponding to the road-level positioning information according to the perception data or positioning height, and determine the validity of the road-level positioning information based on the verification result. Based on this, the technical solution of the embodiment of the present disclosure can be applied in multi-layer map scenarios to avoid the situation where the road-level positioning information is misplaced, thereby improving the accuracy of the road-level positioning information.

[0240] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0241] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0242] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0243] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0244] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0245] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0246] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0247] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the principles of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for processing positioning information, comprising: Determine the road-level positioning information and the layer to be verified of the target vehicle; wherein the layer to be verified is the layer of the road corresponding to the road-level positioning information in the multi-layer map; Determine at least one verification result for the layer to be verified based on the sensing data and / or positioning height of the target vehicle; Based on at least one verification result of the layer to be verified, the validity of the road-level positioning information is determined.

2. The method according to claim 1, wherein: The determining, based on the sensing data and / or positioning height of the target vehicle, at least one verification result for the layer to be verified includes: Determining comparison features between the perception data and each layer of the map based on the grid map corresponding to the perception data and the grid map corresponding to each layer of the multi-layer map; Determining a level in the multi-layer map that matches the perception data based on comparison features between the perception data and each layer of the map; In a case where the layer matching the perception data is the layer to be verified, it is determined that the first verification result of the layer to be verified is verification passed.

3. The method according to claim 2, wherein: The determining, based on the grid map corresponding to the perception data and the grid map corresponding to each layer of the multi-layer map, a comparison feature between the perception data and each layer of the map, comprises: Calculating difference information between the raster map corresponding to the perception data and the raster map corresponding to the i-th layer map in the multi-layer map under different offset modes; wherein i is a positive integer, and i is less than or equal to the number of layers of the multi-layer map; Based on difference information between a grid map corresponding to the perception data and a grid map corresponding to the i-th layer map in different offset modes, a variance of difference information between the perception data and the i-th layer map is determined.

4. The method according to claim 2 or 3, wherein: The determining, based on the comparison features between the perception data and each layer of the map, a layer in the multi-layer map that matches the perception data includes: Based on the comparison features between the perception data and the map of each layer, determining the maximum value and the minimum value of the comparison features; If the maximum value and the minimum value of the compared feature meet a preset gap requirement, the level corresponding to the minimum value in the multi-layer map is determined as the level matching the perception data.

5. The method according to any one of claims 1 to 4, wherein: The determining, based on the sensing data and / or positioning height of the target vehicle, at least one verification result for the layer to be verified includes: Based on the perception data of the target vehicle, determine a first measurement result of the current target information; wherein the target information includes a road width and / or a distance from the target vehicle to a single side curb; Determine a second measurement result of the target information based on the map corresponding to the layer to be verified; Based on the difference between the current first measurement result for the target information and the current second measurement result for the target information, a second verification result for the layer to be verified is determined.

6. The method according to claim 5, wherein: The step of determining a first measurement result of the current target information based on the perception data of the target vehicle includes: Based on the perception data of the target vehicle, determining the distance from the target vehicle to the left boundary of the road and the distance from the target vehicle to the right boundary of the road; Based on the distance from the target vehicle to the left boundary of the road and the distance from the target vehicle to the right boundary of the road, a first measurement result currently for the road width is determined.

7. The method according to claim 5 or 6, wherein: The determining, based on a difference between a current first measurement result for the target information and a current second measurement result for the target information, a second verification result for the layer to be verified includes: Determine, based on the data in the buffer, whether a difference between a first measurement result for the target information at a historical moment and a second measurement result for the target information at a historical moment is less than a first threshold; If the difference between the first measurement result for the target information at a historical moment and the second measurement result for the target information at a historical moment is less than a first threshold, and the difference between the current first measurement result for the target information and the current second measurement result for the target information is less than a second threshold, then the second verification result for the layer to be verified is determined to be passed.

8. The method according to any one of claims 1 to 7, wherein: The determining, based on the sensing data and / or positioning height of the target vehicle, at least one verification result for the layer to be verified includes: detecting a stop line based on the sensing data of the target vehicle; Based on the distance between the target vehicle and the stop line and the road type of the layer to be verified, a third verification result for the layer to be verified is determined.

9. The method according to claim 8, wherein: The determining, based on the distance between the target vehicle and the stop line and the road type of the layer to be verified, a third verification result for the layer to be verified includes: If the distance between the target vehicle and the stop line is less than a third threshold value, and the road type of the layer to be checked is an urban road, then the third check result for the layer to be checked is a check passed; and / or, If the distance between the target vehicle and the stop line is greater than a fourth threshold value, and the road type of the layer to be verified is a highway, the third verification result for the layer to be verified is verification passed.

10. The method according to any one of claims 1 to 9, wherein: The determining, based on the sensing data and / or positioning height of the target vehicle, at least one verification result for the layer to be verified includes: Based on the map corresponding to the layer to be verified, determining the average height of at least one map element within a preset range of the road-level positioning information; Based on the difference between the height average and the positioning height of the target vehicle, a fourth verification result for the layer to be verified is determined.

11. The method according to claim 10, wherein: The determining, based on the difference between the height mean and the positioning height of the target vehicle, a fourth verification result for the layer to be verified, comprises: When the difference between the mean height and the positioning height of the target vehicle is less than a fifth threshold, the fourth verification result for the layer to be verified is determined to be passed; wherein the fifth threshold is determined based on the variance of the heights of the map elements.

12. The method according to any one of claims 1 to 11, wherein: The step of determining the road-level positioning information of the target vehicle and the layer to be verified includes: Based on a preset road-level positioning algorithm, determine the current road-level positioning information of the target vehicle; Performing road-level loop detection based on the current road-level positioning information and the road-level positioning information at historical moments to obtain a road-level loop detection result; When the road-level loop detection result does not meet the preset detection requirement, the layer of the road corresponding to the current road-level positioning information in the multi-layer map is used as a layer to be verified.

13. The method according to claim 12, further comprising: When the road-level loop detection result meets a preset detection requirement, it is determined that the road-level positioning information is valid.

14. The method according to any one of claims 1 to 13, wherein: The step of determining the road-level positioning information of the target vehicle and the layer to be verified includes: When the preset road-level positioning algorithm is in the running initialization state, based on the road-level positioning algorithm, the first road-level positioning information and the second road-level positioning information of the target vehicle are determined; wherein the first road-level positioning information is the road-level positioning information with the highest probability predicted by the road-level positioning algorithm, and the second road-level positioning information is the road-level positioning information with the second highest probability predicted by the road-level positioning algorithm; The level of the road corresponding to the first road-level positioning information in the multi-layer map and the level of the road corresponding to the second road-level positioning information in the multi-layer map are respectively used as layers to be verified; The method further comprises: If the first road-level positioning information is valid, outputting the first road-level positioning information to a downstream module; In the case where the first road-level positioning information is invalid, if the second road-level positioning information is valid, the second road-level positioning information is output to a downstream module.

15. A positioning information processing device, comprising: The module for determining information to be verified is used to determine the road-level positioning information and the layer to be verified of the target vehicle; wherein the layer to be verified is the layer of the road corresponding to the road-level positioning information in the multi-layer map; A verification module, configured to determine at least one verification result for the layer to be verified based on the sensing data and / or positioning height of the target vehicle; The validity determination module is used to determine the validity of the road-level positioning information based on at least one verification result of the layer to be verified.

16. The device according to claim 15, wherein: The verification module includes a multi-layer map verification unit, which is used to: Determining comparison features between the perception data and each layer of the map based on the grid map corresponding to the perception data and the grid map corresponding to each layer of the multi-layer map; Determining a level in the multi-layer map that matches the perception data based on comparison features between the perception data and each layer of the map; In a case where the layer matching the perception data is the layer to be verified, it is determined that the first verification result of the layer to be verified is verification passed.

17. The device according to claim 16, wherein: The multi-layer map verification unit is also used for: Calculating difference information between the raster map corresponding to the perception data and the raster map corresponding to the i-th layer map in the multi-layer map under different offset modes; wherein i is a positive integer, and i is less than or equal to the number of layers of the multi-layer map; Based on difference information between a grid map corresponding to the perception data and a grid map corresponding to the i-th layer map in different offset modes, a variance of difference information between the perception data and the i-th layer map is determined.

18. The device according to claim 16 or 17, wherein: The multi-layer map verification unit is also used for: Based on the comparison features between the perception data and the map of each layer, determining the maximum value and the minimum value of the comparison features; If the maximum value and the minimum value of the compared feature meet a preset gap requirement, the level corresponding to the minimum value in the multi-layer map is determined as the level matching the perception data.

19. The device according to any one of claims 15 to 18, wherein: The verification module includes a first sensing state monitoring unit, which is used to: Based on the perception data of the target vehicle, determine a first measurement result of the current target information; wherein the target information includes a road width and / or a distance from the target vehicle to a single side curb; Determine a second measurement result of the target information based on the map corresponding to the layer to be verified; Based on the difference between the current first measurement result for the target information and the current second measurement result for the target information, a second verification result for the layer to be verified is determined.

20. The device according to claim 19, wherein The first sensing state monitoring unit is further used for: Based on the perception data of the target vehicle, determining the distance from the target vehicle to the left boundary of the road and the distance from the target vehicle to the right boundary of the road; Based on the distance from the target vehicle to the left boundary of the road and the distance from the target vehicle to the right boundary of the road, a first measurement result currently for the road width is determined.

21. The device according to claim 19 or 20, wherein: The first sensing state monitoring unit is further used for: Determine, based on the data in the buffer, whether a difference between a first measurement result for the target information at a historical moment and a second measurement result for the target information at a historical moment is less than a first threshold; If the difference between the first measurement result for the target information at a historical moment and the second measurement result for the target information at a historical moment is less than a first threshold, and the difference between the current first measurement result for the target information and the current second measurement result for the target information is less than a second threshold, then the second verification result for the layer to be verified is determined to be passed.

22. The device according to any one of claims 15 to 21, wherein: The verification module includes a second sensing state monitoring unit, which is used to: detecting a stop line based on the sensing data of the target vehicle; Based on the distance between the target vehicle and the stop line and the road type of the layer to be verified, a third verification result for the layer to be verified is determined.

23. The device according to claim 22, wherein: The second sensing state monitoring unit is further used for: If the distance between the target vehicle and the stop line is less than a third threshold value, and the road type of the layer to be checked is an urban road, then the third check result for the layer to be checked is a check passed; and / or, If the distance between the target vehicle and the stop line is greater than a fourth threshold value, and the road type of the layer to be verified is a highway, the third verification result for the layer to be verified is verification passed.

24. The device according to any one of claims 15 to 23, wherein: The verification module includes a height status monitoring unit, which is used to: Based on the map corresponding to the layer to be verified, determining the average height of at least one map element within a preset range of the road-level positioning information; Based on the difference between the height average and the positioning height of the target vehicle, a fourth verification result for the layer to be verified is determined.

25. The device according to claim 24, wherein: The altitude status monitoring unit is also used for: When the difference between the mean height and the positioning height of the target vehicle is less than a fifth threshold, the fourth verification result for the layer to be verified is determined to be passed; wherein the fifth threshold is determined based on the variance of the heights of the map elements.

26. The device according to any one of claims 15 to 25, wherein: The to-be-verified information determination module includes a real-time monitoring unit, which is used to: Based on a preset road-level positioning algorithm, determine the current road-level positioning information of the target vehicle; Performing road-level loop detection based on the current road-level positioning information and the road-level positioning information at historical moments to obtain a road-level loop detection result; When the road-level loop detection result does not meet the preset detection requirement, the layer of the road corresponding to the current road-level positioning information in the multi-layer map is used as a layer to be verified.

27. The apparatus according to claim 26, further comprising: The loop detection passing module is used to determine that the road-level positioning information is valid when the road-level loop detection result meets the preset detection requirements.

28. The device according to any one of claims 15 to 27, wherein: The to-be-verified information determination module includes an initialization monitoring unit, which is used to: When the preset road-level positioning algorithm is in the running initialization state, based on the road-level positioning algorithm, the first road-level positioning information and the second road-level positioning information of the target vehicle are determined; wherein the first road-level positioning information is the road-level positioning information with the highest probability predicted by the road-level positioning algorithm, and the second road-level positioning information is the road-level positioning information with the second highest probability predicted by the road-level positioning algorithm; The level of the road corresponding to the first road-level positioning information in the multi-layer map and the level of the road corresponding to the second road-level positioning information in the multi-layer map are respectively used as layers to be verified; The device also includes an output module, which is used to: If the first road-level positioning information is valid, outputting the first road-level positioning information to a downstream module; In the case where the first road-level positioning information is invalid, if the second road-level positioning information is valid, the second road-level positioning information is output to a downstream module.

29. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 14.

30. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-14.

31. A computer program product comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 14.

Images