A path matching method, device, and high-precision map engine

Abstract

An embodiment of this specification discloses a path matching method, apparatus, and high-precision map engine. The solution may include: first determining a sequence of coordinate points corresponding to the standard-precision path information in the standard-precision map data to be matched; then determining, from the high-precision map data, a first link that matches the first coordinate point in the sequence of coordinate points; and determining, from the first link or the subsequent link of the first link, a second link that matches the second coordinate point adjacent to the first coordinate point; and then determining the path information of the path formed by the links that match each coordinate point in the sequence of coordinate points as the high-precision path information that matches the standard-precision path information. Based on this solution, it can be ensured that the obtained high-precision path is passable.

Description

Technical Field

[0001] This application relates to the technical field of map navigation, and in particular, to a path matching method, apparatus, and high-precision map engine. Background Art

[0002] Complete path planning in a standard (SD, standard definition) map, output the path planning result, and then perform path matching in a high-precision (HD, high definition) map, and then output a lane-level path, which can be used for autonomous driving. Accurately performing path matching is the key technology for combining SD maps and HD maps to provide autonomous driving navigation services.

[0003] Currently, there are many implementation solutions for matching from standard roads to high-precision roads.

[0004] For the first type of solution, establish and maintain a set of corresponding relationships between standard map data and high-precision map data, and the route between the two types of data can be matched according to this corresponding relationship. The corresponding relationship between the two usually depends on manual maintenance, and the representation methods of the same information in different types of maps are different, which makes the maintenance of the corresponding relationship between maps difficult and the error rate high.

[0005] For the second type of solution, there is no direct corresponding relationship between standard map data and high-precision map data. When matching, search on high-precision data according to the characteristic attributes of the path on the standard data. In the early stage, a matching algorithm based on geometric information was used, considering conventional elements such as shape and angle, but the accuracy was not high and it was not actually widely used. Currently, the most accurate algorithm is the Hidden Markov, which is a type of algorithm based on topological information and probability prediction, and the accuracy is greatly improved compared with the geometric method and it is the most widely used. However, when the Hidden Markov is used for path matching, it cannot be determined that the matched links are continuous, that is, there may be no passage between the matched links. Summary of the Invention

[0006] Embodiments of this specification provide a path matching method, apparatus, and high-precision map engine to solve the problem that the existing path matching methods cannot ensure the continuity between the matched links.

[0007] To solve the above technical problems, the embodiments of this specification are implemented as follows:

[0008] A path matching method provided by an embodiment of this specification includes:

[0009] Determine the coordinate point sequence corresponding to the standard-precision path information in the standard-precision map data to be matched;

[0010] Determine a first link that matches the first coordinate point in the coordinate point sequence from the high-precision map data;

[0011] Determine a second link that matches the second coordinate point adjacent to the first coordinate point from the first link or the subsequent link of the first link; the subsequent direction of the subsequent link is consistent with the extension trend from the first coordinate point to the second coordinate point;

[0012] Determine the path information of the path formed by the links matching each coordinate point in the coordinate point sequence as the high-precision path information that matches the standard-precision path information.

[0013] A path matching device provided by an embodiment of this specification includes:

[0014] A standard-precision map data providing module, configured to provide the standard-precision path information in the standard-precision map data to be matched;

[0015] A high-precision map data providing module, configured to provide link information in the high-precision map data;

[0016] A first link matching module, configured to determine a first link that matches the first coordinate point in the coordinate point sequence from the high-precision map data; the coordinate point sequence is obtained by performing data processing on the standard-precision path information;

[0017] A second link matching module, configured to determine a second link that matches the second coordinate point adjacent to the first coordinate point from the first link or the subsequent link of the first link; the subsequent direction of the subsequent link is consistent with the extension trend from the first coordinate point to the second coordinate point;

[0018] A high-precision path determining module, configured to determine the path information of the path formed by the links matching each coordinate point in the coordinate point sequence as the high-precision path information that matches the standard-precision path information.

[0019] A high-precision map engine provided by an embodiment of this specification includes a standard-precision map data interface, configured to access the standard-precision path information in the standard-precision map data to be matched;

[0020] A high-precision map data providing module, configured to provide link information in the high-precision map data;

[0021] A first link matching module, configured to determine a first link that matches the first coordinate point in the coordinate point sequence from the high-precision map data; the coordinate point sequence is obtained by performing data processing on the standard-precision path information;

[0022] A second link matching module, configured to determine, from the first link or a subsequent link of the first link, a second link that matches a second coordinate point adjacent to the first coordinate point; a subsequent direction of the subsequent link is consistent with an extension trend from the first coordinate point to the second coordinate point;

[0023] A high-precision path determination module, configured to determine path information of a path formed by links matching respective coordinate points in the coordinate point sequence as high-precision path information that matches the standard-precision path information.

[0024] At least one beneficial effect that can be achieved by an embodiment of this specification is as follows: For a standard-precision path to be matched, first determine a first high-precision link corresponding to a first coordinate point in the standard-precision path, and then determine the first high-precision link or a subsequent link of the first high-precision link as a second high-precision link corresponding to a second coordinate point adjacent to the first coordinate point. Thus, a high-precision path formed by high-precision links corresponding to respective coordinate points is continuous, that is, it can be ensured that the high-precision path obtained by path matching is passable. Description of the Drawings

[0025] To more clearly illustrate the technical solutions in the embodiments of this specification or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings described below are only some embodiments recorded in this application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0026] Figure 1 It is a schematic flowchart of a path matching method provided by an embodiment of this specification;

[0027] Figure 2 It is a schematic diagram of a method for determining a high-precision link corresponding to a first coordinate point provided by an embodiment of this specification;

[0028] Figure 3 It is a schematic diagram of a method for determining a high-precision link corresponding to a second coordinate point provided by an embodiment of this specification;

[0029] Figure 4 It is a schematic structural diagram of a path matching device provided by an embodiment of this specification. Detailed Embodiments

[0030] To make the objectives, technical solutions, and advantages of one or more embodiments of this specification clearer, the following will clearly and completely describe the technical solutions of one or more embodiments of this specification in conjunction with specific embodiments of this specification and the corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this specification, rather than all of the embodiments. Based on the embodiments in this specification, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope protected by one or more embodiments of this specification.

[0031] It should be understood that although terms such as first, second, and third may be used in this application document to describe various information, such information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other.

[0032] The following will, in conjunction with the drawings, detail the technical solutions provided by each embodiment of this specification.

[0033] When realizing autonomous driving based on a high-precision map, path planning is usually carried out based on a standard map, and then according to the mapping relationship between the standard map and the high-precision map, the matching path of the planned path in the high-precision map is determined. However, when the sources of the standard map and the high-precision map are different, that is, there is no one-to-one matching relationship between the roads on the high-precision map and the roads on the standard map, the navigation path on the standard map cannot be directly converted into a high-precision map path available for the autonomous driving system.

[0034] Currently, there are many implementation solutions for matching from a standard road to a high-precision road.

[0035] For the first type of solution, a set of corresponding relationships between the standard map data and the high-precision map data is established and maintained, and the matching between the routes in the two types of data can be carried out according to this corresponding relationship. The corresponding relationship between the two usually relies on manual maintenance, and the representation methods of the same type of information in different types of maps are different, which makes the maintenance of the corresponding relationship between the maps difficult and the error rate high.

[0036] For the second type of solution, there is no direct corresponding relationship between the standard map data and the high-precision map data. When matching, the search is performed on the high-precision data according to the characteristic attributes of the path on the standard data. In the early stage, a matching algorithm based on geometric information was used, considering conventional elements such as shape and angle, but the accuracy was not high and it was not actually widely used. Currently, the most accurate algorithm is the Hidden Markov Model, which is a type of algorithm based on topological information and probability prediction. The accuracy is greatly improved compared with the geometric method and it is the most widely used. However, when the Hidden Markov Model is used for path matching, it cannot be determined that the matched links are continuous, that is, it is possible that the matched links are not passable.

[0037] To address the deficiencies in the prior art, in the solution provided in the examples of this specification, when performing path matching, the continuity between links in the matched high-precision path is fully considered, ensuring that the matched path is definitely a passable route. There is continuity between links, and there is no situation of disconnection in the middle or random jumping between different roads.

[0038] In the embodiments of this specification, a link is a vector line representing a road in map data. As is understood by those skilled in the art, in map data, the smallest segmentation unit of a road is usually referred to as a link, and the smallest segmentation unit of a lane is referred to as a lane.

[0039] Next, a path matching method provided in the embodiments of the specification will be specifically described in conjunction with the accompanying drawings.

[0040] Figure 1 It is a schematic flowchart of a path matching method provided in the embodiments of this specification.

[0041] From a program perspective, the execution entity of the process can be any device, equipment, platform, or equipment cluster with computing and processing capabilities.

[0042] As Figure 1 shown, the process may include the following steps.

[0043] Step 102: Determine the coordinate point sequence corresponding to the standard-precision path information in the standard-precision map data to be matched.

[0044] Path matching, also known as route matching, generally refers to matching the heterogeneous standard-precision path planning results with high-precision data to obtain high-precision path information. Among them, the standard-precision path planning results can be used for manual driving navigation. The obtained high-precision path information can be used for autonomous driving navigation.

[0045] In actual applications, before performing path matching, it is necessary to initialize the initial standard-precision path planning results, convert the standard-precision path information in the standard-precision map data to be matched into point sequence information on the path, and then perform matching based on the point sequence and the high-precision map data.

[0046] Specifically, the standard-precision path information in the standard-precision map data to be matched can be determined first, that is, the standard-precision path planning results are determined; then, the standard-precision path information can be converted into a coordinate point sequence to facilitate path matching. The coordinate point sequence is data in units of coordinate points.

[0047] Step 104: Determine the first link in the high-precision map data that matches the first coordinate point in the coordinate point sequence.

[0048] In the embodiments of this specification, after converting the standard-precision path information in the standard-precision map data to be matched into a sequence of coordinate points, the matching calculation of the points on the standard path to the links in the high-precision map data can be sequentially performed in order.

[0049] At the beginning of the matching, the method of box selection can be used to determine the matching link of the first coordinate point in the first coordinate point sequence on the high-precision map data. Wherein, the first coordinate point can be the first point in the sequence of coordinate points.

[0050] Optionally, a circle can be drawn with the first coordinate point as the center and a preset distance value as the radius to determine the matching range of the first coordinate point in the high-precision map. Wherein, the preset distance value can be set as needed. For example, it can be set to 20 meters, 30 meters, etc. Then, the links within the matching range can be determined as the first alternative link set matching the first coordinate point. Specifically, the links with at least a part within the matching range can be determined to belong to the first alternative link set matching the first coordinate point. If no alternative links are collected within this matching range, the next coordinate point (for example, the second coordinate point in the sequence of coordinate points) can be selected and the box selection can be redone.

[0051] As Figure 2 , a schematic diagram of the method for determining the high-precision link corresponding to the first coordinate point in the embodiments of this specification is shown.

[0052] In Figure 2 , point A is the first coordinate point. Based on the preset matching range around point A (such as Figure 2 , taking the preset distance value as 20 meters as an example), the alternative link set corresponding to point A is collected (such as Figure 2 , 7 alternative links can be determined and are shown as solid lines).

[0053] In step 104, the first alternative link set may include the first link that matches the first coordinate point in the sequence of coordinate points.

[0054] In the embodiments of this specification, the matching degree between the first coordinate point and each alternative link in the first alternative link set can be calculated, and in combination with the matching degrees between other coordinate points and their corresponding alternative links, the matching links corresponding to each coordinate point in the sequence of coordinate points can be determined from each alternative link set. The calculation of the matching degree will be introduced below.

[0055] Step 106: Determine a second link that matches a second coordinate point adjacent to the first coordinate point from the first link or a successive link of the first link; the successive direction of the successive link is consistent with the extension trend from the first coordinate point to the second coordinate point.

[0056] In the embodiments of this specification, after determining the alternative link corresponding to the first coordinate point, subsequent points are not selected by box selection. Instead, selection can be based on the matching result of the previous point. In fact, when determining the alternative link corresponding to each subsequent point in the point sequence, selection can be based on the matching result of the previous point. Specifically, it can be the matching link of the previous point or the successive link of the matching link of the previous point.

[0057] Specifically, when determining the corresponding high-precision link of the second coordinate point adjacent to the first coordinate point, the projection point of the second coordinate point on each alternative link or its successive link in the first alternative link set corresponding to the first coordinate point can be calculated first. For example, the second projection point of the second coordinate point perpendicular to the first link or its successive link can be calculated.

[0058] Specifically, the determining, from the first link or a successive link of the first link, of a second link that matches a second coordinate point adjacent to the first coordinate point may specifically include: calculating a second projection point of the second coordinate point perpendicular to the first link or the successive link of the first link; determining whether the second projection point is on the first link or the successive link of the first link to obtain a projection position determination result; if the projection position determination result indicates that the second projection point is on the first link or the successive link of the first link, then determining the first link or the successive link of the first link as the second alternative link that matches the second coordinate point; the second alternative link is included in a second alternative link set, and the second alternative link set includes the second link.

[0059] In practical applications, there may be two cases for the second projection point: on the first link or not on the first link.

[0060] In an alternative embodiment, if the second projection point is on the first link, then the first link can be determined as the second alternative link that matches the second coordinate point. The second alternative link is included in a second alternative link set, and the second alternative link set includes the second link.

[0061] In an alternative embodiment, if the second projection point is not on the first link, for example, projected at the end of the first link or outside the first link, then the second alternative link corresponding to the second link can be determined from the subsequent link of the first link. Specifically, the first subsequent link corresponding to the first link can be determined first; then the projection distance between the second coordinate point and the first subsequent link can be calculated; and it can be determined whether the projection distance meets a preset projection condition to obtain a projection condition determination result; if the projection condition determination result indicates that the projection distance meets the preset projection condition, then the first subsequent link is determined as the second alternative link matched with the second coordinate point. If the projection condition determination result indicates that the projection distance does not meet the preset projection condition, then the first subsequent link is not determined as the second alternative link matched with the second coordinate point.

[0062] Among them, the subsequent link of the first link is determined in the following manner, which may specifically include: determining a first subsequent link distance threshold based on the distance between the second coordinate point and the first coordinate point; then determining the first subsequent link corresponding to the first link in the direction within the first subsequent link distance threshold and consistent with the extension trend from the first coordinate point to the second coordinate point; the distance between the first subsequent link and the second coordinate point is less than the first subsequent link distance threshold.

[0063] For example, the first subsequent link distance threshold maxDistance may be the distance between the second coordinate point and the first coordinate point plus a second preset distance value. Thus, it can be ensured that the links within the second preset distance value range around the second coordinate point can be collected. The second preset distance value here may be the same as or different from the preset distance value when determining the alternative link corresponding to the first coordinate point.

[0064] To ensure the accuracy of link matching, eliminate the interference of redundant data, and reduce the amount of data processing such as subsequent matching degree calculation, for the links collected based on the first subsequent link distance threshold, the second alternative link corresponding to the second coordinate point can be further screened out by calculating whether the projection distances between the second coordinate point and these links meet the preset projection conditions.

[0065] Specifically, first, the projection distance of each link in the first alternative connection link set corresponding to the second coordinate point and the first link can be calculated, and the first alternative connection link set includes the first connection link; then, the link in the first alternative connection link set that is closest to the projection distance of the second coordinate point can be determined as the second alternative link matching the second coordinate point; and it is determined whether the projection distance between the second coordinate point and the second alternative link is less than a preset projection distance threshold to obtain a projection distance threshold judgment result; if the projection distance threshold judgment result indicates that the projection distance between the second coordinate point and the second alternative link is less than the preset projection distance threshold, the second alternative link can be determined as the second alternative link matching the second coordinate point.

[0066] The projection distance threshold may be the same as or different from the preset distance value when determining the alternative link corresponding to the first coordinate point, or the projection distance threshold may be the same as or different from the second preset distance threshold used when determining the first connection link. The projection distance threshold may be set as needed, for example, the projection distance threshold may be 20 meters, 30 meters, etc.

[0067] like Figure 3 , showing a schematic diagram of a method for determining a high-precision link corresponding to a second coordinate point according to an embodiment of this specification.

[0068] exist Figure 3 In the example, point B is the second coordinate point, based on the preset matching range around point B (such as Figure 3 , taking 20 meters as an example), collect the candidate link set corresponding to point B (such as Figure 3 , three candidate links can be determined, shown by solid lines, all of which are the successor links of the link in the first candidate link).

[0069] In step 106, the second candidate link set may include a second link matching the second coordinate point in the coordinate point sequence.

[0070] In an embodiment of the present specification, the matching degree between the second coordinate point and each candidate link in the second candidate link set can be calculated, and combined with the matching degrees between other coordinate points and corresponding candidate links, to determine the matching link corresponding to each coordinate point in the coordinate point column from each candidate link set. The calculation of the matching degree will be introduced below.

[0071] Step 108: Determine the path information of the path formed by the links matching each coordinate point in the coordinate point sequence as high-precision path information matching the standard precision path information.

[0072] After the second coordinate point is matched, the matching of subsequent coordinate points can be continued according to the method described in step 106 until the last point that can be matched successfully. In this way, the link set corresponding to each coordinate point in the coordinate point sequence corresponding to the path to be matched can be obtained, and the link connected to each link in the link set corresponding to the second coordinate point and subsequent coordinate points can be known.

[0073] In actual application, for the standard precision path to be matched, after the high precision links corresponding to the coordinate points in the standard precision path are determined, the path composed of the high precision links can be determined as the high precision path corresponding to the standard precision path to be matched.

[0074] It should be understood that in the methods described in one or more embodiments of this specification, the order of some steps can be adjusted according to actual needs, or some steps can be omitted.

[0075] Figure 1 The method in , for the standard precision path to be matched, first determines the first high precision link corresponding to the first coordinate point in the standard precision path, and then determines the first high precision link or the successor link of the first high precision link as the second high precision link corresponding to the second coordinate point adjacent to the first coordinate point, thereby, the high precision path formed by the high precision links corresponding to each coordinate point is continuous, that is, it can ensure that the high precision path obtained by path matching is passable.

[0076] based on Figure 1 The method, the embodiments of this specification also provide some specific implementation methods of the method, which are described below.

[0077] In the embodiments of the present specification, the standard precision path to be matched is first converted into a coordinate point sequence; then, for each coordinate point in the coordinate point sequence, the set of alternative links corresponding to the coordinate point is determined, and the matching degree between the coordinate point and each alternative link in the corresponding alternative link set is calculated; finally, based on the matching degree between each coordinate point and each corresponding alternative link, a high-precision path with a high matching degree with the standard precision path to be matched is determined.

[0078] Specifically, step 104 may include: determining, from the high-precision map data, a first candidate link set that matches the first coordinate point in the coordinate point sequence. That is, a plurality of the first links may form a first candidate link set.

[0079] Step 106 may specifically include: determining a second alternative link set that matches the second coordinate point adjacent to the first coordinate point from the first alternative link set or the successor link sets corresponding to the links in the first alternative link set. That is, multiple said second links may form a second alternative link set.

[0080] Step 108 may specifically include: on the one hand, calculating the link matching degree between each coordinate point in the coordinate point sequence and each link in the corresponding alternative link set; on the other hand, based on the connection relationship between the links in the alternative link sets corresponding to the adjacent coordinate points in the coordinate point sequence, determining a high-precision alternative path information set corresponding to the to-be-matched standard-precision path information; then, based on the link matching degree of the links included in each alternative path information in the high-precision alternative path information set, determining the path matching degree between each alternative path information and the to-be-matched standard-precision path information; after that, the path with the highest path matching degree between the high-precision alternative path information set and the to-be-matched standard-precision path information may be determined as the high-precision path information that matches the standard-precision path information

[0081] For example, the coordinate point sequence corresponding to the to-be-matched standard-precision path is {point A, point B, point C}; first, according to the method of step 104, the link set corresponding to point A can be determined as {a1, a2, a3, a4, a5}; then, according to the method of step 106, the link set corresponding to point B can be determined as {b1 (successor to a1), b2 (successor to a3), b3 (successor to a5)}, and the link set corresponding to point C can be determined as {c1 (successor to b2), c2 (successor to b3)}; after that, the alternative path information set corresponding to the to-be-matched standard-precision path {a3 - b2 - c1, a5 - b3 - c2} can be obtained, and based on the matching degree between the to-be-matched standard-precision path and each alternative path {a3 - b2 - c1, a5 - b3 - c2}, a high-precision path with a high matching degree can be selected therefrom.

[0082] In actual application, determining the path matching degree between each alternative path information and the to-be-matched standard-precision path information based on the link matching degrees of the links included in each alternative path information in the high-precision alternative path information set may specifically include: adding up the link matching degrees of the links included in a target alternative path and the corresponding coordinate points to obtain the matching degree of the target alternative path. Suppose the target alternative path is composed of alternative link1 (corresponding to coordinate point 1), alternative link2 (corresponding to coordinate point 2), and alternative link3 (corresponding to coordinate point 3). Then, the matching degree between coordinate point 1 and alternative link1, the matching degree between coordinate point 2 and alternative link2, and the matching degree between coordinate point 3 and alternative link3 can be added up to obtain the matching degree corresponding to the target alternative link.

[0083] Continuing with the example above. First, the matching degrees {Aa1, Aa2, Aa3, Aa4, Aa5} between point A and each link in the corresponding link set {a1, a2, a3, a4, a5}, the matching degrees {Bb1, Bb2, Bb3} between point B and each link in the corresponding link set {b1, b2, b3}, and the matching degrees {Cc1, Cc2} between point C and each link in the corresponding link set {c1, c2} can be calculated. Then, the matching degrees between the to-be-matched standard-precision path and each alternative path {a3 - b2 - c1, a5 - b3 - c2} can be calculated. Specifically, the matching degree with path a3 - b2 - c1 can be Aa3 + Bb2 + Cc1, and the matching degree with a5 - b3 - c2 can be Aa5 + Bb3 + Cc2. Then, the path corresponding to the higher matching value between Aa3 + Bb2 + Cc1 and Aa5 + Bb3 + Cc2 is determined as the matched high-precision path. For example, if the matching degree Aa3 + Bb2 + Cc1 > Aa5 + Bb3 + Cc2, then the path a3 - b2 - c1 can be determined as the high-precision path obtained by the matching degree.

[0084] In the embodiments of this specification, a method for calculating the matching degree between a coordinate point and the corresponding high-precision alternative link is provided, which will be introduced in detail below.

[0085] In actual application, due to various road forms such as parallel roads and roads with upper and lower levels, it may cause errors or matching failures in the path matching results. In the embodiments of this specification, various factors are fully considered for path matching. Specifically, various factors are considered when calculating the matching degree between a coordinate point and an alternative link, thereby improving the accuracy of the path matching results.

[0086] In the embodiments of this specification, calculating the link matching degrees between each coordinate point in the coordinate point sequence and each link in the corresponding alternative link set may specifically include: calculating the evaluation items for the link matching degree between the target coordinate point in the coordinate point sequence and the corresponding target link, where the evaluation items include one or more of a distance angle deviation item, a slope deviation item, a migration item, a road type item, and a road grade item.

[0087] In actual application, the evaluation item scores of the evaluation items for the link matching degree between the target coordinate point in the coordinate point sequence and the corresponding target link may be calculated first; then, based on the evaluation item scores of the respective evaluation items and the preset evaluation item weights, the link matching degree between the target coordinate point and the target link may be calculated.

[0088] Among them, the link matching degree between the target coordinate point and the target link is negatively correlated with the scores of each evaluation item. The smaller the scores of each evaluation item, the higher the link matching degree between the target coordinate point and the target link. For example, the sum of the maximum values of the scores of each evaluation item may be 100, and the link matching degree = 100 - the evaluation item score.

[0089] In actual application, the weights of each evaluation item may be adjusted according to the actual situation. For example, due to the existence of ground objects such as toll booths, and when the number of ground objects is greater than the preset number (for example, 2), it may affect the width and angle of the road. In this case, in order to achieve a better matching effect and further improve the accuracy of path matching, the evaluation item weight corresponding to the distance angle deviation item may be reduced.

[0090] In an alternative embodiment, when the evaluation item includes a distance angle deviation item, calculating the link matching degrees between each coordinate point in the coordinate point sequence and each link in the corresponding alternative link set may specifically include: calculating the distance deviation and angle deviation between the target coordinate point in the coordinate point sequence and the corresponding target link; determining the distance angle deviation value between the target coordinate point and the target link based on the distance deviation and the distance deviation weight and the angle deviation and the angle deviation weight; and the link matching degree is negatively correlated with the distance angle deviation value.

[0091] For example, the distance angle deviation item may be calculated based on the formula matchCost = sqrt(diffD2 * factoryD + diffA2 * factoryA), where matchCost represents the value of the distance angle deviation item, diffD represents the distance deviation, diffA represents the angle deviation, factoryD represents the distance deviation weight, factoryA represents the angle deviation weight, and sqrt represents the square root operation.

[0092] Optionally, in the distance and angle deviation term, the distance deviation between the target coordinate point and the target link can be calculated based on the longitude deviation and latitude deviation between the target coordinate point and the target link.

[0093] For example, the distance deviation diffD can be calculated based on the formula diffD = (fabs(diffDX) * factoryX + fabs(diffDY)) * factoryY, where diffDX represents the longitude deviation, diffDY represents the latitude deviation, factoryX represents the longitude deviation weight, factoryY represents the latitude deviation weight, and fabs represents taking the absolute value.

[0094] In practical applications, to further improve the accuracy of path matching, when calculating the distance deviation diffD, the width of the road can be considered. In other words, the distance deviation diffD can be corrected based on the road width. Taking the precision deviation diffDX as an example, if the longitude deviation diffDX is less than half of the road width (linkWidth), it can be considered that the target coordinate point is on the target link, and at this time, diffDX can be directly set to 0; if the longitude deviation diffDX is greater than or equal to half of the road width (linkWidth), it can be considered that the target coordinate point is not on the target link, and at this time, diffDX = diffDX - linkWidth / 2 can be set. The same applies to the latitude deviation diffDY.

[0095] Optionally, in the distance and angle deviation term, the angle deviation between the target coordinate point and the target link specifically refers to the angle difference between the direction from the target coordinate point to the next coordinate point and the direction of the target link.

[0096] In practical applications, to further improve the accuracy of path matching, when calculating the angle deviation diffA, different adjustment coefficients can be multiplied according to different actual scenarios.

[0097] For example, if the target coordinate point is on the target path (for example, the longitude deviation diffDX is less than half of the road width), the angle deviation weight factoryA can be reduced.

[0098] In an alternative embodiment, when the evaluation item includes a slope deviation term, calculating the link matching degree between each coordinate point in the coordinate point sequence and each link in the corresponding set of candidate links may specifically include: determining a first slope value of a target coordinate point in the coordinate point sequence; determining a second slope value of a projection point of the target coordinate point perpendicular to the target link corresponding to the target coordinate point; calculating a slope difference between the first slope value and the second slope value; and the link matching degree is negatively correlated with the slope difference.

[0099] For example, the slope deviation term can be calculated based on the formula slopeCost = MaxSlopCost * slopFactory. Among them, slopeCost represents the slope deviation value; MaxSlopCost is a preset reference value for slope deviation, which can be set as needed. This value is positively correlated with the weight of the evaluation item corresponding to the slope deviation term. For example, it can be set to 20; slopFactory represents the difference between the first slope and the second slope. In actual applications, this difference is a coefficient with a value ranging from 0 to 1.

[0100] In an alternative embodiment, when the evaluation item includes a migration item, calculating the link matching degree between each coordinate point in the coordinate point sequence and each link in the corresponding alternative link set may specifically include: on the one hand, calculating the coordinate point distance between the target coordinate point and the previous coordinate point in the coordinate point sequence, calculating the projection point distance between the projection point of the target coordinate point perpendicular to the link matched by the target coordinate point and the projection point of the previous coordinate point perpendicular to the link matched by the previous coordinate point, and then calculating the point distance deviation between the coordinate point distance and the projection point distance; on the other hand, calculating the coordinate point connection angle between the previous coordinate point and the target coordinate point, calculating the projection point connection angle between the projection point of the previous coordinate point perpendicular to the link matched by the previous coordinate point and the projection point of the target coordinate point perpendicular to the link matched by the target coordinate point, and then calculating the connection angle deviation between the coordinate point connection angle and the projection point connection angle; thus, based on the point distance deviation and the connection angle deviation, the migration score between the target coordinate point and the previous coordinate point can be calculated; the link matching degree is negatively correlated with the migration score.

[0101] For example, the migration item can be calculated according to the formula moveCost = MaxLengthCost * abs(linkLength - baseLength) / linkLength + MaxAngCost * abs(linkAng - baseAng) / 180. Here, moveCost represents the value of the migration item; linkLength represents the length of the link starting from the projection point of the previous point on its corresponding link to the projection point of the current point on its corresponding link; baseLength represents the length from the previous point to the current point; linkAng represents the angle of the line connecting the projection point of the previous point on its corresponding link and the projection point of the current point on its corresponding link; baseAng represents the angle from the previous point to the current point; MaxLengthCost represents a preset reference value for distance deviation, which can be set as needed, and this value is positively correlated with the weight of the evaluation item corresponding to the migration item. For example, it can be set to 10; MaxAngCost represents a preset reference value for connection angle deviation, which can be set as needed, and this value is positively correlated with the weight of the evaluation item corresponding to the migration item. For example, it can be set to 10.

[0102] In an alternative embodiment, when the evaluation item includes a road type item, calculating the link matching degree between each coordinate point in the coordinate point sequence and each link in the corresponding alternative link set may specifically include: obtaining the first road type of the link to which the target coordinate point in the coordinate point sequence belongs; and obtaining the second road type of the target link corresponding to the target coordinate point; then, the road type deviation value corresponding to the road type item can be determined according to the first road type and the second road type; the road type deviation value is used to indicate whether the first road type is consistent with the second road type.

[0103] Specifically, it can be determined whether the first road type is consistent with the second road type to obtain a road type consistency determination result; if the road type consistency determination result indicates that the first road type is consistent with the second road type, the road type deviation value corresponding to the road type item can be set to 0; if the road type consistency determination result indicates that the first road type is inconsistent with the second road type, the road type deviation value corresponding to the road type item can be set to a preset deviation value, and the preset deviation value is greater than 0. The preset deviation value can be set as needed and is positively correlated with the score of the evaluation item corresponding to the road type item. For example, it can be set to 20.

[0104] Among them, the road type may include, for example, highways, urban expressways, ramps, general roads, etc.

[0105] In an alternative embodiment, when the evaluation item includes a road grade item, calculating the link matching degree between each coordinate point in the coordinate point sequence and each link in the corresponding alternative link set may specifically include: obtaining a first road grade of the link to which the target coordinate point in the coordinate point sequence belongs; and obtaining a second road grade of the target link corresponding to the target coordinate point; then, a road grade deviation value corresponding to the road grade item may be determined according to the first road grade and the second road grade; the road grade deviation value is used to reflect the difference between the first road grade and the second road grade.

[0106] Wherein, the link grade may be a grade set in the map data. For example, roads may be divided into grades 0 to 7.

[0107] For example, the score of the road grade item may be calculated based on the formula levelCost = levelBase * diffLevel. Wherein, levelCost is the score of the road grade item; diffLevel represents the difference between the link grade of the link with standard precision where the point is located and the road grade of the target link; levelBase is a preset reference value for the road grade item, which can be set as needed, and this value is positively correlated with the weight of the evaluation item corresponding to the road grade item. For example, it can be set to 15.

[0108] It should be noted that the calculation schemes of the evaluation item scores of the above-mentioned evaluation items are only exemplary and do not constitute a limitation to the technical solution of the present application.

[0109] Based on the solution of the embodiments of this specification, when performing path matching, multiple factors are referred to. Not only are the parameters related to the coordinate points (such as the distance and angle deviation items) considered, but also parameters such as slope, road use, and road level are considered. Therefore, the accuracy of path matching can be improved, and the problems of high path matching error and easy matching failure for special road forms such as parallel roads and upper and lower level roads can be overcome.

[0110] In the embodiments of this specification, the link information in the matched high-precision path may also be converted into lane information and provided for autonomous driving use.

[0111] Among them, the lane information may include two parts. One part is the basic information, that is, the lane groups (lanegroups) on each high-precision link are sorted in order and provided as a list. The other part is to recommend a lane-level route based on the basic information. Specifically, a point list may be provided according to the center line of the recommended lane, and lanes may be recommended according to the connection relationship of the lanegroups. In actual applications, the lane-level road may be calculated and determined based on the principles of less lane change and less time consumption.

[0112] Specifically, after obtaining the high-precision path information that matches the standard-precision path information in the standard-precision map data, it further includes: obtaining the lane group information corresponding to each link in the high-precision path; and determining the recommended lane lines based on each lane group according to the connection relationship of each link.

[0113] In addition, on the basis of obtaining the lane-level road, modules that use route information such as the automatic driving module or the display rendering module can use the route information according to their own needs. For example, the display rendering module can render the recommended lane-level route. Another example is that the automatic driving algorithm module can directly use the recommended lane for automatic driving. Another example is that the automatic driving module can also produce information that the automatic driving focuses on according to the detailed information of the lane grouping.

[0114] Based on the same idea, the embodiments of this specification also provide a device corresponding to the above method.

[0115] Figure 4 For the embodiments of this specification, it is Figure 1 a schematic structural diagram of a path matching device corresponding to Figure 4 As shown, the device may include:

[0116] A standard-precision map data providing module 402, configured to provide the standard-precision path information in the standard-precision map data to be matched;

[0117] A high-precision map data providing module 404, configured to provide the link information in the high-precision map data;

[0118] A first link matching module 406, configured to determine a first link that matches a first coordinate point in the coordinate point sequence from the high-precision map data; the coordinate point sequence is obtained by processing the standard-precision path information;

[0119] A second link matching module 408, configured to determine a second link that matches a second coordinate point adjacent to the first coordinate point from the first link or the subsequent link of the first link; the subsequent direction of the subsequent link is consistent with the extension trend from the first coordinate point to the second coordinate point;

[0120] A high-precision path determining module 410, configured to determine the path information of the path formed by the links that match each coordinate point in the coordinate point sequence as the high-precision path information that matches the standard-precision path information.

[0121] It can be understood that the above-mentioned modules refer to computer programs or program segments for performing one or more specific functions. In addition, the distinction of the above-mentioned modules does not mean that the actual program codes must also be separated.

[0122] Based on the same idea, an embodiment of this specification also provides a high-precision map engine, including: a standard-precision map data interface for accessing the standard-precision path information in the to-be-matched standard-precision map data;

[0123] a high-precision map data providing module for providing link information in the high-precision map data;

[0124] a first link matching module for determining a first link that matches a first coordinate point in the coordinate point sequence from the high-precision map data; the coordinate point sequence is obtained by performing data processing on the standard-precision path information;

[0125] a second link matching module for determining a second link that matches a second coordinate point adjacent to the first coordinate point from the first link or the consecutive link of the first link; the consecutive direction of the consecutive link is consistent with the extension trend from the first coordinate point to the second coordinate point;

[0126] a high-precision path determining module for determining the path information of the path formed by the links matching each coordinate point in the coordinate point sequence as the high-precision path information that matches the standard-precision path information.

[0127] The above describes specific embodiments of this specification. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve the desired result. Additionally, the processes depicted in the drawings do not necessarily require the specific order or consecutive order shown to achieve the desired result. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0128] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between each embodiment can be referred to each other.

[0129] The devices, equipment, and methods provided by the embodiments of this specification are corresponding. Therefore, the devices and equipment also have beneficial technical effects similar to the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the corresponding devices and equipment will not be elaborated here.

[0130] For the convenience of description, when describing the above devices, they are described separately as various units according to functions. Of course, when implementing this application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0131] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0132] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be realized by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for realizing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0133] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that realize the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0134] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for realizing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0135] It should also be noted that the term "comprise", "include" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, commodity or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, commodity or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, commodity or device comprising said element.

[0136] The present application may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application may also be practiced in a distributed computing environment where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media including storage devices.

[0137] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and modifications. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included within the scope of the claims of the present application.

Claims

1. A path matching method, characterized in that, The method includes: Determine the sequence of coordinate points corresponding to the standard-precision path information in the standard-precision map data to be matched; Determine, from the high-precision map data, a first link that matches the first coordinate point in the sequence of coordinate points; Determine, from the first link or the successive link of the first link, a second link that matches the second coordinate point adjacent to the first coordinate point; the successive direction of the successive link is consistent with the extension trend from the first coordinate point to the second coordinate point; Determine the path information of the path formed by the links that match each coordinate point in the sequence of coordinate points as the high-precision path information that matches the standard-precision path information.

2. The method according to claim 1, characterized in that, The determining of the sequence of coordinate points corresponding to the standard-precision path information in the standard-precision map data to be matched specifically includes: Determine the standard-precision path information in the standard-precision map data to be matched; Convert the standard-precision path information into a sequence of coordinate points; the sequence of coordinate points is data in units of coordinate points.

3. The method according to claim 1, characterized in that, The first coordinate point is the first point in the sequence of coordinate points; the determining, from the high-precision map data, of a first link that matches the first coordinate point in the sequence of coordinate points specifically includes: Taking the first coordinate point as the center and a preset distance value as the radius, determine the matching range of the first coordinate point in the high-precision map; Determine the links within the matching range as the first set of alternative links that match the first coordinate point; the first set of alternative links includes the first link.

4. The method according to claim 1, wherein The determining, from the first link or the successive link of the first link, of a second link that matches the second coordinate point adjacent to the first coordinate point specifically includes: Calculate the second projection point of the second coordinate point perpendicular to the first link or the successive link of the first link; Judge whether the second projection point is on the first link or the successive link of the first link to obtain a projection position judgment result; If the projection position judgment result indicates that the second projection point is on the first link or the successive link of the first link, then determine the first link or the successive link of the first link as the second alternative link that matches the second coordinate point; the second alternative link is included in the second set of alternative links, and the second set of alternative links includes the second link.

5. The method according to claim 4, wherein The successive link of the first link is determined by the following method: Based on the distance between the second coordinate point and the first coordinate point, determine a first successive link distance threshold; Determine, in the direction within the first successive link distance threshold and consistent with the extension trend from the first coordinate point to the second coordinate point, a first successive link corresponding to the first link; the distance between the first successive link and the second coordinate point is less than the first successive link distance threshold.

6. The method according to claim 1, wherein Multiple of the first links form a first set of alternative links; multiple of the second links form a second set of alternative links; Determining the path information of the path formed by the links matching each coordinate point in the coordinate point sequence as the high-precision path information matching the standard-precision path information specifically includes: Calculating the link matching degree between each coordinate point in the coordinate point sequence and each link in the corresponding alternative link set; Based on the connection relationship between the links in the alternative link sets corresponding to adjacent coordinate points in the coordinate point sequence, determining a set of high-precision alternative path information corresponding to the standard-precision path information to be matched; Based on the link matching degrees of the links included in each alternative path information in the set of high-precision alternative path information, determining the path matching degree between each alternative path information and the standard-precision path information to be matched; Determining the path with the highest path matching degree with the standard-precision path information in the set of high-precision alternative path information as the high-precision path information matching the standard-precision path information.

7. The method according to claim 6, wherein The calculating the link matching degree between each coordinate point in the coordinate point sequence and each link in the corresponding alternative link set specifically includes: Calculating the evaluation items for the link matching degree between the target coordinate point in the coordinate point sequence and the corresponding target link, and the evaluation items include one or more of a distance angle deviation item, a slope deviation item, a migration item, a road type item, and a road grade item.

8. The method according to claim 6, wherein The calculating the link matching degree between each coordinate point in the coordinate point sequence and each link in the corresponding alternative link set specifically includes: Calculating the distance deviation and angle deviation between the target coordinate point in the coordinate point sequence and the corresponding target link; Based on the distance deviation and the distance deviation weight and the angle deviation and the angle deviation weight, determining the distance angle deviation value between the target coordinate point and the target link; the link matching degree is negatively correlated with the distance angle deviation value.

9. The method according to claim 6, wherein The calculating the link matching degree between each coordinate point in the coordinate point sequence and each link in the corresponding alternative link set specifically includes: Determining the first slope value of the target coordinate point in the coordinate point sequence; Determining the second slope value of the projection point perpendicular to the target link corresponding to the target coordinate point; Calculating the slope difference between the first slope value and the second slope value; the link matching degree is negatively correlated with the slope difference.

10. The method according to claim 6, wherein The calculating the link matching degree between each coordinate point in the coordinate point sequence and each link in the corresponding alternative link set specifically includes: Calculating the coordinate point distance between the target coordinate point and the previous coordinate point in the coordinate point sequence; Calculating the projection point distance between the projection point perpendicular to the link matched by the target coordinate point and the projection point perpendicular to the link matched by the previous coordinate point; Calculating the point distance deviation between the coordinate point distance and the projection point distance; Calculate the angle of the line connecting the previous coordinate point and the target coordinate point; Calculate the angle of the line connecting the projection point of the previous coordinate point perpendicular to the link matched by the previous coordinate point and the projection point of the target coordinate point perpendicular to the link matched by the target coordinate point; Calculate the connection angle deviation between the angle of the line connecting the coordinate points and the angle of the line connecting the projection points; Based on the point distance deviation and the connection angle deviation, calculate the migration score between the target coordinate point and the previous coordinate point; the link matching degree is negatively correlated with the migration score.

11. The method according to claim 6, wherein The calculation of the link matching degree between each coordinate point in the coordinate point sequence and each link in the corresponding alternative link set specifically includes: Obtain the first road type of the link to which the target coordinate point in the coordinate point sequence belongs; Obtain the second road type of the target link corresponding to the target coordinate point; Determine the road type deviation value according to the first road type and the second road type; the road type deviation value is used to indicate whether the first road type and the second road type are consistent.

12. The method according to claim 6, wherein The calculation of the link matching degree between each coordinate point in the coordinate point sequence and each link in the corresponding alternative link set specifically includes: Obtain the first road grade of the link to which the target coordinate point in the coordinate point sequence belongs; Obtain the second road grade of the target link corresponding to the target coordinate point; Determine the road grade deviation value according to the first road grade and the second road grade; the road grade deviation value is used to reflect the difference between the first road grade and the second road grade.

13. A path matching device, characterized in that, The device includes: A standard-precision map data providing module, configured to provide the standard-precision path information in the to-be-matched standard-precision map data; A high-precision map data providing module, configured to provide link information in the high-precision map data; A first link matching module, configured to determine a first link that matches the first coordinate point in the coordinate point sequence from the high-precision map data; the coordinate point sequence is obtained by performing data processing on the standard-precision path information; A second link matching module, configured to determine a second link that matches the second coordinate point adjacent to the first coordinate point from the first link or the subsequent link of the first link; the subsequent direction of the subsequent link is consistent with the extension trend from the first coordinate point to the second coordinate point; A high-precision path determining module, configured to determine the path information of the path formed by the links matched by each coordinate point in the coordinate point sequence as the high-precision path information that matches the standard-precision path information.

14. A high-precision map engine, including a standard-precision map data interface for accessing the standard-precision path information in the to-be-matched standard-precision map data; A high-precision map data providing module, configured to provide link information in the high-precision map data; A first link matching module, configured to determine a first link that matches the first coordinate point in the coordinate point sequence from the high-precision map data; The coordinate point sequence is obtained by processing the data of the standard-precision path information; A second link matching module, configured to determine, from the first link or a subsequent link of the first link, a second link that matches a second coordinate point adjacent to the first coordinate point; the subsequent direction of the subsequent link is consistent with the extension trend from the first coordinate point to the second coordinate point; A high-precision path determination module, configured to determine the path information of the path formed by the links matched with the respective coordinate points in the coordinate point sequence as the high-precision path information that matches the standard-precision path information.

Images