Intersection path generation method and device of map, electronic equipment, storage medium and program product

Abstract

The embodiment of the invention provides a map intersection path generation method and device, electronic equipment, a storage medium and a program product. Relates to the technical field of high-precision maps. The method comprises the following steps: acquiring a trajectory of a self-moving device moving in a current scene, and acquiring lane information of a lane in a preset map; and determining the topological relation of the lane on the intersection according to the trajectory and the lane information. Determining the passing probability of each preset type of passing path on the intersection according to the topological relation; and determining a target driving path of the intersection according to the passing probability, and updating the target driving path to a preset map. The method is used for achieving the effect of improving the accuracy of the passing path of the intersection.

Description

Technical Field

[0001] The present application relates to the field of high-precision map technology, and in particular to the field of high-precision mapping based on crowdsourced data, and in particular to a method, device, electronic device, storage medium and program product for generating intersection paths of a map. Background Art

[0002] At present, high-precision maps are essential technologies in the field of autonomous driving and assisted driving, providing important information for perception, positioning, decision-making and other aspects of the autonomous driving process. Intersections are an important part of high-precision maps. Usually, intersections lack information such as lane boundaries, travel paths, and travel directions. High-precision maps need to obtain and express this information in a certain way.

[0003] In the prior art, the general method for making high-precision maps of intersections is: use acquisition equipment to obtain intersection lane identification information, use determined intersection lane topology connection rules to obtain intersection lane topology connection lines, and generate high-precision map elements such as reference lines and lane center lines within the intersection through a series of rules based on intersection parameters (referring to the angle and distance of lane lines) and the topological relationship between intersection lanes.

[0004] However, in the prior art, it is usually necessary to collect equipment to obtain intersection signs, manually set a series of rules such as relevant topological connection rules, traffic direction rules, lane centerline rules, etc., and generate reference lines and lane centerlines in the intersection according to the determined series of rules. Therefore, the above method uses a large number of manually summarized rules, and the generated results are inconsistent with the real world scene. Moreover, the intersection topology is completely generated based on the intersection signs, and the actual traffic of the intersection lanes may not be completely consistent with the intersection signs, which leads to inaccurate traffic paths at the intersection. Summary of the invention

[0005] The embodiments of the present application provide a method, device, electronic device, storage medium and program product for generating a map intersection path, so as to achieve the effect of improving the accuracy of the traffic path at the intersection.

[0006] In a first aspect, an embodiment of the present application provides a method for generating a road intersection path of a map, comprising:

[0007] Obtain the trajectory of the mobile device in the current scene, and obtain the lane information of the lane in the preset map;

[0008] Determining a topological relationship of the lanes at the intersection according to the trajectory and the lane information;

[0009] According to the topological relationship, the pass probability of each preset type of pass path at the intersection is determined; according to the pass probability, the target driving path of the intersection is determined, and the target driving path is updated to the preset map.

[0010] In a possible implementation, determining the topological relationship of the lane at the intersection according to the trajectory line and the lane information includes:

[0011] Generate a lane model for each lane according to each lane outside the intersection represented by the lane information;

[0012] For each of the trajectory lines and the lane models, determining a candidate lane model associated with a trajectory point in the trajectory line;

[0013] The topological relationship of the lanes at the intersection is determined according to the candidate lane model; wherein the topological relationship includes the number of travel trajectories between the lanes at the intersection.

[0014] In a possible implementation, for each of the trajectory lines and the lane model, determining a candidate lane model associated with a trajectory point in the trajectory line includes:

[0015] For each of the trajectory lines, if the distance between the trajectory point on the trajectory line and the lane model is less than a preset distance threshold, a lane model whose distance is less than the distance threshold is determined as a candidate lane model associated with the trajectory point in the trajectory line.

[0016] In a possible implementation, the lanes outside the intersection include multiple, parallel and adjacent lanes forming a road;

[0017] The preset types of passage paths include a first preset type of passage path, a second preset type of passage path, a third preset type of passage path, and a fourth preset type of passage path;

[0018] Among them, the first preset type of passage path is the trajectory of the road entering the intersection to the various roads at the intersection; the second preset type of passage path is the trajectory of the road entering the intersection to the road exiting the intersection; the third preset type of passage path is the trajectory of the lane outside the entrance to the intersection to the road exiting the intersection; the fourth preset type of passage path is a path that passes through the lane outside the intersection, the intersection, and other lanes outside the intersection in sequence.

[0019] In a possible implementation, determining the target driving path of the intersection according to the traffic probability includes:

[0020] For each preset type of pass probability of a pass path, determine a pass probability less than a preset pass threshold, and filter the travel direction corresponding to the pass probability less than the pass threshold;

[0021] The target driving path of the intersection is determined according to the filtered traveling direction and a passing probability that is greater than or equal to a preset passing threshold.

[0022] In a possible implementation manner, the preset types of passing paths include a first preset type of passing path, a second preset type of passing path, a third preset type of passing path, and a fourth preset type of passing path;

[0023] The passing probability of each preset type of passing path, determining the passing probability less than a preset passing threshold, and filtering the travel direction corresponding to the passing probability less than the passing threshold, includes:

[0024] For the pass probability of the pass path of the first preset type, determine a first pass probability that is less than a preset first pass threshold, and filter the travel direction corresponding to the first pass probability;

[0025] For the pass probability of the pass path of the second preset type, determine a second pass probability that is less than a preset second pass threshold, and filter the travel direction corresponding to the second pass probability;

[0026] For the pass probability of the pass path of the third preset type, determine a third pass probability that is less than a preset third pass threshold, filter the travel direction corresponding to the third pass probability; and filter the travel direction corresponding to the pass probability that is less than a preset fourth pass threshold;

[0027] With respect to the number of passes of the fourth preset type of pass path, a target number of passes that is less than a preset number of passes threshold is determined, and a pass direction corresponding to the target number of passes is filtered.

[0028] In a possible implementation, determining the target driving path of the intersection according to the filtered traveling direction and the passing probability greater than or equal to a preset passing threshold includes:

[0029] Determine the traffic result information of the intersection according to the filtered traveling direction and the traffic probability greater than or equal to the preset traffic threshold; wherein the traffic result information indicates whether the lane of the intersection is passable;

[0030] The target driving path of the intersection is determined according to the traffic result information.

[0031] In a possible implementation manner, the pass probability greater than or equal to the pass threshold includes the pass probability of a first preset type of pass path, the pass probability of a second preset type of pass path, the pass probability of a third preset type of pass path, and the pass times of a fourth preset type of pass path;

[0032] Determining the target driving path of the intersection according to the traffic result information includes:

[0033] If the passage result information represents the passage probability of the first preset type of passage path, the passage probability of the second preset type of passage path, the passage probability of the third preset type of passage path, and the number of passages of the fourth preset type of passage path, then it is determined that the lane outside the intersection to the lane passing through the intersection is a passable path;

[0034] A target driving path of the intersection is determined according to the traversable path and the topological relationship.

[0035] In a possible implementation manner, the lane model includes lane information; wherein the lane information includes any one or more of the following:

[0036] Lane markings, lane left boundary, lane right boundary, lane centerline, direction of travel, and associated roads at the intersection.

[0037] In a second aspect, an embodiment of the present application provides a device for generating a road intersection path of a map, comprising:

[0038] An acquisition module, used to acquire a trajectory line of a mobile device moving in a current scene, and to acquire lane information of a lane in a preset map;

[0039] A first determination module, used to determine the topological relationship of the lanes at the intersection according to the trajectory line and the lane information;

[0040] A second determination module, configured to determine the pass probability of each preset type of pass path at the intersection according to the topological relationship;

[0041] A third determination module is used to determine the target driving path of the intersection according to the passing probability;

[0042] An updating module is used to update the target driving path to the preset map.

[0043] In a possible implementation manner, the first determining module includes:

[0044] A generating unit, configured to generate a lane model of each lane according to each lane outside the intersection represented by the lane information;

[0045] A first determining unit, configured to determine, for each of the trajectory lines and the lane model, a candidate lane model associated with a trajectory point in the trajectory line;

[0046] The second determining unit is used to determine the topological relationship of the lanes at the intersection according to the candidate lane model; wherein the topological relationship includes the number of passing trajectories between the lanes at the intersection.

[0047] In a possible implementation manner, the first determining unit is specifically configured to:

[0048] For each of the trajectory lines, if the distance between the trajectory point on the trajectory line and the lane model is less than a preset distance threshold, a lane model whose distance is less than the distance threshold is determined as a candidate lane model associated with the trajectory point in the trajectory line.

[0049] In a possible implementation, the lanes outside the intersection include multiple, parallel and adjacent lanes forming a road;

[0050] The preset types of passage paths include a first preset type of passage path, a second preset type of passage path, a third preset type of passage path, and a fourth preset type of passage path;

[0051] Among them, the first preset type of passage path is the trajectory of the road entering the intersection to the various roads at the intersection; the second preset type of passage path is the trajectory of the road entering the intersection to the road exiting the intersection; the third preset type of passage path is the trajectory of the lane outside the entrance to the intersection to the road exiting the intersection; the fourth preset type of passage path is a path that passes through the lane outside the intersection, the intersection, and other lanes outside the intersection in sequence.

[0052] In a possible implementation manner, the third determining module includes:

[0053] A third determining unit is used to determine the pass probability less than a preset pass threshold for each preset type of pass path, and filter the travel direction corresponding to the pass probability less than the pass threshold;

[0054] The fourth determination unit is used to determine the target driving path of the intersection according to the filtered traveling direction and the passing probability greater than or equal to a preset passing threshold.

[0055] In a possible implementation manner, the preset types of passing paths include a first preset type of passing path, a second preset type of passing path, a third preset type of passing path, and a fourth preset type of passing path;

[0056] The third determining unit is specifically configured to:

[0057] For the pass probability of the pass path of the first preset type, determine a first pass probability that is less than a preset first pass threshold, and filter the travel direction corresponding to the first pass probability;

[0058] For the pass probability of the pass path of the second preset type, determine a second pass probability that is less than a preset second pass threshold, and filter the travel direction corresponding to the second pass probability;

[0059] For the pass probability of the pass path of the third preset type, determine a third pass probability that is less than a preset third pass threshold, filter the travel direction corresponding to the third pass probability; and filter the travel direction corresponding to the pass probability that is less than a preset fourth pass threshold;

[0060] With respect to the number of passes of the fourth preset type of pass path, a target number of passes that is less than a preset number of passes threshold is determined, and a pass direction corresponding to the target number of passes is filtered.

[0061] In a possible implementation manner, the fourth determining unit includes:

[0062] A first determination subunit is used to determine the traffic result information of the intersection according to the filtered travel direction and the traffic probability greater than or equal to a preset traffic threshold; wherein the traffic result information indicates whether the lane of the intersection is passable;

[0063] The second determining subunit is used to determine a target driving path of the intersection according to the passage result information.

[0064] In a possible implementation manner, the pass probability greater than or equal to the pass threshold includes the pass probability of a first preset type of pass path, the pass probability of a second preset type of pass path, the pass probability of a third preset type of pass path, and the pass times of a fourth preset type of pass path;

[0065] The second determining subunit is specifically used for:

[0066] If the passage result information represents the passage probability of the first preset type of passage path, the passage probability of the second preset type of passage path, the passage probability of the third preset type of passage path, and the number of passages of the fourth preset type of passage path, then it is determined that the lane outside the intersection to the lane passing through the intersection is a passable path;

[0067] A target driving path of the intersection is determined according to the traversable path and the topological relationship.

[0068] In a possible implementation manner, the lane model includes lane information; wherein the lane information includes any one or more of the following:

[0069] Lane markings, lane left boundary, lane right boundary, lane centerline, direction of travel, and associated roads at the intersection.

[0070] In a third aspect, an embodiment of the present application provides an electronic device, including: a memory, a processor;

[0071] The memory stores computer-executable instructions;

[0072] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the above first aspect and / or various possible implementations of the first aspect.

[0073] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the first aspect above and / or various possible implementations of the first aspect.

[0074] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the above first aspect and / or various possible implementation methods of the first aspect.

[0075] The method, device, electronic device, storage medium and program product for generating a path at an intersection of a map provided in an embodiment of the present application obtain a trajectory line of a mobile device moving in a current scene, and obtain lane information of lanes in a preset map. Based on the trajectory line and lane information, determine the topological relationship of the lanes at the intersection. Based on the topological relationship, determine the pass probability of each preset type of pass path at the intersection; based on the pass probability, determine the target driving path of the intersection, and update the target driving path to the preset map. In this solution, a topological relationship is generated according to the traffic relationship of the trajectory in each lane of the intersection, and the driving path between the lanes of the intersection is fitted according to the traffic paths of each preset type of the trajectory at the intersection, so as to determine the target driving path of the intersection. The algorithm is simple and conforms to the actual vehicle behavior. According to the traffic probability of the trajectory at each level of the intersection, the erroneous topological relationship caused by a small amount of abnormal driving behavior can be effectively identified, so that the final target driving path is real, effective and accurate. It solves the reference information within the intersection range that traditional high-precision maps cannot provide in real life, such as the actual topology of the road, the vehicle driving path between lanes, etc., and provides guidance information that is closer to the actual situation for autonomous driving, so as to achieve the effect of improving the accuracy of the traffic path at the intersection. BRIEF DESCRIPTION OF THE DRAWINGS

[0076] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0077] Figure 1 A flowchart of a method for generating a road intersection path for a map provided in an embodiment of the present application Figure 1 ;

[0078] Figure 2 A flowchart of another method for generating a road intersection path on a map provided in an embodiment of the present application Figure 2 ;

[0079] Figure 3 A scenario diagram of a method for generating a road intersection path on a map provided in an embodiment of the present application Figure 1 ;

[0080] Figure 4 A scenario diagram of a method for generating a road intersection path on a map provided in an embodiment of the present application Figure 2 ;

[0081] Figure 5 A scenario diagram of a method for generating a road intersection path on a map provided in an embodiment of the present application Figure 3 ;

[0082] Figure 6 A scenario diagram of a method for generating a road intersection path on a map provided in an embodiment of the present application Figure 4 ;

[0083] Figure 7 A scenario diagram of a method for generating a road intersection path on a map provided in an embodiment of the present application Figure 5 ;

[0084] Figure 8 A scenario diagram of a method for generating a road intersection path on a map provided in an embodiment of the present application Figure 6 ;

[0085] Fig. 9 A schematic diagram of the structure of a device for generating a road intersection path for a map provided in an embodiment of the present application;

[0086] Fig.10 A schematic diagram of the structure of another device for generating a road intersection path for a map provided in an embodiment of the present application;

[0087] Fig.11 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0088] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0089] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0090] At present, high-precision maps are essential technologies in the field of autonomous driving and assisted driving, providing important information for perception, positioning, decision-making and other aspects of the autonomous driving process. Intersections are an important part of high-precision maps. Usually, intersections lack information such as lane boundaries, travel paths, and travel directions. High-precision maps need to obtain and express this information in a certain way.

[0091] In one example, the general method for making high-precision maps of intersections is: use acquisition equipment to obtain intersection lane sign information, use the determined intersection lane topology connection rules to obtain the intersection lane topology connection lines, and generate high-precision map elements such as intersection reference lines and lane center lines through a series of rules based on intersection parameters (referring to the angle and distance of lane lines) and the topological relationship between intersection lanes. However, in the prior art, it is usually necessary to use acquisition equipment to obtain intersection signs, manually set a series of rules such as relevant topology connection rules, traffic direction rules, lane centerline rules, etc., and generate intersection reference lines and lane center lines according to a determined series of rules. Therefore, the above method uses a large number of manually summarized rules, and the generated results are inconsistent with the real-world scene. Moreover, the intersection topology is completely generated based on the intersection signs, and the actual traffic of the intersection lanes may not be completely consistent with the intersection signs, which leads to inaccurate traffic paths at the intersection.

[0092] Terminology explanation:

[0093] Link: It is the abstract information of the road created in the map. One link is associated with multiple lanes.

[0094] In combination with the above-mentioned scenarios, it can be seen that in the prior art, there is a technical problem of inaccurate traffic paths at intersections.

[0095] The method for generating a path at an intersection of a map provided in this application solves the technical problem of inaccurate travel paths at intersections.

[0096] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0097] Figure 1 A schematic diagram of a method for generating a road intersection path for a map provided in this application Figure 1 ,like Figure 1 As shown, the method includes:

[0098] S101. Obtain a trajectory line of a mobile device moving in a current scene, and obtain lane information of a lane in a preset map.

[0099] For example, the execution subject of this embodiment may be an electronic device, or a terminal device, or a device or apparatus for generating a road intersection path of a map, or other devices or apparatuses that can execute this embodiment, and no limitation is imposed on this. In this embodiment, the execution subject is described as an electronic device.

[0100] First, multiple trajectory lines of the mobile device moving in the current scene are obtained, and lane information in a preset map is obtained. The preset map can be a high-precision map. Among them, the trajectory line refers to the route passing through the lane and intersection. The trajectory line includes multiple trajectory points, and each trajectory point has information such as time and coordinates; the lane information represents the lanes (lanes) in each direction outside the intersection. The lanes in each direction outside the intersection include multiple lanes, and multiple parallel and adjacent lanes form a road (i.e., link). The intersection includes a T-junction, a crossroads, etc., which is not limited to this. For example, the lanes outside the T-junction are divided into lanes in three directions, and each direction includes multiple parallel and adjacent lanes, that is, the lane information includes lanes in three directions, and each direction includes multiple parallel and adjacent lanes; the lanes outside the crossroads are divided into lanes in four directions, and each direction includes multiple parallel and adjacent lanes, that is, the lane information includes lanes in four directions, and each direction includes multiple parallel and adjacent lanes.

[0101] S102: Determine the topological relationship of the lanes at the intersection according to the trajectory line and lane information.

[0102] For example, the topological relationship of lanes at the intersection is determined based on information such as the number of paths that the multiple trajectories pass through on each road, lane, and intersection, wherein the topological relationship includes the number of paths that pass between lanes at the intersection.

[0103] S103, determining the pass probability of each preset type of pass path at the intersection according to the topological relationship; determining the target driving path of the intersection according to the pass probability, and updating the target driving path to the preset map.

[0104] Exemplarily, since the lane behavior passing through the intersection has multiple dimensions, for example, the lane behavior includes sequentially passing through a link, an intersection, and another link; sequentially passing through a lane, an intersection, and another link; sequentially passing through a lane, an intersection, and another lane, etc. Among them, for sequentially passing through a link, an intersection, and another link, it is necessary to know whether the lane behavior can turn left, turn right, go straight, etc. For sequentially passing through a lane, an intersection, and another link, it is necessary to know whether the lane behavior can turn left, turn right, go straight, etc. For sequentially passing through a lane, an intersection, and another lane, it is necessary to know which lane of the intersection the lane behavior can reach in the case of going straight, which lane of the intersection the lane behavior can reach in the case of turning right, which lane of the intersection the lane behavior can reach in the case of turning left, etc. Therefore, for complex road conditions, in order to accurately know the actual passing path of the trajectory line, it is necessary to determine the passing probabilities of multiple preset types of passing paths. The preset types of passing paths refer to the passing paths of each level of the intersection under different driving scenarios, that is, the passing paths under multiple dimensions.

[0105] For example, the preset types of passage paths include a first preset type of passage path, a second preset type of passage path, a third preset type of passage path, and a fourth preset type of passage path; the first preset type of passage path is the trajectory of the road entering the intersection to the various roads at the intersection; the second preset type of passage path is the trajectory of the road entering the intersection to the road exiting the intersection; the third preset type of passage path is the trajectory of the lane outside the entrance to the intersection to the road exiting the intersection; the fourth preset type of passage path is a path that passes through the lane outside the intersection, the intersection, and other lanes outside the intersection in sequence.

[0106] In this step, the pass probability of each preset type of pass path at the intersection is calculated based on the topological relationship. Based on the pass probability, the topological reliability of the lane outside the intersection to the lane passing the intersection is calculated, and the target driving path of the intersection is determined based on the topological reliability, and the target driving path is updated to the preset map, thereby obtaining an updated high-precision preset map. It should be noted that the specific calculation process of each pass path is referred to in step S205 below, which will not be repeated here.

[0107] The method for generating a path at an intersection of a map provided in an embodiment of the present application obtains a trajectory line of a mobile device moving in a current scene, and obtains lane information of lanes in a preset map. According to the trajectory line and lane information, the topological relationship of the lanes at the intersection is determined. According to the topological relationship, the pass probability of each preset type of pass path at the intersection is determined; according to the pass probability, the target driving path of the intersection is determined, and the target driving path is updated to the preset map. In this scheme, a topological relationship is generated according to the pass relationship of the trajectory at each lane of the intersection, and the driving path passing between the lanes of the intersection is fitted according to the pass paths of each preset type of the trajectory at the intersection, and then the target driving path of the intersection is determined. The algorithm is simple and conforms to the actual vehicle behavior. According to the pass probability of the trajectory at each level of the intersection, the erroneous topological relationship caused by a small amount of abnormal driving behavior can be effectively identified, so that the target driving path finally obtained is real, effective and accurate, which solves the reference information within the intersection range that traditional high-precision maps cannot provide in real life, such as the actual topology of the road, the vehicle driving path between lanes, etc., and provides guidance information that is closer to the actual situation for automatic driving, so as to achieve the effect of improving the accuracy of the pass path at the intersection.

[0108] Figure 2 A schematic diagram of a method for generating a road intersection path for a map provided in this application Figure 2 ,like Figure 2 As shown, in this embodiment Figure 1 Based on the embodiment, a method for generating a road intersection path of a map is described in detail, and the method includes:

[0109] S201. Obtain a trajectory line of a mobile device moving in a current scene, and obtain lane information of a lane in a preset map.

[0110] For example, this step can be referred to Figure 1 Step 101 in the above is not described in detail.

[0111] S202: Generate a lane model for each lane outside the intersection according to the lane information.

[0112] In one example, the lane model includes lane information; wherein the lane information includes any one or more of the following: lane marking, lane left boundary, lane right boundary, lane centerline, travel direction, and associated roads at the intersection. Multiple lanes are associated in a link.

[0113] For example, Figure 3 A scenario diagram of a method for generating a road intersection path on a map provided in an embodiment of the present application Figure 1 ,like Figure 3As shown, the intersection is a crossroads, and each direction includes a link, link1, link2, link3 and link4. A link includes multiple lanes, and the center line of each lane is a dotted line with an arrow. For example, link1 includes 4 dotted lines with arrows, that is, it includes 4 lanes; link2 includes 2 dotted lines with arrows, that is, it includes 2 lanes; link3 and link4 refer to link1 and link2, and will not be repeated here. Electronic devices can use the lane information in the high-precision map to establish a lane model for lanes with real physical boundaries, that is, each lane corresponds to a lane model. Among them, the lane model contains information such as lane identification ID, left and right boundaries of the lane, lane centerline, driving direction, and associated roads of the intersection (roads are links).

[0114] S203: For each trajectory line and lane model, determine a candidate lane model associated with a trajectory point in the trajectory line.

[0115] In one example, S203 includes: for each trajectory line, if the distance between the trajectory point on the trajectory line and the lane model is less than a preset distance threshold, determining a lane model whose distance is less than the distance threshold as a candidate lane model associated with the trajectory point in the trajectory line.

[0116] Exemplarily, for each high-precision trajectory including multiple trajectory points, the electronic device can associate them with the link through spatial distance, thereby obtaining a lane model that may be associated with the trajectory point, and using the possibly associated lane model as a candidate lane model for trajectory positioning.

[0117] For example, for each trajectory point, each lane model is traversed, the distance d between the trajectory point and the lane boundary of the lane model is calculated, and the lateral distance and direction of the trajectory point relative to the lane boundary are obtained according to the lane travel direction, which is negative on the left and positive on the right, to determine whether the trajectory point is in a certain lane model.

[0118] Furthermore, the criteria for locating a track point to a lane model are as follows: if the lane model has two lane boundaries, the track point must be in the middle of the two lane boundaries; if the lane model has only one lane boundary, the track point must be on the right side of the left lane boundary, or on the left side of the right lane boundary, and the distance d to the lane boundary is less than the lane width w. Successfully located track points are associated with the corresponding lane models. If a track point fails to locate successfully after traversing all lane models, the track point is marked as not located in the lane.

[0119] Figure 4 A scenario diagram of a method for generating a road intersection path on a map provided in an embodiment of the present application Figure 2 ,like Figure 4As shown, both trajectory points A and B have two lane models: lane model 1 and lane model 2. Point A is located to the left of the left boundary of lane model 1 and to the right of the left boundary of lane model 2, and the distance d1 from point A to the left boundary of lane model 2 is less than the lane width w, so trajectory point A is located in lane 2. Trajectory point B is located to the right of the left boundary of lane model 2 and to the left of the right boundary, and the distance d2 from point B to the left boundary of lane model 2 is less than the lane width w, and the distance d3 from point B to the right boundary of lane model 2 is less than the lane width w, so trajectory point B is located in lane model 2.

[0120] Therefore, the physical lane boundary information in the high-precision map and the lane corresponding to the lane model to which the high-precision trajectory belongs are used to ensure that the information is consistent with the real world from the source, thereby improving the accuracy of the lane.

[0121] S204. Determine a topological relationship of lanes at the intersection based on the candidate lane model; wherein the topological relationship includes the number of travel trajectories between lanes at the intersection.

[0122] For example, the electronic device can obtain the candidate lane models associated with the intersection through the associated link information of the intersection obtained in step S202. According to the positioning results of the trajectory points, all lanes passed by all trajectories can be identified, and then the topological relationship of the corresponding lanes of the intersection can be established according to the associated candidate lane models and all lanes passed by all trajectories.

[0123] Figure 5 A scenario diagram of a method for generating a road intersection path on a map provided in an embodiment of the present application Figure 3 ,like Figure 5 As shown, all trajectories of the intersection are traversed, for example, the trajectory passes through lane 1 and lane 2, a topological relationship is established between lane 1 and lane 2, and then the topological relationship of all lanes of the intersection is obtained. Figure 6 A scenario diagram of a method for generating a road intersection path on a map provided in an embodiment of the present application Figure 4 ,like Figure 6 As shown, the topological relationship includes the number of passing trajectories between lanes at the intersection.

[0124] S205: Determine the passing probability of each preset type of passing path at the intersection according to the topological relationship.

[0125] In one example, there are multiple lanes outside the intersection, and the multiple parallel and adjacent lanes form a road; the preset types of passing paths include a first preset type of passing path, a second preset type of passing path, a third preset type of passing path, and a fourth preset type of passing path; wherein, the first preset type of passing path is the trajectory line of the road entering the intersection to the various roads at the intersection; the second preset type of passing path is the trajectory line of the road entering the intersection to the road exiting the intersection; the third preset type of passing path is the trajectory line of the lane outside the intersection to the road exiting the intersection; the fourth preset type of passing path is a path that passes through lanes outside the intersection, the intersection, and other lanes outside the intersection in sequence.

[0126] S206 . For each preset type of travel path, determine a travel probability that is less than a preset travel threshold, and filter the travel directions corresponding to the travel probabilities that are less than the travel threshold.

[0127] In one example, the preset types of passage paths include a first preset type of passage path, a second preset type of passage path, a third preset type of passage path, and a fourth preset type of passage path; S206 includes: for the passage probability of the first preset type of passage path, determining a first passage probability that is less than a preset first passage threshold, and filtering the travel direction corresponding to the first passage probability; for the passage probability of the second preset type of passage path, determining a second passage probability that is less than a preset second passage threshold, and filtering the travel direction corresponding to the second passage probability; for the passage probability of the third preset type of passage path, determining a third passage probability that is less than a preset third passage threshold, filtering the travel direction corresponding to the third passage probability; and filtering the travel direction corresponding to the passage probability that is less than a preset fourth passage threshold; for the passage number of the fourth preset type of passage path, determining a target passage number that is less than a preset passage number threshold, and filtering the passage direction corresponding to the target passage number.

[0128] Exemplarily, for steps S205 and S206, in order to obtain the topological reliability of lane to lane, it is necessary to judge the pass probability of the pass path at each level of the intersection. First, the pass probability to other links at the intersection is judged link by link. For link to link with a pass trajectory, the pass probability of each lane in the link entering the intersection to the link exiting the intersection is further judged. For lanes entering the intersection and linking the exit intersection with a pass trajectory, the pass probability of each lane from the lane entering the intersection to the link of the exit intersection is further judged. Thus, for lanes with established topological relationships, the pass probabilities of link→link, lane→link, lane→lane and other levels are calculated, and the topological reliability of the lane is determined according to different pass probabilities. Figure 7A scenario diagram of a method for generating a road intersection path on a map provided in an embodiment of the present application Figure 5 ,like Figure 7 As shown, the specific process is as follows:

[0129] like Figure 7 As shown in (a), the pass probability of the first preset type of pass path is determined according to the topological relationship and the number of pass trajectories in the topological relationship. The first preset type of pass path is the trajectory line entering the intersection road (link) to each road (link) at the intersection, that is, link->link. Multiple pass trajectories are divided into three groups link->link. Specifically, the pass probability of the trajectory entering the intersection link to each link at the intersection is calculated, and the first pass probability less than the preset first pass threshold thr1 is determined, and the travel direction of the first pass probability is filtered. For example, in this implementation, the threshold is set to thr1 = 0.01, and there is no limitation on this.

[0130] like Figure 7 As shown in (a), determine the pass probability of the second preset type of pass path. The second preset type of pass path is the trajectory line of the road entering the intersection to the road exiting the intersection, that is, the entry intersection link->exit intersection link. Specifically, determine the pass possibility of each entry intersection link->exit intersection link, calculate the pass probability of each entry intersection link passing to the exit intersection link, determine the second pass probability that is less than the preset second pass threshold, and filter the travel direction of the second pass probability. Among them, the second pass threshold = deviation ratio rate1*expected probability, and the expected probability is calculated as: the number of lanes in the entry intersection link that pass to the exit intersection link is n, and the expected probability e=1 / n; in this implementation, the deviation ratio rate1=0.8, which is not limited.

[0131] like Figure 7As shown in (b), determine the pass probability of the third preset type of pass path. The third preset type of pass path is the trajectory line of the lane outside the entrance to the road that passes to the exit intersection, that is, the entrance lane (lane) -> exit link, lane -> link. Specifically, determine the pass possibility of the entrance lane -> exit link, calculate the pass probability of the entrance lane passing to each exit link, determine the third pass probability less than the preset third pass threshold, filter the travel direction corresponding to the third pass probability, and filter the direction with a pass probability less than the preset fourth pass threshold. Among them, the third pass threshold can be 0.05, which is not limited to this; the fourth pass threshold = deviation ratio rate2*expected probability, and the expected probability is calculated as: the number of lanes in the entrance lane that pass to the exit link is n, and the expected probability e=1 / n; in this implementation, the deviation ratio rate2=0.8, which is not limited to this.

[0132] like Figure 7 As shown in (c), in order to more accurately determine whether the fourth preset type of pass path is passable, it is necessary to determine the pass times of the fourth preset type of pass path, for example, the pass times are 0 times, 1 times, 5 times, or 100 times, etc. For data with fewer times such as 1 time, 5 times, etc., in order to prevent the corresponding low pass probability from being filtered out, it is necessary to further determine the pass times of the fourth preset type of pass path. The fourth preset type of pass path is to pass through the lane outside the intersection, the intersection, and other lanes outside the intersection in sequence, that is, lane (lane) -> lane (lane), determine the target pass times less than the preset pass times threshold k, and filter the pass directions corresponding to the target pass times. For example, in this implementation, k = 5, which is not limited.

[0133] S207: Determine a target driving path at the intersection according to the filtered traveling direction and a passing probability that is greater than or equal to a preset passing threshold.

[0134] In one example, S207 includes: determining the traffic result information of the intersection based on the filtered travel direction and the traffic probability greater than or equal to a preset traffic threshold; wherein the traffic result information represents whether the lane of the intersection is passable; and determining the target driving path of the intersection based on the traffic result information.

[0135] In one example, the pass probability greater than or equal to the pass threshold includes the pass probability of a first preset type of pass path, the pass probability of a second preset type of pass path, the pass probability of a third preset type of pass path, and the pass count of a fourth preset type of pass path; "determine the target driving path of the intersection based on the pass result information", including: if the pass result information represents the pass probability of a first preset type of pass path, the pass probability of a second preset type of pass path, the pass probability of a third preset type of pass path, and the pass count of a fourth preset type of pass path, then determine that the lane outside the intersection to the lane passing the intersection is a passable path; determine the target driving path of the intersection based on the passable path and the topological relationship.

[0136] Exemplarily, after filtering, the remaining pass probabilities greater than or equal to the pass threshold include the pass probability of the first preset type of pass path, the pass probability of the second preset type of pass path, the pass probability of the third preset type of pass path, and the number of passes of the fourth preset type of pass path. According to the remaining travel direction after filtering and the pass probability greater than or equal to the preset pass threshold, the pass result information of the intersection is determined. And according to the pass result information, the target driving path of the intersection is determined.

[0137] Among them, the traffic result information indicates whether the lane of the intersection is passable. The traffic result information can indicate the pass probability of the first preset type of pass path, the pass probability of the second preset type of pass path, the pass probability of the third preset type of pass path, and the pass times of the fourth preset type of pass path in sequence. At this time, the traffic result information indicates that the lane of the intersection is passable. If the traffic result information indicates that the pass probability of the four preset types of pass paths is not obtained, the traffic result information indicates that the lane of the intersection is not passable. Alternatively, the traffic result information is expressed as topological credibility, and the topological credibility includes credible or untrustworthy. Credible means passable, and untrustworthy means unpassable, and there is no limitation on this. It should be noted that the order of obtaining the pass probabilities of the four preset types of pass paths is not limited to this.

[0138] For example, if the traffic result information indicates that the traffic probability of the first preset type of traffic path, the traffic probability of the second preset type of traffic path, the traffic probability of the third preset type of traffic path, and the traffic number of the fourth preset type of traffic path are obtained in sequence, it means that the lane outside the intersection to the lane passing the intersection is passable, and the target driving path of the intersection is determined based on the passable path and the topological relationship. If the traffic probability of any preset type cannot be obtained, it means that the lane outside the intersection to the lane passing the intersection is impassable.

[0139] Further, Figure 8A scenario diagram of a method for generating a road intersection path on a map provided in an embodiment of the present application Figure 6 ,like Figure 8 As shown, the steps for determining the target driving path at the intersection are as follows:

[0140] (1) The end point p1 of the center line of the lane entering the intersection and the beginning point p2 of the center line of the lane exiting the intersection are used as the reference line segment m1.

[0141] (2) Calculate the point p' whose longitudinal distance on the line segment m1 is closest to the midpoint of each trajectory point, and record the two points before and after p' on the trajectory.

[0142] (3) Cluster all p's according to the plane distance, select the cluster with the largest number, calculate the centroid, and obtain the point p3 through which the trajectory passes; calculate the centroid of the two points before and after the intersection p3, and connect them to obtain the tangent line m3.

[0143] (4) Draw a ray m4 from point p1 to the center line of the lane entering the intersection, and find the intersection point with the tangent line m3 at point p3 to obtain p4. Calculate the distance between p1 and p4 as d1. In particular, when m3 and m4 are approximately parallel, d1 is assigned a value of 4.0.

[0144] (5) Draw a ray m5 from point p2 in the opposite direction to the center line of the lane at the exit intersection, and find the intersection point p5 with the tangent line m3 at point p3. Calculate the distance between p2 and p5 as d2. In particular, when m3 and m5 are approximately parallel, d2 is assigned a value of 4.0.

[0145] (6) Calculate the distance d3 = (d1 + d2) * rate3. In this implementation, rate3 = 0.5, which is not limited to this.

[0146] (7) Find a point p6 on ray m4 whose distance from p1 is a preset distance, where the preset distance = d1*rate4; find a point p7 on tangent m3 that is between p3 and p4 and whose distance from p3 is d3*rate4. In this implementation, rate4 = 0.8, which is not limited to this.

[0147] (8) Find a point p8 on ray m5 whose distance from p2 is a preset distance, where the preset distance = d2*rate5; find a point p9 on tangent m3 that is between p3 and p5 and whose distance from p3 is d3*rate5. In this implementation, rate3 = 0.8, which is not limited to this.

[0148] (9) Taking p1, p6, p7, and p3 as the driving path control points, generate the second-order Bezier curve S1.

[0149] (10) Taking p3, p9, p8, and p2 as the driving path control points, generate the second-order Bezier curve S2.

[0150] (11) Connect s1 and s2 to obtain the target driving path s for the intersection. It should be noted that both s1 and s2 meet the condition of smooth continuation of Bezier curves, so s is a smooth curve in the high-precision map.

[0151] Therefore, the driving path control points of all the passing trajectories in the topological relationship are calculated based on the passing path of the trajectory at the intersection. Finally, the fitting driving path from lane a through the intersection to lane b is highly consistent with the trajectory, thereby providing autonomous driving guidance information that is closer to the actual situation. In addition, according to the passing probability of the trajectory at the intersection, the topological relationship with low topological confidence is filtered out, noise interference is removed, and the optimal target driving path is obtained.

[0152] S208: Update the driving route to a preset map.

[0153] Exemplarily, the electronic device may update the driving route into a preset map, thereby obtaining an updated high-precision preset map.

[0154] The method for generating a path at an intersection of a map provided in an embodiment of the present application obtains a trajectory line from a mobile device moving in a current scene, and obtains lane information of lanes in a preset map. A lane model for each lane outside of each intersection represented by the lane information is generated. For each trajectory line and lane model, a candidate lane model associated with a trajectory point in the trajectory line is determined. Based on the candidate lane model, a topological relationship of the lanes at the intersection is determined; wherein the topological relationship includes the number of passing trajectories between lanes at the intersection. Based on the topological relationship, the pass probability of each preset type of pass path at the intersection is determined. For each preset type of pass probability of a pass path, a pass probability less than a preset pass threshold is determined, and the travel direction corresponding to the pass probability less than the pass threshold is filtered. Based on the filtered travel direction and the pass probability greater than or equal to the preset pass threshold, the target driving path of the intersection is determined. The driving path is updated to the preset map. In this scheme, a topological relationship is generated according to the traffic relationship of the trajectory in each lane of the intersection, and the driving path between the lanes of the intersection is fitted according to the traffic paths of each preset type of the trajectory at the intersection, so as to determine the target driving path of the intersection. The algorithm is simple and conforms to the actual vehicle behavior. The confidence value of the topological relationship is calculated according to the traffic probability of the trajectory at each level of the intersection and the decision tree, which can effectively identify the erroneous topological relationship caused by a small amount of abnormal driving behavior, so that the final target driving path is real, effective and accurate. It solves the reference information within the intersection range that traditional high-precision maps cannot provide in real life, such as the actual topology of the road, the vehicle driving path between lanes, etc., and provides guidance information that is closer to the actual situation for autonomous driving, so as to achieve the effect of improving the accuracy of the traffic path at the intersection.

[0155] Fig. 9 A schematic diagram of the structure of a map intersection path generation device provided by this application, such as Fig. 9 As shown, the intersection path generating device 40 of the map provided in this embodiment includes:

[0156] An acquisition module 41 is used to acquire a trajectory line of a mobile device moving in a current scene and to acquire lane information of a lane in a preset map;

[0157] A first determination module 42, for determining a topological relationship of lanes at an intersection according to the trajectory line and lane information;

[0158] A second determination module 43, used to determine the passing probability of each preset type of passing path at the intersection according to the topological relationship;

[0159] A third determination module 44 is used to determine a target driving path at the intersection according to the traffic probability;

[0160] The updating module 45 is used to update the target driving path into the preset map.

[0161] Fig.10 A schematic diagram of the structure of another device for generating a road intersection path for a map provided in an embodiment of the present application, Fig. 9 Based on the embodiment shown, Fig.10 As shown, the first determination module 42 includes:

[0162] A generating unit 421, configured to generate a lane model for each lane outside the intersection according to the lane information;

[0163] A first determining unit 422, for determining, for each trajectory line and lane model, a candidate lane model associated with a trajectory point in the trajectory line;

[0164] The second determining unit 423 is used to determine the topological relationship of the lanes at the intersection according to the candidate lane model; wherein the topological relationship includes the number of passing trajectories between the lanes at the intersection.

[0165] In a possible implementation manner, the first determining unit 422 is specifically configured to:

[0166] For each trajectory line, if the distance between the trajectory point on the trajectory line and the lane model is less than a preset distance threshold, the lane model with a distance less than the distance threshold is determined as the candidate lane model associated with the trajectory point in the trajectory line.

[0167] In a possible implementation, the lanes outside the intersection include multiple, parallel and adjacent lanes forming a road;

[0168] The preset types of passage paths include a first preset type of passage path, a second preset type of passage path, a third preset type of passage path, and a fourth preset type of passage path;

[0169] Among them, the first preset type of passage path is the trajectory of the road entering the intersection to the various roads at the intersection; the second preset type of passage path is the trajectory of the road entering the intersection to the road exiting the intersection; the third preset type of passage path is the trajectory of the lane outside the entrance to the intersection to the road exiting the intersection; the fourth preset type of passage path is to pass through the lane outside the intersection, the intersection, and other lanes outside the intersection in sequence.

[0170] In a possible implementation, the third determining module 44 includes:

[0171] The third determining unit 441 is used to determine the pass probability less than a preset pass threshold for each preset type of pass path, and filter the travel direction corresponding to the pass probability less than the pass threshold;

[0172] The fourth determining unit 442 is used to determine the target driving path of the intersection according to the filtered traveling direction and the passing probability greater than or equal to the preset passing threshold.

[0173] In a possible implementation, the preset types of passing paths include a first preset type of passing path, a second preset type of passing path, a third preset type of passing path, and a fourth preset type of passing path;

[0174] The third determining unit 441 is specifically configured to:

[0175] For the pass probability of the first preset type of pass path, determine a first pass probability that is less than a preset first pass threshold, and filter the travel direction corresponding to the first pass probability;

[0176] For the pass probability of the second preset type of pass path, determine a second pass probability that is less than a preset second pass threshold, and filter the travel direction corresponding to the second pass probability;

[0177] For the pass probability of the pass path of the third preset type, determine a third pass probability that is less than a preset third pass threshold, filter the travel direction corresponding to the third pass probability; and filter the travel direction corresponding to the pass probability that is less than a preset fourth pass threshold;

[0178] For the number of passes of the fourth preset type of pass path, a target number of passes that is less than a preset pass number threshold is determined, and the pass directions corresponding to the target number of passes are filtered.

[0179] In a possible implementation, the fourth determining unit 442 includes:

[0180] The first determination subunit 4421 is used to determine the traffic result information of the intersection according to the filtered travel direction and the traffic probability greater than or equal to the preset traffic threshold; wherein the traffic result information indicates whether the lane of the intersection is passable;

[0181] The second determining subunit 4422 is used to determine a target driving path of the intersection according to the traffic result information.

[0182] In a possible implementation, the pass probability greater than or equal to the pass threshold includes the pass probability of a first preset type of pass path, the pass probability of a second preset type of pass path, the pass probability of a third preset type of pass path, and the pass times of a fourth preset type of pass path;

[0183] The second determining subunit 4422 is specifically configured to:

[0184] If the passing result information represents the passing probability of the first preset type of passing path, the passing probability of the second preset type of passing path, the passing probability of the third preset type of passing path, and the passing number of the fourth preset type of passing path, then it is determined that the lane outside the intersection to the lane passing the intersection is a passable path;

[0185] Determine the target driving path of the intersection based on the traversable paths and topological relationships.

[0186] In a possible implementation, the lane model includes lane information; wherein the lane information includes any one or more of the following:

[0187] Lane markings, lane left boundary, lane right boundary, lane centerline, direction of travel, and associated roads at the intersection.

[0188] The device provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and this embodiment will not be described in detail here.

[0189] Fig.11 This is a schematic diagram of the structure of the electronic device subject provided by this application. Fig.11 As shown, the electronic device 50 provided in this embodiment includes: at least one processor 501 and a memory 502. Optionally, the device 50 also includes a communication component 503. The processor 501, the memory 502 and the communication component 503 are connected via a bus 504.

[0190] In a specific implementation process, at least one processor 501 executes the computer-executable instructions stored in the memory 502, so that at least one processor 501 executes the above method.

[0191] The specific implementation process of the processor 501 can be found in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be repeated here.

[0192] In the above embodiments, it should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the invention may be directly implemented as being executed by a hardware processor, or may be executed by a combination of hardware and software modules in the processor.

[0193] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (Non-volatile Memory, NVM), such as at least one disk memory.

[0194] The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of the present application is not limited to only one bus or one type of bus.

[0195] The present application also provides a computer program product, including a computer program, which implements the above method when executed by a processor.

[0196] The present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the above method is implemented.

[0197] The above-mentioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.

[0198] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (Application Specific Integrated Circuits, referred to as: ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0199] The division of units is only a logical function division, and there may be other divisions in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0200] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0201] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0202] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0203] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0204] Finally, it should be noted that those skilled in the art will readily conceive of other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present invention, which follow the general principles of the present invention and include common knowledge or customary technical means in the art not disclosed by the present invention, are not limited to the precise structure described above and shown in the drawings, and may be modified and changed in various ways without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A method for generating a road intersection path of a map, characterized in that: include: Obtaining a trajectory line of a mobile device moving in a current scene, and obtaining lane information of a lane in a preset map; Determining a topological relationship of the lanes at the intersection according to the trajectory and the lane information; According to the topological relationship, the pass probability of each preset type of pass path at the intersection is determined; according to the pass probability, the target driving path of the intersection is determined, and the target driving path is updated to the preset map.

2. The method according to claim 1, characterized in that The determining, according to the trajectory line and the lane information, a topological relationship of the lane at the intersection includes: Generate a lane model for each lane according to each lane outside the intersection represented by the lane information; For each of the trajectory lines and the lane models, determining a candidate lane model associated with a trajectory point in the trajectory line; The topological relationship of the lanes at the intersection is determined according to the candidate lane model; wherein the topological relationship includes the number of travel trajectories between the lanes at the intersection.

3. The method according to claim 2, characterized in that The step of determining, for each of the trajectory lines and the lane model, a candidate lane model associated with a trajectory point in the trajectory line comprises: For each of the trajectory lines, if the distance between the trajectory point on the trajectory line and the lane model is less than a preset distance threshold, a lane model whose distance is less than the distance threshold is determined as a candidate lane model associated with the trajectory point in the trajectory line.

4. The method according to claim 1, characterized in that: The lanes outside the intersection include multiple, parallel and adjacent lanes forming a road; The preset types of passage paths include a first preset type of passage path, a second preset type of passage path, a third preset type of passage path, and a fourth preset type of passage path; Among them, the first preset type of passage path is the trajectory of the road entering the intersection to the various roads at the intersection; the second preset type of passage path is the trajectory of the road entering the intersection to the road exiting the intersection; the third preset type of passage path is the trajectory of the lane outside the entrance to the intersection to the road exiting the intersection; the fourth preset type of passage path is a path that passes through the lane outside the intersection, the intersection, and other lanes outside the intersection in sequence.

5. The method according to claim 1, characterized in that Determining the target driving path of the intersection according to the traffic probability includes: For each preset type of pass probability of a pass path, determine a pass probability less than a preset pass threshold, and filter the travel direction corresponding to the pass probability less than the pass threshold; The target driving path of the intersection is determined according to the filtered traveling direction and a passing probability that is greater than or equal to a preset passing threshold.

6. The method according to claim 5, characterized in that The preset types of passage paths include a first preset type of passage path, a second preset type of passage path, a third preset type of passage path, and a fourth preset type of passage path; The passing probability of each preset type of passing path, determining the passing probability less than a preset passing threshold, and filtering the travel direction corresponding to the passing probability less than the passing threshold, includes: For the pass probability of the pass path of the first preset type, determine a first pass probability that is less than a preset first pass threshold, and filter the travel direction corresponding to the first pass probability; For the pass probability of the pass path of the second preset type, determine a second pass probability that is less than a preset second pass threshold, and filter the travel direction corresponding to the second pass probability; For the pass probability of the pass path of the third preset type, determine a third pass probability that is less than a preset third pass threshold, filter the travel direction corresponding to the third pass probability; and filter the travel direction corresponding to the pass probability that is less than a preset fourth pass threshold; With respect to the number of passes of the fourth preset type of pass path, a target number of passes that is less than a preset number of passes threshold is determined, and a pass direction corresponding to the target number of passes is filtered.

7. The method according to claim 5, characterized in that The step of determining the target driving path of the intersection according to the filtered traveling direction and the passing probability being greater than or equal to a preset passing threshold comprises: Determine the traffic result information of the intersection according to the filtered traveling direction and the traffic probability greater than or equal to the preset traffic threshold; wherein the traffic result information indicates whether the lane of the intersection is passable; The target driving path of the intersection is determined according to the traffic result information.

8. The method according to claim 7, characterized in that The passing probabilities greater than or equal to the passing threshold include the passing probability of a first preset type of passing path, the passing probability of a second preset type of passing path, the passing probability of a third preset type of passing path, and the passing times of a fourth preset type of passing path; Determining the target driving path of the intersection according to the traffic result information includes: If the passage result information represents the passage probability of the first preset type of passage path, the passage probability of the second preset type of passage path, the passage probability of the third preset type of passage path, and the number of passages of the fourth preset type of passage path, then it is determined that the lane outside the intersection to the lane passing through the intersection is a passable path; A target driving path of the intersection is determined according to the traversable path and the topological relationship.

9. A device for generating a road intersection path on a map, characterized in that: include: An acquisition module, used to acquire a trajectory line of a mobile device moving in a current scene, and to acquire lane information of a lane in a preset map; A first determination module, used to determine the topological relationship of the lanes at the intersection according to the trajectory line and the lane information; A second determination module, configured to determine the pass probability of each preset type of pass path at the intersection according to the topological relationship; A third determination module is used to determine the target driving path of the intersection according to the passing probability; An updating module is used to update the target driving path to the preset map.

10. An electronic device / computer-readable storage medium / computer program product, characterized in that: The electronic device comprises: a memory, a processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory, so that the processor executes the method according to any one of claims 1 to 8; and / or, The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 8 when executed by a processor; and / or, The computer program product comprises a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images