Lane matching method, device, equipment, storage medium and product

Abstract

The present application discloses a lane matching method, device, equipment, storage medium and product, which relate to the field of intelligent driving technology. The method obtains lane information of a target area in a driving map, wherein the lane information includes lane connection relationships and lane coordinates; constructs an inter-lane topological relationship based on the lane connection relationship and lane coordinates; constructs a vehicle-lane topological relationship based on a nearest projection method, and determines a lane-vehicle topological relationship based on the vehicle-lane topological relationship; determines an inter-vehicle topological relationship based on the inter-lane topological relationship, the vehicle-lane topological relationship and the lane-vehicle topological relationship, and determines the correspondence between vehicles and lanes in the intelligent driving map data set through the above method, thereby improving the reliability and efficiency of map data support for the intelligent driving system.

Description

Technical Field

[0001] The present application relates to the field of intelligent driving technology, and in particular to a lane matching method, device, equipment, storage medium and product. Background Art

[0002] In the field of intelligent driving, the construction of high-precision map data sets is one of the key technologies to achieve accurate navigation and decision-making for autonomous driving vehicles. With the development of intelligent driving technology, the requirements for the accuracy and real-time performance of map data are getting higher and higher, which requires an efficient and accurate map data production link to meet the needs of intelligent driving systems.

[0003] In the prior art, the production of map data usually relies on large-scale manual annotation and complex data processing processes, which is not only inefficient but also costly. In particular, the prior art often lacks sufficient flexibility and accuracy when processing the relationship between vehicles and lanes in the intelligent driving map data set. First, the data processing process is not automated enough, resulting in low production efficiency; second, the vehicle and lane information in the map data is not updated in real time and cannot meet the needs of the rapidly changing traffic environment; third, the accuracy and efficiency of the prior art when processing the complex relationship between vehicles and lanes in the map need to be improved. The existence of these problems limits the performance and reliability of map data support in the intelligent driving system, and affects the widespread application of intelligent driving vehicles in actual traffic environments.

[0004] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0005] The main purpose of this application is to provide a lane matching method, device, equipment, storage medium and computer program product, aiming to improve the reliability and efficiency of map data support in intelligent driving systems.

[0006] To achieve the above purpose, the present application proposes a lane matching method, which includes:

[0007] Acquire lane information of a target area in a driving map, wherein the lane information includes a lane connection relationship and a lane coordinate;

[0008] Constructing a topological relationship between lanes based on the lane connection relationship and the lane coordinates;

[0009] Constructing a vehicle lane topological relationship based on a nearest projection method, and determining a lane vehicle topological relationship based on the vehicle lane topological relationship;

[0010] Based on the lane-to-lane topological relationship, the vehicle-lane topological relationship, and the lane-to-vehicle topological relationship, a vehicle-to-vehicle topological relationship is determined.

[0011] In one embodiment, the target area includes a target lane and a target associated lane, the target lane includes a target lane sub-line, and the step of constructing a topological relationship between lanes based on the lane connection relationship and the lane coordinates includes:

[0012] Calculate the midpoint coordinates of the target lane according to the starting point coordinates and the end point coordinates of the target lane;

[0013] Determine a first pending lane and a second pending lane based on a minimum projection distance from the midpoint coordinates of the target lane to the target associated lane;

[0014] Constructing a transformation coordinate system based on the starting point coordinates of the target lane and the sub-line orientation angle of the sub-line of the target lane;

[0015] Converting the lane starting point coordinates of the first pending lane and the second pending lane according to the conversion coordinate system to obtain the converted starting point coordinates of the first pending lane and the converted starting point coordinates of the second pending lane;

[0016] The left adjacent lane and the right adjacent lane of the target lane are determined according to the transformed coordinates of the starting point of the first pending lane and the transformed coordinates of the starting point of the second pending lane.

[0017] In one embodiment, the step of constructing a topological relationship between lanes based on the lane connection relationship and the lane coordinates further includes:

[0018] Calculating a first Euclidean distance from the starting point coordinates of the target lane to the ending point coordinates of the target associated lane, and a second Euclidean distance from the ending point coordinates of the target lane to the starting point coordinates of the target associated lane;

[0019] A preceding lane and a succeeding lane of the target lane are determined according to the first Euclidean distance and the second Euclidean distance.

[0020] In one embodiment, the target area includes a target vehicle and a target lane, and the steps of constructing a vehicle-lane topological relationship based on the nearest projection method and determining a lane-vehicle topological relationship based on the vehicle-lane topological relationship include:

[0021] Calculating the projection distance from the target vehicle to the target lane;

[0022] Filtering out the minimum projection distance from the target vehicle to the target lane;

[0023] If the minimum projection distance is less than a preset distance threshold, then obtaining lane information corresponding to the minimum projection distance;

[0024] Associating the target vehicle with lane information corresponding to the minimum projection distance to determine a vehicle lane topology relationship;

[0025] The target vehicle information corresponding to the vehicle lane topology relationship is added to the lane vehicle dictionary of the corresponding lane to obtain the lane vehicle topology relationship.

[0026] In one embodiment, after the step of associating the target vehicle with the lane information corresponding to the minimum projection distance to determine the vehicle lane topological relationship, the step further includes:

[0027] Obtaining target lane subline information of the target lane, wherein the target lane subline information includes subline starting point coordinates, subline midpoint coordinates, and subline length;

[0028] Calculate the projection ratio of the target vehicle on the target lane subline based on the lane subline starting point coordinates, lane subline midpoint coordinates and lane subline length;

[0029] Based on the projection ratio of the target vehicle on the target lane sub-line, a projection distance and a projection ratio of the target vehicle on the target lane are determined.

[0030] In one embodiment, the target area includes a target lane, and the step of determining the topological relationship between vehicles based on the topological relationship between lanes, the topological relationship between vehicles and lanes, and the topological relationship between lanes and vehicles comprises:

[0031] Obtaining the left and right adjacent lanes and the preceding and succeeding lanes information of the target lane through the topological relationship between the lanes;

[0032] Obtaining information between vehicles on the target lane through the lane-vehicle topological relationship;

[0033] Determine vehicle-to-vehicle information outside the target lane based on the left and right adjacent lanes and the preceding and succeeding lanes of the target lane;

[0034] The topological relationship between vehicles is determined according to the information between vehicles on the target lane and the information between vehicles outside the target lane.

[0035] In addition, to achieve the above purpose, the present application also proposes a lane matching device, which includes:

[0036] An acquisition module, used to acquire lane information of a target area in a driving map, wherein the lane information includes a lane connection relationship and lane coordinates;

[0037] A construction module, used for constructing a topological relationship between lanes based on the lane connection relationship and lane coordinates;

[0038] A first determination module is used to construct a vehicle lane topological relationship based on a nearest projection method, and determine a lane vehicle topological relationship based on the vehicle lane topological relationship;

[0039] The second determination module is used to determine the topological relationship between vehicles based on the topological relationship between lanes, the topological relationship between vehicles and lanes, and the topological relationship between lanes and vehicles.

[0040] In addition, to achieve the above-mentioned purpose, the present application also proposes a lane matching device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the lane matching method described above.

[0041] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the lane matching method described above are implemented.

[0042] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the lane matching method described above are implemented.

[0043] One or more technical solutions proposed in the present application obtain lane information of a target area in a driving map, wherein the lane information includes lane connection relationships and lane coordinates; construct an inter-lane topological relationship based on the lane connection relationship and lane coordinates; construct a vehicle-lane topological relationship based on a nearest projection method, and determine a lane-vehicle topological relationship based on the vehicle-lane topological relationship; determine an inter-vehicle topological relationship based on the inter-lane topological relationship, the vehicle-lane topological relationship, and the lane-vehicle topological relationship, and determine the correspondence between vehicles and lanes in the intelligent driving map data set through the above method, thereby improving the reliability and efficiency of map data support for the intelligent driving system. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] 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.

[0045] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0046] Figure 1 A schematic diagram of a process flow provided for the first embodiment of the lane matching method of the present application;

[0047] Figure 2Schematic diagram of the topological relationship between lanes and vehicles in this lane matching method

[0048] Figure 3 A schematic diagram of a process flow provided for the second embodiment of the lane matching method of the present application;

[0049] Figure 4 A schematic diagram of sorting vehicles in ascending order according to their distance from the starting point of the lane in the lane matching method of this application;

[0050] Figure 5 A schematic diagram of calculating the distance between the projection point of the vehicle on the lane and the starting point in the lane matching method of this application;

[0051] Figure 6 A schematic diagram of the topological relationship between vehicles in the lane matching method of this application;

[0052] Figure 7 This is a schematic diagram of the module structure of the lane matching device according to an embodiment of the present application;

[0053] Figure 8 Schematic diagram of the device structure of the hardware operating environment involved in the lane matching method in the embodiment of the present application.

[0054] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0055] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0056] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0057] The main solution of the embodiment of the present application is to construct an algorithm for map topology in a high-precision map data set, aiming to improve the efficiency and accuracy of intelligent driving data processing. The algorithm constructs map topology from two dimensions: frame level and scene level.

[0058] At the frame level, the algorithm first constructs lane information for each frame of data in the scene, including the lane's coordinates, midpoint coordinates, starting point and end point coordinates, length information, direction, etc. Next, the relationship between lanes is defined, such as left and right adjacent lanes and front and rear adjacent lanes, and these relationships are determined by calculating the projection distance from the midpoint of the lane to other lanes. In addition, the relationship between vehicles and lanes is constructed, and the lane in which the vehicle is located is determined based on the principle of minimum projection distance between the vehicle and the lane. Then, based on the vehicle's position information on the lane, the specific position and position ratio of the vehicle to the starting point of the lane are further calculated. Finally, the connection between lanes and vehicles is constructed, the vehicle information is added to the list of the corresponding lanes, and the vehicles are sorted by the distance from the starting point of the lane.

[0059] At the scene level, the algorithm constructs lane information that includes the entire scene and the relationship between lanes to form a scene-level map topology. This includes detailed information about each lane, such as track point coordinates, sub-segment midline point coordinates, start point coordinates, end point coordinates, length, direction, etc. The scene-level topology relationship can quickly query the required lane information through lane numbers, thus achieving effective organization and management of the entire scene map data.

[0060] Through this structured and systematic topology construction method, the technical solution of the present invention can effectively solve the problems of low data processing efficiency, untimely updates, and inaccurate processing of vehicle-lane relationships in the prior art, and provide more refined and real-time map data support for intelligent driving.

[0061] In the prior art, the production of map data usually relies on large-scale manual annotation and complex data processing processes, which is not only inefficient but also costly. In addition, the prior art often lacks sufficient flexibility and accuracy when dealing with the relationship between vehicles and lanes. For example, the prior art may not be able to accurately determine the lane a vehicle belongs to in complex traffic scenarios, or in the case of a vehicle changing lanes or other vehicles invading lanes, the prior art may not be able to timely and accurately update the relationship information between vehicles and lanes.

[0062] The defects of existing technologies are mainly reflected in the following aspects: first, the data processing process is not automated enough, resulting in low production efficiency; second, the update of map data is not real-time enough, which cannot meet the needs of the rapidly changing traffic environment; third, the accuracy and efficiency of existing technologies in processing the complex relationship between vehicles and lanes need to be improved. The existence of these problems limits the performance and reliability of intelligent driving systems and affects the widespread application of intelligent driving vehicles in actual traffic environments.

[0063] This application provides a solution to these defects in the prior art and proposes a new map topology construction algorithm for high-precision map data. The algorithm aims to improve the production efficiency of map data through automated data processing processes and improve the real-time and accuracy of map data by building a more accurate relationship model between vehicles and lanes. This method can effectively solve the problems existing in the prior art and provide more reliable and efficient map data support for intelligent driving systems.

[0064] It should be noted that the execution subject of this embodiment may be a computing service device with lane matching, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a lane matching system, etc. The following takes the lane matching system as an example to illustrate this embodiment and the following embodiments.

[0065] Based on this, the embodiment of the present application provides a lane matching method, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the lane matching method of the present application.

[0066] In this embodiment, the lane matching method includes steps S1000 to S4000:

[0067] Step S1000: Acquire lane information of a target area in a driving map, wherein the lane information includes lane connection relations and lane coordinates;

[0068] It should be noted that in this embodiment, the intelligent driving data set needs to frequently process the relationship between the vehicle agent and the lane, such as determining which lane the vehicle is in, the positional relationship between different vehicles, whether the vehicle changes lanes, whether other vehicles invade the vehicle's lane, etc. If a complete map topology is constructed, it is of great significance to the entire data processing and target mining. Therefore, this application proposes a map topology construction method.

[0069] The embodiments of the present application construct map topology from two dimensions: one is to construct a frame-level map topology, and the other is to construct a scene-level map topology. Here, one data is called a scene. A scene usually contains several frames of data (here a scene can contain several data frames, such as a scene includes 1,000 frames of data). A frame contains map information and information about each vehicle.

[0070] First, refer to Figure 2 , Figure 2This is a schematic diagram of the topological relationship structure between lanes and vehicles in the lane matching method of the present application. A frame-level map topology is constructed. The following operations are performed for each frame data in the scene. For the frame, lane information, vehicle information, the relationship between lanes, the relationship between vehicles, the relationship between lanes and vehicles, and the relationship between vehicles are constructed. These relationships together constitute the frame-level map topology. Any associated roads and any associated vehicle information can be quickly found through roads. Any associated roads and any associated vehicle information can also be quickly found through vehicles. It should be understood that the size that each frame can cover is limited. This size is also the data range that the lane matching method of the present application focuses on and processes, that is, the target area.

[0071] Lane information includes not only the connection relationship of lanes, but also the coordinates of lanes. Lane connection relationship determines how lanes are related to each other, while lane coordinates accurately describe the specific location of lanes on the map. Accurate acquisition of this information is crucial for the construction of subsequent topological relationships.

[0072] In addition, it should be noted that the lane information also includes lane sub-line information, which also includes some data that can characterize the position and attributes of the lane sub-line, such as the starting point coordinates and end point coordinates of the lane. Based on these coordinates, the midpoint coordinates of the lane can be further calculated, which helps to describe the geometric shape and spatial position of the lane in more detail.

[0073] For example, in a specific implementation, the starting and ending coordinates of the lane can be obtained by measuring or from existing map data, and then the midpoint coordinates of the lane can be calculated using a geometric algorithm. These coordinate information will be stored in the corresponding data structure for subsequent processing and query. The frame-level map topology lane information is stored in a dictionary lane_info, where the key value is the lane number laneid, and the value value is the specific information of the lane, which is also composed of a dictionary. In this way, detailed information or required information of the lane can be quickly obtained through the lane number laneid. The specific information of the lane mainly includes the coordinate information point_coords of the lane, which is composed of the coordinates of all points in the lane;

[0074] The coordinate information of the midpoint of the lane sub-segment is center_coods. Here, the sub-segment is a segment composed of two adjacent coordinate points on the lane. The coordinates of the two endpoints of the sub-segment are p1 (x1, y1) and p2 (x2, y2). The coordinates of the midpoint of the sub-segment are ((x1+x2) / 2, (y1+y2) / 2). The coordinates of the midpoint of each sub-segment are obtained.

[0075] The starting point coordinate information of the lane is start, and its coordinates are marked as (x_s, y_s); the end point coordinate information of the lane is end, and its coordinates are marked as (x_e, y_e); the length information of the sub-segment of the lane is lengths, and the coordinates of the two end points of the sub-segment are p1 (x1, y1) and p2 (x2, y2), then the length of the sub-segment is sqrt ((x2-x1)*(x2-x1)+(y2-y1)*(y2-y1));

[0076] The length information of the lane is length, which is obtained by adding up the lengths of the above sub-segments;

[0077] The heading information of the lane indicates the orientation of the lane in the odom coordinate system. The calculation formula is as follows: arctan2(x_e-x_s,y_e-y_s);

[0078] The heading information of the lane sub-segment is denoted by n_segments. Let the coordinates of the two endpoints of the sub-segment be p1 (x1, y1) and p2 (x2, y2). The heading information of the sub-segment is calculated as follows: arctan2(x2–x1, y2–y2).

[0079] Step S2000: constructing a topological relationship between lanes based on the lane connection relationship and lane coordinates;

[0080] It should be noted that constructing the topological relationship between lanes based on the lane connection relationship and lane coordinates is a key step in realizing lane information networking. The construction of the topological relationship between lanes involves determining the relative position and connection method between lanes.

[0081] In addition, it should be noted that the specific operation of constructing the topological relationship between lanes includes calculating the coordinates of the midpoint of the lane based on the starting coordinates and the end coordinates of the lane, and then determining the first pending lane and the second pending lane based on the minimum projection distance of these midpoint coordinates to other lanes. In this way, the left-right adjacent relationship and the front-to-back connection relationship between lanes can be clarified, that is, the required lane number can be quickly queried through the relationship between lanes, and the detailed information of the lane can be obtained in the lane information dictionary.

[0082] For example, in a specific implementation, the midpoint coordinates of the lane are first calculated, and then the projection distances of these midpoint coordinates to other lanes are calculated to determine the left and right adjacent lanes. In addition, a transformation coordinate system can be constructed based on the lane starting point coordinates and the sub-line orientation angle of the lane sub-line information to further determine the front and rear connection relationship of the lane.

[0083] In a feasible implementation manner, the target area includes a target lane and a target associated lane, the target lane includes a target lane subline, and step S2000 may include steps S2100 to S2500:

[0084] Step S2100: Calculating the coordinates of the midpoint of the target lane according to the starting point coordinates and the end point coordinates of the target lane;

[0085] Step S2200: determining a first pending lane and a second pending lane based on a minimum projection distance from the midpoint coordinates of the target lane to the target associated lane;

[0086] Step S2300: constructing a transformation coordinate system based on the starting point coordinates of the target lane and the sub-line orientation angle of the sub-line of the target lane;

[0087] Step S2400: transforming the lane starting point coordinates of the first pending lane and the second pending lane according to the transformation coordinate system to obtain the transformed coordinates of the starting point of the first pending lane and the transformed coordinates of the starting point of the second pending lane;

[0088] Step S2500: Determine the left adjacent lane and the right adjacent lane of the target lane according to the transformed coordinates of the starting point of the first pending lane and the transformed coordinates of the starting point of the second pending lane.

[0089] It should be noted that, in this embodiment, establishing the topological relationship between lanes is crucial for path planning and decision making in the intelligent driving system. By determining the relationship between the target area, that is, the target lane in the current frame, and the target associated lane one by one, the overall topological relationship between lanes in the target area is determined. When a lane in the target area is determined to be the target lane, all other lanes in the target area are considered to be associated lanes. For any target lane, first, by calculating the midpoint coordinates between the starting point coordinates and the end point coordinates of the lane, the geometric center of the lane can be determined, which helps to understand the spatial layout of the lane and also provides a benchmark for the subsequent analysis of the relationship between lanes.

[0090] In addition, it should be noted that, by using the minimum projection distance of the lane midpoint coordinates to other lanes, the system can identify the lanes adjacent to the current lane, namely the first pending lane and the second pending lane. The purpose of this step is to determine the relative position between lanes and lay the foundation for further topological relationship establishment.

[0091] Next, the system constructs a transformation coordinate system based on the lane starting point coordinates and the sub-line orientation angle of the lane sub-line information. The core of this step is to transform the local coordinate information of the lane into a unified reference frame, making the coordinate information of different lanes comparable, thereby more accurately describing the relative direction and position between lanes.

[0092] In addition, the system will transform the lane start coordinates of the first pending lane and the second pending lane according to the transformed coordinate system to obtain the transformed coordinates. This step ensures that even if the lanes have different directions in the original coordinate system, they can be fairly compared in the new coordinate system.

[0093] Finally, the system determines the left adjacent lane and the right adjacent lane based on the transformed coordinates. This step clarifies the left and right adjacent relationship between lanes by comparing the relative positions of the transformed coordinates, completing the construction of the topological relationship between lanes.

[0094] In one feasible implementation, the system first collects and stores the starting and ending coordinates of all lanes. Then, the system calculates the midpoint coordinates of each lane and measures the projection distances of these midpoints to other lanes to determine the pending lanes. Next, the system constructs a transformation coordinate system using the starting coordinates of the lanes and the sub-line orientation angles, and transforms the starting coordinates of the pending lanes into this new coordinate system. Finally, the system determines the left and right adjacent lanes of each lane based on these transformed coordinates, thereby completing the construction of the entire lane topology. This solution not only improves the automation and accuracy of lane information processing, but also provides a clear and accurate lane network model for the intelligent driving system.

[0095] For example, as an implementation method, the relationship information between lanes in the frame-level map topology is stored in a dictionary lane_to_lane, where the key value is the lane number laneid, and the value value is the information related to the lane, which is also composed of a dictionary, specifically including:

[0096] The lane information on the left side of the lane is left, and the lane information on the right side of the lane is right. The adjacent lanes on the left and right sides of the lane can be obtained by the following method:

[0097] First, calculate the coordinates of the midpoint position on the current lane, solve the minimum projection distance from the midpoint position coordinates to other lanes, and take the two lanes corresponding to the two minimum projection distance values, recorded as lane1 and lane2. The starting coordinate of the current lane is recorded as P_c, and the coordinate system is established with P_c as the origin and the direction of the orientation angle on the first sub-line of the current lane as the x-axis (obtained from the above lane information). The starting coordinate P of lane1 is transformed into this coordinate system to obtain the new coordinates (x_new, y_new). If y_new>0, lane1 is the left adjacent lane and lane2 is the right adjacent lane; otherwise, lane1 is the right adjacent lane and lane2 is the left adjacent lane.

[0098] In a feasible implementation manner, step S2000 may further include steps S2600 to S2700:

[0099] Step S2600: Calculate a first Euclidean distance from the starting point coordinates of the target lane to the end point coordinates of the target associated lane, and a second Euclidean distance from the end point coordinates of the target lane to the starting point coordinates of the target associated lane;

[0100] Step S2700: Determine the preceding lane and the succeeding lane of the target lane according to the first Euclidean distance and the second Euclidean distance.

[0101] It should be noted that the coordinates of the starting point and the end point of the lane in this solution are the key coordinate points for constructing the lane topological relationship. They define the position and extension direction of the lane in space. Through these coordinates, the geometric properties and spatial relationship of the lane can be accurately calculated. The first Euclidean distance and the second Euclidean distance represent the straight-line distance from the starting point of the lane to the end point of other lanes and the straight-line distance from the end point of the lane to the starting point of other lanes respectively. The calculation of these two distances is the basis for determining the front-to-back topological relationship between lanes.

[0102] In addition, it should be noted that the purpose of calculating these Euclidean distances is to determine the front-to-back connection relationship between lanes, that is, the predecessor lane and the successor lane. This relationship is crucial to understanding the lane sequence and the possible driving path of the vehicle. By comparing the Euclidean distances between lanes, the closest and most logically connected lane pairs can be identified, thereby constructing the predecessor and successor topological relationship between lanes.

[0103] In a feasible implementation, the system first collects and stores the coordinates of the start and end points of all lanes. Then, the system calculates the first Euclidean distance from the start point of each lane (the lane currently calculated is the target lane, and the lanes outside the target area or the current frame are the target-associated lanes) to the end points of all other lanes, as well as the second Euclidean distance from the end point of each lane to the start points of all other lanes. By comparing these distances, the system can identify the predecessor lane and the successor lane of each lane. For example, for any given lane A, the system will find lane B so that the second Euclidean distance from the end point of lane A to the start point of lane B is the smallest, thereby determining that lane B is the successor lane of lane A. Similarly, the system will also find lane C so that the first Euclidean distance from the end point of lane C to the start point of lane A is the smallest, thereby determining that lane C is the predecessor lane of lane A. In this way, the system can construct a complete lane network topology, providing a solid data foundation for path planning and traffic analysis in intelligent driving systems.

[0104] For example, the lane information already contains the lane's predecessor lane (or predecessor lane) and successor lane information. The lane's predecessor adjacent lane information is prev, and the lane's successor adjacent lane information is next. The predecessor and successor lanes of a lane can be obtained from the upstream front-to-back connection relationship. If the upstream does not have a front-to-back connection relationship, it can be solved by the following method:

[0105] The starting point coordinate information of the lane is start, and its coordinates are marked as (x_s, y_s). The Euclidean distance from the end coordinates of other lanes to the starting coordinates of the current lane is calculated, and the lane corresponding to the minimum value is taken. This lane is the previous lane of the current lane.

[0106] The end coordinate information of the lane is end, and its coordinates are marked as (x_e, y_e). The Euclidean distance from the starting coordinates of other lanes to the end coordinates of the current lane is calculated, and the lane corresponding to the minimum value is taken. This lane is the subsequent lane of the current lane.

[0107] Through the constructed relationship between lanes, detailed information of adjacent lanes of a specified lane can be quickly obtained.

[0108] Build a topological relationship between vehicles and lanes, so that you can quickly query which lane the vehicle is on. The relationship information between vehicles and lanes in the frame-level map topology is stored in a dictionary obj_to_lane, where the key value is the vehicle number obj_id, and the value value is the lane number laneid where the vehicle is located. Through laneid, you can quickly query the detailed information of the corresponding lane in the lane dictionary lane_info.

[0109] Step S3000: constructing a vehicle-lane topological relationship based on the nearest projection method, and determining a lane-vehicle topological relationship based on the vehicle-lane topological relationship;

[0110] It should be noted that determining the topological relationship between lanes and vehicles is to integrate the information between vehicles and lanes to form a detailed list of vehicles on the lanes. This step involves not only the specific location of the vehicle, but also the relative position of the vehicle on the lane.

[0111] In addition, it should be noted that the specific operation includes obtaining lane subline information in the lane information, such as the lane subline starting point coordinates, the lane subline midpoint coordinates and the lane subline length. Based on this information, the projection ratio of the vehicle on the lane subline can be calculated, thereby determining the projection distance of the vehicle on the lane.

[0112] For example, in a specific implementation, the sub-line information of the lane is first obtained, and then the projection ratio of the vehicle on the lane is calculated based on this information. In this way, the relative position of the vehicle on the lane can be accurately described, and this information can be integrated into the lane-vehicle dictionary to form a lane-vehicle topological relationship.

[0113] Step S4000: Determine the topological relationship between vehicles based on the topological relationship between lanes, the topological relationship between vehicles and lanes, and the topological relationship between lanes and vehicles.

[0114] It should be noted that based on the topological relationship between lanes, the topological relationship between vehicles and the topological relationship between lanes, the topological relationship between vehicles and the topological relationship between lanes and vehicles, determining the topological relationship between vehicles is the key to realizing the networking of the relationship between vehicles. This step involves the relative positions and relationships between vehicles, which is crucial for understanding and predicting vehicle behavior patterns.

[0115] In addition, it should be noted that the specific operation includes obtaining the left and right adjacent lanes and the preceding and succeeding lanes information through the lane-to-lane topological relationship, obtaining the vehicle-to-vehicle information on the lane through the lane-to-vehicle topological relationship, and then combining this information to determine the vehicle-to-vehicle information outside the lane. In this way, the topological relationship between vehicles can be fully described.

[0116] For example, in a specific implementation, the adjacent and connected relationships of lanes are first matched through the lane-to-lane topology, and then the vehicle information on the lane is obtained through the lane-to-vehicle topology. Combined with this information, the topological relationship between vehicles can be further determined, thereby providing support for the decision-making of the intelligent driving system.

[0117] The present embodiment provides a lane matching method, which constructs lane information, wherein the lane information includes a lane connection relationship and lane coordinates; constructs an inter-lane topological relationship based on the lane connection relationship and lane coordinates; constructs a vehicle-lane topological relationship based on a nearest projection method, and determines a lane-vehicle topological relationship based on the vehicle-lane topological relationship; determines an inter-vehicle topological relationship based on the inter-lane topological relationship, the vehicle-lane topological relationship, and the lane-vehicle topological relationship, and constructs a correspondence between vehicles and lanes in an intelligent driving map data set through the above method, thereby improving the reliability and efficiency of map data support for an intelligent driving system.

[0118] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 3 , step S3000 of the lane matching method further includes steps S3100 to S3500:

[0119] Step S3100: Calculating the projection distance from the target vehicle to the target lane;

[0120] It should be noted that calculating the projection distance from the vehicle to the lane is an important step in determining the relationship between the vehicle position and the lane. In this process, the system first needs to determine the current coordinates of the current target vehicle, and then project them onto the geometry of the lane to calculate the position of the vehicle relative to the lane. This projection is usually based on the spatial relationship between the vehicle coordinates and the lane coordinates, and can be implemented using geometric algorithms or mathematical formulas.

[0121] Step S3200: Filter out the minimum projection distance from the target vehicle to the target lane;

[0122] It should be noted that, in this embodiment, the purpose of screening the minimum projection distance is to find the lane closest to the current position of the vehicle. The system will compare all calculated projection distances to find the minimum value. This minimum value represents the closest distance between the vehicle and the lane, so that it can be inferred which lane the vehicle is most likely to be in.

[0123] Step S3300: If the minimum projection distance is less than a preset distance threshold, then obtaining lane information corresponding to the minimum projection distance;

[0124] It should be noted that in this embodiment, setting the distance threshold is a key criterion for determining whether the vehicle is within the effective range of the lane. If the minimum projection distance of the vehicle is less than this threshold, the system will consider the vehicle to be in the lane and obtain detailed information of the lane. This threshold can be adjusted according to factors such as actual road conditions and vehicle size.

[0125] Step S3400: Associating the target vehicle with lane information corresponding to the minimum projection distance to determine a vehicle lane topology relationship;

[0126] It should be noted that once the lane the vehicle is in is determined, the system will establish an association between the vehicle and the lane. This association forms the basis of the topological relationship between the vehicle and the lane, which is essential for understanding the location and behavior of the vehicle in the traffic network. The system will record the association information between the vehicle and the lane for further analysis and decision-making.

[0127] In a specific implementation, the system first obtains the current coordinates of the vehicle through sensors or map data. Then, the system calculates the projection distance of the vehicle coordinates on each lane and selects the minimum value among these distances. If this minimum value is less than a preset threshold, the system will obtain detailed information of the corresponding lane, such as lane number, location, length, etc. Finally, the system associates the vehicle with this lane, establishes the vehicle-lane topological relationship, and provides support for the decision-making of the intelligent driving system.

[0128] Step S3500: Add the target vehicle information corresponding to the vehicle lane topology relationship to the lane vehicle dictionary of the corresponding lane to obtain the lane vehicle topology relationship.

[0129] It should be noted that in this embodiment, a mapping relationship between lanes and vehicles is established, which helps the system manage and track vehicles on the lanes. The lane vehicle dictionary is a data structure used to store information about all vehicles on each lane, where the key is the identifier of the lane and the value is a list containing detailed information about all vehicles on the lane.

[0130] In a specific implementation, the system maintains a lane vehicle dictionary for each lane. When the system determines the topological relationship between the vehicle and the lane, for example, the vehicle is located in lane B, the system adds the detailed information of the vehicle as an entry to the dictionary entry corresponding to lane B. The detailed information of the vehicle may include the unique identifier of the vehicle, location, speed, acceleration, etc.

[0131] If the lane vehicle dictionary for lane B does not yet contain the vehicle's information, the system will create a new entry and add the vehicle information as a list element. If the vehicle information already exists in the dictionary, the system will simply append the new vehicle's information to the end of the existing list. In this way, the lane vehicle dictionary for lane B reflects the set of all vehicles in the lane at the current moment, providing data support for traffic flow analysis and vehicle behavior prediction. In this way, the system can update and maintain an accurate view of the lane vehicle topology in real time.

[0132] For example, refer to Figure 4 , Figure 4 This is a schematic diagram of the vehicles in the lane matching method of this application being sorted in ascending order according to the distance from the lane starting point. The topological relationship between lanes and vehicles can be constructed to quickly query the vehicle information on the lane. The relationship information between lanes and vehicles in the frame-level map topology is stored in a dictionary lane_to_obj, where the key value is the lane number laneid, and the value value is a list of all vehicle numbers obj_id in the lane. If there is no vehicle in the lane in the frame frame, the value corresponding to the lane number is an empty list. The detailed information of the vehicle can be quickly obtained in the vehicle information dictionary through the vehicle number obj_id.

[0133] The topological relationship between lanes and vehicles is established as follows: First, each lane is configured with a list to store the vehicles on the lane. Second, the lane binding relationship between the vehicle and the lane can be obtained from the above relationship between the vehicle and the lane. If the vehicle is successfully bound to the lane, the vehicle number obj_id is added to the list corresponding to the bound lane.

[0134] The relationship between lanes and vehicles, lane_to_obj, only stores the relevant vehicles in the lane. If there are multiple vehicles in this lane, these vehicles are not sorted. In this case, all vehicles need to be sorted in ascending order according to the distance from the starting point of the lane, where the distance from the vehicle to the starting point of the lane has been calculated when the vehicle information is constructed. In this way, the relationship between vehicles can be easily established. And use the list of sorted vehicle obj_ids to update the corresponding information in lane_to_obj with the corresponding key value of laneid. Figure 3 As shown, in the relationship lane_to_obj between lanes and vehicles, for lane lane, its corresponding attribute is a list of vehicle numbers sorted in ascending order according to the distance s from the vehicle to the starting point of the lane.

[0135] In a feasible implementation manner, step S3400 may further include steps S3410 to S3430:

[0136] Step S3410: acquiring target lane subline information of the target lane, wherein the target lane subline information includes subline starting point coordinates, subline midpoint coordinates, and subline length;

[0137] Step S3420: Calculating the projection ratio of the target vehicle on the target lane subline based on the lane subline starting point coordinates, lane subline midpoint coordinates and lane subline length;

[0138] Step S3430: Based on the projection ratio of the target vehicle on the sub-line of the target lane, determine the projection distance and projection ratio of the target vehicle on the target lane.

[0139] It should be noted that this solution aims to achieve refined management of vehicle positions and efficient analysis of lane utilization by accurately obtaining lane sub-line information and calculating the projection ratio of the vehicle on it. Lane sub-line information, including starting point coordinates, midpoint coordinates and length, is the basic element to describe the geometric characteristics of the lane, which together define the spatial shape and size of the lane.

[0140] In addition, it should be noted that calculating the projection ratio of the vehicle on the lane sub-line is a key step, which involves mapping the vehicle's position into the local coordinate system of the lane. By comparing the relative position of the vehicle and the lane sub-line, the specific position of the vehicle on the lane sub-line and the proportion it occupies can be determined.

[0141] In addition, based on the projection ratio of the vehicle on the lane sub-line, the projection distance of the vehicle on the lane and the projection ratio of the vehicle on the lane can be further determined. This step not only helps to understand the specific position of the vehicle in the lane, but also provides important data for lane capacity analysis, traffic flow prediction, and vehicle behavior prediction.

[0142] In a feasible implementation, the system first obtains lane sub-line information through high-precision maps or real-time sensor data, including the starting point coordinates, midpoint coordinates and length of each lane. Then, the system uses this information and the current coordinates of the vehicle to determine the position of the vehicle relative to the lane sub-line through geometric calculations. The system calculates the vertical distance from the vehicle to the starting point of the lane sub-line, and calculates the projection ratio of the vehicle based on the length of the lane sub-line. If the projection ratio of the vehicle is 0.6, it means that the vehicle is located at 60% of the length of the lane. Finally, the system integrates this data, updates the topological relationship between the vehicle and the lane, and provides support for intelligent driving decisions. In this way, the system can monitor and analyze traffic conditions in real time, optimize traffic flow, and improve road use efficiency.

[0143] For example, refer to Figure 5 , Figure 5 This is a schematic diagram of calculating the distance between the projection point of the vehicle on the lane and the starting point in this application. The vehicle is bound to the lane. The principle of lane binding is that the projection distance from the vehicle to the lane is the smallest. The lane ID with the smallest projection is regarded as the lane where the vehicle is located. It is also necessary to further judge the size of the projection distance. If the minimum projection distance calculated by the vehicle is greater than a certain threshold, it is considered that the vehicle is not in any lane. At this time, the lane bound to the vehicle can be marked as -1 to indicate that the vehicle binding is unsuccessful.

[0144] Construct vehicle information. The frame-level map topology lane information is stored in a dictionary obj_info, where the key value is the vehicle number obj_id, and the value value is the specific information of the vehicle, which is also composed of a dictionary. The specific information includes the coordinates of the vehicle (obj_x, obj_y); the distance s from the starting point of the lane on the corresponding lane, that is, the specific position information of the vehicle on the lane; the proportion s_portion of the specific position of the vehicle on the lane to the entire lane length, where s and s_portion are obtained through vector calculation, such as Figure 4 As shown, the length of the route represented by green in the lane is recorded as s value.

[0145] The calculation method of s and s_portion is as follows. First, according to the vehicle obj_id, the lane number laneid of the vehicle is obtained from obj_to_lane, and further according to lane_info, the detailed information of the lane of the vehicle is obtained. The number of sub-segments of the lane n_segments, the coordinate information of the lane point_coords, and the length information of the sub-segments of the lane lengths are mainly used. Then the parameter is initialized to s=0.0, and the following operations are performed on each sub-segment in turn from the starting point of the lane. First, the sub-segment index is recorded as lane_seg_idx, and then the coordinates of the starting point of the sub-segment are solved:

[0146] lane_seg_start=lane_info[obj_lane_id]['point_coords'][lane_seg_idx]

[0147] Solve for the coordinates of the end point of the sub-segment:

[0148] lane_seg_end=lane_info[obj_lane_id]['point_coords'][lane_seg_idx+1]

[0149] Sub-segment length:

[0150] lane_seg_length=self.lane_info[obj_lane_id]['lengths'][lane_seg_idx]

[0151] Record obj_coords (obj_x, obj_y) as the vehicle coordinates

[0152] Then calculate:

[0153] s_seg_portion=sum((obj_coords-lane_seg_start)*(lane_seg_end-lane_seg_start)) / lane_seg_length^2

[0154] If s_seg_portion>1.0, s is reassigned to s+lane_seg_length, and lane_seg_idx+1. If the sub-segment corresponding to lane_seg_idx+1 exists, calculate from 3.1. If s_seg_portion<=1.0, the vehicle projection point falls in this sub-segment, s+lane_seg_length*s_seg_portion is the distance from the vehicle to the first point of the lane, and s is reassigned to s+lane_seg_length*s_seg_portion.

[0155] Finally, the total length of the lane is obtained through lane_info[obj_lane_id]['length'], then s / lane_info[obj_lane_id]['length'] is s_portion, which is the proportion of the vehicle's position to the entire lane length.

[0156] In a feasible implementation manner, step S4000 may further include steps S4100 to S4400:

[0157] Step S4100: Obtaining the left and right adjacent lanes and the preceding and succeeding lanes information of the target lane through the topological relationship between the lanes;

[0158] Step S4200: obtaining vehicle-to-vehicle information on the target lane through the lane-to-vehicle topological relationship;

[0159] Step S4300: Determine vehicle-to-vehicle information outside the target lane according to the left and right adjacent lanes and the preceding and succeeding lanes information of the target lane;

[0160] Step S4400: Determine the topological relationship between vehicles based on the information between vehicles on the target lane and the information between vehicles outside the target lane.

[0161] It should be noted that this solution aims to establish a comprehensive traffic network model by comprehensively utilizing the topological relationship between lanes and the topological relationship between lanes and vehicles. The topological relationship between lanes includes the information of the left and right adjacent lanes and the preceding and succeeding lanes of the lane, which is crucial for understanding the network structure of the lane. The topological relationship between lanes and vehicles provides specific information about the vehicles on the lane, including the location and speed of the vehicles.

[0162] In addition, it should be noted that the system can expand the analysis scope and determine the information between vehicles outside the lane through the information of the left and right adjacent lanes and the preceding and succeeding lanes. This includes vehicles in adjacent lanes that may affect the traffic flow of the current lane. For example, by analyzing the driving status of vehicles in adjacent lanes, the possibility of lane change behavior or traffic congestion can be predicted.

[0163] In addition, by combining the information between vehicles on the lane and the information between vehicles outside the lane, the system is able to determine the topological relationship between vehicles. This step is achieved by comprehensively considering the position of vehicles on the lane, their speed, and the relative distance between them. This helps to build a dynamic view of the traffic network, enabling the intelligent driving system to more accurately predict traffic conditions and make decisions.

[0164] In a feasible implementation, the system first obtains the topological relationship between lanes by analyzing high-precision map data and real-time traffic monitoring data. Next, the system uses vehicle positioning data and lane information to construct lane-vehicle topological relationships and record the position and status of vehicles on each lane. Then, the system identifies adjacent lanes outside the lane through the topological relationship between lanes and analyzes the vehicle information on these lanes to predict vehicle behaviors that may affect the current lane traffic flow. Finally, the system integrates the vehicle information on the lane and the vehicle information outside the lane to establish the topological relationship between vehicles and provide data support for traffic management and intelligent driving decisions. Through this solution, the operating efficiency and safety of the transportation system can be effectively improved.

[0165] For example, refer to Figure 6 , Figure 6 This is a schematic diagram of the topological relationship between vehicles in the lane matching method of this application. The relationship information between vehicles in the frame-level map topology is stored in a dictionary obj_to_obj, where the key value is the vehicle number obj_id, and the value value is the vehicle information around the vehicle. It is also composed of a dictionary, specifically including: a list of vehicle numbers left in the adjacent lane to the left of the lane where the vehicle is located, a list of vehicle numbers right in the adjacent lane to the right of the lane where the vehicle is located, a list of vehicle numbers front in front of the same lane sequence where the vehicle is located, and a list of vehicle numbers back in the same lane sequence where the vehicle is located.

[0166] The method for constructing the topological relationship between vehicles is as follows: lane_to_lane can be used to obtain the front, back, left, and right relationships between lanes; obj_to_lane can obtain the laneid of the vehicle; lane_to_obj can obtain the vehicle information on the lane; and by performing a recursive search on the lane, the front vehicle number list front, the rear vehicle number list back, the vehicle number list left on the left adjacent lane, and the vehicle number list right on the right adjacent lane of the current vehicle can be obtained.

[0167] like Figure 4 As shown in the figure, the left adjacent lane of lane 1 is lane 2, and there are two subsequent lanes of lane 1, lane 3 and lane 4. Then the left adjacent vehicle number list of vehicle 0 is [vehicle 1, vehicle 2, vehicle 3, vehicle 4];

[0168] Since the lane where vehicle 0 is located has no adjacent lane on the right, the right adjacent vehicle number list right of vehicle 0 is empty; the vehicle number list front in front of vehicle 0 is [vehicle 11, vehicle 12]; the vehicle number list back behind vehicle 0 is [vehicle 10].

[0169] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the lane matching method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0170] Please refer to Figure 7 The present application further provides a lane matching device 70, the lane matching device comprising:

[0171] An acquisition module 71 is used to acquire lane information of a target area in a driving map, wherein the lane information includes a lane connection relationship and lane coordinates;

[0172] A construction module 72, configured to construct a topological relationship between lanes based on the lane connection relationship and the lane coordinates;

[0173] A first determination module 73, configured to construct a vehicle-lane topological relationship based on a nearest projection method, and determine a lane-vehicle topological relationship based on the vehicle-lane topological relationship;

[0174] The second determination module 74 is used to determine the topological relationship between vehicles based on the topological relationship between lanes, the topological relationship between vehicles and lanes, and the topological relationship between lanes and vehicles.

[0175] The lane matching device provided by the present application adopts the lane matching method in the above embodiment, which can solve the technical problem of lane matching. Compared with the prior art, the beneficial effects of the lane matching device provided by the present application are the same as the beneficial effects of the lane matching method provided by the above embodiment, and other technical features in the lane matching device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0176] The present application provides a lane matching device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the lane matching method in the above-mentioned embodiment 1.

[0177] Reference below Figure 8 , which shows a schematic diagram of the structure of a lane matching device suitable for implementing the embodiment of the present application. The lane matching device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 8 The lane matching device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0178] like Figure 8As shown, the lane matching device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the lane matching device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the lane matching device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows a lane matching device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.

[0179] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0180] The lane matching device provided in the present application adopts the lane matching method in the above-mentioned embodiment. Compared with the prior art, the beneficial effects of the lane matching device provided in the present application are the same as the beneficial effects of the lane matching method provided in the above-mentioned embodiment, and other technical features in the lane matching device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0181] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0182] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0183] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the lane matching method in the above-mentioned embodiment.

[0184] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0185] The computer-readable storage medium may be included in the lane matching device; or may exist independently without being assembled into the lane matching device.

[0186] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the lane matching device, the lane matching device: obtains lane information of the target area in the driving map, and the lane information includes lane connection relationship and lane coordinates; constructs a lane-to-lane topological relationship based on the lane connection relationship and lane coordinates; constructs a vehicle-lane topological relationship based on the nearest projection method, and determines a lane-vehicle topological relationship based on the vehicle-lane topological relationship; determines the vehicle-to-vehicle topological relationship based on the lane-to-lane topological relationship, the vehicle-lane topological relationship, and the lane-vehicle topological relationship.

[0187] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0188] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0189] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0190] The readable storage medium provided in the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the lane matching method described above, and can solve the technical problem of lane matching. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in the present application are the same as the beneficial effects of the lane matching method provided in the above embodiment, and will not be elaborated here.

[0191] The present application also provides a computer program product, including a computer program, which implements the steps of the lane matching method as described above when executed by a processor.

[0192] The computer program product provided in this application can solve the technical problem of lane matching. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as the beneficial effects of the lane matching method provided in the above embodiment, which will not be repeated here.

[0193] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A lane matching method, characterized in that: The method comprises: Acquire lane information of a target area in a driving map, wherein the lane information includes a lane connection relationship and a lane coordinate; Constructing a topological relationship between lanes based on the lane connection relationship and the lane coordinates; Constructing a vehicle-lane topological relationship based on a nearest projection method, and determining a lane-vehicle topological relationship based on the vehicle-lane topological relationship, wherein the vehicle-lane topological relationship includes the lane where the vehicle is located and the position of the vehicle on the lane, and the lane-vehicle topological relationship includes the vehicles on the lane, and the vehicles on the lane are sorted according to the distance from the vehicle to the starting point of the lane; Based on the lane-to-lane topological relationship, the vehicle-lane topological relationship, and the lane-to-vehicle topological relationship, a vehicle-to-vehicle topological relationship is determined.

2. The method according to claim 1, characterized in that The target area includes a target lane and a target associated lane, the target lane includes a target lane sub-line, and the step of constructing a topological relationship between lanes based on the lane connection relationship and the lane coordinates includes: Calculate the midpoint coordinates of the target lane according to the starting point coordinates and the end point coordinates of the target lane; Determine a first pending lane and a second pending lane based on a minimum projection distance from the midpoint coordinates of the target lane to the target associated lane; Constructing a transformation coordinate system based on the starting point coordinates of the target lane and the sub-line orientation angle of the sub-line of the target lane; Converting the lane starting point coordinates of the first pending lane and the second pending lane according to the conversion coordinate system to obtain the converted starting point coordinates of the first pending lane and the converted starting point coordinates of the second pending lane; The left adjacent lane and the right adjacent lane of the target lane are determined according to the transformed coordinates of the starting point of the first pending lane and the transformed coordinates of the starting point of the second pending lane.

3. The method according to claim 2, characterized in that The step of constructing a topological relationship between lanes based on the lane connection relationship and lane coordinates further includes: Calculating a first Euclidean distance from the starting point coordinates of the target lane to the ending point coordinates of the target associated lane, and a second Euclidean distance from the ending point coordinates of the target lane to the starting point coordinates of the target associated lane; A preceding lane and a succeeding lane of the target lane are determined according to the first Euclidean distance and the second Euclidean distance.

4. The method according to claim 1, characterized in that The target area includes a target vehicle and a target lane. The steps of constructing a vehicle-lane topological relationship based on the nearest projection method and determining a lane-vehicle topological relationship based on the vehicle-lane topological relationship include: Calculating the projection distance from the target vehicle to the target lane; Filtering out the minimum projection distance from the target vehicle to the target lane; If the minimum projection distance is less than a preset distance threshold, then obtaining lane information corresponding to the minimum projection distance; Associating the target vehicle with lane information corresponding to the minimum projection distance to determine a vehicle lane topology relationship; The target vehicle information corresponding to the vehicle lane topology relationship is added to the lane vehicle dictionary of the corresponding lane to obtain the lane vehicle topology relationship.

5. The method according to claim 4, characterized in that After the step of associating the target vehicle with the lane information corresponding to the minimum projection distance to determine the vehicle lane topological relationship, the step further includes: Obtaining target lane subline information of the target lane, wherein the target lane subline information includes subline starting point coordinates, subline midpoint coordinates, and subline length; Calculate the projection ratio of the target vehicle on the target lane subline based on the lane subline starting point coordinates, lane subline midpoint coordinates and lane subline length; Based on the projection ratio of the target vehicle on the target lane sub-line, a projection distance and a projection ratio of the target vehicle on the target lane are determined.

6. The method according to claim 1, characterized in that The target area includes a target lane, and the step of determining the topological relationship between vehicles based on the topological relationship between lanes, the topological relationship between vehicles and lanes, and the topological relationship between lanes and vehicles comprises: Obtaining the left and right adjacent lanes and the preceding and succeeding lanes information of the target lane through the topological relationship between the lanes; Obtaining information between vehicles on the target lane through the lane-vehicle topological relationship; Determine vehicle-to-vehicle information outside the target lane based on the left and right adjacent lanes and the preceding and succeeding lanes of the target lane; The topological relationship between vehicles is determined according to the information between vehicles on the target lane and the information between vehicles outside the target lane.

7. A lane matching device, characterized in that: The device comprises: An acquisition module, used to acquire lane information of a target area in a driving map, wherein the lane information includes a lane connection relationship and lane coordinates; A construction module, used for constructing a topological relationship between lanes based on the lane connection relationship and lane coordinates; A first determination module is used to construct a vehicle-lane topological relationship based on a nearest projection method, and determine a lane-vehicle topological relationship based on the vehicle-lane topological relationship, wherein the vehicle-lane topological relationship includes the lane where the vehicle is located and the position of the vehicle on the lane, and the lane-vehicle topological relationship includes the vehicles on the lane, and the vehicles on the lane are sorted according to the distance from the vehicle to the starting point of the lane; The second determination module is used to determine the topological relationship between vehicles based on the topological relationship between lanes, the topological relationship between vehicles and lanes, and the topological relationship between lanes and vehicles.

8. A lane matching device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the lane matching method according to any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the lane matching method according to any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the lane matching method according to any one of claims 1 to 6 are implemented.

Images