Simulation road network generation method, device and storage medium

Abstract

The present application provides a method, device, and storage medium for generating a simulated road network, which relates to, but is not limited to, the field of data processing technology. The method includes generating a target road network directed graph based on each road attribute contained in road network data, determining the node position information and node identification of each road node in the target road network directed graph, and constructing road network node attribute data based on the node position information and node identification of each road node; determining the road identification and lane attributes corresponding to each edge in the target road network directed graph, and constructing road network edge attribute data based on the road identification and lane attributes corresponding to each edge; determining the lane connection relationship between any two adjacent edges based on the lane turning attribute corresponding to each edge in the target road network directed graph; and constructing a target simulated road network based on the road network node attribute data, the road network edge attribute data, and the lane connection relationship. This can reduce the generation cost of the simulated road network and improve the efficiency of road network construction.

Description

Technical Field

[0001] The embodiments of the present application relate to, but are not limited to, the field of data processing technology, and in particular to a method, device, and storage medium for generating a simulated road network. Background Art

[0002] Traffic simulation uses system simulation technology to generate simulated road networks. This technology then recreates the characteristics of actual traffic systems, analyzes the system's likely behavior under various set conditions, and uses simulation experiments to find optimal solutions to real-world traffic problems and evaluate the effectiveness of traffic design solutions, thereby improving the efficiency of traffic strategy generation. Simulated road network construction relies on GIS attribute data, such as the number of lanes, lane line types, and lane turn landmark types. While this attribute data can be collected through manual surveys, high-precision maps, and visual acquisition using floating vehicles, it lacks the lane connectivity and intersection feature attribute data required for constructing simulated road networks. Further manual processing based on GIS attribute data is required to obtain intersection attribute elements and lane-level connectivity data. This results in high cost and low efficiency in constructing simulated road networks. Therefore, a more cost-effective and efficient method for generating simulated road networks based on GIS data is urgently needed. Summary of the Invention

[0003] The embodiments of the present application provide a method, device, and storage medium for generating a simulated road network, aiming to reduce the generation cost of a simulated road network and improve the efficiency of road network construction.

[0004] In a first aspect, an embodiment of the present application provides a method for generating a simulated road network, the method comprising:

[0005] Acquire road network data, and generate a target road network directed graph according to each road attribute contained in the road network data, wherein the target road network directed graph includes a plurality of road nodes and edges connecting two adjacent road nodes;

[0006] Determining the node position information and node identification of each road node in the target road network directed graph, and constructing road network node attribute data according to the node position information and node identification of each road node;

[0007] Determine the road sign and lane attribute corresponding to each edge in the target road network directed graph, and construct road network edge attribute data based on the road sign and lane attribute corresponding to each edge;

[0008] Determine a lane connection relationship between any two adjacent edges based on a lane turning attribute corresponding to each edge in the target road network directed graph;

[0009] A target simulation road network is constructed based on the road network node attribute data, the road network edge attribute data, and the lane connection relationship between any two adjacent edges.

[0010] In a second aspect, an embodiment of the present application provides an electronic device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the simulation road network generation method as described in the first aspect is implemented.

[0011] In a third aspect, an embodiment of the present application provides a computer-readable storage medium, comprising computer-executable instructions stored therein, wherein the computer-executable instructions are used by a processor to execute the simulation road network generation method as described in the first aspect.

[0012] The above-mentioned embodiments of the present application have at least the following beneficial effects: through road network data, a target road network directed graph can be directly constructed based on the road section attributes in the road network data, and GIS attribute data including road network node attribute data, road network edge attribute data and lane connection relationships can be generated based on the target road network directed graph to construct a simulated road network based on the GIS attribute data. Compared with related technologies, the embodiments of the present application do not need to directly collect GIS attribute data, and the acquisition cost of GIS attribute data is lower and the acquisition efficiency is higher. Therefore, the embodiments of the present application can reduce the cost of acquiring GIS attribute data and improve the efficiency of constructing a simulated road network. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 Schematic diagram of the corresponding device modules of the simulated road network generation method according to an embodiment of the present application;

[0014] Figure 2 A schematic diagram of a flow chart of a method for generating a simulated road network according to an embodiment of the present application;

[0015] Figure 3a A schematic diagram of the connection relationship of left-turn lanes at an intersection in one embodiment of the simulated road network generation method of the present application;

[0016] Figure 3b A schematic diagram of the connection relationship of left-turn lanes at an intersection in another embodiment of the method for generating a simulated road network according to an embodiment of the present application;

[0017] Figure 4a A schematic diagram of the connection relationship between through-turn lanes at an intersection in one embodiment of the simulated road network generation method of the present application;

[0018] Figure 4b A schematic diagram of the connection relationship of through lanes at an intersection in another embodiment of the method for generating a simulated road network according to an embodiment of the present application;

[0019] Figure 5a A schematic diagram of the connection relationship of right-turn lanes at an intersection in one embodiment of the simulated road network generation method of the present application;

[0020] Figure 5b A schematic diagram of the connection relationship of right-turn lanes at an intersection in another embodiment of the method for generating a simulated road network according to an embodiment of the present application;

[0021] Figure 6a This is a schematic diagram of the connection relationship between straight-through turn lanes between road sections in one embodiment of the simulated road network generation method of the present application;

[0022] Figure 6b This is a schematic diagram of the connection relationship between straight-through turn lanes between road sections in another embodiment of the method for generating a simulated road network according to an embodiment of the present application;

[0023] Figure 7 A schematic diagram of an embodiment of a method for generating a simulated road network according to an embodiment of the present application;

[0024] Figure 8 A schematic diagram of a target simulation network in the simulation road network generation method according to an embodiment of the present application;

[0025] Figure 9 for Figure 8 An enlarged schematic diagram of the local A is shown;

[0026] Figure 10 Schematic diagram of the hardware structure corresponding to the simulation road network generation method of the application embodiment. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0028] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by those skilled in the art in the technical field of the present application. The terms used herein are only for the purpose of describing the embodiments of the present application and are not intended to limit the present application. The terms "first", "second", "third", "fourth" etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order.

[0029] In addition, the described features, structures or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure can be practiced without one or more of the specific details, or other methods, components, devices, steps, etc. can be adopted. In other cases, well-known methods, devices, implementations or operations are not shown or described in detail to avoid blurring various aspects of the present disclosure.

[0030] Traffic simulation uses system simulation technology to study traffic behavior. It tracks and describes how traffic flows change over time and space. Traffic simulation can reproduce the characteristics of actual traffic systems and analyze their likely behavior under various set conditions. Simulation experiments can then be used to find optimal solutions to real-world traffic problems and evaluate the effectiveness of traffic design solutions. The foundation of traffic simulation is the construction of a simulated road network. The creation of a simulated road network primarily requires GIS attribute data, including road segment attributes (such as the number of lanes, lane line type, and lane turn landmark type), intersection attributes, and lane-level connectivity. By mapping this GIS attribute data to the simulated road network, the simulated road network can be automatically generated. Currently, there are three main ways to obtain the GIS attribute data required for building a simulated road network: 1) Manual survey method, through manual collection of road network topology, survey to obtain road segment attribute elements, intersection attribute elements, and lane-level connection relationship data; 2) High-precision map collection method, a map collection device that collects high-precision map data is mounted on a collection vehicle, and the collection vehicle completes high-precision map data collection while driving on the road. After processing and verification of the collected data, high-precision map data containing attribute elements such as road network topology, road segment attribute elements, intersection attribute elements, and lane-level connection relationships is obtained; Although the GIS attribute data required for the simulated road network can be fully obtained based on manual or high-precision map collection methods, the cost of obtaining GIS attribute data is high, the modeling efficiency of the simulated road network is low, and the practicality is not strong, making it difficult to support the low-cost and rapid generation of simulated road networks within a regional scope.

[0031] In summary, in the prior art, how to provide a method for producing a simulated road network with lower cost and higher construction efficiency is a technical problem that needs to be solved urgently. Based on this, the embodiments of the present application provide a simulated road network generation method, a traffic strategy generation method, a device, and a storage medium, which are intended to reduce the cost of data acquisition and improve the efficiency of constructing a simulated road network.

[0032] Reference Figure 1 As shown, the embodiment of the present application provides a simulated road network generation device, comprising:

[0033] The road network data acquisition module 100 is used to acquire road network data and generate a target road network directed graph based on each road attribute contained in the road network data. The target road network directed graph includes multiple road nodes and edges connecting two adjacent road nodes.

[0034] The node attribute construction module 200 is used to determine the node location information and node identification of each road node in the target road network directed graph, and to construct the road network node attribute data according to the node location information and node identification of each road node;

[0035] The edge attribute construction module 300 is used to determine the road identification and lane attributes corresponding to each edge in the target road network directed graph, and construct the road network edge attribute data according to the road identification and lane attributes corresponding to each edge;

[0036] A connection relationship building module 400 is used to determine the lane connection relationship between any two adjacent edges based on the lane turning attribute corresponding to each edge in the target road network directed graph;

[0037] The road network construction module 500 constructs a target simulation road network based on the road network node attribute data, the road network edge attribute data, and the lane connection relationship between any two adjacent edges.

[0038] It is understandable that referring to Figure 2 As shown, the embodiment of the present application provides a method for generating a simulated road network, and the method for generating a simulated road network includes:

[0039] Step S100: Acquire road network data, and generate a target road network directed graph based on each road attribute contained in the road network data, wherein the target road network directed graph includes a plurality of road nodes and edges connecting two adjacent road nodes;

[0040] Step S200: determining the node location information and node identification of each road node in the target road network directed graph, and constructing road network node attribute data based on the node location information and node identification of each road node;

[0041] Step S300: Determine the road identification and lane attributes corresponding to each edge in the target road network directed graph, and construct road network edge attribute data based on the road identification and lane attributes corresponding to each edge;

[0042] Step S400: determining a lane connection relationship between any two adjacent edges based on the lane turning attribute corresponding to each edge in the target road network directed graph;

[0043] Step S500: Construct a target simulated road network based on the road network node attribute data, the road network edge attribute data, and the lane connection relationship between any two adjacent edges.

[0044] Therefore, through road network data, a target road network directed graph can be directly constructed based on the road section attributes in the road network data, and GIS attribute data including road network node attribute data, road network edge attribute data and lane connection relationships can be generated based on the target road network directed graph to construct a simulated road network based on GIS attribute data. Compared with related technologies, the embodiments of the present application do not need to directly collect GIS attribute data, and the cost of obtaining GIS attribute data is lower and the acquisition efficiency is higher. Therefore, the embodiments of the present application can reduce the cost of obtaining GIS attribute data and improve the efficiency of constructing a simulated road network.

[0045] Road network data represents the driving rules of vehicles on multiple different road segments. The road network data includes segment attributes for multiple road sides. Each segment attribute includes at least the number of lanes, lane line type, and lane turn landmark type for the corresponding road side. This embodiment of the application does not limit the format of each data type in the segment attributes. Those skilled in the art may customize the format. For example, the segment attributes can be shown in Table 1 below:

[0046]

[0047] Table 1

[0048] The target road network directed graph is used to establish relationships between road edges based on their road attributes in a graph format, facilitating analysis of lane connectivity between adjacent road edges. It also allows for the determination of the relative position of each road node and road network edge attribute data.

[0049] Road network node attribute data is a collection of location information for multiple road nodes in a pre-set format. The location information for a road node includes x- and y-coordinate values. The road node identifier is used to improve the efficiency of road node searches. The x- and y-coordinate values ​​can each be a type of road attribute data, or some road nodes can be a type of road attribute data. For example, each road attribute data includes the starting coordinates of the corresponding road edge (i.e., the x- and y-coordinate values ​​of the starting point), the ending coordinates of the corresponding road edge (i.e., the x- and y-coordinate values ​​of the ending point), the number of lanes, the lane line type, and the lane turn landmark type. For another example, in some embodiments, each road attribute data includes the starting coordinates of the corresponding road edge (i.e., the x- and y-coordinate values ​​of the starting point), the length of the corresponding road edge, the number of lanes, the lane line type, and the lane turn landmark type, thereby enabling the ending coordinates to be determined based on the starting coordinates and the road length. For another example, in other embodiments, each road attribute data includes the ending coordinates of the corresponding road edge (i.e., the x- and y-coordinate values ​​of the ending point), the length of the corresponding road edge, the number of lanes, the lane line type, and the lane turn landmark type, thereby enabling the starting coordinates to be determined based on the ending coordinates and the road length. In this regard, the embodiment of the present application does not limit the method for obtaining the node coordinates of each road node, and those skilled in the art can selectively set it according to actual needs.

[0050] Road network edge attribute data is a collection of lane attributes in a pre-set format for each road edge, where the lane attributes represent the lane type of each road edge. In some embodiments, the lane attributes include a starting road node identifier, an ending road node identifier, and a lane type. In other embodiments, the lane attributes include a starting road node identifier, an ending road node identifier, the number of lanes, and the lane type.

[0051] The embodiments of the present application do not limit the recording format of road network edge attribute data and the recording format of road network node attribute data.

[0052] Exemplarily, the road network node attribute data is constructed as follows:

[0053] Traverse each road node in the target road network directed graph in turn, extract the node identifier i and the node location information (i.e., x-coordinate value, y-coordinate value) of the road node, and define each node according to the format to form the road network node attribute data. For example, if the node identifier = 373, the x-coordinate value = 0, and the y-coordinate value = 0, then the road node is defined according to the format as<node id="373"x="0"y="0" / > .

[0054] For example, the road network edge attribute data is constructed as follows:

[0055] Traverse each road edge in the target road network directed graph in sequence, extract the road edge's attribute values, such as road ID j, starting road node ID, ending road node ID, number of lanes, and lane type. Define each road edge according to the format, and combine them to obtain the road network edge attribute data. For example, for a road edge with road ID = 2, starting road node ID = 40, ending road node ID = 39, number of lanes = 3, and lane type = {1:[0,0],2:[0,0],3:[0,1]}, the following data can be obtained according to the format definition:

[0056] <edge id="2"from="40"to="39"numLanes="3">

[0057] <l ane index="0"changeLeft="no"changeRight="no" / >

[0058] <l ane index="1"changeLeft="no"changeRight="no" / >

[0059] <l ane index="2"changeLeft="no"changeRight="a l l" / >

[0060]

[0061] Where id represents the road sign on the roadside; from represents the starting road node identifier on the roadside; to represents the ending road node identifier on the roadside; numLanes represents the number of lanes on the roadside; index represents the lane number. Note that lane numbers start at 0, that is, index="0" represents the first lane; changeLeft indicates whether vehicles in this lane can change lanes to the left, and the value is "no" or "all". "no" means that all vehicles cannot change lanes to the left, and "all" means that all vehicles can change lanes to the left; changeRight indicates whether vehicles in this lane can turn right, and the value is "no" or "all". "no" means that all vehicles cannot change lanes to the right, and "all" means that all vehicles can change lanes to the right.

[0062] Lane connectivity represents the corresponding relationship between lanes on two adjacent road sides that a vehicle passes through. This allows for prediction of the vehicle's possible travel direction and thus determines traffic congestion.

[0063] It is understandable that the target road network directed graph is generated according to each road attribute included in the road network data, including:

[0064] Extracting node attributes and edge attributes from the road network data to determine a candidate road network directed graph; the candidate road network directed graph includes a plurality of candidate road nodes and a first candidate edge connecting two adjacent candidate road nodes;

[0065] Determining the node in-degree of each first candidate edge according to the node attributes of the candidate road node and the edge attributes of the first candidate edge;

[0066] Determine the first candidate edge whose node in-degree is greater than a preset in-degree threshold as a candidate cross edge;

[0067] According to each candidate intersection edge, multiple candidate intersection edges that can form an intersection are determined, and corresponding directed closed-loop subgraphs are generated according to multiple candidate intersection edges of the same intersection;

[0068] According to the directed closed-loop subgraph, the candidate road network directed graph is updated to obtain the target road network directed graph, wherein the target road network directed graph is a directed graph obtained by removing the candidate cross edges of the directed closed-loop subgraph from the candidate road network directed graph.

[0069] Compared with deep learning-based methods that identify road attribute element data such as the number of lanes, lane turn landmark types, and lane line types, by constructing directed closed-loop subgraphs and candidate road network directed graphs, human intervention is eliminated. Relying on the road network topology, this method focuses on solving the problem of automatically obtaining intersection attribute elements and lane-level connection relationships, thereby automatically generating a .net.xml simulation road network that meets the format requirements of the SUMO traffic simulation software at low cost and high efficiency.

[0070] The node in-degree represents the total number of lane edges entering and exiting the road edge. For example, at an intersection, as shown in Figure 3, each intersection boundary can be considered a road edge. In some embodiments, road edges with an edge length less than or equal to a set threshold (e.g., 50 meters) can be considered potential intersection edges. When the node in-degree of an intersection edge is greater than the preset in-degree threshold, it indicates a higher probability of being at an intersection.

[0071] The in-degree threshold can be set based on human experience. Generally, the in-degree of an intersection node is at least 3, so the in-degree threshold can be set to 3.

[0072] Whether an intersection can be formed can be determined by whether a loop can be formed between each candidate intersection edge. Therefore, by first screening out candidate intersection edges and then determining whether a loop is formed between the candidate intersection edges, the intersection edges that are not intersections can be further eliminated to reduce the efficiency of intersection determination.

[0073] By deleting the candidate cross edges of the directed closed-loop subgraph in the candidate road network directed graph, the efficiency of lane connection relationship analysis can be improved and the difficulty of traffic strategy analysis of the target simulation road network can be reduced.

[0074] Exemplarily, the target road network directed graph is generated as follows:

[0075] Obtain road network data, which includes the attributes of multiple road segments. Each segment attribute includes at least the number of lanes, lane type, lane turn landmark type, and road node coordinates. Then, a candidate network directed graph G(V, E, P) of the GIS road network is constructed based on the segment attributes of each road. V ,P E ), specifically including the following steps:

[0076] 1) Convert the n road segment attributes in the road network data into a candidate road network directed graph G(V, E, P V ,P E ).

[0077] Where V is the node set {v1,v2,v3,v4,...v n}; E is the edge set {e1,e2,e3,e4,...e n};P V is the attribute value set of the node, including three attribute values: node identifier i, x coordinate value, y coordinate value, etc.; P E is the attribute value set of the edge, including the road identifier j and the starting node identifier v i , end node identifier v j , number of lanes, lane line type, lane turning landmark type, and edge length.

[0078] 2) Statistical directed graph G(V,E,P V ,P E ) is the in-degree of each road node.

[0079] 3) Initial screening to obtain the edge set E of potential intersections 1 .

[0080] The edge of a potential intersection is defined as an edge whose length is less than or equal to a set threshold (such as 50 meters) and the node in-and-out degree of the starting and ending points of the edge is greater than or equal to 3. V ,P E ) to initially screen out the edges of potential intersections and construct a new edge set E 1 ;

[0081] 4) Construct a directed graph of potential intersections

[0082] Based on the new edge set E 1 , forming a new directed graph Since the directed graph can more efficiently determine the set of road edges, the edge set E 1 Convert to directed graph G 1 Identify intersections.

[0083] 5) Extract the directed closed-loop subgraph of each intersection

[0084] In the new directed graph Extract all directed closed-loop subgraphs from Each directed closed subgraph Represents an intersection.

[0085] 6) Based on directed closed-loop subgraph Update the candidate road network directed graph G(V,E,P V ,P E ), and get the updated G(V,E,P V ,P E ) as the target road network directed graph.

[0086] It can be understood that, based on the directed closed-loop subgraph, the candidate road network directed graph is updated to obtain the target road network directed graph, including:

[0087] Traverse each directed closed-loop subgraph and delete each candidate cross edge in the traversed directed closed-loop subgraph in the candidate road network directed graph;

[0088] The coordinates of each road node in the same directed closed loop subgraph are averaged and the Figure 1 A corresponding mean coordinate point;

[0089] Update the starting point of the road edge in the downstream direction directly connected to the endpoint of each deleted candidate intersection edge to the corresponding mean coordinate point;

[0090] Update the starting point of the upstream road edge directly connected to the endpoint of each deleted candidate intersection edge to the corresponding mean coordinate point;

[0091] In the candidate road network directed graph, the information of each road node in the directed closed-loop subgraph is deleted and the mean coordinate point is added.

[0092] Both the upstream and downstream directions are defined relative to the vehicle's travel direction. The downstream edge is the destination edge in the upstream direction, and the upstream edge is the starting edge in the downstream direction. When a vehicle travels from Road 1 to Road 2, Road 1 is the upstream direction of Road 2, and Road 2 is the downstream direction of Road 1. For example, Road 2 is the downstream edge of Road 1, and Road 1 is the upstream edge of Road 2.

[0093] By updating the connection coordinates of the road nodes after deleting the edges, the road nodes can be retained while facilitating the subsequent analysis of the turning connection relationship.

[0094] For example, assuming there are k directed closed-loop subgraphs, the following processing steps are performed for each directed closed-loop subgraph:

[0095] 1) In the candidate road network directed graph G(V,E,P V ,P E ) is a directed closed subgraph The edge set of the cross edges of ; is a directed closed subgraph The attribute set of the cross edge;

[0096] 2) In the candidate road network directed graph G(V,E,P V ,P E ), update and The starting points of other directly connected downstream edges are That is, for the i-th directed closed-loop subgraph of The intersection ratio edge and the starting point of other downstream edges are set to

[0097]

[0098] 3) In the candidate road network directed graph G(V,E,P V ,P E ), update and The endpoints of other directly connected upstream edges are That is, for the i-th directed closed-loop subgraph of The intersection ratio edge and the starting point of other downstream edges are set to

[0099]

[0100] 4) In the candidate road network directed graph G(V,E,P V ,P E ), update the node The coordinates are The average value of all node coordinates. By setting the average value, each downstream edge and the upper right edge directly connected to the center of the shape formed by the intersection. That is, assuming that the i-th directed closed loop subgraph The coordinates of each road node are L1~Lm; then Represents ((L1.x+...Lm.x) / m, (L1.y+...Lm.y) / m).

[0101] 5) In the candidate road network directed graph G(V,E,P V ,P E ), delete The nodes contained in , except for the node outside.

[0102] It can be understood that based on the lane turning attributes corresponding to each edge in the target road network directed graph, the lane connection relationship between any two adjacent edges is determined, including:

[0103] Traverse each road edge in the directed graph of the target road network as a second candidate edge in sequence and determine a downstream edge set corresponding to each second candidate edge according to the lane turning attribute of each second candidate edge;

[0104] Determine, based on the turning attributes of each lane and the corresponding downstream edge set, a turning relationship between each second candidate edge and each corresponding downstream edge;

[0105] A lane connection relationship between any two adjacent edges is generated based on the turning relationship between each second candidate edge and each corresponding downstream edge, and the lane turning attributes of the second candidate edge and the corresponding downstream edge.

[0106] The lane turning attribute records lane turning related data, including the lane turning landmark type.

[0107] For example, if lane 1 with edge number 9 is connected to lane 2 with edge number 65, the lane connection relationship is as follows:<connect ion from="9"to="65"fromLane="1"toLane="2" / > .

[0108] The downstream edge set is set in a one-to-one correspondence with the second candidate edge. The downstream edge set is a set of road edges that each lane in the corresponding second candidate edge can travel in the downstream direction.

[0109] It can be understood that, based on the turning attributes of each lane and the corresponding set of downstream edges, determining the turning relationship between each second candidate edge and each corresponding downstream edge includes:

[0110] Each edge in the downstream edge set is taken as a candidate turning edge;

[0111] Calculate the counterclockwise angle between each second candidate edge and each corresponding candidate turning edge according to the turning attribute of each lane;

[0112] According to the counterclockwise angle, a turning relationship between the second candidate edge and each corresponding candidate turning edge is determined, wherein each turning relationship is one of a U-turn turning relationship, a left turn turning relationship, a straight turning relationship, and a right turn turning relationship.

[0113] It is understandable that the counterclockwise angle may be determined based on the starting point coordinates and the ending point coordinates of the second candidate edge and the coordinates of the connection point with each corresponding candidate turning edge.

[0114] The embodiment of the present application does not limit the relationship between the U-turn relationship, the left turn relationship, the straight turn relationship, and the right turn relationship and the counterclockwise angle, and those skilled in the art can selectively set it according to the actual road conditions. i With candidate turning edges The counterclockwise angle of the second candidate edge is between 150° and 210°. i To the candidate turning edge The turning relationship is a U-turn turning relationship; when the second candidate edge e i With candidate turning edges The counterclockwise angle of the second candidate edge is between 30° and 150°. i To the candidate turning edge The turning relationship is a left-turn turning relationship; when the second candidate edge e i With candidate turning edges The counterclockwise angle of the second candidate edge is between 0°-30° and 330°-360°. i To the candidate turning edge The turning relationship is a straight-ahead turning relationship; when the second candidate edge e i With candidate turning edges The counterclockwise angle of the second candidate edge is between 210° and 330°. i To the candidate turning edge The steering relationship is a right turn relationship.

[0115] The second candidate edge e i And the corresponding candidate turning edges The counterclockwise angle θ is calculated as follows:

[0116]

[0117] The calculation formulas for k and n are as follows:

[0118]

[0119] n=(x2-x1)·(y4-y3)-(x4-x3)·(y2-y1)

[0120] Where x1, y1 are the second candidate edge e i The starting point x, y coordinates; x2, y2 are the second candidate edge e i The x, y coordinates of the end point; x3, y3 are the downstream edges The starting point x, y coordinates; x4, y4 are candidate turning edges The x,y coordinates of the end point; π is radians, expressed as 180°.

[0121] It can be understood that, based on the turning relationship between each second candidate edge and each corresponding downstream edge, as well as the lane turning attributes of the second candidate edge and the corresponding downstream edge, a lane connection relationship between any two adjacent edges is generated, including:

[0122] Determine the number of turning lanes of the second candidate edge at different turning relationships according to the lane turning attribute of the second candidate edge, and determine the number of exit lanes of the downstream edge at the turning relationship according to the lane attribute of the downstream edge;

[0123] The downstream edge that has a non-straight-turning relationship with the second candidate edge is used as the corresponding first target downstream edge;

[0124] When the number of turning lanes of the second candidate edge turning toward the first target downstream edge is less than or equal to the number of exit lanes of the corresponding first target downstream edge and the second candidate edge has multiple turning relationships, sequentially connect each turning lane of the second candidate edge turning toward the first target downstream edge with each corresponding lane of the first target downstream edge one by one to obtain a lane connection relationship between the second candidate edge and the first target downstream edge;

[0125] When the number of turning lanes of the second candidate edge turning toward the first target downstream edge is greater than the number of exit lanes of the corresponding first target downstream edge and there are multiple turning relationships of the second candidate edge, each lane in the first target downstream edge that supports the turning of the second candidate edge is sequentially connected to a corresponding turning lane in the second candidate edge, and the remaining turning lanes in the second candidate edge turning toward the first target downstream edge are all connected to the corresponding outermost lanes in the first target downstream edge to obtain the lane connection relationship between the second candidate edge and the first target downstream edge.

[0126] The second candidate edge has multiple turning relationships indicating that it is a roadside at an intersection. The outermost lane is the last lane connected when the roadside is connected sequentially.

[0127] When the turning relationship with the second candidate edge is a non-straight turning relationship, the lane connection rules of the intersection entrance and exit lanes need to be considered: among them, non-straight turning relationships include left turn relationships, U-turn turning relationships, and right turn relationships.

[0128] Take the first target downstream edge as the downstream edge For example, when the second candidate edge e i To the downstream side The steering relationship is left turn / U-turn, and the e i The left turn / U-turn lane in the downstream lane is connected to the The lanes in the corresponding connection are divided into two situations, as follows:

[0129] Case 1: e i The number of U-turn / left-turn lanes is less than or equal to Number of exit lanes, refer to Figure 3a As shown, e i The second lane is the left-turn lane (i.e. the turning lane corresponding to the left-turn direction), and the number of left-turn lanes is 1. There are 3 lanes, that is, the number of exit lanes is 3. When the lanes are connected in sequence, e i Lane 2 and The third lane of the connection, that is, e i Lane 2 and Connect to the first exit lane in the upstream direction.

[0130] Case 2: e i The number of U-turn / left-turn lanes is greater than The number of exit lanes, such as Figure 3b As shown, e i Lanes 1, 2, and 3 are all left-turn lanes, and there are 3 left-turn lanes. There are 2 lanes, and when the lanes are connected sequentially, e i Lane 3 and The second lane connection (also known as e i The first left turn lane First exit lane connection), e i Lane 2 and Lane 1 of the connection, e i Lane 1 and Lane 1 connection; The first lane is The outermost lane.

[0131] Similarly, for a scenario where the steering system is a U-turn, the lane connection relationship can be determined by referring to the above method.

[0132] Lane connection rules for intersection entrance and exit lanes: When the second candidate edge e i To the first target downstream edge The turning relationship is right turn; the forward direction is from right to left, and the second candidate edge e i The right turn lane in the first target lane is The lanes in the corresponding connection. There are two situations.

[0133] Case 1: e i The number of right-turn lanes is less than or equal to The number of exit lanes, such as Figure 5a As shown, e i The first lane is the right-turn lane (that is, the turning lane corresponding to the right-turn direction). There are 3 lanes, when connected sequentially, e i Lane 1 and Lane 1 connection; The first lane is the upstream lane when turning right. The first lane.

[0134] Case 2: e i The number of right-turn lanes is greater than The number of exit lanes, such as Figure 5b As shown, e i Lanes 1, 2, and 3 are all right-turn lanes. If there are 2 lanes, then when connected sequentially, e i Lane 1 and Lane 1 of the connection, e i Lane 2 and The second lane of the connection, e i The third lane on the upstream side The 2nd lane connects.

[0135] Therefore, by analyzing the relationship between the number of lanes in the turning relationship and the number of exit lanes on the downstream edge for each non-straight turning relationship, the lane connection relationship between each second candidate edge and the corresponding downstream edge can be constructed. Figure 3a 、 Figure 3b You can get the left turn lane connection relationship, refer to Figure 5a and Figure 5b The right-turn lane connection relationship can be obtained.

[0136] It is understood that generating a lane connection relationship between any two adjacent edges based on the turning relationship between each second candidate edge and each corresponding downstream edge, as well as the lane turning attributes of the second candidate edge and the corresponding downstream edge, further includes at least one of the following:

[0137] The downstream edge that has a turning relationship of straight ahead with the second candidate edge is used as the corresponding second target downstream edge;

[0138] When the second candidate edge has multiple turning relationships, obtain the reserved turning lane of the second target downstream edge and sequentially connect the remaining lanes of the second target downstream edge except the reserved turning lane to the through lane of the second candidate edge to obtain the lane connection relationship between the second candidate edge and the second target downstream edge;

[0139] When the number of lanes on the second candidate edge is greater than the number of exit lanes on the second target downstream edge and all turning relationships on the second candidate edge are straight-line turning relationships, sequentially connect each through lane on the second target downstream edge with a through lane on the second candidate edge, and connect all remaining through lanes on the second candidate edge with the outermost through lane on the second target downstream edge to obtain a lane connection relationship between the second candidate edge and the second target downstream edge;

[0140] When the number of lanes of the second candidate edge is less than or equal to the number of exit lanes of the second target downstream edge and the turning relationships of the second candidate edge are all linear turning relationships, each through lane of the second candidate edge is sequentially connected to each through lane of the second target downstream edge one by one to obtain the lane connection relationship between the second candidate edge and the second target downstream edge.

[0141] When the second candidate edge has multiple turning relationships, it should follow the lane connection rules of the intersection entrance and exit lanes: that is, when the edge e i To the downstream side The turning relationship is a straight turning relationship. In order to eliminate the lateral left turn to the corresponding downstream edge Traffic going straight to the downstream side To solve the interference of traffic flow, it is necessary to analyze the two situations: the number of through lanes + the number of lateral left-turn lanes is less than or equal to the number of exit lanes, and the number of through lanes + the number of lateral left-turn lanes is greater than the number of exit lanes.

[0142] The second target downstream edge The other upstream edge is e k For example, the following is an example:

[0143] Case 1: e i Number of straight lanes + e k The number of lateral left-turn lanes is less than or equal to Number of exit lanes, e.g. Figure 4a As shown, The sideways turn to the left and downstream side should be eliminated After the lane, connect e i The straight lane and For the remaining lanes, take the order from left to right in the forward direction as an example, then e i The through lanes in The remaining lanes in correspond to connections. Figure 4a As shown, e i The second lane in the middle is the straight-through turning lane. There are 3 lanes, and 1 lane on the side turns left Then e i Lane 2 and downstream edge The 2nd lane connects.

[0144] Case 2: e i Number of straight lanes + e k The number of lateral left-turn lanes is greater than Number of exit lanes. If there is a conflict between straight-moving vehicles and left-turning vehicles on the side, k lanes need to be eliminated and then e lanes need to be connected in sequence. i and For example, if we take the left lane as an example, we will remove the downstream edge from the left lane in the forward direction. After the k lanes in the forward direction, the upstream edge e i The straight lane in the downstream lane is connected in sequence The lanes in the corresponding connection, k is calculated as follows: k = max (downstream edge Number of exit lanes - upstream edge e i The number of straight lanes in ,0). At this time, if Figure 4b As shown, e i The 1st and 2nd lanes are straight-through turn lanes. There are 2 lanes, and 1 lane on the side to turn left Then k=max(2-2,0)=0, the downstream edge No lane needs to be removed, so the upstream edge e i Lane 2 and downstream edge The second lane of the connection, the upstream edge e i Lane 1 and downstream edge The 2nd lane connects.

[0145] The turning relationships of the second candidate edge are all straight-line turning relationships, so the lane connection relationship should follow the lane connection rules between road segments, and the lanes between the second candidate edge and the corresponding downstream edge can be connected sequentially. The sequential connection can be from left to right in the forward direction. For example, the second candidate edge is e i , the downstream edge of the second target is For example, the following example:

[0146] Case 1: e i The number of lanes is less than or equal to The number of exit lanes, such as Figure 6a As shown, e i There are 3 lanes. There are 4 lanes, then e i Lane 3 and The 4th lane connects to; i Lane 2 and The 3rd lane connects to; i Lane 1 and The second lane of the connection; i Lane 1 and The 1st lane connects.

[0147] Case 2: e i The number of lanes is greater than The number of exit lanes, such as Figure 6b As shown, e i There are 4 lanes. There are 3 lanes, then e i Lane 4 and The 3rd lane connects to; i Lane 3 and The second lane of the connection; i Lane 2 and Lane 1 of the connection; e i Lane 1 and The 1st lane connects.

[0148] At this time, refer to the above Figures 3a to 6b , we can get the lane connection relationship between each turning relationship on each road edge and the corresponding downstream edge.

[0149] The turn lane is determined by the following steps:

[0150] The number of interfering lanes of the second candidate edge is obtained according to the sum of the number of straight lanes of the second candidate edge and the number of left-turn lanes from other upstream edges of the second target downstream edge to the second target downstream edge;

[0151] When the number of interfering lanes is less than or equal to the number of exit lanes of the corresponding second target downstream edge, the number of left-turn lanes from other upstream edges of the second target downstream edge to the second target downstream edge is used as the number of reserved turning lanes of the second target downstream edge;

[0152] When the number of interfering lanes is less than or equal to the number of exit lanes of the corresponding second target downstream edge, the turning reserved lane is determined according to the lane difference between the number of exit lanes of the first target downstream edge and the number of turning lanes of the second candidate edge in the straight direction.

[0153] Refer to the following Figure 7 The process of constructing a target simulation road network according to one embodiment of the present application is described as follows:

[0154] S1. Input road network data:

[0155] The road network data is required to be in .geojson or .shp format. The road network data includes the segment attribute values ​​of multiple road sides. Each segment attribute contains at least three attribute values: the number of lanes, lane line type, and lane turn landmark type. The segment attribute values ​​can be shown in Table 1.

[0156] S2. Construct the candidate road network directed graph G((V,E,P V ,P e ):

[0157] Convert the road network data into a candidate road network directed graph G(V,E,P V ,P E ); where V is a node set {v1,v2,v3,v4,...v n}; E is the edge set {e1,e2,e3,e4,...e n};P V is the attribute value set of the node, including three attribute values: node identifier i, x coordinate value, y coordinate value, etc.; P E is the attribute value set of the edge, including the road identifier j and the starting node identifier v i , end node identifier v j , number of lanes, lane line type, lane turning landmark type, and edge length.

[0158] S3. Identify intersections:

[0159] 1) Statistics of candidate road network directed graph (V, E, P V ,P E ) The in-and-out degree of each road node;

[0160] 2) Initial screening to obtain the edge set E of potential intersections 1 :

[0161] The intersection edge of a potential intersection is defined as an edge whose length is less than or equal to a set threshold (such as 50 meters) and the node in-and-out degree of the starting and ending points of the intersection edge is greater than or equal to 3. V ,P E ) to initially screen out the cross edges of potential intersections and construct a new edge set E 1 ;

[0162] 3) Construct a directed graph of potential intersections

[0163] Based on the new edge set E 1 , forming a new directed graph

[0164] 4) Extract the directed closed-loop subgraph of each intersection

[0165] In the new directed graph Extract all directed closed-loop subgraphs from Each directed closed subgraph Represents an intersection.

[0166] S4, intersection node aggregation, update directed graph G(V,E,P V ,P E ):

[0167] For each directed closed subgraph in S2 All the traversals are performed according to the following processing steps. After traversing all the directed closed-loop subgraphs We can get the updated directed graph G(V,E,P V ,P E ):

[0168] 1) In the candidate road network directed graph G(V,E,P V ,P E )

[0169] 2) In the candidate road network directed graph G(V,E,P v ,P E ), update and The starting points of other directly connected downstream edges are

[0170] 3) In the candidate road network directed graph G(V,E,P V ,P E ), update and The endpoints of other directly connected upstream edges are

[0171] 4) In the candidate network directed graph G(V,E,PV ,P E ), update the node The coordinates are The average value of all node coordinates;

[0172] 5) In the candidate road network directed graph G(V,E,P V ,P E ), delete The nodes contained in , except for the node outside.

[0173] S5.1. Build the road network node attribute file:

[0174] Traverse the updated G(V,E,P V ,P E ), extract the node identifier i, x-coordinate value, y-coordinate value and other three attribute values ​​of the node, define each road node according to the format, and combine them to form a road network node attribute file.

[0175] For example, if the node number is 373, the x-coordinate value is 0, and the y-coordinate value is 0, then the node is defined according to the format, as shown in the following example:

[0176] <node id="373"x="0"y="0" / > ;

[0177] S5.2. Build the road network edge attribute file:

[0178] Traverse the updated G(V,E,P V ,P E ) extracts the road edge attributes, such as the road ID j, starting node ID, ending node ID, number of lanes, and lane type, and defines each edge according to the format. These attributes are combined to form a road network edge attribute file. For example, if the edge number is 2, the starting node number is 40, the ending node number is 39, the number of lanes is 3, and the lane type is {1:[0,0],2:[0,0],3:[0,1]}, then the edge is defined according to the format. An example is as follows:

[0179] <edge id="2"from="40"to="39"numLanes="3">

[0180] <l ane index="0"changeLeft="no"changeRight="no" / >

[0181] <l ane index="1"changeLeft="no"changeRight="no" / >

[0182] <l ane index="2"changeLeft="no"changeRight="a l l" / >

[0183]

[0184] Where id represents the road sign on the roadside; from represents the starting node identifier of the roadside; to represents the ending node identifier of the edge; numLanes represents the number of lanes on the roadside; index represents the lane number. Note that lane numbers start at 0, that is, index="0" represents the first lane; changeLeft indicates whether vehicles in this lane can change lanes to the left, and the value is "no" or "all". "no" means that all vehicles cannot change lanes to the left, and "all" means that all vehicles can change lanes to the left; changeRight indicates whether vehicles in this lane can turn right, and the value is "no" or "all". "no" means that all vehicles cannot change lanes to the right, and "all" means that all vehicles can change lanes to the right.

[0185] S5.3. Build the road network lane connection relationship file:

[0186] Traverse the updated G(V,E,P V ,P E ) for each second candidate edge e i , construct the second candidate edge e i The lane connectivity between the downstream edges directly connected to this edge.

[0187] 1) According to the second candidate edge e i Attribute data of the second candidate edge e i The lane turning distribution, that is, which lanes can make U-turns, which lanes can turn left, which lanes can go straight, and which lanes can turn right.

[0188] 2) In G(V,E,P V ,P E ) to find the second candidate edge e i The set of directly connected downstream edges

[0189] 3) Calculate the second candidate edge e in sequence i With downstream edge The counterclockwise angle of the side e is determined according to the turning relationship judgment rule. i To the downstream side The steering relationship is mainly defined as U-turn, left turn, straight ahead and right turn.

[0190] 4) According to the second candidate edge ei With downstream edge The turning relationship, the second candidate edge e i Lane turning distribution, downstream edge The number of lanes, according to the lane connection rules, generates the second candidate edge e in the format i With downstream edge Lane connection relationship.

[0191] For example, if lane 1 with edge number 9 is connected to lane 2 with edge number 65, the lane connection relationship is defined in the following format:

[0192] <connect ion from="9"to="65"fromLane="1"toLane="2" / > .

[0193] The rules for determining the steering relationship are as follows:

[0194] Calculate the second candidate edge e i With candidate turning edges The counterclockwise angle of the second candidate edge e i With candidate turning edges The counterclockwise angle of the second candidate edge is between 150° and 210°. i To the candidate turning edge The turning relationship is a U-turn; when the second candidate edge e i With candidate turning edges The counterclockwise angle of the second candidate edge is between 30° and 150°. i To the candidate turning edge The turning relationship is left turn; when the second candidate edge e i With candidate turning edges The counterclockwise angle of the second candidate edge is between 0°-30° and 330°-360°. i To the candidate turning edge The turning relationship is straight; when the second candidate edge e i With candidate turning edges The counterclockwise angle of the second candidate edge is between 210° and 330°. i To the candidate turning edge The turning relationship is right turn. i With candidate turning edges The counterclockwise angle θ is calculated as follows:

[0195]

[0196] The calculation formulas for k and n are as follows:

[0197]

[0198] n=(x2-x1)·(y4-y3)-(x4-x3)·(y2-y1)

[0199] Where x1, y1 are the second candidate edge e i The starting point x, y coordinates; x2, y2 are the second candidate edge e i The x, y coordinates of the end point; x3, y3 are the downstream edges The starting point x, y coordinates; x4, y4 are candidate turning edges The x,y coordinates of the end point; π is radians, expressed as 180°.

[0200] The lane connection rules are as follows:

[0201] Lane connection rules are divided into lane connection rules for intersection entrances and exits and lane connection rules between road sections. i The end node is the intersection node, and the lane connection relationship is constructed according to the lane connection rules of the intersection entrance and exit lanes. Otherwise, the lane connection relationship is constructed according to the lane connection rules between road sections.

[0202] Among them, the lane connection rule of the intersection entrance and exit lanes is: when the second candidate edge e i To the downstream side The turning relationship is left turn / U-turn; according to the forward direction from left to right, the upstream edge e i The left turn / U-turn lane in the downstream lane is connected to the The lanes in are connected accordingly. There are two cases.

[0203] Case 1: e i The number of U-turn / left-turn lanes is less than or equal to Number of exit lanes, refer to Figure 3a As shown, e i The second lane in the middle is the left turn lane. When there are 3 lanes, e i Lane 2 and The 3rd lane connects.

[0204] Case 2: e i The number of U-turn / left-turn lanes is greater than The number of exit lanes, such as Figure 3b As shown, e i Lanes 1, 2, and 3 are all left-turn lanes. There are 2 lanes, e i Lane 3 and The second lane of the connection, e i Lane 2 and The 1st lane connects.

[0205] Among them, the lane connection rules for the entrance and exit lanes of the intersection are: when the edge e i To the downstream side The turning relationship is straight in order to eliminate the sideways turn to the left Traffic going straight to the side The interference of traffic flow needs to be considered in two situations.

[0206] Case 1: e i Number of straight lanes + e k The number of lateral left-turn lanes is less than or equal to Number of exit lanes, e.g. Figure 4a As shown, The sideways turn to the left and downstream side should be eliminated After the lane, from left to right in the direction of travel, i The through lanes in The remaining lanes in correspond to connections. Figure 4a As shown, e i The second lane in the middle is the straight-through turning lane. There are 3 lanes, and 1 lane on the side turns left Then e i Lane 2 and downstream edge The 2nd lane connects.

[0207] Case 2: e i Number of straight lanes + e k The number of lateral left-turn lanes is greater than Number of exit lanes. If there is a conflict between straight-moving vehicles and left-turning vehicles on the side, k lanes need to be eliminated and then e lanes need to be connected in sequence. i and Lane, remove the downstream edge starting from the left in the forward direction After the k lanes in the forward direction, the upstream edge e i The straight lane in the downstream lane is connected in sequence The lanes in the corresponding connection, where k = max (downstream edge Number of exit lanes - upstream edge e i The number of straight lanes in ,0). At this time, if Figure 4b As shown, e i The 1st and 2nd lanes are straight-through turn lanes. There are 2 lanes, and 1 lane on the side to turn left Then k=max(2-2,0)=0, the downstream edge No lane needs to be removed, so the upstream edge e i Lane 2 and downstream edge The second lane of the connection, the upstream edge e i Lane 1 and downstream edge The 2nd lane connects.

[0208] Among them, the lane connection rules for the entrance and exit lanes of the intersection are: when the edge e i To the downstream side The turning relationship is to turn right and follow the forward direction from right to left. i The right turn lane in the downstream lane is The lanes in are connected accordingly. There are two cases.

[0209] Case 1: e i The number of right-turn lanes is less than or equal to The number of exit lanes, such as Figure 5a As shown, e i The first lane in the middle is the right turn lane. There are 3 lanes, e i Lane 1 and Lane 1 connection; The first lane is the upstream lane when turning right. The first lane.

[0210] Case 2: e i The number of right-turn lanes is greater than The number of exit lanes, such as Figure 5b As shown, e i Lanes 1, 2, and 3 are all right-turn lanes. There are 2 lanes, e i Lane 1 and Lane 1 of the connection, e i Lane 2 and The second lane of the connection, e i The third lane on the upstream side The 2nd lane connects.

[0211] Among them, the lane connection rule between road sections is to connect the upstream edge e from left to right in the forward direction. i The lanes in the downstream side are The lanes in the corresponding connection. There are two cases:

[0212] Case 1: e i The number of lanes is less than or equal to The number of exit lanes, such as Figure 6a As shown, e i There are 3 lanes. There are 4 lanes, then e i Lane 3 and The 4th lane connects to; i Lane 2 and The 3rd lane connects to; i Lane 1 and The second lane of the connection;i Lane 1 and The 1st lane connects.

[0213] Case 2: e i The number of lanes is greater than The number of exit lanes, such as Figure 6b As shown, e i There are 4 lanes. There are 3 lanes, then e i Lane 4 and The 3rd lane connects to; i Lane 3 and The second lane of the connection; i Lane 2 and Lane 1 of the connection; e i Lane 1 and The 1st lane connects.

[0214] S6. Construct the target simulation road network:

[0215] Based on the road network node attribute file, road network edge attribute file, and road network lane connection relationship file, the netconvert tool provided by SUMO is used to generate the target simulation road network as follows Figure 8 shown.

[0216] The above method of the present application is mainly used in large-scale urban traffic simulation scenarios. By using the method of automatically generating a simulated road network using road network data, on the one hand, the human modeling cost of the traffic simulation road network in the large-scale urban traffic simulation scenario can be greatly reduced. On the other hand, according to the adjustment changes of the real road network, by adjusting the relevant attribute data in the GIS road network, the simulated road network can be updated quickly and at low cost to ensure the fidelity of the traffic simulation road network data; at the same time, for the scenario of comparing and evaluating different road network traffic organization schemes under traffic improvement scenarios, the simulated road network under different road network traffic organizations can be generated quickly and at low cost, and simulation decision-making applications can be efficiently supported.

[0217] It is understandable that the embodiment of the present application also provides a traffic strategy generation method, which includes:

[0218] Obtain a target simulated road network, wherein the target simulated road network can be obtained by the simulated road network generation method provided in the previous embodiment. The construction structure of the target simulated road network can be found in the previous embodiment and will not be described in detail here.

[0219] Determining a target road area to be simulated in a target simulation road network;

[0220] Carry out traffic flow simulation in the target road area and output simulation results;

[0221] Determine the traffic strategy based on the simulation results.

[0222] Reference Figure 8 and Figure 9 As shown, when traffic strategy needs to be determined, you can import Figure 8 In the target simulation road network, and select the area A to be analyzed, you can get Figure 9 As shown in the simulation diagram, at this time, based on Figure 9 The lane connection relationship simulates the vehicle driving state under different traffic flow conditions to analyze and predict the traffic flow and congestion conditions at each traffic light, thereby determining the traffic strategy. In other embodiments, the existing traffic strategy can also be evaluated based on the analysis and prediction of the traffic flow and congestion conditions at each traffic light.

[0223] Reference Figure 10 As shown, an embodiment of the present application further provides an electronic device, including:

[0224] One or more processors 601;

[0225] The memory 602 stores one or more programs. When the one or more programs are executed by the one or more processors 601, the one or more processors 601 implement the method provided in any embodiment of the present application.

[0226] The memory 602 is a non-transient network system that can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory 602 may include a high-speed random access memory and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory 602 may optionally include a memory 602 remotely located relative to the processor 601, and these remote memories 602 may be connected to the processor 601 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0227] The memory 602 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 602 can store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 602 and is called by the processor 601 to execute the methods of the embodiments of this application.

[0228] The processor 601 can be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application.

[0229] In some embodiments, the electronic device further comprises:

[0230] Input / output interface, used to realize information input and output;

[0231] Communication interface, used to enable communication between this device and other devices. Communication can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, Wi-Fi, Bluetooth, etc.);

[0232] A bus that transmits information between various components of the device (e.g., processor 601, memory 602, input / output interfaces, and communication interfaces);

[0233] The processor 601 , the memory 602 , the input / output interface and the communication interface can be connected to each other in communication within the device via a bus.

[0234] An embodiment of the present application further provides a computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions are used to execute the method provided in any embodiment of the present application.

[0235] An embodiment of the present application also provides a computer program product, including a computer program or computer instructions, which are stored in a computer-readable storage medium. A processor of a computer device reads the computer program or computer instructions from the computer-readable storage medium, and the processor executes the computer program or computer instructions, so that the computer device performs a method as provided in any embodiment of the present application.

[0236] The system architecture and application scenarios described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of the system architecture and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are equally applicable to similar technical problems.

[0237] Those skilled in the art will appreciate that all or some of the steps in the methods, systems, and functional modules / units in the devices disclosed above may be implemented as software, firmware, hardware, or appropriate combinations thereof.

[0238] In a hardware implementation, the division between the functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed by several physical components in cooperation. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or implemented as hardware, or implemented as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include a computer storage medium (or non-transitory medium) and a communication medium (or temporary medium). As known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and can be accessed by a computer. Furthermore, as is well known to those skilled in the art, communication media typically embodies computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0239] As used in this specification, the terms "component," "module," "system," and the like are used to refer to computer-related entities, hardware, firmware, a combination of hardware and software, software, or software in execution. For example, a component can be, but is not limited to, a process running on a processor, a processor, an object, an executable file, an execution thread, a program, or a computer. By way of illustration, both applications running on a computing device and a computing device can be components. One or more components can reside in a process or execution thread, and a component can be located on one computer or distributed between two or more computers. In addition, these components can be executed from various computer-readable media having various data structures stored thereon. Components can communicate, for example, through local or remote processes based on signals having one or more data packets (e.g., data from two components interacting with another component on a local system, a distributed system, or a network, such as the Internet interacting with other systems via signals).

[0240] The above description of some embodiments of the present application with reference to the accompanying drawings does not limit the scope of the present invention. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and essence of the present invention shall be within the scope of the present application.

Claims

1. A method for generating a simulated road network, characterized in that: The simulation road network generation method comprises: Acquire road network data, and generate a target road network directed graph according to each road attribute contained in the road network data, wherein the target road network directed graph includes a plurality of road nodes and edges connecting two adjacent road nodes; Determining the node position information and node identification of each road node in the target road network directed graph, and constructing road network node attribute data according to the node position information and node identification of each road node; Determine the road sign and lane attribute corresponding to each edge in the target road network directed graph, and construct road network edge attribute data based on the road sign and lane attribute corresponding to each edge; Determine a lane connection relationship between any two adjacent edges based on a lane turning attribute corresponding to each edge in the target road network directed graph; Constructing a target simulated road network based on the road network node attribute data, the road network edge attribute data, and the lane connection relationship between any two adjacent edges; The determining of the lane connection relationship between any two adjacent edges based on the lane turning attribute corresponding to each edge in the target road network directed graph includes: Traversing each road edge in the target road network directed graph as a second candidate edge in sequence and determining a downstream edge set corresponding to each second candidate edge according to a lane turning attribute of each second candidate edge; Determining, based on each lane turning attribute and the corresponding downstream edge set, a turning relationship between each second candidate edge and each corresponding downstream edge; The lane connection relationship between any two adjacent edges is generated according to the turning relationship between each second candidate edge and each corresponding downstream edge, and the lane turning attributes of the second candidate edge and the corresponding downstream edge.

2. The method for generating a simulated road network according to claim 1, wherein: Generating a target road network directed graph according to each road attribute included in the road network data includes: Extracting node attributes and edge attributes from the road network data to determine a candidate road network directed graph; the candidate road network directed graph includes a plurality of candidate road nodes and a first candidate edge connecting two adjacent candidate road nodes; Determining the node in-degree of each first candidate edge according to the node attributes of the candidate road node and the edge attributes of the first candidate edge; Determine the first candidate edge whose node in-degree is greater than a preset in-degree threshold as a candidate cross edge; Determining multiple candidate intersection edges that can form an intersection based on each of the candidate intersection edges, and generating corresponding directed closed-loop subgraphs based on the multiple candidate intersection edges at the same intersection; According to the directed closed-loop subgraph, the candidate road network directed graph is updated to obtain the target road network directed graph, wherein the target road network directed graph is a directed graph obtained by removing the candidate cross edges of the directed closed-loop subgraph in the candidate road network directed graph.

3. The method for generating a simulated road network according to claim 2, wherein: The updating of the candidate road network directed graph according to the directed closed-loop subgraph to obtain the target road network directed graph includes: Traversing each of the directed closed-loop subgraphs, and deleting each candidate cross edge in the traversed directed closed-loop subgraph in the candidate road network directed graph; Calculating the mean of the coordinates of each road node in the same directed closed-loop subgraph to obtain the mean coordinate points corresponding to the directed closed-loop subgraph one by one; Update the starting point of the road edge in the downstream direction directly connected to the endpoint of each deleted candidate intersection edge to the mean coordinate point; Update the starting point of the upstream road edge directly connected to the endpoint of each deleted candidate intersection edge to the mean coordinate point; In the candidate road network directed graph, each road node information in the directed closed-loop subgraph is deleted and the mean coordinate point is added.

4. The method for generating a simulated road network according to claim 1, wherein: The determining, based on each lane turning attribute and the corresponding downstream edge set, a turning relationship between each second candidate edge and each corresponding downstream edge includes: Taking each edge in the downstream edge set as a candidate turning edge; Calculating, according to each lane turning attribute, a counterclockwise angle between each second candidate edge and each corresponding candidate turning edge; According to the counterclockwise angle, a steering relationship between the second candidate edge and each corresponding candidate turning edge is determined, wherein each steering relationship is one of a U-turn steering relationship, a left turn steering relationship, a straight-ahead steering relationship, and a right turn steering relationship.

5. The method for generating a simulated road network according to claim 1, wherein: Generating the lane connection relationship between any two adjacent edges based on the turning relationship between each of the second candidate edges and each corresponding downstream edge, and the lane turning attributes of the second candidate edges and the corresponding downstream edges, includes: Determining the number of turning lanes of the second candidate edge at different turning relationships according to the lane turning attribute of the second candidate edge, and determining the number of exit lanes of the downstream edge at the corresponding turning relationship according to the lane attribute of the downstream edge; The downstream edge having a non-straight-turning relationship with the second candidate edge is used as the corresponding first target downstream edge; When the number of turning lanes of the second candidate edge turning toward the first target downstream edge is less than or equal to the number of corresponding exit lanes of the first target downstream edge and the second candidate edge has multiple turning relationships, sequentially connecting each turning lane of the second candidate edge turning toward the first target downstream edge with each corresponding lane of the first target downstream edge one by one to obtain a lane connection relationship between the second candidate edge and the first target downstream edge; When the number of turning lanes of the second candidate edge turning toward the first target downstream edge is greater than the corresponding number of exit lanes of the first target downstream edge and there are multiple turning relationships for the second candidate edge, each lane in the first target downstream edge that supports the turning of the second candidate edge is sequentially connected to a corresponding turning lane in the second candidate edge; and the remaining turning lanes in the second candidate edge turning toward the first target downstream edge are all connected to the corresponding outermost lanes in the first target downstream edge, to obtain the lane connection relationship between the second candidate edge and the first target downstream edge.

6. The method for generating a simulated road network according to claim 5, wherein: Generating the lane connection relationship between any two adjacent edges based on the turning relationship between each of the second candidate edges and each corresponding downstream edge, and the lane turning attributes of the second candidate edges and the corresponding downstream edges, further includes at least one of the following: The downstream edge that has a turning relationship of straight ahead with the second candidate edge is used as the corresponding second target downstream edge; When the second candidate edge has multiple turning relationships, obtaining a reserved turning lane of the second target downstream edge, and sequentially connecting the remaining lanes of the second target downstream edge except the reserved turning lane to the through lanes of the second candidate edge to obtain a lane connection relationship between the second candidate edge and the second target downstream edge; When the number of lanes on the second candidate edge is greater than the number of exit lanes on the second target downstream edge and all turning relationships on the second candidate edge are straight-turn relationships, sequentially connect each through lane on the second target downstream edge with a through lane on the second candidate edge; and connect all remaining through lanes on the second candidate edge with the outermost through lane on the second target downstream edge to obtain a lane connection relationship between the second candidate edge and the second target downstream edge; When the number of lanes of the second candidate edge is less than or equal to the number of exit lanes of the second target downstream edge and the turning relationships of the second candidate edge are all straight-through turning relationships, each straight lane of the second candidate edge is sequentially connected to each straight lane of the second target downstream edge one by one to obtain a lane connection relationship between the second candidate edge and the second target downstream edge.

7. The method for generating a simulated road network according to claim 6, wherein: The reserved lane for turning is determined by the following steps: Obtaining the number of interfering lanes of the second candidate edge according to the sum of the number of through lanes of the second candidate edge and the number of left-turn lanes from other upstream edges of the second target downstream edge to the second target downstream edge; When the number of interfering lanes is less than or equal to the number of corresponding exit lanes of the second target downstream edge, the number of left-turn lanes from other upstream edges of the second target downstream edge to the second target downstream edge is used as the number of reserved turning lanes of the second target downstream edge; When the number of interfering lanes is less than or equal to the corresponding number of exit lanes of the second target downstream edge, the turning reserved lane is determined according to the lane difference between the number of exit lanes of the first target downstream edge and the number of turning lanes of the second candidate edge in the straight direction.

8. An electronic device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the simulation road network generation method according to any one of claims 1 to 7 when executing the computer program.

9. A computer-readable storage medium, characterized in that The method comprises storing computer executable instructions, wherein the computer executable instructions are used to be executed by a processor to implement the simulation road network generation method according to any one of claims 1 to 7.

Images