Lane recommendation method, storage medium, electronic device and target vehicle

Abstract

The present application relates to a lane recommendation method, a storage medium, an electronic device and a target vehicle. The method comprises: obtaining a target lane set corresponding to a target vehicle, wherein the target lane set includes a target lane where the target vehicle is located and a target lane within a preset distance range in front of the target vehicle; constructing a lane structure diagram according to the target lane set, wherein nodes in the lane structure diagram represent target lanes in the target lane set, and weights corresponding to edges in the lane structure diagram represent movement costs of the target vehicle between target lanes corresponding to nodes connected by the edges; adjusting weights corresponding to edges in the lane structure diagram according to lane information corresponding to the target lanes to obtain an adjusted lane structure diagram; determining a moving path whose movement cost satisfies preset conditions in the adjusted lane structure diagram, and recommending the target lane on the moving path that satisfies the preset conditions to the target vehicle, thereby improving the accuracy of the recommended lane.

Description

Technical Field

[0001] The present application relates to the field of navigation technology, and in particular to a lane recommendation method, a storage medium, an electronic device and a target vehicle. Background Art

[0002] In autonomous driving, path planning is a key link. Through path planning, lanes can be recommended for the vehicle, allowing the vehicle to perform autonomous driving in the recommended lane.

[0003] Currently, lanes can be recommended through high-precision maps. However, the accuracy of lanes recommended through high-precision maps is low. Summary of the invention

[0004] The embodiments of the present application provide a lane recommendation method, a storage medium, an electronic device, and a target vehicle, which can improve the accuracy of the recommended lane to at least partially solve the above-mentioned technical problems.

[0005] In order to achieve the above object, according to a first aspect of the present application, a lane recommendation method is provided, comprising:

[0006] Obtaining a target lane set corresponding to the target vehicle, the target lane set including the target lane where the target vehicle is located and the target lane within a preset distance range in front of the target vehicle;

[0007] According to the target lane set, a lane structure graph is constructed, wherein the nodes in the lane structure graph represent the target lanes in the target lane set, and the weights corresponding to the edges in the lane structure graph represent the movement costs of the target vehicle between the target lanes corresponding to the nodes connected by the edges;

[0008] According to the lane information corresponding to the target lane, the weights corresponding to the edges in the lane structure graph are adjusted to obtain an adjusted lane structure graph;

[0009] A moving path whose moving cost satisfies a preset condition in the adjusted lane structure diagram is determined, and a target lane on the moving path that satisfies the preset condition is recommended to the target vehicle.

[0010] Optionally, the weights corresponding to the edges in the lane structure graph are adjusted according to the lane information corresponding to the target lane to obtain an adjusted structure graph, including:

[0011] Reading a node group from the lane structure graph, the node group including two adjacent nodes in the lane structure graph;

[0012] According to the lane information of the target lane corresponding to at least one of the two nodes, the weights corresponding to the edges between the two nodes in the lane structure graph are adjusted to obtain an adjusted lane structure graph.

[0013] Optionally, the lane information includes at least one type of lane attribute information and / or lane historical recommendation information;

[0014] The weights corresponding to the edges between the two nodes in the lane structure diagram are adjusted according to the lane information of the target lane corresponding to at least one of the two nodes to obtain the adjusted lane structure diagram, including:

[0015] According to the lane attribute information of the target lane corresponding to at least one of the two nodes, the weight corresponding to the edge between the two nodes in the lane structure diagram is increased to obtain an adjusted lane structure diagram; and / or,

[0016] According to the historical recommendation information of the target lane corresponding to at least one of the two nodes, the weight corresponding to the edge between the two nodes in the lane structure graph is reduced to obtain an adjusted lane structure graph.

[0017] Optionally, the lane information includes at least one of the lane attribute information, and according to the lane attribute information of the target lane corresponding to at least one of the two nodes, the weight corresponding to the edge between the two nodes in the lane structure graph is increased to obtain an adjusted lane structure graph, including:

[0018] Determine a target lane corresponding to at least one of the two nodes;

[0019] Determine a first weight value corresponding to lane attribute information of a target lane corresponding to the at least one node;

[0020] The weight of the edge between the two nodes in the lane structure graph is added to the first weight value to obtain an adjusted lane structure graph.

[0021] Optionally, the lane attribute information indicates an attribute value corresponding to a lane attribute, and the step of determining a target lane corresponding to at least one of the two nodes includes:

[0022] Get the above lane attributes;

[0023] According to the lane attributes, at least one node is determined from the two nodes;

[0024] Determine a target lane corresponding to the at least one node.

[0025] Optionally, the edge between the two nodes in the lane structure graph includes a direction; and the determining of at least one node from the two nodes according to the lane attributes includes:

[0026] Get the direction of the above edge;

[0027] At least one node is determined from the two nodes according to the lane attributes and the direction of the edge.

[0028] Optionally, the determining of at least one node from the two nodes according to the lane attribute and the direction of the edge includes:

[0029] If the lane attribute is the lane length, then according to the direction of the edge, determine the node at the starting point of the edge;

[0030] A node located at a starting point of the edge is determined as at least one node.

[0031] Optionally, the determining of at least one node from the two nodes according to the lane attribute and the direction of the edge includes:

[0032] If the lane attribute is a lane type, then according to the direction of the edge, determine the node at the end position of the edge;

[0033] A node at the end position of the edge is determined as at least one node.

[0034] Optionally, the lane attribute information is a lane width value, and the determining of at least one node from the two nodes according to the lane attribute and the direction of the edge includes:

[0035] If the lane attribute is lane width, then according to the direction of the edge, determine the node at the end position of the edge;

[0036] Obtain the lane width value of the target lane corresponding to the node at the end position of the above edge;

[0037] If the lane width value is less than a preset threshold, the node at the end position of the edge is determined as at least one node.

[0038] Optionally, the determining of at least one node from the two nodes according to the lane attribute and the direction of the edge includes:

[0039] If the lane attribute is a lane line type and the direction of the edge is bidirectional, the node connected by the edge is determined to be at least one node.

[0040] Optionally, the lane information includes the historical recommendation information, and the weight corresponding to the edge between the two nodes in the lane structure graph is reduced according to the historical recommendation information of the target lane corresponding to at least one of the two nodes to obtain the adjusted lane structure graph, including:

[0041] According to the above historical recommendation information, determine whether the target lanes corresponding to the above two nodes are historically recommended lanes;

[0042] If the target lanes corresponding to the above two nodes are historically recommended lanes, a second weight value is obtained;

[0043] The weight of the edge between the two nodes in the lane structure graph is subtracted from the second weight value to obtain an adjusted lane structure graph.

[0044] According to a second aspect of the present application, a lane recommendation device is provided, comprising:

[0045] An acquisition module is used to acquire a target lane set corresponding to a target vehicle, wherein the target lane set includes a target lane where the target vehicle is located and a target lane within a preset distance range in front of the target vehicle;

[0046] A construction module is used to construct a lane structure graph according to the target lane set, wherein the nodes in the lane structure graph represent the target lanes in the target lane set, and the weights corresponding to the edges in the lane structure graph represent the movement costs of the target vehicle between the target lanes corresponding to the nodes connected by the edges;

[0047] An adjustment module is used to adjust the weights corresponding to the edges in the lane structure diagram according to the lane information corresponding to the target lane, so as to obtain an adjusted lane structure diagram;

[0048] The recommendation module is used to determine a moving path whose moving cost meets the preset conditions in the adjusted lane structure diagram, and recommend a target lane on the moving path that meets the preset conditions to the target vehicle.

[0049] In a third aspect, an embodiment of the present application further provides an electronic device, comprising a memory storing a plurality of instructions, and the processor loads instructions from the memory to execute any lane recommendation method provided in the embodiment of the present application.

[0050] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a plurality of instructions, and the instructions are suitable for loading by a processor to execute any lane recommendation method provided in an embodiment of the present application.

[0051] In a fifth aspect, an embodiment of the present application further provides a target vehicle, including a memory storing a plurality of instructions, and the processor loads instructions from the memory to execute any lane recommendation method provided in the embodiment of the present application.

[0052] In an embodiment of the present application, a target lane set corresponding to a target vehicle is obtained, the target lane set including a target lane where the target vehicle is located and a target lane within a preset distance range in front of the target vehicle; a lane structure graph is constructed based on the target lane set, the nodes in the lane structure graph represent the target lanes in the target lane set, and the weights corresponding to the edges in the lane structure graph represent the movement costs of the target vehicle between the target lanes corresponding to the nodes connected by the edges; based on the lane information corresponding to the target lanes, the weights corresponding to the edges in the lane structure graph are adjusted to obtain an adjusted lane structure graph; a moving path in the adjusted lane structure graph whose moving cost meets preset conditions is determined, and the target lane on the moving path that meets the preset conditions is recommended to the target vehicle, so as to recommend a lane to the target vehicle based on the moving cost in the lane construction graph and improve the accuracy of the recommended lane.

[0053] Other features and advantages of the present application will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application, and those skilled in the art can obtain other drawings based on these drawings without creative work.

[0055] In order to more completely understand the present application and its beneficial effects, the following description will be given in conjunction with the accompanying drawings, wherein the same figure numbers represent the same parts in the following description.

[0056] Figure 1 is a flowchart of a lane recommendation method provided in an exemplary embodiment of the present application;

[0057] Figure 2 is a schematic diagram of a target lane provided in an exemplary embodiment of the present application;

[0058] Figure 3 is a schematic diagram of a lane structure diagram provided in an exemplary embodiment of the present application;

[0059] Figure 4 is another schematic diagram of a lane structure diagram provided in an exemplary embodiment of the present application;

[0060] Figure 5 is another schematic diagram of a lane structure diagram provided in an exemplary embodiment of the present application;

[0061] Figure 6 is another schematic diagram of a target lane provided in an exemplary embodiment of the present application;

[0062] Figure 7 is a schematic diagram of a lane recommendation device provided in an exemplary embodiment of the present application;

[0063] Figure 8 It is a schematic diagram of the structure of an electronic device provided in an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0064] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0065] The embodiment of the present application provides a lane recommendation method, a storage medium, an electronic device, and a target vehicle. Specifically, the lane recommendation method of the embodiment of the present application can be executed by an electronic device or a target vehicle, wherein the electronic device can be a terminal or a server. The terminal can be a terminal device such as a smart phone, a tablet computer, a laptop computer, a touch screen, a game console, a personal computer (PC, Personal Computer), a personal digital assistant (Personal Digital Assistant, PDA), and a vehicle-mounted terminal.

[0066] The server can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), as well as big data and artificial intelligence platforms.

[0067] The embodiment of the present application provides a lane recommendation method. In the embodiment of the present application, the target vehicle is used as the execution subject for description. Figure 1 FIG. 1 is a flowchart of a lane recommendation method provided by an exemplary embodiment of the present application. Figure 1 As shown, the lane recommendation method includes the following steps:

[0068] S101. Obtain a target lane set corresponding to a target vehicle, where the target lane set includes a target lane where the target vehicle is located and a target lane within a preset distance range in front of the target vehicle.

[0069] The target vehicle may refer to a vehicle for which a lane is recommended. The preset distance range is a preset distance range, which may be set according to actual conditions, for example, the preset distance range may be 2 kilometers or 3 kilometers, which is not limited in the present embodiment of the application.

[0070] Specifically, the target vehicle can obtain a target route, the starting point of the target route is the starting position of the target vehicle, and the end point of the target route is the end point to be reached by the target vehicle. Then, according to the current position of the target vehicle and the preset distance range, the target lane where the target vehicle is located and the target lane within the preset distance range in front of the target vehicle are screened out from the lanes on the target route to obtain a target lane set.

[0071] It is understandable that the target lanes in the target lane set may be all lanes on the target route or part of the lanes on the target route. For example, when the current position of the target vehicle is the starting position and the length of the target route is a preset distance range, the target lanes in the target lane set are all lanes on the target route. For another example, when the preset distance range is less than the length of the target route, the target lanes in the target lane set are part of the lanes on the target route. At this time, if the current position of the target vehicle is the starting position, the target lanes may include the lanes where the starting position is located, and if the current position of the target vehicle is at the preset distance range of the terminal position, the target lanes may include the lanes where the terminal position is located.

[0072] Optionally, the user can set the starting location and the ending location in the navigation map, generate at least one route from the starting location to the ending location through the navigation map, the target vehicle obtains and displays at least one route from the navigation map, and then responds to a selection operation of at least one route, determines the route corresponding to the selection operation as the target route.

[0073] Optionally, after the target vehicle obtains the target route, since the target lane where the target vehicle is located may change during the movement of the target vehicle, the target vehicle may obtain a target lane set corresponding to the target vehicle from the lanes on the target route multiple times.

[0074] When the target vehicle obtains the target lane set corresponding to the target vehicle from the lanes on the target route multiple times, the target lane set corresponding to the target vehicle can be obtained when a change in the target lane where the target vehicle is located is detected, or the target vehicle can also obtain the target lane set corresponding to the target vehicle when the Electronic Horizon Reconstructor (EHR) receives a frame of high-precision map data (the high-precision map data may include lane attribute information).

[0075] S102. Construct a lane structure graph according to the target lane set, where the nodes in the lane structure graph represent the target lanes in the target lane set, and the weights corresponding to the edges in the lane structure graph represent the movement costs of the target vehicle between the target lanes corresponding to the nodes connected by the edges.

[0076] The moving cost refers to the cost required for the target vehicle to move between different target lanes, and the cost may include at least one of time cost, energy cost, safety cost, and stability cost. The larger the weight corresponding to the edge, the greater the moving cost of the target vehicle between the target lanes corresponding to the nodes connected by the edge, and the smaller the weight corresponding to the edge, the smaller the moving cost of the target vehicle between the target lanes corresponding to the nodes connected by the edge.

[0077] Specifically, the target vehicle can construct a lane structure diagram according to the positional relationship between each target lane in the target lane set.

[0078] Optionally, according to the positional relationship between each target lane in the target lane set, the process of constructing the lane structure diagram may be:

[0079] The target lane where the target vehicle is located is used as the starting target lane;

[0080] Construct the first node corresponding to the starting target lane;

[0081] Filter out a target lane adjacent to the starting target lane position from the target lane set;

[0082] If the adjacent target lane is in a parallel position relationship with the starting target lane, a node parallel to the first node is constructed according to the adjacent target lane;

[0083] If the adjacent target lane is in a front-to-back position relationship with the starting target lane, a child node of the first node is constructed according to the adjacent target lane;

[0084] The target lane adjacent to the starting target lane is taken as the starting target lane, and the step of selecting the target lane adjacent to the starting target lane from the target lane set is returned.

[0085] For example, the target lanes included in the target lane set can be Figure 2 As shown, the target lane where the target vehicle is located is lane 1-1, and the first node corresponding to lane 1-1 is constructed. The first node corresponding to lane 1-1 can be as follows Figure 3 As shown in n1, the target lanes adjacent to lane 1-1 include lane 1-2 and lane 2-1. Since lane 1-2 and lane 1-1 are in parallel position, the node corresponding to lane 1-2 can be as follows Figure 3As shown in n2, since lane 2-1 and lane 1-1 are in a front-to-back position relationship, the node corresponding to lane 2-1 can be as follows Figure 3 As shown in n3, then, lane 1-2 is determined as the starting target lane. The target lanes adjacent to lane 1-2 include lane 1-1, lane 1-3, and lane 2-2. Since lane 1-3 and lane 1-2 are in parallel position, the node corresponding to lane 1-3 can be as follows: Figure 3 As shown in n4, since lane 2-2 and lane 1-2 are in a front-to-back position relationship, the node corresponding to lane 2-2 can be as follows Figure 3 The process is executed in a loop until all nodes corresponding to the target lanes in the target set are created. At this time, the constructed nodes form a lane structure graph, which can be shown as Figure 3 shown.

[0086] Alternatively, the target lane set may include multiple lane subsets (lane subsets may also be referred to as road sections), each lane subset includes parallel target lanes, and according to the positional relationship between the target lanes in the target lane set, the process of constructing the lane structure diagram may also be:

[0087] Determine a lane subset corresponding to a target lane where the target vehicle is located, and obtain a first lane subset;

[0088] Taking the target lane in the first lane subset as the starting target lane;

[0089] Constructing the first node corresponding to the starting target lane, each first node is a parallel node;

[0090] Filtering out a second lane subset adjacent to the first lane subset from the target lane set, wherein the target lanes in the second lane subset and the target lanes in the first lane subset are adjacent lanes;

[0091] Constructing child nodes of each first node according to the second lane subset;

[0092] The second lane subset is used as the first lane subset, and the step of filtering out the second lane subset adjacent to the first lane subset from the target lane set is returned.

[0093] For example, the target lane in the target lane set can be Figure 2As shown, the target lane set includes lane subset c1, lane subset c2 and lane subset c3. Lane subset c1 includes lane 1-1, lane 1-2 and lane 1-3. Lane subset c2 includes lane 2-1, lane 2-2 and lane 2-3. Lane subset c3 includes lane 3-1, lane 3-2 and lane 3-3. Since the target lane where the target vehicle is located is lane 1-1, the first lane subset is lane subset c1. The first nodes corresponding to lane 1-1, lane 1-2 and lane 1-3 are constructed. The first node corresponding to lane 1-1 can be as follows: Figure 3 As shown in n1, the first node corresponding to lane 1-2 can be Figure 3 As shown in n2, the first node corresponding to lanes 1-3 can be Figure 3 As shown in n4, the lane subset adjacent to the lane subset c1 is the lane subset c2. Therefore, the nodes corresponding to lane 2-1, lane 2-2 and lane 2-3 are constructed. The nodes corresponding to lane 2-1, lane 2-2 and lane 2-3 are child nodes of the first node. The node corresponding to lane 2-1 can be as follows: Figure 3 As shown in n3, the node corresponding to lane 2-2 can be Figure 3 As shown in n5, the nodes corresponding to lanes 2-3 can be Figure 3 As shown in n8, the process is executed in a loop until all nodes corresponding to the target lanes in all lane subsets are created.

[0094] It should be noted that the edge in the lane structure graph can be an undirected edge or a directed edge. The weight corresponding to the edge in the lane structure graph can be initialized to a preset weight, which can be 0 or 5, for example.

[0095] Among them, the weights corresponding to all edges in the lane structure diagram may be the same or different. When the weights corresponding to all edges in the lane structure diagram are different, the weights corresponding to the edges may be set according to the direction of the edges or the number of edges. For example, when the direction of the edge in the lane structure diagram is unidirectional, the weight corresponding to the unidirectional edge may be the first preset weight, and when the direction of the edge in the lane structure diagram is bidirectional, the weight corresponding to the bidirectional edge may be the second preset weight. For another example, when the edge between two nodes in the lane structure diagram includes one, the weight corresponding to the edge between the two nodes may be the first preset weight, and when the edge between two nodes in the lane structure diagram includes two, the weight corresponding to the edge between the two nodes may be the second preset weight.

[0096] The second preset weight may be greater than the first preset weight. For example, the second preset weight may be 20 or 25, and the first preset weight may be 0 or 5, which is not limited in the embodiment of the present application.

[0097] S103. According to the lane information corresponding to the target lane, the weights corresponding to the edges in the lane structure graph are adjusted to obtain an adjusted lane structure graph.

[0098] The lane information refers to information related to the lane, which can be used to describe the lane attributes, lane regulations and / or the relevant situation of the vehicle occupying the lane. For example, the lane information can include at least one of the lane attribute information and the lane historical recommendation information. The lane attribute information is used to describe the lane attributes, which can be set according to the actual situation. For example, the lane attribute information can include at least one of the lane type information, lane length value, lane width value, and lane line type information. The lane historical recommendation information refers to the target lane recommended in history.

[0099] Optionally, when the lane attribute information is different, the magnitude of adjustment of the weights corresponding to the edges can be different or the same. For example, when the lane attribute information is the lane length value, different lane length values ​​correspond to the same first weight value, and the weight corresponding to the edge is added to the first weight value to obtain the adjusted lane structure diagram. At this time, the weights corresponding to different lane attribute information are the same, and the magnitude of adjustment of the weights corresponding to the edges is also the same. For another example, when the lane attribute information is the lane length value, different lane length values ​​correspond to different first weight values. At this time, the magnitude of adjustment of the weights corresponding to the edges is different.

[0100] Optionally, a first weight value corresponding to the lane attribute information can be set, and the first weight value and the weight corresponding to the edge in the lane structure diagram can be added to obtain an adjusted lane structure diagram, and / or a second weight value corresponding to the historical recommendation information can be set, and the second weight value and the weight corresponding to the edge in the lane structure diagram can be subtracted to obtain an adjusted lane structure diagram.

[0101] In some embodiments, according to the lane information corresponding to the target lane, the weight corresponding to the edge in the lane structure graph is adjusted to obtain the adjusted structure graph, which may include:

[0102] Read a node from the lane structure graph;

[0103] According to the lane information of the target lane corresponding to a node, the weight corresponding to the edge connecting the node in the lane structure graph is adjusted to obtain the adjusted lane structure graph.

[0104] In some embodiments, according to the lane information corresponding to the target lane, the weights corresponding to the edges in the lane structure graph are adjusted to obtain an adjusted structure graph, including:

[0105] Read a node group from the lane structure graph, where the node group includes two adjacent nodes in the lane structure graph;

[0106] According to the lane information of the target lane corresponding to at least one of the two nodes, the weights corresponding to the edges between the two nodes in the lane structure graph are adjusted to obtain an adjusted lane structure graph.

[0107] Among them, the target vehicle can start from the root node in the lane structure graph and read the node group from the lane structure graph. Specifically, the target vehicle can start from the root node in the lane structure graph, read all the node groups from the lane structure graph, and then adjust the weights corresponding to the edges between two nodes in all the node groups. Alternatively, the target vehicle can also start from the root node in the lane structure graph, first read a node group from the lane structure graph, and then adjust the weights corresponding to the edges between two nodes in the node group, and then read a new node group from the lane structure graph, and execute the process in a loop until all the nodes in the lane structure graph are read and the process is stopped.

[0108] It is understandable that two nodes in different node groups may be partially identical or may not be identical. For example, node group C1 includes node n1 and node n2, and node group C2 includes node n2 and node n3. In this case, node group C1 and node group C2 include the same node n2. For another example, node group C1 includes node n1 and node n2, and node group C2 includes node n3 and node n4. In this case, node group C1 and node group C2 include different nodes.

[0109] The two adjacent nodes included in the node group can be understood as two nodes directly connected in the lane structure diagram. Figure 3 As shown, node n1 and node n2 are two adjacent nodes, node n1 and node n3 are two adjacent nodes, and node n1 and node n5 are not two adjacent nodes.

[0110] In an embodiment of the present application, a node group is read from a lane structure graph, the node group includes two adjacent nodes in the lane structure graph, and the weight corresponding to the edge between the two nodes in the lane structure graph is adjusted according to the lane information of the target lane corresponding to at least one of the two nodes to obtain an adjusted lane structure graph, so as to adjust the weight corresponding to the edge between the two nodes in the node group through the lane information of the target lane corresponding to at least one node in the node group. Compared with the method of reading a node and adjusting the weight corresponding to the edge according to the lane information of the target lane corresponding to a node, multiple adjustments to the weight corresponding to the same edge can be avoided, thereby improving the speed of adjusting the lane structure graph.

[0111] In some embodiments, the lane information includes at least one lane attribute information and / or historical recommendation information of the lane. According to the lane information of the target lane corresponding to at least one of the two nodes, the weight corresponding to the edge between the two nodes in the lane structure graph is adjusted to obtain the adjusted lane structure graph, including:

[0112] According to the lane attribute information of the target lane corresponding to at least one of the two nodes, the weight corresponding to the edge between the two nodes in the lane structure graph is increased to obtain an adjusted lane structure graph; and / or,

[0113] According to the historical recommendation information of the target lane corresponding to at least one of the two nodes, the weight corresponding to the edge between the two nodes in the lane structure graph is reduced to obtain an adjusted lane structure graph.

[0114] Wherein, at least one of the two nodes may be any one of the two nodes, or may be both nodes. For example, the two nodes include a first node and a second node, and at least one of the two nodes may be the first node and / or the second node.

[0115] In some embodiments, the lane information includes at least one type of lane attribute information. According to the lane attribute information of the target lane corresponding to at least one of the two nodes, the weight corresponding to the edge between the two nodes in the lane structure graph is increased to obtain an adjusted lane structure graph, including:

[0116] Determine a target lane corresponding to at least one of the two nodes;

[0117] Determine a first weight value corresponding to lane attribute information of a target lane corresponding to at least one node;

[0118] The weight of the edge between two nodes in the lane structure graph is added to the first weight value to obtain the adjusted lane structure graph.

[0119] The first weight value corresponding to the lane attribute information may be a preset value or a value determined in real time according to the lane attribute information. For example, when the lane attribute information is a lane length value, the first weight value corresponding to the lane attribute information may be a lane length value. For another example, when the lane attribute information is lane type information, the first weight value corresponding to the lane type information may be a preset value of 500.

[0120] In an embodiment of the present application, after determining the target lane corresponding to at least one node, the first weight value corresponding to the lane attribute information of the target lane corresponding to at least one node and the weight of the edge between two nodes are added to obtain an adjusted lane structure diagram.

[0121] For example, the lane attribute information of at least one node in the node group includes a lane length value and a lane type information. The first weight value corresponding to the lane length value is w1, and the first weight value corresponding to the lane type information is w2. The weight of the edge between two nodes in the node group is w0. Add w0, w1, and w2 to obtain the edge weight (w0+w1+w2).

[0122] In some embodiments, the lane attribute information represents an attribute value corresponding to the lane attribute, and determining a target lane corresponding to at least one of the two nodes includes:

[0123] Get lane attributes;

[0124] According to the lane attribute, at least one node is determined from the two nodes;

[0125] Determine a target lane corresponding to at least one node.

[0126] The lane attribute information is a specific attribute value corresponding to a certain lane attribute, and the lane attribute information of different target lanes for the same lane attribute may be the same or different.

[0127] For example, the lane attribute is the lane length, the lane attribute information is the lane length value, the lane length value of the target lane L1 is 1 km, the lane length value of the target lane L2 is 1 km, the lane length value of the target lane L3 is 2 km, the lane length values ​​of the target lane L1 and the target lane L2 are the same, and the lane length values ​​of the target lane L1 and the target lane 3 are different.

[0128] It should be noted that the first weight values ​​corresponding to different lane attribute information for the same lane attribute may be the same or different. For example, when the lane attribute is a lane type, if the lane attribute information is an acceleration lane, the acceleration lane may be, for example, an acceleration lane of a ramp, then the first weight value may be 500, and if the lane attribute information is a non-acceleration lane, then the first weight value may be 0.

[0129] Alternatively, after determining at least one node according to the lane attributes, the target vehicle may determine whether the lane attribute information of the target lane corresponding to the at least one node is the target lane attribute information. If it is the target lane attribute information, determine the first weight value corresponding to the target lane attribute information.

[0130] For example, the lane attribute is the lane type, and the target lane attribute information of the lane type is the acceleration lane. The acceleration lane may be, for example, the acceleration lane of the ramp. If the lane attribute information is the acceleration lane of the ramp, the first weight value corresponding to the acceleration lane is determined to be 500. If the lane attribute information is not the acceleration lane of the ramp, there is no need to adjust the weight corresponding to the edge.

[0131] In an embodiment of the present application, lane attributes are obtained, and based on the lane attributes, at least one node is determined from two nodes, and a target lane corresponding to the at least one node is determined, so that when the lane attributes are different, at least one node is different, so that when the lane structure map is adjusted based on the first weight value corresponding to the lane attribute information of the target lane corresponding to the at least one node, the accuracy of the adjustment of the lane structure map can be improved, and the accuracy of the target lane recommended based on the adjusted lane structure map can be further improved.

[0132] In some embodiments, the process of determining at least one node from two nodes based on lane attributes can be set according to actual conditions. For example, the nodes corresponding to the lane attributes can be set in advance, and then at least one node can be determined from the two nodes based on the lane attributes and the nodes corresponding to the lane attributes. For another example, if the edge has a direction, at least one node can be determined from the two nodes based on the lane attributes and the direction of the edge.

[0133] When at least one node is determined from two nodes based on the lane attribute and the node corresponding to the lane attribute, for example, Figure 3 As shown, the two nodes include node n1 and node n3, the lane attribute is lane length, the node corresponding to the lane length is the parent node, and the parent node of node n1 and node n3 is node n1, so node n1 is determined as at least one node.

[0134] When at least one node is determined from two nodes according to the lane attribute and the direction of the edge, at least one node is determined from two nodes according to the lane attribute, including:

[0135] Get the direction of the edge;

[0136] At least one node is determined from two nodes according to the lane attributes and the direction of the edge.

[0137] Among them, if the edge between two nodes includes one, when the positional relationship between the two target lanes corresponding to the two nodes is a parallel positional relationship, the direction of the edge between the two nodes can be bidirectional, and when the positional relationship between the two target lanes corresponding to the two nodes is a front-and-back positional relationship, the direction of the edge between the two nodes can be unidirectional.

[0138] For example, when the target lane in the target lane set can be Figure 2 When the lane structure diagram is shown, Figure 4As shown, the target lane corresponding to node n1 is lane 1-1, the target lane corresponding to node n2 is lane 1-2, the target lane corresponding to node n4 is lane 1-3, the target lane corresponding to node n3 is lane 2-1, the target lane corresponding to node n5 is lane 2-2, the target lane corresponding to node n8 is lane 2-3, the target lane corresponding to node n6 is lane 3-1, the target lane corresponding to node n7 is lane 3-2, and the target lane corresponding to node n9 is lane 3-3. Since lane 1-1 and lane 1-2 are in a parallel position relationship, the edge between node n1 and node n2 is a bidirectional edge. Since lane 1-1 and lane 2-1 are in a front-to-back position relationship, the edge between node n1 and node n3 is a unidirectional edge. The directions of other edges in the lane structure diagram are similar.

[0139] It can be understood that when the direction of the edge between two nodes is bidirectional, in order to improve the convenience of determining at least one node, the edge between the two nodes can be set to include two, each edge is unidirectional. At this time, the bidirectional edge is represented by two unidirectional edges.

[0140] For example, the lane structure diagram is as follows Figure 4 As shown in the figure, the direction of the edge between node n1 and node n2 is bidirectional. When two unidirectional edges are used to represent the lane structure diagram, the lane structure diagram can be as follows: Figure 5 As shown, at this time, the edge between node n1 and node n2 includes two unidirectional edges.

[0141] In an embodiment of the present application, the direction of the edge is obtained, and at least one node is determined from two nodes based on the lane attributes and the direction of the edge, so that when the lane attributes are different and the directions of the edges are different, at least one node is different, so that when the lane structure map is adjusted according to the first weight value corresponding to the lane attribute information of the target lane corresponding to at least one node, the accuracy of the adjustment of the lane structure map can be improved, and the accuracy of the target lane recommended based on the adjusted lane structure map can be further improved.

[0142] In some embodiments, determining at least one node from two nodes according to the lane attribute and the direction of the edge includes:

[0143] If the lane attribute is the lane length, the node at the starting point of the edge is determined according to the direction of the edge;

[0144] A node at a starting point of the edge is determined as at least one node.

[0145] Among them, when the direction of the edge includes one-way or two-way, if the direction of the edge is one-way, the node at the starting point of the edge is determined according to the direction of the edge; if the direction of the edge is two-way, the node at the starting point of the edge is not determined according to the direction of the edge, that is, the weight corresponding to the edge is not adjusted according to the lane length value.

[0146] When there are one or two edges, if there is one edge, the node at the starting point of the edge is determined according to the direction of the edge; if there are two edges, the node at the starting point of the edge is not determined according to the direction of the edge.

[0147] For example, Figure 4 As shown, when the two nodes are node n1 and node n3, since the edge between node n1 and node n3 is unidirectional, the node at the starting position of the edge between node n1 and node n3 is node n1, therefore, node n1 is determined as at least one node, at this time, according to the lane length value of the target lane corresponding to node n1, the weight of the edge between node n1 and node n3 is adjusted, and when the two nodes are node n1 and node n2, since the edge between node n1 and node n2 is bidirectional, therefore, at least one node is not determined, and the weight of the edge between node n1 and node n2 is not adjusted according to the lane length value of the target lane corresponding to node n1 and / or node n2.

[0148] For example, Figure 5 As shown, when the two nodes are node n1 and node n3, since the edge between node n1 and node n3 includes one, the node at the starting position of the edge between node n1 and node n3 is node n1, therefore, node n1 is determined as at least one node, at this time, according to the lane length value of the target lane corresponding to node n1, the weight of the edge between node n1 and node n3 is adjusted, and when the two nodes are node n1 and node n2, since the edge between node n1 and node n2 includes two, therefore, at least one node is not determined, and the weight of the edge between node n1 and node n2 is not adjusted according to the lane length value of the target lane corresponding to node n1 and / or node n2.

[0149] In some embodiments, determining at least one node from two nodes according to the lane attribute and the direction of the edge includes:

[0150] If the lane attribute is a lane type, the node at the end position of the edge is determined according to the direction of the edge;

[0151] A node at an end position of the edge is determined as at least one node.

[0152] For example, Figure 5As shown, when the two nodes are node n1 and node n3, since the node at the end position of the edge between node n1 and node n3 is node n3, node n3 is determined to be at least one node. At this time, the weight of the edge between node n1 and node n3 is adjusted according to the lane type information of the target lane corresponding to node n3. When the two nodes are node n1 and node n2, for edge e1, the node at the end position of edge e1 is node n1, node n1 is determined to be at least one node, and the weight corresponding to edge e1 is adjusted according to the lane type information of the target lane corresponding to node n1. For edge e2, the node at the end position of edge e2 is node n2, node n2 is determined to be at least one node, and the weight corresponding to edge e2 is adjusted according to the lane type information of the target lane corresponding to node n2.

[0153] In some embodiments, the lane attribute information is a lane width value, and at least one node is determined from two nodes according to the lane attribute and the direction of the edge, including:

[0154] If the lane attribute is lane width, then the node at the end position of the edge is determined according to the direction of the edge;

[0155] Get the lane width value of the target lane corresponding to the node at the end position of the edge;

[0156] If the lane width value is less than a preset threshold, the node at the end position of the edge is determined as at least one node.

[0157] Among them, the preset threshold is a pre-set value, which can be set according to actual conditions. For example, the preset threshold can be 2.5 meters or 3 meters, which is not limited in the embodiments of the present application.

[0158] At this time, if the lane width value is greater than or equal to the preset threshold, the node at the end position of the edge is not determined as at least one node, that is, the weight corresponding to the edge is not adjusted according to the lane width value.

[0159] For example, Figure 5As shown, when the two nodes are node n1 and node n3, since the node at the end position of the edge between node n1 and node n3 is node n3, node n3 is determined as at least one node. At this time, if the lane width value of the target lane corresponding to node n3 is less than the preset threshold, the weight of the edge between node n1 and node n3 is adjusted according to the lane width value. When the two nodes are node n1 and node n2, for edge e1, the node at the end position of edge e1 is node n1, node n1 is determined as at least one node, if the lane width value of the target lane corresponding to node n1 is less than the preset threshold, then the weight corresponding to edge e1 is adjusted according to the lane width value. For edge e2, the node at the end position of edge e2 is node n2, node n2 is determined as at least one node, if the lane width value of the target lane corresponding to node n2 is less than the preset threshold, then the weight corresponding to edge e2 is adjusted according to the lane width value.

[0160] In some embodiments, determining at least one node from two nodes according to the lane attribute and the direction of the edge includes:

[0161] If the lane attribute is a lane line type and the direction of the edge is bidirectional, the node connected by the edge is determined to be at least one node.

[0162] Among them, when a bidirectional edge is represented by two unidirectional edges, if the lane attribute is a lane line type and the direction of the edge is bidirectional, the nodes connected by the edge are determined to be at least one node. It can also be understood that if the lane attribute is a lane line type and the edge includes two, the nodes connected by the edge are determined to be at least one node.

[0163] At this time, if the direction of the edge is unidirectional or the edge includes one lane, the weight corresponding to the edge is not adjusted according to the lane line type information.

[0164] For example, Figure 4 As shown, when the two nodes are node n1 and node n3, since the edge between node n1 and node n3 is unidirectional, the weight of the edge between node n1 and node n3 is not adjusted according to the lane line type information; when the two nodes are node n1 and node n2, since the edge between node n1 and node n2 is bidirectional, node n1 and node n2 are determined to be at least one node. At this time, the weight of the edge between node n1 and node n2 is adjusted according to the lane line type information between the target lanes corresponding to node n1 and node n2.

[0165] For example, Figure 5As shown, when the two nodes are node n1 and node n3, since the edge between node n1 and node n3 includes one lane, the weight of the edge between node n1 and node n3 is not adjusted according to the lane line type information; when the two nodes are node n1 and node n2, since the edge between node n1 and node n2 includes two lanes, node n1 and node n2 are determined to be at least one node. At this time, the weight of the edge between node n1 and node n2 is adjusted according to the lane line type information between the target lanes corresponding to node n1 and node n2.

[0166] In some embodiments, the lane information includes historical recommendation information, and according to the historical recommendation information of the target lane corresponding to at least one of the two nodes, the weight corresponding to the edge between the two nodes in the lane structure graph is reduced to obtain an adjusted lane structure graph, including:

[0167] According to the historical recommendation information, determine whether the target lanes corresponding to the two nodes are historically recommended lanes;

[0168] If the target lanes corresponding to the two nodes are historically recommended lanes, a second weight value is obtained;

[0169] Subtract the weight of the edge between two nodes in the lane structure graph from the second weight value to obtain the adjusted lane structure graph.

[0170] For example, Figure 5 As shown, the historical recommendation information is lane 1-1, lane 2-1 and lane 2-3, lane 1-1 corresponds to node n1, lane 2-1 corresponds to node n3, lane 3-1 corresponds to node n6, when the two nodes are node n1 and node n3, the weight of the edge between node n1 and node n3 is subtracted from the second weight value, when the two nodes are node n2 and node n4, since the target lanes corresponding to node n2 and node n4 are not historically recommended lanes, there is no need to adjust the weight value of the edge between node n2 and node n4 according to the second weight value.

[0171] In an embodiment of the present application, based on historical recommendation information, it is determined whether the target lanes corresponding to the two nodes are historically recommended lanes. If the target lanes corresponding to the two nodes are historically recommended lanes, a second weight value is obtained, and the weight of the edge between the two nodes in the lane structure diagram is subtracted from the second weight value to obtain an adjusted lane structure diagram, thereby adjusting the lane structure diagram based on the historical recommendation information, thereby improving the accuracy of the target lane recommended for the target vehicle based on the adjusted lane structure diagram.

[0172] In some embodiments, the lane information includes lane attribute information and historical recommendation information of the lane, and according to the lane attribute information of the target lane corresponding to at least one of the two nodes, the weight corresponding to the edge between the two nodes in the lane structure graph is increased to obtain an adjusted lane structure graph, and according to the historical recommendation information of the target lane corresponding to at least one of the two nodes, the weight corresponding to the edge between the two nodes in the lane structure graph is reduced to obtain an adjusted lane structure graph, including:

[0173] Determine a target lane corresponding to at least one of the two nodes;

[0174] Determine a first weight value corresponding to lane attribute information of a target lane corresponding to at least one node;

[0175] According to the historical recommendation information, determine whether the target lanes corresponding to the two nodes are historically recommended lanes;

[0176] If the target lanes corresponding to the two nodes are historically recommended lanes, a second weight value is obtained;

[0177] The weight of the edge between two nodes in the lane structure graph is subtracted from the second weight value and added to the first weight value to obtain an adjusted lane structure graph.

[0178] Among them, the weight of the edge between the two nodes and the first weight value can be added first, and then the addition result and the second weight value are subtracted to obtain the adjusted lane structure diagram, or the weight of the edge between the two nodes and the second weight value can be subtracted first, and then the subtraction result and the first weight value are added to obtain the adjusted lane structure diagram.

[0179] S104: Determine a moving path whose moving cost satisfies a preset condition in the adjusted lane structure diagram, and recommend a target lane on the moving path that satisfies the preset condition to the target vehicle.

[0180] The moving path refers to a path from a root node in the adjusted lane structure graph to an end node in the adjusted lane structure graph, that is, a path from a starting target lane in the target lane set to an end target lane.

[0181] The movement cost of a movement path refers to the sum of the weights of the edges on the movement path. Figure 5 As shown, when the moving path is node n1-node n3-node n6, the weight of the edge between node n1 and node n3 is w1, the weight of the edge between node n3 and node n6 is w2, and the moving cost of the moving path is (w1+w2).

[0182] The preset condition can be set according to actual conditions. For example, the smallest or second smallest moving cost among the moving costs can be determined as the moving cost that meets the preset condition. The embodiment of the present application is not limited here.

[0183] The method for determining a moving path in the adjusted lane structure diagram whose moving cost satisfies preset conditions can be set according to actual conditions. For example, the moving path in the adjusted lane structure diagram whose moving cost satisfies preset conditions can be determined by Dijkstra algorithm or Floyd algorithm. The embodiments of the present application are not limited here.

[0184] In an embodiment of the present application, a lane structure graph is constructed based on a target lane set, and then the weights of the edges between the nodes in the lane structure graph are adjusted based on the lane information of the target lane, thereby improving the accuracy of the target lane recommended based on the adjusted lane structure graph. The lane information may include at least one of lane attribute information and historical recommendation information.

[0185] For example, lane information includes lane attribute information, and lane attribute information includes lane type information, such as Figure 6 As shown, the target vehicle is in lane 1-1 of road 1. If the target vehicle needs to change lanes to the left and merge into the main road, since there are roads 2 and 3 in front of the target vehicle, the lane recommended by the high-precision map will not initiate a lane change on road 1, but will change lanes to the left on road 2 or road 3. In the event of congestion, changing lanes on road 2 or road 3 will affect the traffic efficiency of the target vehicle.

[0186] In the embodiment of the present application, the weight of the edge in the lane structure graph and the first weight value corresponding to the lane type information are added, so that the movement cost between lane 1-1, lane 2-1, lane 3-1 and lane 3-2 is increased, so that the movement cost between lane 1-1, lane 1-2, lane 2-2 and lane 3-2 is less than the movement cost between lane 1-1, lane 2-1, lane 3-1 and lane 3-2, so that lane 1-1, lane 2-1, lane 3-1 to lane 3-2 can be recommended to the target vehicle, so that the target vehicle can change lanes in advance, improve the accuracy of the recommended lane, and thus improve the traffic efficiency of the target vehicle.

[0187] For another example, lane information includes historical recommendation information, such as Figure 2As shown, the target vehicle is in lane 1-1. Due to the error in the positioning of the target vehicle by the high-precision map, the high-precision map believes that the target vehicle is in lane 1-2. At this time, the high-precision map recommends lane 1-2, lane 2-2 and lane 3-2 for the target vehicle. The target vehicle changes lanes to the left. During the lane change process, if the positioning of the target vehicle by the high-precision map becomes correct, the high-precision map believes that the target vehicle is in lane 1-1. At this time, the high-precision map recommends lane 1-1, lane 2-1 and lane 3-1 for the target vehicle. The lane change of the target vehicle is terminated and returns to lane 1-1, resulting in invalid lane change and reducing the stability of autonomous driving.

[0188] In the embodiment of the present application, the target vehicle is in lane 1-1. Since there is an error in the positioning of the target vehicle by the high-precision map, the high-precision map believes that the target vehicle is in lane 1-2. At this time, the lanes recommended by the high-precision map for the target vehicle are lane 1-2, lane 2-2 and lane 3-2. The target vehicle changes lanes to the left. During the lane changing process, if the positioning of the target vehicle by the high-precision map becomes correct, the high-precision map believes that the target vehicle is in lane 1-1. Since lanes 1-2, lanes 2-2 and lane 3-2 are historically recommended lanes, after adjusting the weights between the nodes in the lane structure diagram according to historical information, the weights between lanes 1-2, lanes 2-2 and lane 3-2 are reduced, so that the recommended lanes finally output are still lanes 1-2, lanes 2-2 and lane 3-2, so the target vehicle will not initiate an invalid lane change, thereby improving the stability of autonomous driving.

[0189] In an embodiment of the present application, a target lane set corresponding to a target vehicle is obtained, the target lane set including a target lane where the target vehicle is located and a target lane within a preset distance range in front of the target vehicle; a lane structure graph is constructed based on the target lane set, the nodes in the lane structure graph represent the target lanes in the target lane set, and the weights corresponding to the edges in the lane structure graph represent the movement costs of the target vehicle between the target lanes corresponding to the nodes connected by the edges; based on the lane information corresponding to the target lanes, the weights corresponding to the edges in the lane structure graph are adjusted to obtain an adjusted lane structure graph; a moving path in the adjusted lane structure graph whose moving cost meets preset conditions is determined, and the target lane on the moving path that meets the preset conditions is recommended to the target vehicle, so as to recommend a lane to the target vehicle based on the moving cost in the lane construction graph and improve the accuracy of the recommended lane.

[0190] In order to better implement the lane recommendation method provided in the embodiment of the present application, the embodiment of the present application also provides a device based on the lane recommendation method. The meanings of the terms are the same as those in the lane recommendation method, and the specific implementation details can refer to the description in the method embodiment.

[0191] For example, Figure 7As shown, the lane recommendation device may include:

[0192] The acquisition module 701 is used to acquire a target lane set corresponding to the target vehicle, where the target lane set includes the target lane where the target vehicle is located and the target lanes within a preset distance range in front of the target vehicle.

[0193] The construction module 702 is used to construct a lane structure diagram according to the target lane set, wherein the nodes in the lane structure diagram represent the target lanes in the target lane set, and the weights corresponding to the edges in the lane structure diagram represent the movement costs of the target vehicle between the target lanes corresponding to the nodes connected by the edges.

[0194] The adjustment module 703 is used to adjust the weights corresponding to the edges in the lane structure graph according to the lane information corresponding to the target lane, so as to obtain an adjusted lane structure graph.

[0195] The recommendation module 704 is used to determine a moving path whose moving cost meets a preset condition in the adjusted lane structure diagram, and recommend a target lane on the moving path that meets the preset condition to the target vehicle.

[0196] In some embodiments, the adjustment module 703 is specifically configured to perform:

[0197] Read a node group from the lane structure graph, where the node group includes two adjacent nodes in the lane structure graph;

[0198] According to the lane information of the target lane corresponding to at least one of the two nodes, the weights corresponding to the edges between the two nodes in the lane structure graph are adjusted to obtain an adjusted lane structure graph.

[0199] In some embodiments, the lane information includes at least one type of lane attribute information and / or historical recommendation information of the lane, and the adjustment module 703 is specifically used to perform:

[0200] According to the lane attribute information of the target lane corresponding to at least one of the two nodes, the weight corresponding to the edge between the two nodes in the lane structure graph is increased to obtain an adjusted lane structure graph; and / or,

[0201] According to the historical recommendation information of the target lane corresponding to at least one of the two nodes, the weight corresponding to the edge between the two nodes in the lane structure graph is reduced to obtain an adjusted lane structure graph.

[0202] In some embodiments, the lane information includes at least one lane attribute information, and the adjustment module 703 is specifically used to perform:

[0203] Determine a target lane corresponding to at least one of the two nodes;

[0204] Determine a first weight value corresponding to lane attribute information of a target lane corresponding to at least one node;

[0205] The weight of the edge between two nodes in the lane structure graph is added to the first weight value to obtain the adjusted lane structure graph.

[0206] In some embodiments, the lane attribute information indicates an attribute value corresponding to the lane attribute, and the adjustment module 703 is specifically used to perform:

[0207] Get lane attributes;

[0208] According to the lane attribute, at least one node is determined from the two nodes;

[0209] Determine a target lane corresponding to at least one node.

[0210] In some embodiments, the edge between two nodes in the lane structure graph includes a direction, and the adjustment module 703 is specifically used to perform:

[0211] Get the direction of the edge;

[0212] At least one node is determined from two nodes according to the lane attributes and the direction of the edge.

[0213] In some embodiments, the adjustment module 703 is specifically configured to perform:

[0214] If the lane attribute is the lane length, the node at the starting point of the edge is determined according to the direction of the edge;

[0215] A node at a starting point of the edge is determined as at least one node.

[0216] In some embodiments, the adjustment module 703 is specifically configured to perform:

[0217] If the lane attribute is a lane type, the node at the end position of the edge is determined according to the direction of the edge;

[0218] A node at an end position of the edge is determined as at least one node.

[0219] In some embodiments, the lane attribute information is a lane width value, and the adjustment module 703 is specifically used to perform:

[0220] If the lane attribute is lane width, then the node at the end position of the edge is determined according to the direction of the edge;

[0221] Get the lane width value of the target lane corresponding to the node at the end position of the edge;

[0222] If the lane width value is less than a preset threshold, the node at the end position of the edge is determined as at least one node.

[0223] In some embodiments, the adjustment module 703 is specifically configured to perform:

[0224] If the lane attribute is a lane line type and the direction of the edge is bidirectional, the node connected by the edge is determined to be at least one node.

[0225] In some embodiments, the lane information includes historical recommendation information, and the adjustment module 703 is specifically used to perform:

[0226] According to the historical recommendation information, determine whether the target lanes corresponding to the two nodes are historically recommended lanes;

[0227] If the target lanes corresponding to the two nodes are historically recommended lanes, a second weight value is obtained;

[0228] Subtract the weight of the edge between two nodes in the lane structure graph from the second weight value to obtain the adjusted lane structure graph.

[0229] In specific implementation, the above modules can be implemented as independent entities, or can be arbitrarily combined and implemented as the same or several entities. The specific implementation methods and corresponding beneficial effects of the above modules can be found in the previous method embodiments, which will not be repeated here.

[0230] Accordingly, the embodiment of the present application also provides an electronic device, which may be a terminal, and the terminal may be a smart phone, a tablet computer, a laptop computer, a touch screen, a game console, a personal computer (PC, Personal Computer), a personal digital assistant (Personal Digital Assistant, PDA) and other terminal devices. Figure 8 As shown, Figure 8 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device 800 includes a processor 801 having one or more processing cores, a memory 802 having one or more computer-readable storage media, and a computer program stored in the memory 802 and executable on the processor. The processor 801 is electrically connected to the memory 802. Those skilled in the art will appreciate that the electronic device structure shown in the figure does not constitute a limitation on the electronic device, and may include more or fewer components than shown, or combine certain components, or arrange components differently.

[0231] The processor 801 is the control center of the electronic device 800. It uses various interfaces and lines to connect various parts of the entire electronic device 800, executes various functions of the electronic device 800 and processes data by running or loading software programs and / or modules stored in the memory 802, and calling data stored in the memory 802, thereby monitoring the electronic device 800 as a whole.

[0232] In the embodiment of the present application, the processor 801 in the electronic device 800 will load instructions corresponding to the processes of one or more application programs into the memory 802 according to the following steps, and the processor 801 will run the application programs stored in the memory 802 to implement various functions, such as:

[0233] Obtain a target lane set corresponding to the target vehicle, the target lane set including the target lane where the target vehicle is located and the target lanes within a preset distance range in front of the target vehicle;

[0234] According to the target lane set, a lane structure graph is constructed. The nodes in the lane structure graph represent the target lanes in the target lane set, and the weights corresponding to the edges in the lane structure graph represent the moving costs of the target vehicle between the target lanes corresponding to the nodes connected by the edges.

[0235] According to the lane information corresponding to the target lane, the weights corresponding to the edges in the lane structure graph are adjusted to obtain an adjusted lane structure graph;

[0236] A moving path whose moving cost meets preset conditions in the adjusted lane structure diagram is determined, and a target lane on the moving path that meets the preset conditions is recommended to the target vehicle.

[0237] The specific implementation methods and corresponding beneficial effects of the above operations can be found in the detailed description of the lane recommendation method above, which will not be elaborated here.

[0238] Alternatively, if Figure 8 As shown, the electronic device 800 further includes: a touch screen 803, a radio frequency circuit 804, an audio circuit 805, an input unit 806, and a power supply 807. The processor 801 is electrically connected to the touch screen 803, the radio frequency circuit 804, the audio circuit 805, the input unit 806, and the power supply 807, respectively. Those skilled in the art can understand that Figure 8 The electronic device structure shown in the figure does not constitute a limitation of the electronic device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0239] The touch display screen 803 can be used to display a graphical user interface and receive operation instructions generated by the user acting on the graphical user interface. The touch display screen 803 may include a display panel and a touch panel. Among them, the display panel can be used to display information input by the user or information provided to the user and various graphical user interfaces of the electronic device, which can be composed of graphics, text, icons, videos and any combination thereof. Optionally, the display panel can be configured in the form of a liquid crystal display (LCD, Liquid Crystal Display), an organic light-emitting diode (OLED, Organic Light-Emitting Diode), etc. The touch panel can be used to collect the user's touch operations on or near it (such as the user's operation on the touch panel or near the touch panel using any suitable object or accessory such as a finger, stylus, etc.), and generate corresponding operation instructions, and the operation instructions execute the corresponding program. Optionally, the touch panel may include two parts: a touch detection device and a touch controller. Among them, the touch detection device detects the user's touch orientation, detects the signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts it into the touch point coordinates, and then sends it to the processor 801, and can receive the command sent by the processor 801 and execute it. The touch panel can cover the display panel. When the touch panel detects a touch operation on or near it, it is transmitted to the processor 801 to determine the type of touch event, and then the processor 801 provides a corresponding visual output on the display panel according to the type of touch event. In an embodiment of the present application, the touch panel and the display panel can be integrated into the touch display screen 803 to realize the input and output functions. However, in some embodiments, the touch panel and the touch panel can be used as two independent components to realize the input and output functions. That is, the touch display screen 803 can also be used as a part of the input unit 806 to realize the input function.

[0240] The radio frequency circuit 804 may be used to send and receive radio frequency signals, so as to establish wireless communication with a network device or other electronic devices through wireless communication, and to send and receive signals with the network device or other electronic devices.

[0241] The audio circuit 805 can be used to provide an audio interface between the user and the electronic device through a speaker and a microphone. The audio circuit 805 can transmit the electrical signal converted from the received audio data to the speaker, which is converted into a sound signal for output; on the other hand, the microphone converts the collected sound signal into an electrical signal, which is received by the audio circuit 805 and converted into audio data, and then the audio data is output to the processor 801 for processing, and then sent to another electronic device through the radio frequency circuit 804, or the audio data is output to the memory 802 for further processing. The audio circuit 805 may also include an earplug jack to provide communication between an external headset and an electronic device.

[0242] The input unit 806 may be used to receive input numbers, character information or user feature information (such as fingerprint, iris, facial information, etc.), and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control.

[0243] The power supply 807 is used to supply power to various components of the electronic device 800. Optionally, the power supply 807 can be logically connected to the processor 801 through a power management system, so that the power management system can manage charging, discharging, and power consumption. The power supply 807 can also include one or more DC or AC power supplies, recharging systems, power failure detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0244] although Figure 8 Not shown, the electronic device 800 may also include a camera, a sensor, a wireless fidelity module, a Bluetooth module, etc., which will not be described in detail here.

[0245] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0246] A person of ordinary skill in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be completed by instructions, or by controlling related hardware through instructions. The instructions may be stored in a computer-readable storage medium and loaded and executed by a processor.

[0247] To this end, an embodiment of the present application provides a computer-readable storage medium, in which a plurality of computer programs are stored, and the computer program can be loaded by a processor to execute any lane recommendation method provided in the embodiment of the present application. For example, the computer program can execute the following steps:

[0248] Obtain a target lane set corresponding to the target vehicle, the target lane set including the target lane where the target vehicle is located and the target lanes within a preset distance range in front of the target vehicle;

[0249] According to the target lane set, a lane structure graph is constructed. The nodes in the lane structure graph represent the target lanes in the target lane set, and the weights corresponding to the edges in the lane structure graph represent the moving costs of the target vehicle between the target lanes corresponding to the nodes connected by the edges.

[0250] According to the lane information corresponding to the target lane, the weights corresponding to the edges in the lane structure graph are adjusted to obtain an adjusted lane structure graph;

[0251] A moving path whose moving cost meets preset conditions in the adjusted lane structure diagram is determined, and a target lane on the moving path that meets the preset conditions is recommended to the target vehicle.

[0252] The specific implementation methods and corresponding beneficial effects of the above operations can be found in the detailed description of the lane recommendation method above, which will not be elaborated here.

[0253] The computer-readable storage medium may include: a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0254] Since the computer program stored in the computer-readable storage medium can execute any lane recommendation method provided in the embodiments of the present application, the beneficial effects that can be achieved by any lane recommendation method provided in the embodiments of the present application can be achieved. Please refer to the previous embodiments for details and will not be repeated here.

[0255] Optionally, an embodiment of the present application provides a target vehicle, the target vehicle includes a processor and a memory, the memory stores multiple instructions; the processor loads the instructions from the memory to execute the lane recommendation method provided in the embodiment of the present application.

[0256] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0257] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0258] The embodiments, implementation methods and related technical features of the present application can be combined and replaced with each other without conflict.

[0259] The above are only preferred embodiments of the present application and do not constitute any form of limitation to the present application. Although the descriptions of various embodiments in the embodiments of the present application have different focuses, for parts not described in detail in a certain embodiment, reference can be made to the relevant embodiments of other embodiments. However, any modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present application without departing from the content of the technical solution of the present application are still within the scope of the technical solution of the present application.

Claims

1. A lane recommendation method, characterized in that: include: Obtain a target lane set corresponding to a target vehicle, the target lane set including a target lane where the target vehicle is located and a target lane within a preset distance range in front of the target vehicle; According to the target lane set, a lane structure graph is constructed, wherein the nodes in the lane structure graph represent the target lanes in the target lane set, and the weights corresponding to the edges in the lane structure graph represent the movement costs of the target vehicle between the target lanes corresponding to the nodes connected by the edges; Reading a node group from the lane structure graph, the node group including two adjacent nodes in the lane structure graph; According to lane information of a target lane corresponding to at least one of the two nodes, a weight corresponding to an edge between the two nodes in the lane structure graph is adjusted to obtain an adjusted lane structure graph, wherein the lane information includes at least one lane attribute information, and the at least one node is determined according to a lane attribute corresponding to the lane attribute information and a direction of the edge between the two nodes; A moving path whose moving cost satisfies a preset condition in the adjusted lane structure diagram is determined, and a target lane on the moving path that satisfies the preset condition is recommended to the target vehicle.

2. The lane recommendation method according to claim 1, characterized in that: The lane information includes at least one lane attribute information and historical recommendation information of the lane; The method of adjusting the weights corresponding to the edges between the two nodes in the lane structure graph according to the lane information of the target lane corresponding to at least one of the two nodes to obtain the adjusted lane structure graph includes: According to the lane attribute information of the target lane corresponding to at least one of the two nodes, the weight corresponding to the edge between the two nodes in the lane structure graph is increased to obtain an adjusted lane structure graph; and, According to the historical recommendation information of the target lane corresponding to at least one of the two nodes, the weight corresponding to the edge between the two nodes in the lane structure graph is reduced to obtain an adjusted lane structure graph.

3. The lane recommendation method according to claim 2, characterized in that: The lane information includes at least one of the lane attribute information, and the weight corresponding to the edge between the two nodes in the lane structure graph is increased according to the lane attribute information of the target lane corresponding to at least one of the two nodes to obtain the adjusted lane structure graph, including: Determine a target lane corresponding to at least one of the two nodes; Determine a first weight value corresponding to lane attribute information of a target lane corresponding to the at least one node; The weight of the edge between the two nodes in the lane structure graph and the first weight value are added to obtain an adjusted lane structure graph.

4. The lane recommendation method according to claim 3, characterized in that: The determining at least one of the two nodes comprises: Get the direction of the edge; At least one node is determined from the two nodes according to the lane attribute and the direction of the edge.

5. The lane recommendation method according to claim 4, characterized in that: The determining at least one node from the two nodes according to the lane attribute and the direction of the edge includes: If the lane attribute is lane length, then according to the direction of the edge, determine the node at the starting position of the edge; A node at a starting point of the edge is determined as at least one node.

6. The lane recommendation method according to claim 4, characterized in that: The determining at least one node from the two nodes according to the lane attribute and the direction of the edge includes: If the lane attribute is a lane type, determining a node at an end position of the edge according to the direction of the edge; A node at an end position of the edge is determined as at least one node.

7. The lane recommendation method according to claim 4, characterized in that: The lane attribute information is a lane width value, and determining at least one node from the two nodes according to the lane attribute and the direction of the edge includes: If the lane attribute is lane width, determining a node at an end position of the edge according to the direction of the edge; Obtaining a lane width value of a target lane corresponding to a node at an end position of the edge; If the lane width value is less than a preset threshold, a node at the end position of the edge is determined as at least one node.

8. The lane recommendation method according to claim 4, characterized in that: The determining at least one node from the two nodes according to the lane attribute and the direction of the edge includes: If the lane attribute is a lane line type and the direction of the edge is bidirectional, the node connected by the edge is determined to be at least one node.

9. The lane recommendation method according to claim 2, characterized in that: The lane information includes the historical recommendation information, and the weight corresponding to the edge between the two nodes in the lane structure graph is reduced according to the historical recommendation information of the target lane corresponding to at least one of the two nodes to obtain the adjusted lane structure graph, including: Determining, according to the historical recommendation information, whether the target lanes corresponding to the two nodes are historically recommended lanes; If the target lanes corresponding to the two nodes are historically recommended lanes, obtaining a second weight value; The weight of the edge between the two nodes in the lane structure graph is subtracted from the second weight value to obtain an adjusted lane structure graph.

10. A computer-readable storage medium storing a plurality of instructions, wherein the instructions are suitable for being loaded by a processor to execute the lane recommendation method according to any one of claims 1 to 9.

11. An electronic device, characterized in that: It comprises a processor and a memory, wherein the memory stores a plurality of instructions; the processor loads instructions from the memory to execute the lane recommendation method as claimed in any one of claims 1 to 9.

12. A target vehicle, characterized in that: It comprises a processor and a memory, wherein the memory stores a plurality of instructions; the processor loads instructions from the memory to execute the lane recommendation method as claimed in any one of claims 1 to 9.

Images