Road Network Prediction Tree Expansion Method, Device, EHP Equipment and Storage Medium

Abstract

An embodiment of the present application provides a method, device, EHP device and storage medium for expanding a road network prediction tree. The method includes: determining the positioning position of a vehicle and the positioning section in the road network that matches the positioning position; if the vehicle is about to drive into an intersection along the positioning section, determining the distance between the positioning position and the intersection; when the distance is greater than a preset distance threshold, creating a node corresponding to the intersection in the road network prediction tree, and determining the node attributes of the node according to the MPP sections connected to the intersection; when the distance is less than the distance threshold, expanding the forked path corresponding to the node in the road network prediction tree, and adding attributes related to the forked path to the node attributes based on the expanded forked path. The embodiments of the present application can reasonably expand the road network prediction tree when there is an intersection of roads in front of the vehicle.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of intelligent driving technology, and in particular, to a method, device, EHP device and storage medium for expanding a road network prediction tree. Background Art

[0002] EHP (Electronic Horizon Provider) is a service that provides vehicles with information beyond the line of sight. By using the information beyond the line of sight provided by EHP, the normal operation of intelligent driving functions such as the vehicle's ADAS (Advanced Driver Assistance Systems) can be ensured, which helps to improve the safety and comfort of the vehicle driving process.

[0003] As the basis of the information beyond the line of sight, the road network prediction tree can describe the road network topology within a certain area in front of the vehicle through a tree-like data structure. Therefore, EHP can expand the road network prediction tree during the vehicle driving process and provide it to the vehicle, so as to provide a basis for the intelligent driving decision-making and control of the vehicle. However, due to the complex road conditions of the road network, when there is a road intersection in front of the vehicle, how to reasonably expand the road network prediction tree has become a difficult problem. Summary of the Invention

[0004] In view of this, the embodiments of the present application provide a method, device, EHP device and storage medium for expanding a road network prediction tree to reasonably expand the road network prediction tree when there is a road intersection in front of the vehicle.

[0005] To achieve the above object, the embodiments of the present application provide the following technical solutions.

[0006] In a first aspect, the embodiments of the present application provide a method for expanding a road network prediction tree, including:

[0007] Determine the positioning position of the vehicle and the positioning section in the road network that matches the positioning position;

[0008] If the vehicle is about to drive into an intersection along the positioning section, determine the distance between the positioning position and the intersection;

[0009] When the distance is greater than a preset distance threshold, create a node corresponding to the intersection in the road network prediction tree, and determine the node attributes of the node according to the MPP section connected to the intersection;

[0010] When the distance is less than the distance threshold, expand the bifurcation path corresponding to the node in the road network prediction tree, and add attributes related to the bifurcation path to the node attributes based on the expanded bifurcation path.

[0011] Second aspect, an embodiment of the present application provides a road network prediction tree expansion device, including:

[0012] A positioning position and road section determination module, configured to determine the positioning position of the vehicle and the positioning road section matched by the positioning position in the road network;

[0013] A distance determination module, configured to determine the distance between the positioning position and the intersection if the vehicle is about to drive into the intersection along the positioning road section;

[0014] A node creation and attribute determination module, configured to create a node corresponding to the intersection in the road network prediction tree when the distance is greater than a preset distance threshold, and determine the node attributes of the node according to the MPP road sections connected to the intersection;

[0015] A path expansion and attribute supplement module, configured to expand the fork path corresponding to the node in the road network prediction tree when the distance is less than the distance threshold, and add attributes related to the fork path to the node attributes based on the expanded fork path.

[0016] Third aspect, an embodiment of the present application provides an EHP device, including: at least one memory and at least one processor, the memory stores one or more computer-executable instructions, and the processor calls the one or more computer-executable instructions to execute the road network prediction tree expansion method as described above.

[0017] Fourth aspect, an embodiment of the present application provides a storage medium, the storage medium stores one or more computer-executable instructions, and when the one or more computer-executable instructions are executed, the road network prediction tree expansion method as described above is implemented.

[0018] Fifth aspect, an embodiment of the present application provides a computer program, and when the computer program is executed, the road network prediction tree expansion method as described above is implemented.

[0019] The road network prediction tree expansion method provided by the embodiments of the present application can determine the distance between the vehicle's positioning position and the intersection when there is a road intersection in front of the vehicle, so as to gradually expand the road network topology structure related to the intersection in the road network prediction tree as the vehicle approaches the intersection. When the road network prediction tree expands to the intersection of the road, it is necessary to create a node corresponding to the intersection and the forked paths corresponding to the node. The embodiments of the present application can consider that the vehicle is far from the intersection when the distance between the vehicle's positioning position and the intersection is greater than a preset distance threshold. At this time, only a node corresponding to the intersection is created in the road network prediction tree, and the node attributes are determined based on the MPP section connected to the intersection, so that the node attributes express the attributes of the MPP paths connected to the intersection. Thus, when the vehicle is far from the intersection, the road network prediction tree can meet the vehicle's driving decision-making needs by providing the node of the intersection and the attributes of the MPP paths forked from the intersection, while avoiding the over-occupation of the data size space of the road network prediction tree by the road network topology structure information related to the intersection. Furthermore, as the vehicle travels, when the distance between the vehicle's positioning position and the intersection is less than the distance threshold, it is considered that the vehicle is close to the intersection. At this time, the embodiments of the present application can expand the forked paths corresponding to the nodes in the road network prediction tree and add attributes related to the forked paths to the node attributes, so that the road network prediction tree can more comprehensively express the road network topology information of the intersection to meet the vehicle's driving decision-making needs when the vehicle is close to the intersection, realizing the expansion of the road network information of the intersection in the road network prediction tree.

[0020] It can be seen that the embodiments of the present application can first create a node corresponding to the intersection and some node attributes in the road network prediction tree when the vehicle is far from the intersection of the road, and then expand the forked paths corresponding to the nodes and add node attributes in the road network prediction tree when the vehicle is close to the intersection of the road, so that the closer the vehicle is to the intersection of the road, the more comprehensive the road network topology structure information about the intersection in the road network prediction tree is. Thus, under the condition that the data size of the road network prediction tree is limited, the road network topology structure that meets the vehicle's driving needs is gradually expanded in the road network prediction tree, achieving the balance between the data size limitation of the road network prediction tree and the vehicle's driving needs, and achieving the effect of reasonably expanding the road network prediction tree. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only the embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained according to the provided drawings without creative efforts.

[0022] Figure 1 It is a schematic diagram of the road network prediction tree.

[0023] Figure 2 It is a flowchart of the road network prediction tree expansion method provided by the embodiment of the present application.

[0024] Figure 3A It is a schematic diagram of the road network topology in front of the positioning section.

[0025] Figure 3B It is another schematic diagram of the road network topology in front of the positioning section.

[0026] Figure 4A It is an example diagram of expanding the road network prediction tree according to the embodiment of the present application.

[0027] Figure 4B It is another example diagram of expanding the road network prediction tree according to the embodiment of the present application.

[0028] Figure 5A It is a flowchart of the method for determining node attributes.

[0029] Figure 5B It is a flowchart of the method for adding node attributes.

[0030] Figure 6 It is another example diagram of expanding the road network prediction tree according to the embodiment of the present application.

[0031] Figure 7 It is a block diagram of the road network prediction tree expansion device provided by the embodiment of the present application.

[0032] Figure 8 It is a block diagram of the EHP device. Specific embodiments

[0033] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0034] The road network prediction tree is a tree-like data structure, which is based on the positioning section of the vehicle and determines the MPP (Most Probable Path) section and non-MPP section from the road network through the set section expansion strategy, so as to describe the road network topology within a certain area in front of the vehicle. In one example, Figure 1 An optional schematic diagram of the road network prediction tree is exemplarily shown, such as Figure 1 shown Figure 1 The square in represents the positioning position of the vehicle, and the section matched by the positioning position of the vehicle in the road network is called the positioning section. Based on the driving direction of the vehicle (for example Figure 1In the direction indicated by the arrow, EHP can expand the MMP path and non-MMP path in front of the positioning section in the road network prediction tree. Specifically, when there is a road intersection in front of the positioning section, EHP needs to create a node for the intersection in the road network prediction tree and expand the corresponding fork paths (subpaths) of the node. The fork paths include the MPP path and non-MPP path; among them, Figure 1 The solid line connecting two points in can represent an MPP section (the MPP section can be the section where the vehicle is most likely to travel). Each MPP section is connected to form an MPP path ( Figure 1 The solid line in can represent the MPP path), Figure 1 The dashed line connecting two points in can represent a non-MPP section (the non-MPP section can be the section where the vehicle is not most likely to travel). Continuous non-MPP sections can form a non-MPP path ( Figure 1 The dashed line in can represent the non-MPP path), that is, a non-MPP path includes continuous non-MPP sections. The relationship between the path and the section can be regarded as the path including one or more sections.

[0035] From Figure 1 the example, it can be seen that the road network prediction tree is constructed based on the vehicle's positioning section during the vehicle's driving process by expanding the MPP path and non-MPP path. And the depth of the road network prediction tree is positively correlated with the length of the MPP path (that is, the longer the MPP path, the deeper the depth of the road network prediction tree), and the breadth of the road network prediction tree is positively correlated with the length of the non-MPP path (that is, the longer the non-MPP path, the wider the breadth of the road network prediction tree). Among them, the depth of the road network prediction tree represents the vehicle's farthest vision distance, and the breadth can represent the section fork level.

[0036] However, due to factors such as system memory and traffic restrictions, there are limitations on the data size of the road network prediction tree constructed by EHP. For example, as the vehicle drives, the road network information that the vehicle has left in the road network prediction tree needs to be deleted, and the road network information used by the vehicle for subsequent driving needs to be created in the road network prediction tree. In this case, when there is an intersection in front of the vehicle, the road network information that the road network prediction tree needs to create is relatively complex (including creating a node corresponding to the intersection and expanding the fork paths bifurcated from the intersection). Therefore, under the limitation of the data size of the road network prediction tree, when there is an intersection in front of the vehicle, how to reasonably expand the road network prediction tree has become a difficult problem.

[0037] It can be understood that during the driving of the vehicle, if there is a road intersection ahead of the vehicle, the EHP needs to create a node corresponding to the intersection and the forked paths corresponding to the node in the road network prediction tree. If the EHP creates the road network topology structure related to the intersection (such as the node corresponding to the intersection and the forked paths) in the road network prediction tree at one time, then in order to enable the road network prediction tree to have enough data size space to store the above road network topology structure, it is necessary to delete the road network information that has been traveled by the vehicle with the corresponding data size in the road network prediction tree. This results in a mutation in the addition and deletion of road network information in the road network prediction tree, which is not conducive to the intelligent driving decision-making and control of the vehicle.

[0038] Based on this, the embodiments of the present application can gradually create a node corresponding to the intersection and the forked paths corresponding to the node in the road network prediction tree in stages based on the distance between the vehicle position and the road intersection. That is to say, when the vehicle is far from the road intersection, a node corresponding to the intersection is first created in the road network prediction tree, and when the vehicle is close to the road intersection, the forked paths corresponding to the node are then expanded in the road network prediction tree, so that the closer the vehicle is to the road intersection, the more comprehensive the road network topology structure information about the intersection in the road network prediction tree is. Thus, under the condition that the data size of the road network prediction tree is limited, the road network topology structure that meets the driving requirements of the vehicle is gradually expanded in the road network prediction tree, achieving both the data size limitation of the road network prediction tree and the driving requirements of the vehicle, and achieving the effect of reasonably expanding the road network prediction tree.

[0039] Based on the above idea, the embodiments of the present application provide a new road network prediction tree expansion scheme to gradually expand the road network prediction tree in stages when there is a road intersection ahead of the vehicle. As an optional implementation, Figure 2 An optional flowchart of the road network prediction tree expansion method provided by the embodiments of the present application is exemplarily shown. This method flow can be implemented by an EHP device. The EHP device is an electronic device that can provide over-the-horizon information such as road attributes for the vehicle, so as to provide safety assistance for intelligent driving systems such as the vehicle's ADAS (Advanced Driver Assistance Systems). The EHP device referred to in the embodiments of the present application is, for example, an EHP terminal deployed on the vehicle or an EHP server deployed on the network side. Refer to Figure 2 , this method flow may include the following steps.

[0040] In step S210, determine the positioning position of the vehicle and the positioning section in the road network that matches the positioning position.

[0041] During the driving of the vehicle, the embodiment of the present application can determine the positioning location of the vehicle (for example, by using positioning means such as satellite positioning to determine the positioning location of the vehicle), and determine the positioning section in the road network that matches the positioning location of the vehicle. This positioning section can be regarded as the current driving section of the vehicle in the road network, for example, the MPP section where the vehicle is currently located.

[0042] In step S211, if the vehicle is about to drive into an intersection along the positioning section, determine the distance between the positioning location and the intersection.

[0043] The embodiment of the present application can determine the front and rear of the positioning section according to the driving direction of the vehicle. The front of the positioning section can be the driving direction of the vehicle along the positioning section (that is, the front of the positioning section corresponds to the driving direction of the vehicle). Thus, according to the driving direction of the vehicle, the embodiment of the present application can determine whether the vehicle is about to drive into an intersection along the positioning section, that is, determine whether there is an intersection in the front of the vehicle's driving direction.

[0044] In some embodiments, the embodiment of the present application can determine whether the vehicle is about to drive into an intersection along the positioning section by determining whether there is an intersection of the connected road in the front of the positioning section; if there is an intersection of the connected road in the driving direction of the vehicle for the positioning section, the embodiment of the present application can determine that the vehicle is about to drive into the intersection along the positioning section, that is to say, there is an intersection in the front of the vehicle's driving direction. In this case, the embodiment of the present application can gradually expand the road network prediction tree in stages according to the distance between the positioning location of the vehicle and the intersection, avoiding expanding all the road network topological structures of the intersection in the road network prediction tree at one time, so as to ensure that the road network topological structure information of the front intersection in the road network prediction tree is gradually created as the vehicle gradually approaches the intersection, and the road network information that the vehicle has traveled through in the road network prediction tree is gradually deleted as the distance between the vehicle position and the intersection approaches, ensuring the reasonable expansion of the road network prediction tree.

[0045] In some embodiments, the embodiment of the present application can determine whether the positioning section is connected to multiple fork sections (for example, at least two fork sections) in the driving direction of the vehicle. If so, determine that there is an intersection of the connected road in the front of the positioning section (that is, the vehicle is about to drive into the intersection along the positioning section); if not, determine that there is no intersection of the connected road in the front of the positioning section. In one example, Figure 3A Exemplarily shows a schematic diagram of the front road network topology of the positioning section, such as Figure 3A shown. In the figure, the square represents the vehicle, the arrow direction represents the driving direction of the vehicle, section 311 is the positioning section of the vehicle in the road network, and there are two fork sections (i.e., section 312 and section 313) connected in the front of section 311 in the road network. Then there is an intersection 314 of the connected road in the front of section 311, that is, intersection 314 branches out section 312 and section 313. In another example, Figure 3BAnother schematic diagram showing the topological structure of the road network ahead of the positioning section is shown as an example. Figure 3B As shown, the road section 311 is a positioning road section, and the front of the road section 311 is connected to a road section 315, and the front of the road section 311 is not connected to a road intersection.

[0046] When a vehicle is about to enter an intersection along a positioned road section, an embodiment of the present application can determine the distance between the vehicle's positioned position and the intersection, thereby gradually expanding the road network topology structure related to the intersection in the road network prediction tree in stages as the vehicle's positioned position approaches the intersection.

[0047] In step S212, when the distance is greater than a preset distance threshold, a node corresponding to the intersection is created in the road network prediction tree, and the node attribute of the node is determined based on the MPP section connected to the intersection.

[0048] The distance threshold is a trigger distance for triggering the expansion of the road network topology structure related to the intersection in the road network prediction tree. In some embodiments, the distance threshold can be pre-set. For example, in an embodiment of the present application, the distance threshold can be pre-configured based on the vehicle speed and the distance from the positioning section to the intersection; wherein the vehicle speed is negatively correlated with the distance threshold (i.e., the faster the vehicle speed, the smaller the distance threshold, and the slower the vehicle speed, the larger the distance threshold, that is, when the vehicle is traveling quickly, the distance threshold needs to be reduced accordingly to meet the rapid expansion requirements of the road network prediction tree); the distance from the positioning section to the intersection can be regarded as the distance from the starting point of the positioning section to the intersection, and the distance from the positioning section to the intersection is positively correlated with the distance threshold (i.e., the greater the distance from the positioning section to the intersection, the greater the distance threshold, and the smaller the distance from the positioning section to the intersection, the smaller the distance threshold, to adapt to the actual driving conditions of the vehicle in the road network).

[0049] The embodiment of the present application can trigger the expansion of the road network topology structure related to the intersection in the road network prediction tree according to the positioning position of the vehicle when the vehicle is about to enter the intersection along the positioning section. When the distance between the vehicle position and the intersection is greater than the distance threshold, the embodiment of the present application can first create a node corresponding to the intersection in the road network prediction tree and determine the node attributes. At this time, the embodiment of the present application does not expand the bifurcation path of the intersection (that is, it does not expand the MPP path and non-MPP path extending from the intersection), thereby avoiding the one-time expansion of all the road network topology structures of the intersection in the road network prediction tree. When the vehicle is far away from the intersection, it can avoid the road network topology structure information of the intersection from excessively occupying the data size of the road network prediction tree.

[0050] Based on the fact that the forked paths branched from an intersection correspond to MPP paths and non-MPP paths in the road network prediction tree, the node attributes of a node can represent the attributes of the MPP paths branched from the intersection and the attributes of the non-MPP paths branched from the intersection. Under the idea of gradually expanding the road network prediction tree in stages in the embodiments of the present application, when the distance between the positioning position of the vehicle and the intersection is greater than the distance threshold, the attributes of the MPP paths branched from the intersection can be recorded in the node attributes first, without recording the attributes of the non-MPP paths branched from the intersection, so as to avoid the road network topology information of the intersection occupying too much data size of the road network prediction tree when the vehicle is far from the intersection.

[0051] In some embodiments, the embodiments of the present application can determine the attributes of the MPP paths branched from the intersection according to the relationship between the positioned road section and the MPP road sections connected to the intersection, so as to determine the node attributes for the nodes created in the road network prediction tree when the distance between the positioning position of the vehicle and the intersection is greater than the distance threshold. As an optional implementation, the attributes of a path branched from the intersection can include the steering angle information of the path and the path identifier. Therefore, when the distance between the positioning position of the vehicle and the intersection is greater than the distance threshold, the embodiments of the present application can determine the steering angle information of the MPP path branched from the intersection and the identifier of the MPP path, and record them in the node attributes, so as to determine the node attributes when the distance between the positioning position of the vehicle and the intersection is greater than the distance threshold.

[0052] In one example, on the basis of Figure 3A the example, Figure 4A an exemplary diagram showing the expansion of the road network prediction tree in the embodiments of the present application is shown. As Figure 4A shown, when the distance between the positioning position of the vehicle and intersection 314 is greater than the distance threshold, the embodiments of the present application can create a node for intersection 314 in the road network prediction tree, and determine the node attributes based on the steering angle information and identifier of MPP path 41 branched from intersection 314.

[0053] In further some embodiments, the embodiments of the present application can also determine the lane connection relationship of the intersection in the road network prediction tree when the distance between the positioning position of the vehicle and the intersection is greater than the distance threshold. At this time, the lane connection relationship only includes the lane connection relationship between MPP road sections, and does not include the lane connection relationship between MPP paths and non-MPP paths at the intersection. For example, the embodiments of the present application can make the lane connection relationship of the intersection in the road network prediction tree according to the lane connection identifier (connector ID) of the positioned road section and the lane connection identifier of the MPP road sections branched from the intersection. Combining Figure 4AAs shown, assuming that the section 312 where the intersection 314 bifurcates is an MPP section, in the embodiment of the present application, when the distance between the positioning position of the vehicle and the intersection is greater than the distance threshold, the lane connection relationship of the intersection can be made in the road network prediction tree according to the lane connection identifier of the positioning section 311 and the lane connection identifier of the section 312. It can be seen that when the distance between the positioning position of the vehicle and the intersection is greater than the distance threshold, the node attribute only expresses the turning angle information of the MPP path at the intersection and the path identifier of the MPP path, and the lane connection relationship only expresses the lane connection relationship between the positioning section and the MPP section bifurcated from the intersection.

[0054] In step S213, when the distance is less than the distance threshold, expand the bifurcated path corresponding to the node in the road network prediction tree, and add attributes related to the bifurcated path to the node attribute based on the expanded bifurcated path.

[0055] As the vehicle travels, the distance between the positioning position of the vehicle and the intersection is continuously shrinking. When the distance between the positioning position of the vehicle and the intersection is less than the distance threshold, the embodiment of the present application performs the next-stage expansion of the road network topology related to the intersection in the road network prediction tree. At this time, the embodiment of the present application can expand the bifurcated path corresponding to the node in the road network prediction tree. For example, expand the MPP path and non-MPP path bifurcated from the intersection in the road network prediction tree.

[0056] In some embodiments, the embodiment of the present application can determine the bifurcated sections connected to the positioning section at the intersection from the road network, and start to expand the bifurcated paths from each bifurcated section respectively, so as to stop expanding the bifurcated paths when the expansion of the bifurcated paths reaches the expansion stop condition, and realize expanding the bifurcated path corresponding to the node in the road network prediction tree.

[0057] As an optional implementation, the bifurcated sections connected to the intersection may be MPP sections or non-MPP sections. Therefore, the embodiment of the present application can start to expand the MPP path from the MPP section connected to the intersection and start to expand the non-MPP path from the non-MPP section connected to the intersection, so as to realize expanding the bifurcated path corresponding to the node.

[0058] Optionally, the embodiments of the present application may define the extended cut-off conditions for MPP paths and non-MPP paths, such as the extended cut-off lengths of MPP paths and non-MPP paths, etc. When the MPP path extended from an intersection reaches the extended cut-off condition of the MPP path (for example, the length of the MPP path extended from the intersection reaches the extended cut-off length of the MPP path), the embodiments of the present application may stop extending the MPP path. When the non-MPP path extended from an intersection reaches the extended cut-off condition of the non-MPP path (for example, the length of the non-MPP path extended from the intersection reaches the extended cut-off length of the non-MPP path), the embodiments of the present application may stop extending the non-MPP path, so as to realize the expansion of the forked paths at the nodes of the road network prediction tree. It should be noted that the embodiments of the present application may also support setting the extended cut-off condition of the MPP path as the extended cut-off level of the MPP path (such as the cut-off level of the MPP section in the extended MPP path), and the extended cut-off condition of the non-MPP section as the extended cut-off level of the non-MPP section (such as the cut-off level of the non-MPP section in the extended non-MPP path), rather than being limited to defining the extended cut-off condition by setting the extended cut-off length. In other possible implementations, the extended cut-off conditions for MPP paths and non-MPP paths may be the same or different. For example, the same or different extended cut-off lengths may be set for MPP paths and non-MPP paths, etc.

[0059] In one example, based on Figure 4A the example, Figure 4B Another example diagram showing the expansion of the road network prediction tree according to the embodiments of the present application is exemplarily shown. When the distance between the positioning position of the vehicle and intersection 314 is less than the distance threshold, the embodiments of the present application may, on the basis of the node corresponding to intersection 314 that has been created in the road network prediction tree, continue to expand the forked paths branched from the intersection. Assuming that the section 312 branched from intersection 314 is an MPP section, the embodiments of the present application may expand the MPP section 312 at the node in the road network prediction tree, and start to expand the MPP path 41 from the MPP section 312 until the extended MPP path 41 reaches the extended cut-off condition of the MPP path. Based on the fact that the section 313 branched from intersection 314 is a non-MPP section, the embodiments of the present application may expand the non-MPP section 313 at the node in the road network prediction tree, and start to expand the non-MPP path 42 from the non-MPP section 313 until the extended non-MPP path 42 reaches the extended cut-off condition of the non-MPP path. If there are multiple non-MPP sections among the sections branched from intersection 314, each non-MPP section may similarly expand the non-MPP path in the road network prediction tree.

[0060] After expanding the forked paths corresponding to the nodes in the road network prediction tree, the embodiments of the present application need to further update the node attributes based on the expanded forked paths. Since when the distance between the positioning position of the vehicle and the intersection is greater than the distance threshold, the embodiments of the present application have expressed the attributes of the MPP paths forked from the intersection in the node attributes (such as the steering angle information and identification of the MPP paths), so when the distance between the positioning position of the vehicle and the intersection is less than the distance threshold, the embodiments of the present application can further add the attributes of the non-MPP paths forked from the intersection (such as the steering angle information and identification of the non-MPP paths) in the node attributes. As an optional implementation, for a forked path expanded from a node, if the forked path is a non-MPP path, the embodiments of the present application can determine the root section of the forked path. The root section can be regarded as the first section where a forked path starts to expand at the intersection. For example Figure 4B in the road network prediction tree shown, the root section of the non-MPP path 42 is the first non-MPP section 313 expanded from the intersection; furthermore, the embodiments of the present application can calculate the steering angle information between the positioning section and the root section of the forked path (for example, the steering angle information when entering the root section from the positioning section), so as to obtain the steering angle information of the non-MPP section forked from the intersection (this steering angle information can be used as the steering angle information of the non-MPP path forked from the intersection), and record it in the node attributes; at the same time, create a path identification for the non-MPP path in the node attributes.

[0061] In some further embodiments, when the distance between the positioning position of the vehicle and the intersection is less than the distance threshold, the embodiments of the present application can also add the lane connection relationship of the intersection in the road network prediction tree. At this time, the lane connection relationship needs to add the lane connection relationship between the positioning section and the non-MPP section forked from the intersection. For example, the embodiments of the present application can add the lane connection relationship of the intersection in the road network prediction tree according to the lane connection identification of the positioning section and the lane connection identification of the non-MPP section forked from the intersection. At this time, the lane connection relationship of the intersection includes the lane connection relationship of the MPP section and the non-MPP section at the intersection.

[0062] The road network prediction tree expansion method provided by the embodiments of the present application can determine the distance between the vehicle's positioning position and the intersection when there is a road intersection ahead of the vehicle, so as to gradually expand the road network topology structure related to the intersection in the road network prediction tree as the vehicle approaches the intersection. When the road network prediction tree expands to the intersection of the road, it is necessary to create a node corresponding to the intersection and the forked paths corresponding to the node. In the embodiments of the present application, when the distance between the vehicle's positioning position and the intersection is greater than a preset distance threshold, it is considered that the vehicle is far from the intersection. At this time, only a node corresponding to the intersection is created in the road network prediction tree, and based on the MPP section connected to the intersection, the node attributes are determined, so that the node attributes express the attributes of the MPP paths connected to the intersection; thus, when the vehicle is far from the intersection, the road network prediction tree can meet the vehicle's driving decision-making needs by providing the node of the intersection and the attributes of the MPP paths forked from the intersection, and at the same time avoid the road network topology structure information related to the intersection from occupying too much data size space of the road network prediction tree when the vehicle is far from the intersection; furthermore, as the vehicle travels, when the distance between the vehicle's positioning position and the intersection is less than the distance threshold, it is considered that the vehicle is close to the intersection. At this time, the embodiments of the present application can expand the forked paths corresponding to the nodes in the road network prediction tree and add attributes related to the forked paths to the node attributes, so that the road network prediction tree can more comprehensively express the road network topology information of the intersection to meet the vehicle's driving decision-making needs when the vehicle is close to the intersection, and realize the expansion of the road network information of the intersection in the road network prediction tree.

[0063] It can be seen that in the embodiments of the present application, when the vehicle is far from the intersection of the road, a node corresponding to the intersection and some node attributes can be created in the road network prediction tree first, and when the vehicle is close to the intersection of the road, the forked paths corresponding to the nodes can be expanded in the road network prediction tree and the node attributes can be added, so that the closer the vehicle is to the intersection of the road, the more comprehensive the road network topology structure information about the intersection in the road network prediction tree is. Thus, under the condition that the data size of the road network prediction tree is limited, the road network topology structure that meets the vehicle's driving needs can be gradually expanded in the road network prediction tree, achieving a balance between the data size limit of the road network prediction tree and the vehicle's driving needs, and achieving a reasonable effect of expanding the road network prediction tree.

[0064] In some embodiments, when the distance between the vehicle's positioning position and the intersection is greater than the distance threshold, the embodiments of the present application can determine the attributes of the MPP paths forked from the intersection for the nodes created in the road network prediction tree and record them in the node attributes. As an optional implementation, Figure 5A An exemplary flowchart of an optional method for determining node attributes is shown. Refer to Figure 5A and the method flow may include the following steps.

[0065] In step S510, determine the MPP section from among the multiple forked sections forked from the intersection.

[0066] In some embodiments, the branched road segments branched from an intersection may refer to the road segments that the positioning road segment can enter from the intersection. The branched road segments branched from the intersection may be MPP road segments or non-MPP road segments. Therefore, embodiments of the present application need to determine whether the branched road segment is an MPP road segment or a non-MPP road segment.

[0067] As an alternative implementation for determining MPP road segments and non-MPP road segments, in the vehicle navigation state, embodiments of the present application may use the navigation road segment of the vehicle as the MPP road segment and the non-navigation road segment as the non-MMP road segment. For example, the branched road segment corresponding to the navigation road segment branched from the intersection is used as the MPP road segment, and other branched road segments are used as non-MPP road segments. In other possible implementations, in the vehicle cruising state, embodiments of the present application may determine the MPP road segment that the vehicle is most likely to travel on from the branched road segments branched from the intersection based on the vehicle's historical driving trajectory (for example, using the branched road segment with the most historical driving times as the MMP road segment), and other branched road segments as non-MMP road segments. It should be noted that the strategy for determining MMP road segments and non-MMP road segments can be defined according to actual situations and needs, and embodiments of the present application do not limit this.

[0068] In step S511, determine the steering angle information for entering the MPP road segment from the positioning road segment to obtain the steering angle information of the MPP road segment connected to the intersection, and record the steering angle information of the MPP road segment in the node attributes.

[0069] The node attributes may include the attributes of the MPP paths and non-MPP paths branched from the intersection. In some embodiments, the attributes of the MPP paths branched from the intersection may include the steering angle information of the MPP paths branched from the intersection and the identifiers of the MPP paths. As an alternative implementation, the steering angle information of the MPP paths branched from the intersection may be determined by the steering angle between the positioning road segment and the root road segment of the MPP paths branched from the intersection. The root road segment of the MPP paths branched from the intersection can be regarded as the first MPP road segment of the MPP paths branched from the intersection, that is, the MPP road segment connected to the intersection. Therefore, embodiments of the present application can determine the steering angle information for entering the MPP road segment connected to the intersection from the positioning road segment as the steering angle information of the MPP paths branched from the intersection and record it in the node attributes. In one example, as shown in Figure 4A shown, embodiments of the present application can determine the steering angle information of the MPP road segment 312 branched from the positioning road segment 311 and the intersection 314 as the steering angle information of the MPP path 41 branched from the intersection 314 and record it in the node attributes of the road network prediction tree.

[0070] In step S512, the path identifier of the MPP path where the positioning section is located is used as the path identifier corresponding to the MPP section and is recorded in the node attribute.

[0071] The path identifier corresponding to the MPP section connected to the intersection can be the path identifier of the MPP path where the MPP section connected to the intersection is located. In some embodiments, for the MPP path forked from the intersection, the embodiment of the present application can continue the identifier of the parent path of the MPP path. Since the MPP path where the positioning section is located is the parent path of the MPP path forked from the intersection, the embodiment of the present application can determine the path identifier of the MPP path where the positioning section is located as the identifier of the MPP path forked from the intersection (that is, the path identifier corresponding to the MPP section connected to the intersection), and record it in the node attribute. That is to say, for the forked path forked from the intersection, if the forked path is a sub-path of the MPP path, the forked path continues the path identifier (path ID) of the MPP path. In one example, combined with Figure 4A As shown, for the MPP path 41 that branches off at the intersection 314, the embodiment of the present application can continue to locate the path identifier of the MPP path where the road segment 311 is located, and record it in the node attributes of the road network prediction tree.

[0072] In some embodiments, when the distance between the vehicle's location and the intersection is less than a distance threshold, the embodiment of the present application needs to add content to the node attribute based on the bifurcated path of the road network prediction tree at the intersection. As an optional implementation, Figure 5B The following is an exemplary flowchart of an optional method for adding node attributes, see Figure 5B The method flow may include the following steps.

[0073] In step S520, for any forked path, if the forked path is a non-MPP path, determine the root section of the forked path, and determine the turning angle information of the positioning section entering the root section to obtain the steering angle information of the non-MPP section connected to the intersection, and record the steering angle information of the non-MPP section in the node attribute.

[0074] When the distance between the vehicle's position and the intersection is greater than the distance threshold, the node attributes have recorded the attributes of the MPP paths branched from the intersection. Therefore, when the distance between the vehicle's position and the intersection is less than the distance threshold, the embodiments of the present application can supplement the attributes of the non-MPP paths branched from the intersection in the node attributes. As an optional implementation, if the branched paths from the intersection are non-MPP paths, the embodiments of the present application can determine the root section of the branched path (i.e., the non-MPP section connected to the intersection), calculate the steering angle information of the positioning path entering the root section, so as to obtain the steering angle information of the non-MPP section connected to the intersection. The steering angle information of this non-MPP section can be used as the steering angle information of the non-MPP path branched from the intersection and recorded in the node attributes. In one example, in combination with Figure 4B As shown in the example, for the non-MPP path 42 branched from the intersection, the embodiments of the present application can determine the root section 313 of the non-MPP path 42 (i.e., the non-MPP section 313 connected to the intersection), so as to calculate the steering angle information of the positioning section 311 entering the non-MPP section 313, obtain the steering angle information of the non-MPP path 42 branched from the intersection 314, and add it to the node attributes of the road network prediction tree.

[0075] In step S521, create a path identifier for the non-MPP path and record it in the node attributes.

[0076] Since there is no situation where the non-MPP paths branched from the intersection continue the original non-MPP paths, the embodiments of the present application can directly create a path identifier for this non-MPP path and record it in the node attributes. In one example, in combination with Figure 4B As shown, for the non-MPP path 42 branched from the intersection, the embodiments of the present application can create a path identifier for the non-MPP path 42 and record it in the node attributes of the road network prediction tree.

[0077] When the distance between the positioning position of the vehicle and the intersection is greater than the distance threshold, the embodiments of the present application create a node corresponding to the intersection in the road network prediction tree and update the attributes of the MPP paths branched from the intersection (including the steering angle information and identifiers of the MPP paths) in the node attributes; then when the distance between the positioning position of the vehicle and the intersection is less than the distance threshold, expand the branched paths (including MPP paths and non-MPP paths) of the node bifurcation in the road network prediction tree, and add the attributes of the non-MPP paths branched from the intersection (including the steering angle information and identifiers of the non-MPP paths) in the node attributes, so as to comprehensively record the attributes of the branched paths branched from the intersection in the node attributes and complete the update and production of the node attributes in the road network prediction tree. That is to say, by gradually updating the node attributes in segments, the node attributes can describe the steering angles of the branched paths branched from the intersection and whether the branched paths are the paths continued by the positioning section.

[0078] In one example, for a forked path, the node attributes can record two pieces of information: the turning angle and the path identifier (pathID). For example, taking the forked paths branched out from an intersection as Forked Path 1 and Forked Path 2, the node attributes can record {TurnAngle1, pathId1, TurnAngle2, pathId2}, where TurnAngle1 represents the turning angle of Forked Path 1, pathID1 represents the identifier of Forked Path 1, TurnAngle2 represents the turning angle of Forked Path 2, and pathID2 represents the identifier of Forked Path 2.

[0079] After the update of the node attributes in the road network prediction tree is completed, the embodiments of the present application can set the update status of the node attributes and transfer the node attributes in the road network prediction tree to intelligent driving systems such as the vehicle's ADAS in the form of updated data, so as to organize the road network for the vehicle and provide support for the vehicle's driving decision-making.

[0080] In some further embodiments, when the road network prediction tree expands to an intersection, in addition to creating the nodes corresponding to the intersection, expanding the forked paths of the intersection, and updating the node attributes of the nodes, the embodiments of the present application can also create the lane connection relationships of the intersection. In some embodiments, the positioning section can be used as the parent link of the sections branched out from the intersection (including the MPP sections and non-MPP sections branched out from the intersection). When making the lane connection relationships between the positioning section and the sections branched out from the intersection, the embodiments of the present application can obtain the connection relationships of the lane models corresponding to the positioning section, for example, by obtaining the connection relationships of the lane models corresponding to the positioning section through the Lane Group information in the high-precision road data of the road network, and obtaining the connection relationships of the lane models of the forked sections connected to the intersection; thus, associating the connection relationships of the lane models of the forked sections connected to the intersection with the connection relationships of the lane models of the positioning section to create the lane connection relationships between the positioning section and the forked sections connected to the intersection. As an alternative implementation, when associating the connection relationships of the lane models of the forked sections connected to the intersection with the connection relationships of the lane models of the positioning section, the embodiments of the present application can obtain the lane connection identifier (connector ID) in the lane model of the positioning section and obtain the lane connection identifier in the lane model of the forked section, so as to associate the lane connection identifiers of the positioning section and the forked section to realize the creation of the lane connection relationships of the intersection.

[0081] As an optional implementation, the forked road sections connected to the intersection include MPP road sections and non-MPP road sections. In the embodiments of the present application, when the distance between the positioning position of the vehicle and the intersection is greater than the distance threshold, the lane connection relationship between the positioning road section and the MPP road section connected to the intersection can be created first. For example, according to the lane connection identifier of the positioning road section and the lane connection identifier of the MPP road section connected to the intersection, the lane connection relationship of the intersection can be determined in the road network prediction tree. Furthermore, when the distance between the positioning position of the vehicle and the intersection is less than the distance threshold, the lane connection relationship between the positioning road section and the non-MPP road section connected to the intersection can be created. For example, according to the lane connection identifier of the positioning road section and the lane connection identifier of the non-MPP road section connected to the intersection, the lane connection relationship of the intersection can be added to the road network prediction tree, thereby realizing the determination of the lane connection relationship of the intersection.

[0082] Furthermore, the determined lane connection relationship of the intersection can be added to the lane connection relationship of the lane model of the positioning road section and set to the updated state.

[0083] In one example, Figure 6 Exemplarily shows another example diagram of expanding the road network prediction tree in the embodiments of the present application, as Figure 6 shown, the square represents the vehicle, the road section 610 is the current positioning road section of the vehicle, and there is an intersection 620 in the driving direction of the vehicle (as Figure 6 shown by the arrow). When the distance between the positioning position of the vehicle and the intersection 620 is greater than the distance threshold, the EHP can create a corresponding node for the intersection 620 in the road network prediction tree. At the same time, the MPP road section can be determined from the forked road sections 630 and 640 of the intersection 620. Assuming that the road section 630 is the MPP road section, the EHP can determine the steering angle information of the road section 610 entering the road section 630. This steering angle information is used as the steering angle information of the MPP path 61 forked at the intersection 620 and recorded in the node attributes. At the same time, the identifier of the MPP path where the road section 610 is located is used as the identifier of the MPP path 61 forked at the intersection and recorded in the node attributes.

[0084] Furthermore, the EHP can determine the lane connection identifier in the lane model of the road section 610 and the lane connection identifier in the lane model of the road section 630, associate the two, create the lane connection relationship between the road section 610 and the road section 630, and add it to the lane connection relationship of the lane model of the road section 610.

[0085] As the vehicle travels, when the distance between the vehicle's positioning location and intersection 620 is less than the distance threshold, the EHP can expand the forked paths 61 and 62 that fork at intersection 620 in the road network prediction tree. Among them, forked path 62 is used as a non-MPP path. The EHP can determine the steering angle information of section 610 entering the root section 640 of forked path 62. This steering angle information is used as the steering angle information of forked path 62 and recorded in the node attributes. At the same time, a path identifier for forked path 62 is created and recorded in the node attributes. Thus, the node attributes can record the attributes of the MPP path and non-MPP path of the intersection fork, realizing the update of the node attributes.

[0086] Furthermore, the EHP can determine the lane connectivity identifier in the lane model of section 610 and the lane connectivity identifier in the lane model of section 640, correlate the two, create the lane connectivity relationship between section 610 and section 640, and add it to the lane connectivity relationship of the lane model of section 610. Thus, the lane connectivity relationship of the lane model of lane 610 can relatively completely record the lane connectivity relationship of the intersection, realizing the creation of the lane connectivity relationship of the intersection.

[0087] Furthermore, after completing the update of the node attributes and the creation of the lane connectivity relationship of the intersection, the embodiment of the present application can trigger the updated manner of the road network prediction tree to be sent to the vehicle's ADAS and other intelligent driving systems. For example, the nodes, node attributes, and lane connectivity relationships are sent to the vehicle's intelligent driving system in the form of updated data, so as to facilitate the vehicle's intelligent driving system to organize the road network and judge the lane connectivity relationship, providing support for the vehicle's driving decision-making and control.

[0088] In the embodiment of the present application, during the process of expanding the road network prediction tree, when facing the road intersection in front of the vehicle, the EHP needs to create nodes of the intersection, expand the forked paths that fork at the nodes, and update data such as the lane connectivity relationship, so as to transmit them to intelligent driving applications such as ADAS for organizing the road network and judging the lane connectivity relationship. Based on the road network prediction tree expansion scheme provided by the embodiment of the present application, the EHP can gradually expand the road network topology of the road network prediction tree at the intersection in stages based on the distance between the vehicle's positioning location and the intersection, and can achieve a reasonable effect of expanding the road network prediction tree while taking into account the data size limit of the road network prediction tree and the driving needs of the vehicle.

[0089] Next, the road network prediction tree expansion device provided by the embodiment of the present application will be introduced. The device content described below can be considered as the functional modules that the EHP device needs to set up to implement the road network prediction tree expansion method provided by the embodiment of the present application. The device content described below can be mutually corresponding and referred to with the method content described above.

[0090] As an optional implementation, Figure 7The block diagram of the road network prediction tree expansion device provided by an embodiment of the present application is exemplarily shown. This device can be applied to EHP equipment. Refer to Figure 7 , the device may include:

[0091] A positioning position and road section determination module 710, configured to determine the positioning position of the vehicle and the positioning road section matched by the positioning position in the road network;

[0092] A distance determination module 720, configured to determine the distance between the positioning position and the intersection if the vehicle is about to enter the intersection along the positioning road section;

[0093] A node creation and attribute determination module 730, configured to create a node corresponding to the intersection in the road network prediction tree when the distance is greater than a preset distance threshold, and determine the node attributes of the node according to the MPP road sections connected to the intersection;

[0094] A path expansion and attribute supplement module 740, configured to expand the fork path corresponding to the node in the road network prediction tree when the distance is less than the distance threshold, and add attributes related to the fork path to the node attributes based on the expanded fork path.

[0095] In some embodiments, the node attributes include the steering angle information of the road sections connected to the intersection and the path identifiers corresponding to the road sections connected to the intersection. The node creation and attribute determination module 730 is configured to determine the node attributes of the node according to the MPP road sections connected to the intersection, including:

[0096] Determine the MPP road sections from multiple fork road sections branched out from the intersection;

[0097] Determine the steering angle information for entering the MPP road section from the positioning road section to obtain the steering angle information of the MPP road sections connected to the intersection, and record the steering angle information of the MPP road sections in the node attributes;

[0098] And, use the path identifier of the MPP path where the positioning road section is located as the path identifier corresponding to the MPP road section and record it in the node attributes.

[0099] In some embodiments, the fork path includes the MPP path and non-MPP path branched out from the intersection. The path expansion and attribute supplement module 740 is configured to expand the fork path corresponding to the node in the road network prediction tree, including:

[0100] In the road network prediction tree, expand the MPP road section connected to the intersection by the positioning road section, and start expanding the MPP path from the MPP road section until the expansion cut-off condition of the MPP path is reached;

[0101] Further, in the road network prediction tree, expand the non-MPP road sections connected to the positioning road section at the intersection, and start expanding the non-MPP path from the non-MPP road section until the expansion cut-off condition of the non-MPP path is reached.

[0102] In some embodiments, the path expansion and attribute supplement module 740 is configured to add attributes related to the forked path to the node attributes based on the expanded forked path, including:

[0103] For any forked path, if the forked path is a non-MPP path, determine the root road section of the forked path, and determine the turning angle information of the positioning road section entering the root road section, so as to obtain the turning angle information of the non-MPP road section connected to the intersection, and record the turning angle information of the non-MPP road section in the node attributes;

[0104] Further, create a path identifier for the non-MPP path and record it in the node attributes.

[0105] In some further embodiments, the road network prediction tree expansion device provided by the embodiments of the present application can also be used for:

[0106] Obtain the connectivity relationship of the lane model corresponding to the positioning road section and the connectivity relationship of the lane model of the forked road section connected to the intersection;

[0107] Associate the connectivity relationship between the lane model of the forked road section and the lane model of the positioning road section to create the lane connectivity relationship between the positioning road section and the forked road section;

[0108] Add the lane connectivity relationship between the positioning road section and the forked road section to the connectivity relationship of the lane model of the positioning road section to obtain the lane connectivity relationship of the intersection.

[0109] In some embodiments, the device for obtaining the connectivity relationship of the lane model corresponding to the positioning road section and the connectivity relationship of the lane model of the forked road section connected to the intersection includes:

[0110] Obtain the lane connectivity identifier in the lane model of the positioning road section and obtain the lane connectivity identifier in the lane model of the forked road section.

[0111] In some embodiments, the device for associating the connectivity relationship between the lane model of the forked road section and the lane model of the positioning road section to create the lane connectivity relationship between the positioning road section and the forked road section includes:

[0112] Associate the lane connectivity identifiers of the positioning road section and the forked road section to create the lane connectivity relationship between the positioning road section and the forked road section.

[0113] In some embodiments, the device is used to associate the lane connection identifiers of the positioning section and the fork section to create the lane connection relationship between the positioning section and the fork section, including:

[0114] When the distance is greater than the distance threshold, associate the lane connection identifier of the positioning section and the lane connection identifier of the MPP section connected to the intersection to create the lane connection relationship between the positioning section and the MPP section connected to the intersection;

[0115] When the distance is less than the distance threshold, associate the lane connection identifier of the positioning section and the lane connection identifier of the non-MPP section connected to the intersection to create the lane connection relationship between the positioning section and the non-MPP section connected to the intersection.

[0116] In some further embodiments, the road network prediction tree expansion device provided in the embodiments of the present application can also be used to: send the node attributes and the lane connection relationship of the intersection to the intelligent driving system of the vehicle in an updated manner, so that the intelligent driving system can organize the road network and judge the lane connection relationship.

[0117] The embodiments of the present application also provide an EHP device, such as an EHP terminal or an EHP server. The EHP device can implement the road network prediction tree expansion method provided in the embodiments of the present application by setting the above-mentioned road network prediction tree expansion device. As an optional implementation, Figure 8 An optional block diagram of the EHP device is exemplarily shown. As Figure 8 shown, the EHP device may include: at least one processor 81, at least one communication interface 82, at least one memory 83, and at least one communication bus 84.

[0118] In the embodiments of the present application, the number of the processor 81, the communication interface 82, the memory 83, and the communication bus 84 is at least one, and the processor 81, the communication interface 82, and the memory 83 communicate with each other through the communication bus 84.

[0119] Optionally, the communication interface 82 can be an interface of a communication module for network communication.

[0120] Optionally, the processor 81 may be a CPU, a GPU (Graphics Processing Unit), an NPU (embedded neural network processor), an FPGA (Field Programmable Gate Array), a TPU (tensor processing unit), an AI chip, an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application, etc.

[0121] The memory 83 may include a high-speed RAM memory and may also include non-volatile memory, such as at least one disk memory.

[0122] Among them, the memory 83 stores one or more computer-executable instructions, and the processor 81 invokes the one or more computer-executable instructions to execute the road network prediction tree expansion method provided by the embodiments of the present application.

[0123] The embodiments of the present application also provide a storage medium that can store one or more computer-executable instructions. When the one or more computer-executable instructions are executed, the road network prediction tree expansion method provided by the embodiments of the present application is implemented.

[0124] The embodiments of the present application also provide a computer program. When the computer program is executed, the road network prediction tree expansion method provided by the embodiments of the present application is implemented.

[0125] The above describes multiple embodiment solutions provided by the embodiments of the present application. The optional methods described in each embodiment solution can be combined and cross-referenced with each other without conflict, thereby extending a variety of possible embodiment solutions. All of these can be considered as the embodiment solutions disclosed and made public by the embodiments of the present application.

[0126] Although the embodiments of the present application are disclosed as above, the present application is not limited thereto. Any person skilled in the art can make various changes and modifications without departing from the spirit and scope of the present application. Therefore, the protection scope of the present application should be subject to the scope defined by the claims.

Claims

1. A method for expanding a road network prediction tree, wherein, including: determining the positioning location of the vehicle and the positioning section in the road network that matches the positioning location; if the vehicle is about to enter an intersection along the positioning section, determining the distance between the positioning location and the intersection; when the distance is greater than a preset distance threshold, creating a node corresponding to the intersection in the road network prediction tree, and determining the node attributes of the node according to the MPP sections connected to the intersection; when the distance is less than the distance threshold, expanding the fork path corresponding to the node in the road network prediction tree, and adding attributes related to the fork path to the node attributes based on the expanded fork path; wherein, the distance threshold is a trigger distance for triggering the expansion of the road network topology related to the intersection in the road network prediction tree, and the vehicle speed has a negative correlation with the distance threshold; 2. The method according to claim 1, wherein, the node attributes include the steering angle information of the sections connected to the intersection and the path identifiers corresponding to the sections connected to the intersection; the determining the node attributes of the node according to the MPP sections connected to the intersection includes: determining the MPP sections from multiple fork sections branched from the intersection; determining the steering angle information for entering the MPP section from the positioning section to obtain the steering angle information of the MPP section connected to the intersection, and recording the steering angle information of the MPP section in the node attributes; and using the path identifier of the MPP path where the positioning section is located as the path identifier corresponding to the MPP section and recording it in the node attributes; 3. The method according to claim 1 or 2, wherein the fork path includes the MPP path and the non-MPP path branched from the intersection; the expanding the fork path corresponding to the node in the road network prediction tree includes: in the road network prediction tree, expanding the MPP section connected to the intersection by the positioning section, and starting from the MPP section to expand the MPP path until the expansion cut-off condition of the MPP path is reached; and in the road network prediction tree, expanding the non-MPP section connected to the intersection by the positioning section, and starting from the non-MPP section to expand the non-MPP path until the expansion cut-off condition of the non-MPP path is reached; 4. The method according to claim 3, wherein, the adding attributes related to the fork path to the node attributes based on the expanded fork path includes: for any fork path, if the fork path is a non-MPP path, determining the root section of the fork path and determining the steering angle information for entering the root section from the positioning section to obtain the steering angle information of the non-MPP section connected to the intersection, and recording the steering angle information of the non-MPP section in the node attributes; and creating the path identifier of the non-MPP path and recording it in the node attributes; 5. The method according to claim 4, wherein, also including: obtaining the connectivity relationship of the lane model corresponding to the positioning section and the connectivity relationship of the lane models of the fork sections connected to the intersection; associating the connectivity relationship of the lane models of the fork sections with the connectivity relationship of the lane model of the positioning section to create the lane connectivity relationship between the positioning section and the fork sections; Add the lane connection relationship between the positioning section and the fork section to the connection relationship of the lane model of the positioning section to obtain the lane connection relationship of the intersection.

6. The method according to claim 5, wherein The obtaining of the connection relationship of the lane model corresponding to the positioning section and the connection relationship of the lane model of the fork section connected to the intersection includes: Obtain the lane connection identifier in the lane model of the positioning section and obtain the lane connection identifier in the lane model of the fork section; The associating the connection relationship between the lane model of the fork section and the lane model of the positioning section to create the lane connection relationship between the positioning section and the fork section includes: Associate the lane connection identifiers of the positioning section and the fork section to create the lane connection relationship between the positioning section and the fork section.

7. The method according to claim 6, wherein, The associating the lane connection identifiers of the positioning section and the fork section to create the lane connection relationship between the positioning section and the fork section includes: When the distance is greater than the distance threshold, associate the lane connection identifier of the positioning section and the lane connection identifier of the MPP section connected to the intersection to create the lane connection relationship between the positioning section and the MPP section connected to the intersection; When the distance is less than the distance threshold, associate the lane connection identifier of the positioning section and the lane connection identifier of the non-MPP section connected to the intersection to create the lane connection relationship between the positioning section and the non-MPP section connected to the intersection.

8. The method according to any one of claims 5-7, wherein, Further includes: Send the node attributes and the lane connection relationship of the intersection to the intelligent driving system of the vehicle in an update manner, so that the intelligent driving system can organize the road network and judge the lane connection relationship.

9. An apparatus for expanding a road network prediction tree, wherein, Includes: A positioning position and section determination module, configured to determine the positioning position of the vehicle and the positioning section matched by the positioning position in the road network; A distance determination module, configured to determine the distance between the positioning position and the intersection if the vehicle is about to enter the intersection along the positioning section; A node creation and attribute determination module, configured to create a node corresponding to the intersection in the road network prediction tree when the distance is greater than a preset distance threshold, and determine the node attributes of the node according to the MPP section connected to the intersection; A path extension and attribute supplement module, configured to extend the fork path corresponding to the node in the road network prediction tree when the distance is less than the distance threshold, and add attributes related to the fork path to the node attributes based on the extended fork path; Wherein, the distance threshold is a trigger distance for triggering the expansion of the road network topology related to the intersection in the road network prediction tree, and the vehicle speed has a negative correlation with the distance threshold.

10. An EHP device, wherein, Includes: At least one memory and at least one processor, the memory stores one or more computer-executable instructions, and the processor calls the one or more computer-executable instructions to execute the road network prediction tree expansion method according to any one of claims 1-8.

11. A storage medium, wherein, The storage medium stores one or more computer-executable instructions, and when the one or more computer-executable instructions are executed, the road network prediction tree expansion method described in any one of claims 1-8 is implemented.

12. A computer program product, wherein, When the computer program product is executed, the road network prediction tree expansion method described in any one of claims 1-8 is implemented.

Images