A method, device and system for generating a road network prediction tree

Abstract

The present disclosure discloses a method, device and system for generating a road network prediction tree. The method comprises: obtaining a navigation path planned based on topological data of common roads in common map data; obtaining high-precision road segments corresponding to common road segments included in the navigation path according to a mapping relationship between the common road segments in the common map data and the high-precision road segments in high-precision map data; and determining the road network prediction tree, and assigning a preset mark to the high-precision road segments corresponding to the common road segments included in the road network prediction tree to support intelligent driving capability based on the high-precision map data. The present disclosure combines the comprehensive characteristics of the coverage geographical area of the common map data and the more accurate characteristics of the real world restoration of the high-precision map data to provide support for the intelligent driving capability of the intelligent connected vehicle and ensure the safety of intelligent driving.

Description

Technical Field

[0001] This disclosure relates to the field of intelligent driving technology, and in particular to a method, apparatus and system for generating road network prediction trees. Background Technology

[0002] High-definition (HD) map data can serve as the data foundation for perception, positioning, and driving control in intelligent driving vehicles. HD map data includes high-precision road geometry, lane geometry, lane marking geometry, road boundaries, roadside facilities, and overhead facilities, etc. Standard (SD) map data, also known as navigation electronic maps or internet electronic maps, has lower precision than HD maps and provides a less accurate representation of the real world. In navigation scenarios, standard map data is used for "person guidance," while HD map data is used for "vehicle guidance." However, currently, the coverage and update speed of HD map data for actual geographical areas are insufficient to support autonomous driving across all road sections. Therefore, assisted driving based on HD maps or autonomous driving in limited scenarios has become a currently achievable function for intelligent driving vehicles. The inventors have found that for these two scenarios, the combined use of ordinary map data and HD map data is becoming a trend. How to ensure safe driving when using them in combination is a problem that those skilled in the art must consider and solve. Summary of the Invention

[0003] In view of the above problems, this disclosure is made in order to provide a method, apparatus and system for generating a road network prediction tree that overcomes or at least partially solves the above problems.

[0004] In a first aspect, embodiments of this disclosure provide a method for generating a road network prediction tree, comprising:

[0005] Obtain navigation routes planned based on the topological data of ordinary roads in ordinary map data;

[0006] Based on the mapping relationship between ordinary road segments in ordinary map data and high-precision road segments in high-precision map data, the high-precision road segments corresponding to the ordinary road segments included in the navigation path are obtained.

[0007] A road network prediction tree is determined, and the high-precision road segments corresponding to the ordinary road segments contained in the road network prediction tree are assigned preset labels to support intelligent driving capabilities based on high-precision map data.

[0008] Secondly, embodiments of this disclosure provide an apparatus for generating a road network prediction tree, comprising:

[0009] The acquisition module is used to acquire navigation paths planned based on the topological data of ordinary roads in ordinary map data;

[0010] The acquisition module is used to obtain the high-precision road segments corresponding to the ordinary road segments included in the navigation path planned by the planning module, based on the mapping relationship between ordinary road segments in ordinary map data and high-precision road segments in high-precision map data.

[0011] The determination module is used to determine the road network prediction tree and assign preset labels to the high-precision road segments corresponding to the ordinary road segments included in the road network prediction tree, so as to support intelligent driving capabilities based on high-precision map data.

[0012] Thirdly, embodiments of this disclosure provide a navigation system, including a navigation device and a terminal control device;

[0013] The navigation device is equipped with the aforementioned road network prediction tree generation device;

[0014] The terminal control device is used for autonomous driving navigation of the intelligent driving terminal based on the marked road network prediction tree sent by the navigation device.

[0015] Fourthly, embodiments of this disclosure provide a computer program product with navigation functionality, including a computer program / instructions, wherein the computer program / instructions, when executed by a processor, implement the aforementioned method for generating a road network prediction tree.

[0016] The road network prediction tree generation method provided in this disclosure obtains a navigation path planned based on the topology data of ordinary roads in ordinary map data; according to the mapping relationship between ordinary road segments in ordinary map data and high-precision road segments in high-precision map data, it obtains the high-precision road segments corresponding to the ordinary road segments included in the navigation path; it determines the road network prediction tree, and assigns preset labels to the high-precision road segments corresponding to the ordinary road segments included in the road network prediction tree, so as to support intelligent driving capabilities based on high-precision map data. The beneficial effects of the above technical solutions provided in this disclosure include at least:

[0017] (1) Taking advantage of the wide geographical coverage of ordinary map data, the ordinary map navigation path is first obtained. Then, through the mapping relationship between ordinary road segments in ordinary map data and high-precision road segments in high-precision map data, the ordinary map navigation path is converted into a high-precision map navigation path. Based on the high-precision map navigation path, the road network prediction tree is determined, and the high-precision road segments included in the high-precision map navigation path are marked. This achieves an effective combination of the comprehensive geographical coverage of ordinary map data and the more accurate restoration of the real world by high-precision map data. The marked road network prediction tree provides support for the intelligent driving capability of intelligent connected vehicles and ensures the safety of intelligent driving.

[0018] (2) Since the generated road network prediction tree includes not only the high-precision road segments corresponding to the ordinary road segments in the navigation path, but also other connecting road segments, if the intelligent connected vehicle does not follow the navigation, the vehicle's driving path is still within the scope of the road network prediction tree, and there is still enough time to re-obtain the navigation path based on the vehicle's current location to determine a new road network prediction tree, thereby increasing the universality and rationality of the method.

[0019] Other features and advantages of this disclosure will be set forth in the following description and will be apparent in part from the description or may be learned by practicing the disclosure. The objects and other advantages of this disclosure may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings.

[0020] The technical solutions of this disclosure will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0021] The accompanying drawings are provided to further illustrate the present disclosure and form part of the specification. They are used together with the embodiments of the present disclosure to explain the disclosure and do not constitute a limitation thereof. In the drawings:

[0022] Figure 1 This is a flowchart of the method for generating a road network prediction tree in Embodiment 1 of this disclosure;

[0023] Figure 2 This is a flowchart illustrating the specific implementation of determining that the road network prediction tree reaches a preset range in Embodiment 1 of this disclosure;

[0024] Figure 3 This is an example diagram of the road network prediction tree in Embodiment 1 of this disclosure;

[0025] Figure 4 This is an example diagram of the road network prediction tree generation method in the embodiments of this disclosure;

[0026] Figure 5 This is an example diagram illustrating the conversion between SD navigation paths and HD navigation paths in an embodiment of this disclosure;

[0027] Figure 6 This is a flowchart illustrating the specific implementation of the road network prediction tree generation method in Embodiment 2 of this disclosure;

[0028] Figure 7 This is a flowchart illustrating the specific implementation of another method for generating a road network prediction tree in Embodiment 3 of this disclosure;

[0029] Figure 8 This is a schematic diagram of the structure of the road network prediction tree generation device in an embodiment of this disclosure;

[0030] Figure 9This is a schematic diagram of the navigation system in an embodiment of this disclosure. Detailed Implementation

[0031] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0032] To address the problem in existing technologies where it is difficult to effectively combine ordinary map data and high-precision map data to achieve intelligent navigation, embodiments of this disclosure provide a method, apparatus, and system for generating a road network prediction tree. This method combines the comprehensive geographical coverage of ordinary map data with the more accurate representation of the real world by high-precision map data, thereby supporting the intelligent driving capabilities of connected vehicles and ensuring the safety of intelligent driving.

[0033] Example 1

[0034] Embodiment 1 of this disclosure provides a method for generating a road network prediction tree, the process of which is as follows: Figure 1 As shown, it includes the following steps:

[0035] Step S11: Obtain the navigation path planned based on the topology data of ordinary roads in ordinary map data.

[0036] Currently, high-precision maps have incomplete geographical coverage and slow data updates, while ordinary maps have wider geographical coverage and faster data updates. Therefore, when an Electronic Horizon Provider (EHP) (i.e., high-precision map software that provides road network prediction trees for intelligent connected vehicles) receives a navigation request from an intelligent connected vehicle, it can send the intelligent connected vehicle's current location and navigation destination information to the ordinary map software. The ordinary map software then calculates the route based on the intelligent connected vehicle's current location and navigation destination information to obtain the ordinary map navigation path.

[0037] The aforementioned route calculation is the process of determining the navigation path from the current location of the intelligent connected vehicle to the navigation destination. The determined navigation path is a set of ordinary road segments connecting the vehicle's (intelligent connected vehicle's) current location and the navigation destination. More specifically, it is a set of ordinary road segments connecting the matching ordinary road segments of the vehicle's current location to the matching ordinary road segments of the navigation destination. Typically, the navigation path is represented in map data by the IDs of a set of ordinary road segments.

[0038] Step S12: Based on the mapping relationship between ordinary road segments in ordinary map data and high-precision road segments in high-precision map data, obtain the high-precision road segments corresponding to the ordinary road segments included in the navigation path.

[0039] Based on the mapping relationship between ordinary road segments in ordinary map data and high-precision road segments in high-precision map data, the high-precision road segments corresponding to the ordinary road segments included in the navigation path are obtained. In other words, the ordinary map navigation path is converted into a high-precision map navigation path, which effectively combines the advantages of both ordinary and high-precision maps.

[0040] The pre-establishment of the mapping relationship between ordinary road segments in specific ordinary map data and high-precision road segments in high-precision map data can include the following three methods:

[0041] Method 1: Using ordinary road segments in ordinary map data as buffers, the high-precision road segments that match the buffers are extracted from the high-precision map data using a buffer intersection algorithm, thus obtaining the mapping relationship between ordinary road segments in ordinary map data and high-precision road segments in high-precision map data;

[0042] Method 2: Using high-precision road segments in high-precision map data as buffers, the ordinary road segments that match the buffers are extracted from the ordinary map data using a buffer intersection algorithm, thus obtaining the mapping relationship between ordinary road segments in ordinary map data and high-precision road segments in high-precision map data;

[0043] Method 3: Establish a mapping relationship between ordinary road segments in ordinary map data and high-precision road segments in high-precision map data by matching the shape points of roads.

[0044] Step S13: Determine the road network prediction tree and assign preset labels to the high-precision road segments corresponding to the ordinary road segments contained in the road network prediction tree to support intelligent driving capabilities based on high-precision map data.

[0045] Step S13 can be repeated at set time intervals during navigation.

[0046] Determining the road network prediction tree can specifically include: determining the matching point of the current location of the intelligent connected vehicle in the high-precision map data and the matching high-precision road segment where the matching point is located; starting from the matching high-precision road segment, determining the high-precision road segments that can be entered along the current high-precision road segment according to the topological relationship of the high-precision roads in the high-precision map data, until it is determined that the currently obtained road network prediction tree reaches the preset range.

[0047] In one embodiment, it is determined that the currently obtained road network prediction tree has reached a preset range, referring to... Figure 2 As shown, the following steps may be included:

[0048] Step S21: Determine each path in the currently obtained road network prediction tree that starts with a matching high-precision road segment.

[0049] The road network prediction tree often contains multiple possible paths. First, determine each path that starts with a matching high-precision road segment. For each path, depending on whether the high-precision road segments contained in the path are all high-precision road segments corresponding to ordinary road segments (ordinary road segments in the navigation path), execute step S22 or step S23.

[0050] Step S22: If the high-precision road segments contained in the path are all high-precision road segments corresponding to ordinary road segments, and the path length from the matching point to the destination is not less than the first preset length, then the path is determined to have reached the preset range.

[0051] Step S23: If at least one road segment in the path is not a high-precision road segment corresponding to a normal road segment, and the path length from the matching point to the endpoint is determined to be no less than the second preset length, or the path length of the high-precision road segment in the path that is not a normal road segment is determined to be no less than the third preset length, then the path is determined to have reached the preset range.

[0052] Step S24: When all paths have reached the preset range, determine that the currently obtained road network prediction tree has reached the preset range.

[0053] Optionally, determining that the currently obtained road network prediction tree has reached a preset range may also include, based on the currently obtained road network prediction tree, determining a path that starts with matching high-precision road segments and includes high-precision road segments corresponding to ordinary road segments; if the path length from the matching point to the endpoint is not less than a first preset length, determining that the currently obtained road network prediction tree has reached a preset range.

[0054] A preset label is assigned to the high-precision road segment corresponding to the ordinary road segment contained in the road network prediction tree. Specifically, the high-precision road segment corresponding to the ordinary road segment can be marked as a navigation path. The specific label symbol is not limited in this embodiment.

[0055] Reference Figure 3 As shown, road segments 5, 6, 7, 8, and 9 are marked. Figure 3 The paths shown in bold form constitute the Most Probable Path (MPP), which is a part of the high-precision map navigation path; the paths containing road segments 10, 11, 12, or 13 are other possible paths.

[0056] The autonomous driving control device guides the intelligent connected vehicle to drive autonomously according to the MPP navigation path. At the same time, according to the second preset interval, it determines the high-precision road segment where the matching point of the intelligent connected vehicle's current position is located in the high-precision map data. It determines whether the high-precision road segment is a high-precision road segment marked with the preset mark in the current road network prediction tree. If the determination is no, that is, when it is determined that the intelligent connected vehicle has left the MPP navigation path, it guides the vehicle to drive autonomously according to the corresponding other possible paths, and returns to step S11 to obtain the updated navigation path and road network prediction tree.

[0057] The method for generating a road network prediction tree provided in this embodiment utilizes the wide geographical coverage of ordinary map data. First, a navigation path is obtained from the ordinary map. Then, through the mapping relationship between ordinary road segments in the ordinary map data and high-precision road segments in the high-precision map data, the ordinary map navigation path is converted into a high-precision map navigation path. Based on the high-precision map navigation path, a road network prediction tree is determined, and the high-precision road segments included in the high-precision map navigation path are marked. This effectively combines the comprehensive geographical coverage of ordinary map data with the more accurate representation of the real world by high-precision map data. The marked road network prediction tree supports the intelligent driving capabilities of intelligent connected vehicles, ensuring the safety of intelligent driving.

[0058] The method for generating a road network prediction tree provided in this embodiment includes not only high-precision road segments corresponding to ordinary road segments in the navigation path, but also other connecting road segments. Therefore, if an intelligent connected vehicle does not follow the navigation, the vehicle's driving path is still within the scope of the road network prediction tree, and there is still enough time to re-obtain the navigation path based on the vehicle's current location to determine a new road network prediction tree, thereby increasing the universality and rationality of the method.

[0059] Reference Figure 4 As shown, the method for generating the road network prediction tree can be summarized as follows: The Electronic Horizon Provider (EHP), i.e., the HD EHP, receives the SD navigation path (standard map navigation path, ordinary map navigation path) sent by the SD map software and then sends the SD navigation path to the SD-HD Mapping service, i.e., the server. The SD-HD Mapping service converts the SD navigation path into an HD navigation path (high-precision map navigation path) based on the mapping relationship between ordinary map road segments and high-precision map road segments. (Refer to...) Figure 5As shown, for example, the SD navigation path containing ordinary map road segments 1-4 is converted into an HD navigation path containing high-precision map road segments 5-7, and the HD navigation path is sent to HD EHP; HD EHP performs road network prediction based on the current location of the intelligent connected vehicle and the HD navigation path at a first preset interval, generates a road network prediction tree, and sends the road network prediction tree to the vehicle control system, so that the vehicle control system can guide the intelligent connected vehicle to drive autonomously based on the received road network prediction tree.

[0060] It should be noted that, since the coverage of high-precision map data is not very high at present and does not reach full coverage, when using the road network prediction tree generated by the road network prediction tree generation method provided in this embodiment for intelligent driving assisted navigation, if it is predicted that the vehicle is about to enter the range where high-precision map data is missing, that is, if it is predicted that the ordinary road segment the vehicle is about to enter does not have a corresponding high-precision road segment, the vehicle (user) needs to be prompted to switch back to manual driving.

[0061] Example 2

[0062] Embodiment 2 of this disclosure provides a specific implementation flow of a method for generating a road network prediction tree, such as... Figure 6 As shown, it includes the following steps:

[0063] Step S61: Starting from matching high-precision road segments, determine the high-precision road segments that can be entered along the current high-precision road segment based on the topological relationship of high-precision roads in the high-precision map data, until the first preset range is exceeded or there are multiple currently determined high-precision road segments that can be entered.

[0064] There are currently multiple identified high-precision road sections that can be accessed, meaning there are multiple high-precision road sections that can be accessed by following the current high-precision road sections.

[0065] Starting with matching high-precision road segments, based on the topological relationship of high-precision roads in the high-precision map data, determine the high-precision road segments that can be accessed along the current high-precision road segment. If the preset range is reached and there is only one accessible high-precision road segment for the current high-precision road segment, then a road network prediction tree containing a unique path is obtained. The preset range means that the path length from the matching point to the destination of the currently obtained path is not less than the first preset length.

[0066] If there are multiple accessible high-precision road segments before reaching the preset range, then for the high-precision road segments that are consistent with the high-precision road segments in the high-precision map navigation path (the high-precision road segments corresponding to the ordinary road segments included in the ordinary map navigation path), step S62 is executed; for each high-precision road segment that is inconsistent with the high-precision road segments in the high-precision map navigation path, step S63 is executed respectively.

[0067] Step S62: Starting from the high-precision road segment that is consistent with the high-precision road segment in the high-precision map navigation path among the multiple drivable high-precision road segments, determine the high-precision road segments that can be entered along the current high-precision road segment according to the topological relationship of the high-precision roads in the high-precision map data, until the first preset range is exceeded or there are multiple currently determined drivable high-precision road segments.

[0068] If there are multiple drivable high-precision road sections currently identified in step S62, steps S62 and S63 are executed cyclically.

[0069] Step S63: Starting from the high-precision road segments that are inconsistent with the high-precision road segments in the high-precision map navigation path, determine the high-precision road segments that can be entered along the current high-precision road segment according to the topology relationship, until the second preset range is exceeded or there are multiple currently determined high-precision road segments that can be entered.

[0070] If there are multiple drivable high-precision road sections currently identified in step S63, step S63 is executed repeatedly.

[0071] Specifically, steps S62 and S63 above have no order; either step can be executed first, or they can be executed simultaneously.

[0072] The above embodiment two determines that the currently obtained road network prediction tree has reached a preset range, which may specifically include:

[0073] Determine each path in the currently obtained road network prediction tree that starts with a matching high-precision road segment;

[0074] If the high-precision road segments contained in the path are all high-precision road segments corresponding to ordinary road segments, and the path length from the matching point to the destination is not less than the first preset length, then the path is determined to have reached the first preset range.

[0075] If at least one road segment in the path is not a high-precision road segment corresponding to a normal road segment, the path length from the matching point to the endpoint is determined to be no less than the second preset length, or the path length of the high-precision road segment that is not a normal road segment in the path is determined to be no less than the third preset length, the path is determined to reach the second preset range.

[0076] When all paths reach the first or second preset range, it is determined that the currently obtained road network prediction tree has reached the preset range.

[0077] Example 3

[0078] Embodiment 3 of this disclosure provides a specific implementation flow of another method for generating road network prediction trees, such as... Figure 7 As shown, it includes the following steps:

[0079] Step S71: Starting from matching high-precision road segments, determine the high-precision road segments that can be entered along the current high-precision road segment based on the topological relationship of high-precision roads in the high-precision map data, until the first preset range is exceeded or there are multiple currently determined high-precision road segments that can be entered.

[0080] Starting with matching high-precision road segments, based on the topological relationship of high-precision roads in the high-precision map data, determine the high-precision road segments that can be accessed along the current high-precision road segment. If the preset range is reached and there is only one accessible high-precision road segment for the current high-precision road segment, then a road network prediction tree containing a unique path is obtained. The preset range means that the path length from the matching point to the destination of the currently obtained path is not less than the first preset length.

[0081] If there are multiple accessible high-precision road segments before reaching the preset range, then for the high-precision road segments that are consistent with the high-precision road segments in the high-precision map navigation path, step S72 is executed; for each high-precision road segment that is inconsistent with the high-precision road segments in the high-precision map navigation path, the accessible high-precision road segments are no longer determined.

[0082] Step S72: Starting with a high-precision road segment that is consistent with the high-precision road segment in the high-precision map navigation path from among multiple drivable high-precision road segments, determine the high-precision road segments that can be entered along the current high-precision road segment according to the topological relationship of the high-precision roads in the high-precision map data, until the first preset range is exceeded or there are multiple currently determined drivable high-precision road segments.

[0083] If there are multiple drivable high-precision road segments currently identified in step S72, step S72 is executed repeatedly for the high-precision road segments that are consistent with the high-precision road segments in the high-precision map navigation path; for each high-precision road segment that is inconsistent with the high-precision road segments in the high-precision map navigation path, the drivable high-precision road segments are no longer determined.

[0084] In the above embodiment three, determining that the currently obtained road network prediction tree has reached the preset range can specifically include:

[0085] Based on the current road network prediction tree, determine the starting road segment with matching high-precision road segments, and ensure that the high-precision road segments included are all high-precision road segments corresponding to ordinary road segments.

[0086] If the path length from the matching point to the destination is not less than the first preset length, it is determined that the currently obtained road network prediction tree has reached the preset range.

[0087] The road network prediction tree generation method provided in Example 3 reduces computation by no longer determining accessible high-precision road segments for those that do not match the high-precision road segments in the high-precision map navigation path. The road network prediction tree generation method provided in Example 2, however, continues to predict subsequent road network prediction trees from those road segments for high-precision road segments that do not match the high-precision road segments in the high-precision map navigation path. While this increases computation compared to the method in Example 3, it allows more time to re-determine the high-precision map navigation path and road network prediction tree based on the vehicle's current location when navigation is initiated using the road network prediction tree determined by this method. Therefore, both methods have their advantages, and the appropriate method can be flexibly chosen based on actual needs.

[0088] Based on the inventive concept of this disclosure, embodiments of this disclosure also provide a road network prediction tree generation apparatus, the structure of which is as follows: Figure 8 As shown, it includes:

[0089] The first acquisition module 81 is used to acquire a navigation path planned based on the topology data of ordinary roads in ordinary map data;

[0090] The second acquisition module 82 is used to obtain the high-precision road segments corresponding to the ordinary road segments included in the navigation path acquired by the first acquisition module 81, based on the mapping relationship between ordinary road segments in ordinary map data and high-precision road segments in high-precision map data.

[0091] The determination module 83 is used to determine the road network prediction tree and assign preset labels to the high-precision road segments corresponding to the ordinary road segments included in the road network prediction tree, so as to support intelligent driving capabilities based on high-precision map data.

[0092] In one embodiment, the determining module 83 determines the road network prediction tree, specifically for:

[0093] Determine the matching point of the intelligent connected vehicle's current location in the high-precision map data and the matching high-precision road segment where the matching point is located; starting from the matching high-precision road segment, determine the high-precision road segments that can be entered along the current high-precision road segment according to the topological relationship of the high-precision roads in the high-precision map data, until it is determined that the currently obtained road network prediction tree reaches the preset range.

[0094] In one embodiment, the determining module 83 determines that the currently obtained road network prediction tree has reached a preset range, specifically for:

[0095] The path in the currently obtained road network prediction tree that starts with the matched high-precision road segment is determined. If the high-precision road segments contained in the path are all high-precision road segments corresponding to the ordinary road segments, and the path length from the matching point to the destination is not less than a first preset length, the path is determined to have reached a preset range. If at least one road segment contained in the path is not a high-precision road segment corresponding to the ordinary road segment, and the path length from the matching point to the destination is not less than a second preset length, or the path length of the high-precision road segment that is not corresponding to the ordinary road segment is not less than a third preset length, the path is determined to have reached a preset range. When all paths reach the preset range, the currently obtained road network prediction tree is determined to have reached the preset range.

[0096] In one embodiment, the determining module 83 determines that the currently obtained road network prediction tree has reached a preset range, specifically for:

[0097] Based on the currently obtained road network prediction tree, determine the path starting from the matched high-precision road segment, and include high-precision road segments that are all high-precision road segments corresponding to the ordinary road segments; if the path length from the matching point to the endpoint is not less than the first preset length, determine that the currently obtained road network prediction tree has reached the preset range.

[0098] Based on the inventive concept of this disclosure, embodiments of this disclosure also provide a navigation system, the structure of which is as follows: Figure 9 As shown, it includes a navigation device 91 and a terminal control device 92;

[0099] The navigation device 91 is equipped with the aforementioned road network prediction tree generation device;

[0100] The terminal control device 92 is used for autonomous driving navigation of the intelligent driving terminal based on the marked road network prediction tree sent by the navigation device 91.

[0101] Regarding the apparatus and system in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0102] Based on the inventive concept of this disclosure, embodiments of this disclosure also provide a computer program product with navigation function, which includes a computer program / instruction, wherein the computer program / instruction, when executed by a processor, implements the above-described method for generating a road network prediction tree.

[0103] Unless otherwise specifically stated, terms such as processing, calculation, operation, determination, display, etc., may refer to the actions and / or processes of one or more processing or computing systems or similar devices that represent the manipulation and conversion of data representing physical (e.g., electronic) quantities within the registers or memory of the processing system into other data similarly representing physical quantities within the memory, registers, or other such information storage, transmission, or display devices of the processing system. Information and signals can be represented using any of a variety of different techniques and methods. For example, data, instructions, commands, information, signals, bits, symbols, and chips mentioned throughout the above description can be represented by voltage, current, electromagnetic waves, magnetic fields or particles, light fields or particles, or any combination thereof.

[0104] It should be understood that the specific order or hierarchy of steps in the disclosed process is an example of an exemplary method. Based on design preferences, it should be understood that the specific order or hierarchy of steps in the process may be rearranged without departing from the scope of this disclosure. The appended method claims provide elements of various steps in an exemplary order and are not intended to limit the scope to the specific order or hierarchy described.

[0105] In the above detailed description, various features are combined together in a single embodiment to simplify this disclosure. This approach to disclosure should not be construed as reflecting an intention that embodiments of the claimed subject matter require more features than are explicitly stated in each claim. Rather, as reflected in the appended claims, this disclosure is in a state of having fewer features than all of the features of a single disclosed embodiment. Therefore, the appended claims are hereby explicitly incorporated into the detailed description, with each claim representing a separate preferred embodiment of this disclosure.

[0106] Those skilled in the art will also understand that the various illustrative logic blocks, modules, circuits, and algorithm steps described in conjunction with the embodiments herein can be implemented as electronic hardware, computer software, or a combination thereof. To clearly illustrate the interchangeability between hardware and software, the various illustrative components, blocks, modules, circuits, and steps described above are generally described in terms of their functionality. Whether such functionality is implemented as hardware or software depends on the specific application and the design constraints imposed on the overall system. Those skilled in the art can implement the described functionality in alternative ways for each specific application; however, such implementation decisions should not be construed as departing from the scope of this disclosure.

[0107] The steps of the methods or algorithms described in conjunction with the embodiments herein can be directly embodied in hardware, software modules executed by a processor, or a combination thereof. The software modules can reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disks, removable disks, CD-ROMs, or any other form of storage medium well known in the art. An exemplary storage medium is connected to the processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and storage medium can reside in an ASIC. The ASIC can reside in a user terminal. Alternatively, the processor and storage medium can exist as discrete components in the user terminal.

[0108] For software implementation, the techniques described in this application can be implemented using modules (e.g., procedures, functions, etc.) that perform the functions described in this application. This software code can be stored in memory units and executed by a processor. The memory units can be implemented within the processor or outside the processor; in the latter case, they are communicatively coupled to the processor via various means, as is well known in the art.

[0109] The foregoing description includes examples of one or more embodiments. It is certainly impossible to describe all possible combinations of components or methods in order to describe the above embodiments, but those skilled in the art will recognize that further combinations and arrangements of the various embodiments are possible. Therefore, the embodiments described herein are intended to cover all such changes, modifications, and variations that fall within the scope of the appended claims. Furthermore, the term “comprising” as used in the specification or claims is interpreted in a manner similar to the term “including,” as it is understood when used as a conjunction in the claims. Additionally, the use of any term “or” in the specification of the claims is intended to mean “non-exclusive or.” The terms “first,” “second,” and “third” are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

Claims

1. A method for generating a road network prediction tree, wherein, include: Obtain navigation routes planned based on the topological data of ordinary roads in ordinary map data; Based on the mapping relationship between ordinary road segments in ordinary map data and high-precision road segments in high-precision map data, the high-precision road segments corresponding to the ordinary road segments included in the navigation path are obtained. A road network prediction tree is determined, and a preset label is assigned to the high-precision road segments corresponding to the ordinary road segments included in the road network prediction tree. The labeled road network prediction tree is used to support intelligent driving capabilities based on high-precision map data.

2. The method as described in claim 1, wherein, The pre-establishment of the mapping relationship includes the following steps: Using ordinary road segments in ordinary map data as buffers, a buffer intersection algorithm is used to extract high-precision road segments in high-precision map data that match the buffer, thus obtaining the mapping relationship between ordinary road segments in ordinary map data and high-precision road segments in high-precision map data. or, Using high-precision road segments in high-precision map data as buffers, the ordinary road segments that match the buffers are extracted from ordinary map data using a buffer intersection algorithm, thus obtaining the mapping relationship between ordinary road segments in ordinary map data and high-precision road segments in high-precision map data. or, The mapping relationship between ordinary road segments in ordinary map data and high-precision road segments in high-precision map data is established by matching the shape points of roads.

3. The method as described in claim 1, wherein, The determination of the road network prediction tree specifically includes: Determine the matching point of the intelligent connected vehicle's current location in the high-precision map data and the matching high-precision road segment where the matching point is located; Starting from the matched high-precision road segment, based on the topological relationship of the high-precision roads in the high-precision map data, determine the high-precision road segments that can be entered along the current high-precision road segment, until it is determined that the currently obtained road network prediction tree reaches the preset range.

4. The method of claim 3, wherein, The determination that the currently obtained road network prediction tree has reached the preset range specifically includes: Determine each path in the currently obtained road network prediction tree that starts with the matched high-precision road segment; If the high-precision road segments included in the path are all high-precision road segments corresponding to the ordinary road segments, and the path length from the matching point to the destination is not less than the first preset length, then the path is determined to have reached the preset range. If at least one road segment in the path is not a high-precision road segment corresponding to the ordinary road segment, and the path length from the matching point to the endpoint is not less than the second preset length, or the path length of the high-precision road segment that is not a regular road segment is not less than the third preset length, then the path is determined to have reached the preset range. When all paths reach the preset range, it is determined that the current road network prediction tree has reached the preset range.

5. The method of claim 3, wherein, The determination that the currently obtained road network prediction tree has reached the preset range specifically includes: Based on the current road network prediction tree, determine the starting road segment with the matched high-precision road segment, and the included high-precision road segments are all paths corresponding to the high-precision road segments of the ordinary road segments; If the path length from the matching point to the destination is not less than the first preset length, it is determined that the currently obtained road network prediction tree has reached the preset range.

6. The method of claim 1, wherein, Also includes: At a first preset interval, the step of determining the road network prediction tree and assigning preset labels to the high-precision road segments corresponding to the ordinary road segments included in the road network prediction tree is repeated.

7. The method according to any one of claims 1 to 6, wherein, Also includes: According to the second preset interval, determine the high-precision road segment where the matching point of the current location of the intelligent connected vehicle is located in the high-precision map data, and determine whether the high-precision road segment is a high-precision road segment marked with the preset mark in the current road network prediction tree; If not, return to the step of obtaining the navigation path planned based on the topology data of ordinary roads in ordinary map data.

8. A device for generating a road network prediction tree, wherein, include: The first acquisition module is used to acquire navigation paths planned based on the topological data of ordinary roads in ordinary map data; The second acquisition module is used to obtain the high-precision road segments corresponding to the ordinary road segments included in the navigation path planned by the first acquisition module, based on the mapping relationship between ordinary road segments in ordinary map data and high-precision road segments in high-precision map data. The determination module is used to determine the road network prediction tree and assign preset labels to the high-precision road segments corresponding to the ordinary road segments included in the road network prediction tree. The labeled road network prediction tree is used to support intelligent driving capabilities based on high-precision map data.

9. A navigation system, wherein, The system includes navigation equipment and terminal control equipment; The navigation device is equipped with the road network prediction tree generation device as described in claim 8; The terminal control device is used for autonomous driving navigation of the intelligent driving terminal based on the marked road network prediction tree sent by the navigation device.

10. A computer program product with navigation functionality, wherein, It includes a computer program / instruction, wherein when the computer program / instruction is executed by a processor, it implements the method for generating a road network prediction tree as described in any one of claims 1 to 7.

Images