Method for generating simulation map and related apparatus

Abstract

A method for generating a simulation map and related apparatus, a device, a computer-readable storage medium, and a computer program product, which can be applied to the field of intelligent driving. The method comprises: acquiring navigation data, wherein the navigation data comprises topology data and electronic horizon data, the topology data comprising data of road sections in a navigation path, the electronic horizon data comprising first description information, and the first description information is description information of a first road corresponding to a vehicle position, and the vehicle position is a position in the navigation path (301); and generating, according to the topology data and the electronic horizon data, a simulation map corresponding to the navigation path (302). According to the method, there is no need to actually collect a complete high-precision map on site on the first road, thereby improving the generation efficiency of the simulation map; and only a simulation map corresponding to a position area that a vehicle will travel through during a simulation test is generated, thereby conserving the resources that would be otherwise consumed in the generation process of a simulation map corresponding to an unused position area, and further improving the generation efficiency of the simulation map.

Description

Method for generating simulation map and related device

[0001] The present application claims priority to the Chinese patent application No. 202411029214.1, filed on July 29, 2024, and entitled "Method for generating simulation map and related device", the whole content of which is incorporated herein by reference. TECHNICAL FIELD

[0002] The present application relates to intelligent driving technology, and in particular to a method for generating a simulation map and related device. BACKGROUND

[0003] In the scenario of testing intelligent driving vehicles, compared with testing intelligent driving vehicles on real first roads, simulation testing of intelligent driving vehicles has the advantages of safe testing process, high testing efficiency, etc., and therefore plays an increasingly important role.

[0004] In the conventional construction process of a simulation map, a precise instrument carried by a collection vehicle can be used to collect data of different road segments to generate a complete high-definition map in a certain area, and then generate a complete simulation map in the certain area according to the complete high-definition map in the certain area.

[0005] However, since the generation efficiency of a complete high-definition map in a certain area is low, a more efficient simulation map generation scheme is urgently needed. SUMMARY

[0006] The present application provides a method for generating a simulation map and related device for improving the efficiency of the simulation map generation process.

[0007] The present application provides the following technical solutions:

[0008] In a first aspect, the present application provides a method for generating a simulation map, which can be used in the field of intelligent driving. In the method, a first device can obtain navigation data, and then obtain topological data corresponding to a navigation path and electronic horizon provider (EHP) data corresponding to a vehicle position from the navigation data. The first device generates a simulation map corresponding to the navigation path according to the topological data and the electronic horizon provider data.

[0009] Exemplarily, the first device generates a simulation map corresponding to at least one road segment in the navigation path according to the topological data and the electronic horizon provider data, which can include that the first device generates a simulation map corresponding to the navigation path according to data of the road segment in the navigation path and first description information of a first road corresponding to the vehicle position.

[0010] The navigation path can include one or more road segments, and the topological data can include data of each road segment included in the navigation path. For example, the data of each road segment can include identification information of each road segment, and can also include coordinate points at endpoints of the road segment. The topological data can also indicate a shape of each road segment in the navigation path. For example, the topological data can include line segments corresponding to each road segment in the navigation path, so that the shape of the navigation path can be determined by the line segments.

[0011] Optionally, the topological data can also include a length of each road segment in the navigation path, or the first device can also determine the length of each road segment according to the coordinate points at the endpoints of each road segment in the navigation path.

[0012] For example, the electronic horizon is a service that provides beyond-visual-range road traffic information for a vehicle, and the electronic horizon data can include description information of a road beyond the sensor range of the vehicle, i.e., the electronic horizon data can include first description information that is description information of at least one first road corresponding to a vehicle position. The vehicle position is a position in the navigation path. For example, the at least one first road can include a road on which the vehicle position is located, and optionally can also include roads connected to the road on which the vehicle position is located.

[0013] The first device can obtain one or more electronic horizon data from the navigation data, and each electronic horizon data is related to a vehicle position at which the electronic horizon data is obtained.

[0014] For example, the description information of each first road can include at least one of the following: road attribute, speed limit information on the road, number of lanes on the road, distance length from a starting point of the navigation path to a starting point of the first road, distance length from the starting point of the navigation path to an ending point of the first road, length of the first road, or other information, etc. For example, the road attribute can be a city road, a highway, a ramp, or other road attributes, etc. The specific road attribute can be determined in combination with an actual application scenario.

[0015] Optionally, the first device can determine the length of the first road according to the distance length from the starting point of the navigation path to the starting point of the first road and the distance length from the starting point of the navigation path to the ending point of the first road.

[0016] In the present implementation, the entire navigation path is determined based on the topological data in the navigation data, that is, the entire navigation path is comprehensively understood with the aid of the topological data, the electronic horizon data includes first description information corresponding to the vehicle position, so that the road on the navigation path can be understood in more detail with the aid of the electronic horizon data, and thus a simulation map corresponding to the navigation path can be generated according to the topological data and the electronic horizon data, that is, a scheme for generating a simulation map corresponding to the navigation path based on navigation data is provided. Since the navigation data can be obtained based on the navigation service provided by a third party, it is not necessary to actually collect a complete high-precision map on the first road, which greatly improves the generation efficiency of the simulation map and reduces the generation cost of the simulation map. In addition, since the vehicle travels along a certain predetermined path in the simulation environment, even if a complete simulation map in the region is generated, the intelligent vehicle will only travel along a predetermined path in the simulation map, and thus the simulation map corresponding to the position region outside the travel path of the vehicle will not be used, resulting in waste of the simulation map corresponding to the position region outside the travel path of the vehicle. In the present application, only the simulation map corresponding to the navigation path is generated, that is, only the simulation map corresponding to the position region that will be traveled by the intelligent vehicle in the simulation test process is generated, which not only meets the demand for simulation test of the intelligent vehicle, but also saves the resources wasted in the generation process of the simulation map corresponding to the position region that will not be used, further improving the efficiency of the simulation map generation process.

[0017] In a possible implementation, the electronic horizon data obtained by the first device from the navigation data further includes second description information, and the second description information is description information of an intersection corresponding to each of the at least one first road. Illustratively, the description information of the intersection can include: intersection attributes, angles corresponding to each branch road connected by the intersection; for example, the intersection attributes can be a crossroads, a three-way intersection, or other intersection attributes; optionally, the angles corresponding to each branch road connected by the intersection can be the angle between any two adjacent branch roads, or can be the angle between each out-road and in-road of all branch roads connected by the intersection.

[0018] Illustratively, the first device generates a simulation map corresponding to at least one road segment in the navigation path according to the topological data and the electronic horizon data, which can include: the first device generates a simulation map corresponding to at least one road segment in the navigation path according to the data of the road segment in the navigation path, the first description information of the first road corresponding to the vehicle position, and the second description information of the intersection corresponding to the first road.

[0019] In the present implementation, the second description information of the intersection connected with the road is also obtained from the navigation data, and then the simulation map corresponding to the navigation path is generated based on the data of the road segments in the navigation path included in the topology data, the description information of the road corresponding to the vehicle position, and the description information of the intersection. The second description information can provide more detailed information about the intersection in the navigation path, which is conducive to further improving the restoration degree of the simulation map to the traffic environment, so that the vehicle can drive in a more realistic simulation environment, which is conducive to improving the accuracy of the simulation test of the vehicle.

[0020] In a possible implementation, the first device can further obtain at least one turning data from the navigation data, each turning data indicating a drivable direction of each lane in a second road, the second road being a road in the navigation path, and the navigation data indicating that the vehicle has a turning behavior at an intersection connected with the second road, in other words, the navigation data indicating that the vehicle needs to turn at the intersection connected with the second road. For example, each turning data can include identification information of the road segment corresponding to the turning data and the drivable direction of each lane in the second road, for example, the drivable direction of a lane can include at least one of the following directions: straight, left turn, right turn, U-turn, or other directions, etc.

[0021] For example, the first device generates the simulation map corresponding to at least one road segment in the navigation path according to the topology data and the electronic horizon data, which can include: the first device generates the simulation map corresponding to part or all of the road segments in the navigation path according to the data of the road segments in the navigation path, the first description information of the first road corresponding to the vehicle position, and the drivable direction of each lane in the second road.

[0022] In the present implementation, the turning data is also obtained from the navigation data, which indicates the drivable direction of each lane in the second road, that is, the turning data can provide lane-level description information. With the turning data, the second road can be understood in more detail, which is conducive to further improving the restoration degree of the simulation map to the traffic environment, and is also conducive to improving the accuracy of the simulation test of the vehicle.

[0023] In a possible implementation, the topological data includes data of each first road segment in the at least one first road segment in the navigation path, and the electronic horizon data includes at least one first description information; the method further includes: determining, by the first device, a first matching relationship, the first matching relationship indicating a matching relationship between the at least one first description information and the at least one first road segment, in other words, the first matching relationship indicating which first road segment each first description information in the at least one first description information is matched with, that is, which first road segment each first description information is the description information of, so that the first description information can be fused with data of the first road segment, and then the fused data can be used to generate a simulation map corresponding to the first road segment. The first device generates the simulation map corresponding to the navigation path according to the topological data and the electronic horizon data, including: generating, by the first device, the simulation map corresponding to the navigation path according to data of road segments in the navigation path, the first description information of the first road corresponding to the vehicle position, and the first matching relationship.

[0024] In the implementation, the matching relationship between the at least one first description information and the at least one first road segment is determined, so that it can be determined which road segment the description information of the road included in the electronic horizon data corresponds to, the fineness of the entire process of generating the simulation map is improved, the difficulty of the step of generating the simulation map is reduced, and the simulation map that is more similar to the real road environment can be generated.

[0025] In a possible implementation, the first device can further obtain at least one turning data from the navigation data, each turning data indicating a drivable direction of each lane in a second road, the second road being a road in the navigation path, and the vehicle having a turning behavior at a junction connected by the second road. The method can further include: determining, by the first device, a second matching relationship, the second matching relationship indicating a matching relationship between the turning data and the at least one first road segment, the second matching relationship indicating which first road segment each turning data describes the drivable direction of each lane in, so that the turning data can be fused with data of the first road segment, and then the fused data can be used to generate a simulation map corresponding to the first road segment. The first device generates the simulation map according to the topological data, the first description information, and the first matching relationship, including: generating, by the first device, the simulation map corresponding to the navigation path according to data of road segments in the navigation path, the first description information of the first road corresponding to the vehicle position, the turning data, the first matching relationship, and the second matching relationship.

[0026] In the present embodiment, the matching relationship between the turning data and the at least one first section is also determined, so that it can be determined which drivable direction of each lane in which section is described by each piece of turning data, and the fineness of the whole process of generating the simulation map is improved, the difficulty of generating the simulation map is further reduced, and a simulation map more similar to the real road environment is generated.

[0027] In a possible implementation, the first device determining the first matching relationship can include: the first device determining the first matching relationship according to the length of the first section and the length of the first road, the length of the first road being obtained based on the first description information. In the present embodiment, the matching relationship between the at least one first road and the at least one first section is determined based on the length of each first section and the length of each first road, which provides a simple scheme for determining the first matching relationship, and the reliability of determining the first matching relationship by means of the length of the section and the road is high, that is, a simple and accurate scheme is provided.

[0028] In a possible implementation, the first device can form a first sequence of the length of each first section in the at least one first section, form a second sequence of the length of each first road in the at least one first road, model a longest common subsequence matching problem based on the first numerical sequence and the second numerical sequence, solve the aforementioned longest common subsequence matching problem, and obtain a longest common subsequence; wherein the lengths included in the longest common subsequence exist in both the first sequence and the second sequence, and the order between the lengths in the longest common subsequence is consistent with the order between the lengths in the first sequence and the order between the lengths in the second sequence; the first road and the first section with the same length determined based on the longest common subsequence are considered to have a matching relationship.

[0029] If the longest common subsequence indicates the matching relationship between the part of the first road and the first section in the electronic horizon data, the first device can determine a first sub-matching relationship according to the longest common subsequence, the first sub-matching relationship including the matching relationship between the first road and the first section with the same length indicated by the longest common subsequence; the first device can determine a second sub-matching relationship by using a fuzzy matching algorithm based on the length of the first road that has not been matched and the length of the first section that has not been matched, and the first matching relationship includes the first sub-matching relationship and the second sub-matching relationship.

[0030] In a possible implementation, the first device can match the identification information of the section included in each piece of turning data with the identification information of each first section included in the topological data, so as to determine the drivable direction of each lane in which first section is described by each piece of turning data, that is, the second matching relationship is determined.

[0031] In a possible implementation, the simulation map comprises a first map element, the first map element is generated according to the electronic horizon data and a preset rule, or the first map element is generated according to the electronic horizon data by using a machine learning model; and the navigation data does not comprise description information of the first map element. For example, the first map element can be a shape of an intersection connected with a road segment, a stop line of a road connected with the intersection, a lane line in the intersection, a connection relationship of the lane line in the intersection, a direction of a partial road connected with the intersection, a width of the road, or another type of map element. For example, the partial road can be a road that does not need to be traveled by the vehicle in the navigation path.

[0032] In the implementation, the first map element in the simulation map is generated based on the preset rule or the machine learning model, and the navigation data does not comprise description information of the first map element, that is, the first map element is generated based on the preset rule or the machine learning model. The first map element generated in this way has diversity, so that a more diversified road network structure can be generated under the premise that the generated simulation map meets the real road network as much as possible, so that the vehicle can encounter more diverse simulation maps in the simulation test stage, which is beneficial to increasing the difficulty of the vehicle in the simulation test process, so that the safety of the vehicle tested on the real road is higher.

[0033] In a second aspect, the present application provides a simulation map generation device, which can be used in the field of intelligent driving. The simulation map generation device comprises: an acquisition module configured to acquire navigation data, the navigation data comprising topological data and electronic horizon data EHP, the topological data comprising data of road segments in a navigation path, and the electronic horizon data comprising first description information, the first description information being description information of a first road corresponding to a vehicle position, the vehicle position being a position in the navigation path; and a generation module configured to generate a simulation map corresponding to the navigation path according to the topological data and the electronic horizon data.

[0034] In the second aspect of the present application, the simulation map generation device is also configured to perform the steps performed by the first device in the first aspect and the various possible implementation manners of the first aspect, and the meanings of the terms in the second aspect of the present application and the various possible implementation manners, and the beneficial effects brought by each possible implementation manner can be referred to the descriptions in the various possible implementation manners of the first aspect, which will not be described here in detail.

[0035] In a third aspect, the embodiments of the present application provide a device, which comprises a processor and a memory, the processor is coupled with the memory, the memory is configured to store a program, and the processor is configured to execute the program in the memory, so that the device executes the method in the first aspect.

[0036] In a fourth aspect, an embodiment of the present application provides a computer readable storage medium, which stores a computer program. When the computer program is run on a computer, the computer program enables the computer to perform the method in the first aspect.

[0037] In a fifth aspect, an embodiment of the present application provides a computer program product, which includes a program. When the program is run on a computer, the program enables the computer to perform the method in the first aspect.

[0038] In a sixth aspect, the present application provides a chip system, which includes a processor for supporting the implementation of the functions involved in the above aspects, such as sending or processing the data and / or information involved in the above method. In a possible design, the chip system further includes a memory, which is configured to store the necessary program instructions and data of the terminal device or the communication device. The chip system can be composed of a chip, or can include a chip and other discrete devices. BRIEF DESCRIPTION OF DRAWINGS

[0039] FIG. 1 is a schematic diagram of a simulation test scene construction according to an embodiment of the present application;

[0040] FIG. 2 is a schematic diagram of a simulation map according to an embodiment of the present application;

[0041] FIG. 3 is a schematic diagram of a simulation map generation method according to an embodiment of the present application;

[0042] FIG. 4 is a schematic diagram of displaying multiple position points according to an embodiment of the present application;

[0043] FIG. 5 is a schematic diagram of a navigation path according to an embodiment of the present application;

[0044] FIG. 6 is another schematic diagram of a simulation map generation method according to an embodiment of the present application;

[0045] FIG. 7 is a schematic diagram of matching a first sequence and a second sequence to obtain a longest common subsequence according to an embodiment of the present application;

[0046] FIG. 8 is a schematic diagram of determining a first matching relationship according to an embodiment of the present application;

[0047] FIG. 9 is a schematic diagram of generating a simulation map corresponding to an intersection according to an embodiment of the present application;

[0048] FIG. 10 is a schematic diagram of a simulation map corresponding to an intersection according to an embodiment of the present application;

[0049] FIG. 11 is a schematic diagram of generating a simulation map using a machine learning model according to an embodiment of the present application;

[0050] FIG. 12 is a structural schematic diagram of a device for generating a simulation map according to an embodiment of the present application;

[0051] FIG. 13 is a structural schematic diagram of a device according to an embodiment of the present application. DETAILED DESCRIPTION

[0052] The embodiments of the present application will be described below in conjunction with the drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all the embodiments. Those skilled in the art can know that with the emergence of new application scenarios, the technical solutions provided by the embodiments of the present application are also applicable to similar technical problems.

[0053] The terms "first", "second", and the like in the specification and claims of the present application and the above-described drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or a chronological sequence. It should be understood that the terms used in this way can be interchanged under appropriate circumstances, which is only a distinguishing way used in the description of the embodiments of the present application to describe the objects with the same attributes. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, so that the processes, methods, systems, products or devices containing a series of units do not have to be limited to those units, but can include other units not clearly listed or inherent to these processes, methods, products or devices.

[0054] In the embodiments of the present application, "indication" can include direct indication and indirect indication, and can also include explicit indication and implicit indication. The information indicated by certain information (indication information described below) is referred to as to-be-indicated information, and there are many ways to indicate the to-be-indicated information in the implementation process, for example, but not limited to, the to-be-indicated information can be directly indicated, such as the to-be-indicated information itself or the index of the to-be-indicated information. The to-be-indicated information can also be indirectly indicated by indicating other information, where the other information and the to-be-indicated information have an association relationship; the to-be-indicated information can also be indicated only by a part, and the other part of the to-be-indicated information is known or agreed in advance, for example, the arrangement order of each information agreed in advance (for example, predefined by a protocol) can be used to indicate a specific information, thereby reducing the indication overhead to a certain extent. The specific manner of indication is not limited in the present application. It can be understood that for the sender of the indication information, the indication information can be used to indicate the to-be-indicated information, and for the receiver of the indication information, the indication information can be used to determine the to-be-indicated information.

[0055] The method provided in the application can be applied to a scenario in which a simulation map needs to be used, and optionally, a simulation traffic scenario needs to be generated based on the simulation map, for example, in a scenario in which a vehicle is subjected to simulation testing, and then the vehicle can be subjected to simulation testing in the simulation traffic scenario. The simulation traffic scenario in the application can also be referred to as a simulation test scenario. Exemplarily, refer to FIG. 1 first, which is a schematic diagram of construction of a simulation test scenario provided in an embodiment of the application. As shown in FIG. 1, the construction process of the simulation test scenario mainly includes six layers. The first layer is a road layer, which mainly includes the topological shape of a road and an intersection and the like. The second layer is a traffic infrastructure, for example, a traffic signal, a traffic sign or other traffic infrastructure lights. The first layer and the second layer are used to simulate road network information in a traffic environment. The third layer is a temporary operation of the first layer and the second layer, for example, a construction site on a road, a traffic accident on a road or other temporarily occurring events and the like. The fourth layer is an object, for example, a static object, a dynamic object or an interactive object in a traffic environment, and is used to simulate interaction of a traffic participant and a vehicle in the traffic environment. The fifth layer is an environment, for example, weather, light or other environmental factors in which the traffic environment is located, and is used to simulate weather conditions in which the traffic environment is located. The sixth layer is digital information, for example, digital map information and the like, and is used to simulate data exchange of wireless services. It should be understood that the examples in FIG. 1 are only for facilitating understanding of the present solution and are not used to limit the present solution.

[0056] The method provided in the application is used to generate a simulation map, wherein the simulation map mainly corresponds to the road layer and optionally also corresponds to the traffic infrastructure layer. In order to have a more intuitive understanding of the simulation map, refer to FIG. 2, which is a schematic diagram of a simulation map provided in an embodiment of the application. As shown in the figure, the simulation map includes the topological shape of a road and an intersection, the number of lanes in the road and the connection relationship between different roads and the like. It should be understood that the examples in FIG. 2 are only for facilitating understanding of the present solution and are not used to limit the present solution.

[0057] In the related art, a precise instrument carried by a collection vehicle is used to collect data of different road sections to generate a complete high-definition map in a region, and then a complete simulation map in the region is generated according to the complete high-definition map in the region. However, the generation efficiency of the complete high-definition map in the region is low. In order to improve the generation efficiency of the simulation map, the present application discloses that the topological data and the electronic horizon data in the navigation data are obtained, the topological data includes the data of the road sections in the navigation path, and the electronic horizon data includes the first description information of the first road corresponding to the vehicle position. The vehicle position is a position in the navigation path. Then, the simulation map corresponding to the navigation path can be generated according to the data of the road sections in the navigation path and the first description information of the first road corresponding to the vehicle position. Since the topological data can provide an overall understanding of the entire navigation path, and the electronic horizon data can provide a more detailed understanding of the road on the navigation path, the simulation map corresponding to the navigation path can be generated according to the topological data and the electronic horizon data. That is, a scheme for generating a simulation map corresponding to a navigation path based on navigation data is provided. Since the navigation data can be obtained based on the navigation service provided by a third party, it is not necessary to collect a complete high-definition map on the first road in the field, which greatly improves the generation efficiency of the simulation map and reduces the generation cost of the simulation map. In addition, the vehicle also travels along a certain predetermined path in the simulation environment. Even if a complete simulation map in the region is generated, the intelligent vehicle will only travel along a predetermined path in the simulation map. Therefore, the simulation map corresponding to the position region outside the travel path of the vehicle will not be used, resulting in waste of the simulation map corresponding to the position region outside the travel path of the vehicle. In the present application, only the simulation map corresponding to the navigation path is generated, that is, only the simulation map corresponding to the position region that will be traveled by the intelligent vehicle in the simulation test process is generated. This meets the demand for simulation testing of the intelligent vehicle and saves resources wasted in the generation process of the simulation map corresponding to the position region that will not be used, further improving the efficiency of the simulation map generation process.

[0058] In combination with the above description, the detailed implementation process of the simulation map generation method provided by the present application is introduced as follows. Specifically, refer to FIG. 3, which is a flowchart of the simulation map generation method provided by an embodiment of the present application. As shown in FIG. 3, the simulation map generation method provided by the present application can include:

[0059] 301, obtaining navigation data, the navigation data including topological data and electronic horizon data, the topological data including data of road sections in a navigation path, and the electronic horizon data including first description information, the first description information being description information of a first road corresponding to a vehicle position, the vehicle position being a position in the navigation path.

[0060] Exemplarily, in an implementation, the first device can send a navigation request to a second device, the navigation request being used to request navigation data from a start point to an end point, the second device being a cloud server used to provide a navigation service; correspondingly, the second device can receive the navigation request sent by the first device, and in response to the received navigation request, send navigation data corresponding to the start point and the end point to the first device, the navigation data indicating a navigation path between the start point and the end point; the first device can obtain topology data and electronic horizon data from the navigation data. The navigation request in the present application can also be referred to as a route calculation request, and the navigation data in the present application can also be referred to as a route calculation result.

[0061] Exemplarily, the navigation request can include first location information of the start point and second location information of the end point, for example, the first location information and the second location information can both be expressed as coordinate information, or the first location information and the second location information can also be location information in a text form, for example, the location information in the text form can be XX Province XX City XX District XX Street XX Mansion, XX Subway Station (XX City), XX City XX District XX Badminton Hall (XX District Store), XX City XX District XX Swimming Pool, XX TV Tower, and the like, which are not exhaustively listed here.

[0062] Optionally, the first device can be deployed with a first application (APP) of a navigation type and a second application, a function of the second application including generating a simulation map, the first application of the navigation type being provided with an access interface, the first device can send the navigation request to the second device through the first application of the navigation type, the second device sends the navigation data to the first application in the first device in response to the received navigation request, after the first application receives the navigation data, the second application in the first device obtains the navigation data by calling the access interface, and then performs subsequent steps.

[0063] Alternatively, the second application in the first device can also directly send the navigation request to the second device, and the second device sends the navigation data to the second application in the first device in response to the received navigation request.

[0064] For a specific implementation of determining the start point and the end point by the first device, in an implementation, the first device can pre-store a first location point set, the first location point set including a plurality of location points and location information corresponding to each location point, a user can select first location information of a start point and second location information of an end point from the plurality of location points, and the first device can determine the first location information of the start point and the second location information of the end point according to a selection operation performed by the user on the start point and the end point.

[0065] For example, the first device can display the position information corresponding to each of the plurality of position points in text form to the user, so that the user can select the start point and the end point from the plurality of position points according to the position information corresponding to each of the plurality of position points in text form, and the first device can obtain the selection operation of the start point and the end point by the user. Alternatively, the user can also select the start point and the end point in the first application of the navigation type, for example, in the first application of the navigation type, the first device can display the plurality of position points in a map, so that the user can select the start point and the end point from the plurality of position points in the map, and the first device can obtain the selection operation of the start point and the end point by the user.

[0066] For a more intuitive understanding of the present scheme, please refer to FIG. 4, which is a schematic diagram provided by an embodiment of the present application for displaying a plurality of position points. As shown in FIG. 4, the first device can display the position information (i.e., position information 1 to position information 7 in FIG. 4) corresponding to the plurality of position points to the user, and the user can perform a selection operation on the position information by clicking the circle in front of any position information, that is, the user can select the position information of the start point and the end point from the plurality of position information in turn, and correspondingly, the first device can obtain the first position information of the start point and the second position information of the end point. It should be understood that the example in FIG. 4 is only for facilitating the understanding of the present scheme and is not used to limit the present scheme.

[0067] In an implementation manner, the first device can pre-store a first position point set, and the first position point set includes the position information corresponding to each of the plurality of position points. The first device can randomly select the first position information of the start point and the second position information of the end point from the position information of the plurality of position points.

[0068] In another implementation manner, the user can also set the start point and the end point of any position, for example, the user can input the first position information of the start point and the second position information of the end point, and the first device can directly obtain the first position information of the start point and the second position information of the end point.

[0069] In another implementation manner, the first device can also pre-store a second position point set, and the second position point set includes the position information corresponding to each group of position points in at least one group of position points. Each group of position points includes a start point and an end point. The first device can select a group of position points from the at least one group of position points as the start point and the end point, so as to obtain the first position information of the start point and the second position information of the end point, and the like. The first device can obtain the position information of the start point and the end point in a plurality of ways, which can be determined in combination with the actual application scenario.

[0070] The navigation data includes topology data corresponding to the navigation path, the topology data can indicate the shape of the entire navigation path, the navigation path can include a plurality of road segments, and the topology data includes data of each road segment in at least one road segment included in the navigation path. For example, the data of each road segment can include identification information of each road segment, and can also include coordinate points at the endpoints of the road segment; the topology data can also indicate the shape of each road segment in the navigation path, for example, the topology data can include a line segment corresponding to each road segment in the navigation path, so that the shape of the navigation path can be determined by a plurality of line segments.

[0071] Optionally, the topology data can also include the length of each road segment in the navigation path, or the first device can also determine the length of each road segment according to the coordinate points at the endpoints of each road segment in the navigation path. For a more intuitive understanding of the present solution, please refer to FIG. 5, which is a schematic diagram of a navigation path provided by an embodiment of the present application. As shown in FIG. 5, there are a plurality of road segments between the starting point and the ending point. It should be understood that the example in FIG. 5 is only for the convenience of understanding the present solution and is not used to limit the present solution.

[0072] The navigation data further includes electronic horizon data (EHP). For example, the electronic horizon is a service that provides vehicles with beyond-visual-range road traffic information, and the electronic horizon data can include description information of roads beyond the sensor range of the vehicle, i.e., the electronic horizon data can include first description information of at least one first road corresponding to the position of the vehicle, and the position of the vehicle is a position in the navigation path. For example, the at least one first road can include the road where the vehicle is located, and can optionally include roads connected to the road where the vehicle is located; in other words, the at least one first road can include the road currently traveled by the vehicle, and can optionally include roads connected to the road currently traveled by the vehicle.

[0073] For example, the description information of each first road can include at least one of the following: road attribute, speed limit information on the road, number of lanes on the road, distance length from the starting point of the navigation path to the starting point of the first road, distance length from the starting point of the navigation path to the ending point of the first road, length of the first road, or other information, etc., which is not exhaustively listed in the present application. For example, the road attribute can be a city road, a highway, a ramp, or other road attributes, etc., which can be determined in combination with actual application scenarios.

[0074] Optionally, the first device can determine the length of the first road according to the distance length from the starting point of the navigation path to the starting point of the first road and the distance length from the starting point of the navigation path to the ending point of the first road.

[0075] Optionally, the electronic horizon data further comprises second description information, the second description information being description information of an intersection corresponding to each of the at least one first road. Illustratively, the description information of the intersection can comprise: intersection attribute, angle corresponding to each branch road connected by the intersection; for example, the intersection attribute can be a crossroad, a three-way road or other intersection attribute, etc., which can be determined in combination with actual application scenarios; optionally, the angle corresponding to each branch road connected by the intersection can be an angle between any two adjacent branch roads, can be an angle between each out-road and in-road of all branch roads connected by the intersection, or other types of angles, etc. Optionally, the description information of the intersection can further comprise distance length between the starting point of the navigation path and the intersection; optionally, if there is a traffic signal at a certain intersection, the description information of the intersection can further comprise position information of the traffic signal.

[0076] Illustratively, the first device can obtain one or more electronic horizon data from the navigation data, each electronic horizon data being related to a vehicle position; optionally, in the process of driving the vehicle according to the navigation path, the vehicle can send the vehicle position to the second device, and the second device can send each electronic horizon data to the first device in turn according to the vehicle position.

[0077] Optionally, after the first device sends the navigation request to the second device, the first time feedback navigation data of the second device can include the topological data corresponding to the navigation path and the electronic horizon data corresponding to the initial position (i.e., the first position information of the starting point) of the vehicle; and then, according to the topological data and the electronic horizon data 1 corresponding to the initial position of the vehicle, the simulation map corresponding to the road segment 1 in the navigation path is generated through step 302, and then the simulation environment 1 corresponding to the road segment 1 in the navigation path can be obtained. The vehicle can simulate driving in the simulation environment 1. During the simulation driving of the vehicle in the simulation environment 1, the vehicle position is updated constantly, and then the first device can send the vehicle position to the second device, and the corresponding second device can send the electronic horizon data 2 to the first device according to the vehicle position; and then, according to the topological data and the electronic horizon data 2 (optionally, the electronic horizon data 1 can also be included), the simulation map corresponding to the road segment 2 in the navigation path is generated through step 302, and then the simulation environment 2 corresponding to the road segment 2 in the navigation path can be obtained. The simulation environment 1 and the simulation environment 2 can have an overlapping part, or the simulation environment 1 and the simulation environment 2 can also be completely non-overlapping. The first device repeats the foregoing steps at least once, and the simulation map corresponding to the entire navigation path can be obtained, and the simulation environment corresponding to the entire navigation path can also be obtained, and the test of the vehicle in the simulation environment is also realized. In other words, during the test of the vehicle in the simulation environment, the first device generates the simulation map based on the topological data and the electronic horizon data that has been obtained, and generates the simulation environment based on the simulation map; the vehicle drives in the simulation environment to obtain the vehicle position and the test data, the next electronic horizon data is obtained based on the obtained vehicle position, the simulation map is generated again based on the topological data and the next electronic horizon data, the simulation environment is generated based on the simulation map generated again, the vehicle drives in the simulation environment to obtain the vehicle position and the test data, and the above process is repeated until the simulation environment corresponding to the entire navigation path is generated, and the test of the vehicle in the simulation environment is completed.

[0078] In the embodiments of the present application, during the simulation test of the vehicle, the simulation test of the vehicle and the acquisition of new electronic horizon data are performed simultaneously, and then a larger range of simulation map can be generated to continue the simulation test of the vehicle, and the efficiency of the simulation test of the vehicle is further improved.

[0079] Optionally, the first device can further obtain at least one turning data from the navigation data, each turning data indicating a drivable direction of each lane in a second road, the second road being a road in the navigation path, the navigation data indicating that there is a turning behavior at a junction where the second road connects, in other words, the navigation data indicating that the vehicle needs to turn at the junction where the second road connects. Illustratively, each turning data can include identification information of the road segment to which the turning data corresponds and the drivable direction of each lane in the second road, for example, the drivable direction of a lane can include at least one of the following directions: straight, left turn, right turn, U-turn, or other directions, etc., which can be determined in combination with actual application scenarios.

[0080] In one case, the second device can send the turning data based on the vehicle position during the driving of the vehicle along the navigation path, for example, the second device can determine whether there is a turning behavior at a preset number of junctions to be passed by the vehicle in the future based on the vehicle position, if there is a turning behavior, the turning data is sent; if there is no turning behavior, the turning data is not sent; the preset number can be 1, 2, 3 or other values, etc., which can be determined in combination with actual application scenarios.

[0081] Optionally, similar to the above-mentioned obtaining method of the plurality of electronic horizon data, during the testing of the vehicle in the simulation environment, the first device generates the simulation environment, the vehicle position is sent to the second device during the driving of the vehicle in the generated simulation environment, the second device determines not only the electronic horizon data but also the turning data based on the vehicle position, the second device sends the electronic horizon data and the turning data to the first device to continue to generate a new simulation map, and generates a new simulation environment based on the new simulation map, and so on, until the simulation environment corresponding to the entire navigation path is generated, and the testing of the vehicle in the simulation environment is completed.

[0082] In another case, the second device can send all the turning data corresponding to the entire navigation path to the first device when sending the navigation data to the first device for the first time, and the navigation data obtained by the first device for the first time includes one or more turning data.

[0083] In another implementation, the first device can acquire the navigation data sent by the vehicle. Illustratively, the vehicle can send a navigation request to the second device, the navigation request being used to request the navigation data from the starting point to the ending point; correspondingly, the second device can receive the navigation request sent by the vehicle, and in response to the received navigation request, send the topological data corresponding to the navigation path and the electronic horizon data corresponding to the starting point (i.e., the initial position of the vehicle) to the vehicle; during the driving of the vehicle along the navigation path, the vehicle can send the current vehicle position to the second device, and the second device can send the electronic horizon data corresponding to the current vehicle position to the vehicle, and optionally, the second device can also send the steering data corresponding to the current vehicle position to the vehicle; the foregoing steps are repeated at least once until the vehicle drives to the ending point along the navigation path, and the vehicle acquires the navigation data corresponding to the entire navigation path; the vehicle can send the navigation data corresponding to the entire navigation path to the first device, and then the first device can acquire the navigation data corresponding to the entire navigation path; the navigation data corresponding to the entire navigation path includes the topological data corresponding to the navigation path, at least one electronic horizon data corresponding to the entire navigation path, and optionally, at least one steering data corresponding to the entire navigation path.

[0084] 302. generate a simulation map corresponding to the navigation path according to the topological data and the electronic horizon data.

[0085] Illustratively, the step 302 can include that the first device generates the simulation map corresponding to the navigation path according to the data of the road segments in the navigation path and the description information of the first road corresponding to the vehicle position (i.e., the first description information).

[0086] Optionally, if the electronic horizon data acquired by the first device from the navigation data further includes the second description information, the step 302 can include that the first device generates the simulation map corresponding to part of the road segments or all of the road segments in the navigation path according to the data of the road segments in the navigation path, the first description information of the first road corresponding to the vehicle position, and the second description information of the intersection corresponding to the first road.

[0087] In the embodiments of the present application, the second description information of the intersection connected with the road is also acquired from the navigation data, and then the simulation map corresponding to the navigation path is generated based on the data of the road segments in the navigation path included in the topological data, the description information of the road corresponding to the vehicle position, and the description information of the intersection, so that the intersection in the navigation path can be known in more details by means of the second description information, which is beneficial to further improve the restoration degree of the simulation map to the traffic environment, and the vehicle can drive in a more real simulation environment, which is beneficial to improve the accuracy when the vehicle is simulated and tested.

[0088] Optionally, if the first device further obtains turning data from the navigation data, the step 302 can comprise: the first device generates the simulation map according to the topology data, the electronic horizon data and the turning data; for example, the first device generates the simulation map corresponding to part or all of the road segments in the navigation path according to the data of the road segments in the navigation path, the first description information of the first road corresponding to the vehicle position and the drivable directions of each lane in the second road. In the embodiment of the application, the turning data is further obtained from the navigation data, which indicates the drivable directions of each lane in the second road, i.e., the turning data can provide lane-level description information, and with the turning data, the second road can be understood in more detail, which is beneficial to further improve the restoration degree of the simulation map to the traffic environment and improve the accuracy of the simulation test of the vehicle.

[0089] Further, in one case, if the electronic horizon data obtained in the step 301 includes the electronic horizon data corresponding to the position information of the starting point (i.e., the initial vehicle position), and the aforementioned electronic horizon data corresponds to the first road segment in the navigation path, the first device can generate the simulation map corresponding to the first road segment in the navigation path according to the topology data corresponding to the entire navigation path and the electronic horizon data (optionally, further including the turning data) corresponding to the first road segment in the navigation path, and further generate the simulation environment corresponding to the first road segment in the navigation path based on the simulation map corresponding to the first road segment in the navigation path; during the driving of the vehicle in the simulation environment, the step 301 can be entered again, the first device continues to obtain more electronic horizon data (optionally, further including the turning data), and then enters the step 302 again, the first device can continue to generate the simulation environment corresponding to the second road segment in the navigation path according to the topology data corresponding to the entire navigation path and the newly obtained electronic horizon data (optionally, further including the turning data), wherein the first road segment and the second road segment can be overlapping road segments or completely different road segments in the navigation path; the first device can alternately execute the steps 301 and 302 for multiple times until the simulation map corresponding to the entire navigation path is generated.

[0090] In another case, if the electronic horizon data obtained in the step 301 includes the electronic horizon data corresponding to the entire navigation path, the first device can generate the simulation map corresponding to the entire navigation path according to the topology data corresponding to the entire navigation path and the electronic horizon data (optionally, further including the turning data) corresponding to the entire navigation path, i.e., generate the simulation map corresponding to all road segments in the navigation path.

[0091] In the embodiments of the present application, the topology data in the navigation data has an overall understanding of the entire navigation path, the electronic horizon data includes the description information of the first road corresponding to the vehicle position, so that the electronic horizon data can have a more detailed understanding of the road on the navigation path, and the simulation map corresponding to the navigation path can be generated according to the topology data and the electronic horizon data, that is, a scheme for generating a simulation map corresponding to the navigation path based on navigation data is provided. Since the navigation data can be obtained based on the navigation service provided by the third party, it is not necessary to collect a complete high-precision map on the first road on site, which greatly improves the generation efficiency of the simulation map and reduces the generation cost of the simulation map. In addition, since the vehicle travels along a certain predetermined path in the simulation environment, even if a complete simulation map in the region is generated, the intelligent vehicle will only travel along a predetermined path in the simulation map, and therefore the simulation map corresponding to the position region outside the travel path of the vehicle will not be used, resulting in waste of the simulation map corresponding to the position region outside the travel path of the vehicle. In the present application, only the simulation map corresponding to the navigation path is generated, that is, only the simulation map corresponding to the position region that the intelligent vehicle will travel in the simulation test process is generated, which not only meets the demand of the simulation test of the intelligent vehicle, but also saves the resources wasted in the generation process of the simulation map corresponding to the position region that will not be used, further improving the efficiency of the simulation map generation process.

[0092] Optionally, based on the above-mentioned embodiment corresponding to FIG. 3, please refer to FIG. 6, which is another flowchart of the simulation map generation method provided by the embodiments of the present application. As shown in FIG. 6, the simulation map generation method provided by the present application can include:

[0093] 601, obtaining navigation data, the navigation data including topology data and electronic horizon data, the topology data including data of road segments in the navigation path, the electronic horizon data including first description information, the first description information being description information of a first road corresponding to a vehicle position, the vehicle position being a position in the navigation path.

[0094] Exemplarily, the specific implementation of the first device performing step 601 can refer to the description of step 301 in the above-mentioned embodiment corresponding to FIG. 3, and the specific meaning of the terms in step 601 can also refer to the description of step 301, which will not be repeated here.

[0095] 602, determining a first matching relationship, the first matching relationship indicating a matching relationship between at least one first description information and at least one first road segment.

[0096] In the embodiments of the present application, step 602 is an optional step. Illustratively, the above-mentioned topological data can include data of each first road segment in the at least one road segment (hereinafter referred to as "first road segment" for convenience of description) in the navigation path, and the electronic horizon data includes at least one first description information, each first description information including description information of a first road.

[0097] The first matching relationship indicates a matching relationship between the at least one first description information and the at least one first road segment, in other words, the first matching relationship indicates which first road segment each first description information in the at least one first description information is matched with, i.e., which first road segment each first description information is the description information of, so that the first description information can be fused with the data of the first road segment, and further the fused data can be used to generate a simulation map corresponding to the first road segment.

[0098] Optionally, in an implementation, step 602 can include: determining, by the first device, the first matching relationship according to a length of each first road segment in the at least one first road segment and a length of each first road in the at least one first road. The length of the first road can be obtained based on the first description information, and the specific obtaining manner can refer to the description of step 301 in the corresponding embodiment of FIG. 3, which will not be repeated here.

[0099] Illustratively, after obtaining the length of each first road segment and the length of each first road, the first device can form a first sequence with the length of each first road segment in the at least one first road segment, form a second sequence with the length of each first road in the at least one first road, model a longest common subsequence matching problem based on the first numerical sequence and the second numerical sequence, solve the above-mentioned longest common subsequence matching problem, and obtain the longest common subsequence; for example, the dynamic programming (DP) algorithm, the sequence matching algorithm or other algorithms can be used to solve the above-mentioned longest common subsequence matching problem.

[0100] The lengths included in the longest common subsequence exist in both the first sequence and the second sequence, and the order between the lengths in the longest common subsequence is consistent with the order between the lengths in the first sequence and the order between the lengths in the second sequence. The first road and the first road segment with the same length determined based on the longest common subsequence are considered to have a matching relationship. For example, if the electronic horizon data includes description information of the first road 1, the first road 2 and the first road 3, the lengths of the first road 1, the first road 2 and the first road 3 are 187, 74 and 40 in turn; if the topological data includes data of the first road segment 1, the first road segment 2, the first road segment 3, the first road segment 4, the first road segment 5 and the first road segment 6, the lengths of the first road segment 1, the first road segment 2, the first road segment 3, the first road segment 4, the first road segment 5 and the first road segment 6 are 51, 187, 74, 40, 52 and 78 in turn, the longest common subsequence is 187, 74 and 40, the first road 1 with the length of 187 and the first road segment 2 have a matching relationship, the first road 2 with the length of 74 and the first road segment 3 have a matching relationship, and the first road 3 with the length of 40 and the first road segment 4 have a matching relationship. It should be understood that the example herein is only for the convenience of understanding the present solution, and is not used to limit the present solution.

[0101] For a more intuitive understanding of the present solution, please refer to FIG. 7, which is a schematic diagram provided by an embodiment of the present application for matching the first sequence and the second sequence to obtain the longest common subsequence. As shown in FIG. 7, the horizontal axis represents the first sequence, i.e., the lengths of the plurality of road segments included in the navigation path, and the vertical axis represents the second sequence, i.e., the lengths of the plurality of first roads corresponding to the vehicle position. As shown in FIG. 7, the lengths included in the first sequence are 31, 187, 53, 74, 40, 52, 75 and 26 in turn, and the lengths included in the second sequence are 77, 187, 63, 74 and 40 in turn. The longest common subsequence of the first sequence and the second sequence includes three lengths, and the longest common subsequence is 187, 74 and 40. It should be understood that the example in FIG. 7 is only for the convenience of understanding the present solution, and is not used to limit the present solution.

[0102] If the longest common subsequence indicates the matching relationship between all the first roads and the first road segments in the electronic horizon data, the first device can directly determine the first matching relationship according to the longest common subsequence; refer to the above example, the electronic horizon data includes the description information of the first road 1, the first road 2 and the first road 3, the lengths of the first road 1, the first road 2 and the first road 3 are 187, 74 and 40 in turn; the longest common subsequence is 187, 74 and 40, the longest common sequence indicates that the first road 1 with the length of 187 has a matching relationship with the first road segment 2, the first road 2 with the length of 74 has a matching relationship with the first road segment 3, and the first road 3 with the length of 40 has a matching relationship with the first road segment 4, since the matching relationship between all the first roads and the first road segments in the electronic horizon data has been determined, it can be determined that the first matching relationship includes that the first road 1 has a matching relationship with the first road segment 2, the first road 2 has a matching relationship with the first road segment 3, and the first road 3 has a matching relationship with the first road segment 4, it should be understood that the example here is only for the convenience of understanding the scheme and is not used to limit the scheme.

[0103] If the longest common subsequence indicates the matching relationship between part of the first roads and the first road segments in the electronic horizon data, the first device can determine a first sub-matching relationship according to the longest common subsequence, the first sub-matching relationship includes the matching relationship between the first roads and the first road segments with the same length indicated by the longest common subsequence; the first device can determine a second sub-matching relationship by using a fuzzy matching algorithm based on the length of the first road that has not been matched and the length of the first road segment that has not been matched. Exemplarily, there can be one-to-one matching relationship, many-to-many matching relationship, one-to-many matching relationship or many-to-one matching relationship in the second sub-matching relationship, which can be determined in combination with actual application scenarios, which is not limited here.

[0104] Optionally, the first device can determine a second sub-matching relationship by using a fuzzy matching algorithm based on the length of the first road that has not been matched, the length of the first road segment that has not been matched, the number of the first road that has not been matched and the number of the first road segment that has not been matched, and the first matching relationship includes the first sub-matching relationship and the second sub-matching relationship.

[0105] Exemplarily, if the electronic horizon data includes the first description information of the first road 1 to the first road 9, the lengths of the first road 1 to the first road 10 are 77, 187, 53, 63, 74, 40, 69, 51, 24 and 26 in sequence, and the topology data includes the data of the first road section 1 to the first road section 11, the lengths of the first road section 1 to the first road section 11 are 31, 187, 53, 74, 40, 52, 75, 26, 32, 83 and 56 in sequence. The longest common subsequence is 187, 53, 74, 40 and 26, and the first sub-matching relationship indicated by the longest common subsequence includes that the first road 2 and the first road section 2 have a matching relationship, the first road 3 and the first road section 3 have a matching relationship, the first road 5 and the first road section 4 have a matching relationship, the first road 6 and the first road section 5 have a matching relationship, and the first road 10 and the first road section 8 have a matching relationship. There are five first roads that have not been matched, and the lengths of the five first roads that have not been matched are 77, 63, 69, 51 and 24 in sequence. There are seven first road sections that have not been matched, and the lengths of the seven first road sections that have not been matched are 31, 52, 75, 32, 83 and 56 in sequence. The second sub-matching relationship obtained by using the fuzzy matching algorithm includes that the first road 7 and the first road 8 and the first road section 7 have a matching relationship. Therefore, the first matching relationship includes that the first road 2 and the first road section 2 have a matching relationship, the first road 3 and the first road section 3 have a matching relationship, the first road 5 and the first road section 4 have a matching relationship, the first road 6 and the first road section 5 have a matching relationship, the first road 7 and the first road 8 and the first road section 7 have a matching relationship, and the first road 10 and the first road section 8 have a matching relationship. It should be understood that the example herein is only for facilitating understanding of the scheme and is not used to limit the scheme.

[0106] In the embodiment of the application, the matching relationship between the at least one first road and the at least one first road section is determined based on the length of each first road section and the length of each first road, so that a simple scheme for determining the first matching relationship is provided, and the reliability of determining the first matching relationship by means of the lengths of the road sections and the roads is high, that is, a simple and accurate scheme is provided.

[0107] In another implementation manner, the first device can input the data of each first road section included in the topology data and each first description information in the at least one first description information into the first machine learning model to obtain first indication information output by the first machine learning model, and the first indication information is used to indicate the first matching relationship.

[0108] Optionally, if the electronic horizon data obtained by the first device from the navigation data further comprises at least one second description information, the first device can further determine a matching relationship between the at least one second description information and the data of the at least one first road segment.

[0109] Optionally, in an implementation, the first device can determine a third matching relationship between the at least one second description information and the at least one first description information, i.e., determine which first road the intersection described by each of the at least one second description information is connected to, so as to be able to fuse each of the at least one second description information with the corresponding first description information; for example, if the electronic horizon data comprises the first description information 1 of the first road 1, the first description information 2 of the first road 2, and the first description information 3 of the first road 3, and the electronic horizon data further comprises the second description information 1 of the intersection 1, the intersection 1 is connected to the first road 1, i.e., the second description information 1 corresponds to the first description information 1, then the second description information 1 can be fused with the first description information 1, and it should be understood that the example is only for the convenience of understanding the present solution and is not used to limit the present solution.

[0110] The first device can determine a matching relationship between each of the at least one second description information and the at least one first description information based on the first matching relationship and the third matching relationship, i.e., determine which first road segment the intersection described by each of the at least one second description information is connected to, so as to be able to fuse the second description information with the data of the first road segment, and further be able to generate a simulation map corresponding to the intersection connected to the first road segment by using the fused data.

[0111] Alternatively, in another implementation, the first device can input the data of each of the first road segments included in the topological data and each of the at least one second description information into a second machine learning model, obtain second indication information output by the second machine learning model, and the second indication information is used to indicate a matching relationship between the at least one second description information and the data of the at least one first road segment.

[0112] For a more intuitive understanding of the scheme, please refer to FIG. 8, which is a flowchart for determining the first matching relationship provided by an embodiment of the present application. As shown in FIG. 8, after the first device obtains the topological data corresponding to the navigation path, the first description information and the second description information included in the electronic horizon data from the navigation data, the first device can first fuse each second description information with the corresponding first description information to obtain the semantic data corresponding to the road and the intersection as shown in FIG. 8; then the first device can match the first road and the first road segment according to the length of each first road segment and the length of each first road to obtain the first matching sub-relationship; and then match the first road that has not been matched and the first road segment that has not been matched based on the length of the first road that has not been matched and the length of the first road segment that has not been matched to obtain the second matching sub-relationship, and then fuse each first description information and second description information with the data of the corresponding first road segment. It should be understood that the example in FIG. 8 is only for the convenience of understanding the scheme and does not limit the scheme.

[0113] 603, determining a second matching relationship, the second matching relationship indicating a matching relationship between the turning data and at least one first road segment.

[0114] In the embodiment of the present application, step 603 is an optional step. If the first device also obtains the turning data from the navigation data, the first device can also determine a second matching relationship between each turning data and the data of at least one first road segment, which indicates which first road segment each turning data describes the drivable direction of each lane in the first road segment, so that the turning data and the data of the first road segment can be fused, and then the simulation map corresponding to the first road segment can be generated using the fused data.

[0115] For example, the first device can match the identification information of the road segment included in each turning data with the identification information of each first road segment included in the topological data to determine which first road segment each turning data describes the drivable direction of each lane in the first road segment.

[0116] 604, generating a simulation map corresponding to the navigation path according to the topological data and the electronic horizon data.

[0117] The specific implementation of the first device performing step 604 can be understood in combination with the description of step 302 in the above-mentioned corresponding embodiment of FIG. 3, and the specific meaning of the terms in step 604 can also be referred to the description of step 302 above, and the repeated parts will not be described here.

[0118] Optionally, if step 602 is performed, step 604 can include: the first device generating the simulation map corresponding to the part of the navigation path or the whole navigation path according to the topological data, the first description information (optionally, the second description information is also included) and the first matching relationship. In the embodiment of the application, the matching relationship between the at least one first description information and the at least one first road segment is determined, so that it is determined which road segment the description information of the road included in the electronic horizon data corresponds to, the fineness of the whole process of generating the simulation map is improved, which is conducive to reducing the difficulty of the link of generating the simulation map, and is conducive to generating the simulation map more similar to the real road environment.

[0119] Optionally, if steps 602 and 603 are performed, step 604 can include: the first device generating the simulation map according to the topological data, the first description information (optionally, the second description information is also included), the turning data, the first matching relationship and the second matching relationship. In the embodiment of the application, the matching relationship between the turning data and the at least one first road segment is also determined, so that it is determined which road segment each turning data describes the drivable direction of the lane, which is conducive to further improving the fineness of the whole process of generating the simulation map, so as to further reduce the difficulty of the link of generating the simulation map, and then conducive to generating the simulation map more similar to the real road environment.

[0120] Optionally, the simulation map includes first map elements, the first map elements are generated according to the electronic horizon data and a preset rule, or the first map elements are generated according to the electronic horizon data through a machine learning model; wherein the description information of the first map elements does not exist in the navigation data, for example, the first map elements can be the shape of the intersection connected with the road segment, the stop line of the road connected with the intersection, the lane line in the intersection, the connection relationship of the lane line in the intersection, the direction of the part of the road connected with the intersection, the width of the road or other types of map elements, etc., for example, the aforementioned part of the road can be the road which does not need to be driven by the vehicle in the navigation path, and it needs to be noted that which first map elements are specifically included can be determined in combination with the actual application scenario.

[0121] In the embodiment of the application, the first map elements in the simulation map are generated based on the preset rule or the machine learning model, and the description information of the first map elements does not exist in the navigation data, that is, the first map elements are generated based on the preset rule or the machine learning model, so that the generated first map elements have diversity, so that under the premise that the generated simulation map meets the real road network as much as possible, a more diversified road network structure can be generated, so that the vehicle can encounter more diverse simulation maps in the simulation test stage, which is conducive to increasing the difficulty of the vehicle in the simulation test process, so that the safety of the vehicle tested on the real road is higher.

[0122] Exemplarily, in an implementation manner, preset rules corresponding to each of a plurality of types of road elements can be deployed in the first device, for example, the plurality of types of map elements can include: ordinary road segments, NN road segments, intersections, ramps, roundabouts, or other types of map elements, etc., which can be determined in combination with actual application scenarios, and this place does not make an exhaustive enumeration, wherein the NN road segment refers to a road segment whose number of lanes changes. Then, the first device can generate a simulation map corresponding to each first road segment according to the data of the first road segment in the navigation path included in the topological data, the at least one first description information included in the electronic horizon data, and the preset rules, that is, generate a simulation map corresponding to part or all of the road segments in the navigation path.

[0123] Exemplarily, after the first device obtains the first matching relationship, the first device can determine which first description information and which first road segment have a matching relationship based on the first matching relationship, so as to be able to fuse the first description information (optionally, also including the second description information bound with the first description information) with the data of the corresponding first road segment, to obtain the fused data of at least one first road segment, the fused data of the first road segment including the data of the first road segment and the first description information (optionally, also including the second description information), wherein the first description information includes the description information of the road, and the second description information includes the description information of the intersection connected with the road.

[0124] Optionally, the first device can also determine which turning data and which first road segment have a matching relationship based on the second matching relationship, so as to be able to fuse the turning data with the data of the corresponding first road segment, to obtain the fused data of the aforementioned first road segment, the fused data of the aforementioned first road segment further including the turning data, the turning data including the drivable direction of each lane in the road where the turning behavior exists.

[0125] The first device can generate a simulation map corresponding to each first road segment and the intersection connected with the road segment according to the fused data of each first road segment and the preset rules, that is, generate a simulation map corresponding to part or all of the road segments in the navigation path.

[0126] Exemplarily, the following introduces the generation process of generating a simulation map corresponding to an intersection based on preset rules in combination with an actual example. The first device can determine that the intersection is a four-way intersection according to the intersection attribute in the second description information, and then model each intersection in the four-way intersection: the distance from the stop line of the intersection road to the center point of the intersection The included angle between the intersection road and the road entering the intersection The distance between the center line of each branch road connected with the intersection and the road boundary on both sides And

[0127] In the process of generating the simulation map corresponding to the intersection, the map elements involved in the intersection can include: intersection shape, stop line of each branch road connected by the intersection, lane line in the intersection, and continuity of lane line in the intersection. Typically, the first device can determine the included angle between each branch road and the approach road at the intersection according to the angle corresponding to each branch road connected by the intersection in the second description information The first device can store a large number of distances from the stop line of the approach road to the center point of the intersection, and randomly sample one distance from the large number of distances as the distance from the stop line of the approach road to the center point of the intersection in the quad intersection The randomly sampled distance is also used as the distance from the stop line of each road in the quad intersection to the center point of the intersection, and each road is truncated according to the distance. The first device can determine the distance between the center line of each branch road connected by the intersection and the road boundary on both sides according to the first description information And Thus, the width of each branch road can be determined. After the width of each branch road is determined, the end points of each branch road can be connected to obtain the shape of the branch intersection. The first device can determine the drivable direction of each lane in the approach road according to the turning data, and then determine the continuity of the lane line in the intersection based on the drivable direction of each lane in the approach road. The first device can generate the shape of the intersection, and generate the lane line in the intersection according to the drivable direction of each lane in the approach road and the continuity of the lane line in the intersection.

[0128] Optionally, if the first device also obtains the position information of the traffic signal at the intersection from the navigation data, it can also determine whether there is a traffic signal at the intersection based on the obtained position information of the traffic signal at the intersection.

[0129] For a more intuitive understanding of the scheme, please refer to FIG. 9, which is a flowchart provided by an embodiment of the present application for generating a simulation map corresponding to an intersection. FIG. 9 demonstrates the process of generating a simulation map corresponding to an intersection in the form of a line graph. FIG. 9 includes three sub-diagrams: left, middle, and right. First, refer to the left sub-diagram of FIG. 9. The first device can determine the included angle between each branch road and the approach road at the intersection based on the angle corresponding to each branch road connected to the intersection in the second description information, thereby modeling the direction of each branch road at the intersection. Then, the first device can determine the distance between the stop line of each branch road and the center point of the intersection, and truncate each road based on the aforementioned distance. The truncated diagram is shown in the middle sub-diagram of FIG. 9. The first device can also determine the width of each branch road, and then determine the shape of the branch road. The lane lines and their continuity within the branch road are reconstructed to obtain a simulation map corresponding to the intersection. The simulation map corresponding to the intersection is shown in the right sub-diagram of FIG. 9. It should be understood that the examples in FIG. 9 are only for the convenience of understanding the scheme and do not limit the scheme.

[0130] Please continue to refer to FIG. 10, which is a schematic diagram of a simulation map corresponding to an intersection provided by an embodiment of the present application. As shown in FIG. 10, the intersection is a four-way intersection. The simulation map corresponding to the intersection includes the stop lines of the four roads connected to the intersection, the shape of the intersection, the lane lines within the intersection connected to the approach road, and the continuity of the lane lines within the intersection connected to the approach road. It should be understood that the examples in FIG. 10 are only for the convenience of understanding the scheme and do not limit the scheme.

[0131] In another implementation manner, after obtaining the data of the first road segment in the navigation path included in the topological data and the electronic horizon data, the first device can further generate a simulation map corresponding to part or all of the road segments in the navigation path through a third machine learning model.

[0132] For example, the first device can input the data of the first road segment in the navigation path included in the topological data and the first description information (optionally, the second description information is also included) included in the electronic horizon data into the third machine learning model, and generate a simulation map corresponding to part or all of the road segments in the navigation path based on the information output by the third machine learning model.

[0133] For example, the third machine learning model can be a convolutional neural network, a fully connected neural network, a neural network based on an attention mechanism, a support vector machine, or other types of machine learning models, etc.; optionally, the third machine learning model can adopt a generative model (Diffusion Model), for example, the third machine learning model can be a variational auto encoder (VAE), a flow-based generative model, or other types of machine learning models, etc., which are not exhaustively listed here.

[0134] Optionally, the first device can generate graph structure data based on the data obtained from the navigation data, the graph structure data including nodes and edges, the nodes being used to store data of intersections, the edges being used to store data of road segments, and the connections between the nodes and the edges in the graph structure reflecting the connection relationship between the road segments and the intersections; for example, the data stored in the nodes can include intersection attributes, angle information of branch roads connected by the intersection, and position information of traffic lights at the intersection; the data stored in the edges can include the shape of the road segment, the speed limit, the number of lanes in each direction, and the width of the lane; optionally, the data stored in the edges can also include the drivable direction of part of the lane. The first device can input the graph structure data into the third machine learning model to obtain the parameter information generated by the third machine learning model; and the first device can generate a simulation map corresponding to part or all of the road segments in the navigation path according to the data obtained from the navigation data and the parameter information generated by the third machine learning model.

[0135] For example, the parameter information can include first parameter information related to roads and second parameter information related to intersections; the first parameter information can indicate at least one of the following: road width, lane shape, lane line type, lane line continuity relationship, or other information, etc., for example, the lane line type can include a dashed line, a solid line, a double solid line, or other types, etc., which are not exhaustively listed here; the second parameter information can indicate at least one of the following: intersection shape, stop line of each branch road connected by the intersection, pedestrian crosswalk line at the intersection, dashed and solid line at the intersection, static obstacle in the intersection, or other information, etc., which can be determined in combination with actual application scenarios.

[0136] For the generation process of the above graph structure data, exemplarily, the first device can determine the edges, nodes and connection relationships between different edges included in the graph structure data based on the data of all road segments in the navigation path included in the topology data, to obtain an initialized graph structure; the first device can determine which first description information and which first road segment have a matching relationship according to the first matching relationship, so as to be able to fuse the first description information and the data of the corresponding first road segment, and then put the foregoing first description information and the data of the corresponding first road segment into the edge; optionally, since in step 602, the first device also determines that the description information of the intersection included in each second description information is matched with the data of which first road segment, the first device can also put the second description information into the node; optionally, the first device can also store the turning data into the corresponding edge based on the second matching relationship, the turning data including the drivable directions of each lane in the road where the turning behavior exists, to obtain the graph structure data.

[0137] In order to more intuitively understand the scheme, please refer to FIG. 11, which is a schematic diagram of generating a simulation map by using a machine learning model provided by an embodiment of the present application, as shown in FIG. 11, the first device can input the graph structure data obtained by converting the data acquired from the navigation data into the third machine learning model, and take the third machine learning model including an encoder and a decoder as an example in FIG. 11, and then generate a simulation map corresponding to part or all of the road segments in the navigation path based on the information output by the third machine learning model. It should be understood that the example in FIG. 11 is only for the convenience of understanding the scheme, and is not used to limit the scheme.

[0138] Optionally, the first device can also input the data of the first road segment in the navigation path included in the topology data, the first description information (optionally, the second description information is also included) included in the electronic horizon data, and the first matching relationship into the third machine learning model, to obtain a simulation map corresponding to part or all of the road segments in the navigation path generated by the third machine learning model.

[0139] Optionally, the first device can also input the data of the first road segment in the navigation path included in the topology data, the first description information (optionally, the second description information is also included) included in the electronic horizon data, the first matching relationship, the turning data and the second matching relationship into the third machine learning model, to obtain a simulation map corresponding to part or all of the road segments in the navigation path generated by the third machine learning model.

[0140] Exemplarily, if the electronic horizon data acquired by the first device each time corresponds to only part of the road segments in the navigation path, after acquiring new electronic horizon data each time, in one case, the first device can generate a simulation map corresponding to the newly acquired electronic horizon data based on the data of all the road segments in the navigation path included in the topological data and the newly acquired electronic horizon data, that is, generate a simulation map corresponding to the new road segments in the navigation path.

[0141] In another case, after acquiring new electronic horizon data each time, the first device can regenerate the simulation map based on the data of all the road segments in the navigation path included in the topological data and all the electronic horizon data that has been acquired, and then part of the map elements or all the map elements in the simulation map that has been generated can be refreshed, in other words, the simulation map that has been generated can be refreshed.

[0142] Optionally, when the simulation map is refreshed, the simulation map within the perception range of the current position of the vehicle is not refreshed, and the simulation map outside the perception range of the current position of the vehicle is refreshed, thereby ensuring the stability of the map during the vehicle test.

[0143] Exemplarily, the size of the perception range of the current position of the vehicle can be preset, for example, the perception range of the current position of the vehicle can be 100 meters, 150 meters or other range sizes around the current position of the vehicle, etc.; or the size of the perception range of the current position of the vehicle can also be the actual perception range of the vehicle, etc., which can be determined in combination with actual application scenarios.

[0144] Optionally, after the first device generates the simulation map corresponding to part of the road segments or all the road segments in the navigation path, the first device can add the generated simulation map to the shared memory / resource pool of the simulator for calling by the simulator; when the simulator performs simulation test on the vehicle by using the simulation map, the simulation map can be called.

[0145] Optionally, the first device can also generate a simulation test scene based on the simulation map, for example, the first device takes the simulation map as a base map, adds dynamic and / or static obstacles in the simulation map to simulate the obstacles in the traffic environment, thereby obtaining the simulation test scene; when the vehicle runs in the simulation test scene, the intelligent driving system in the vehicle controls the vehicle to travel, which can update the state information of the ego vehicle, and the vehicle can interact with the dynamic and / or static obstacles in the simulation test scene to achieve the simulation test on the vehicle.

[0146] Based on the embodiments corresponding to FIG. 1 to FIG. 11, in order to better implement the above scheme of the embodiments of the present application, the following further provides related equipment for implementing the above scheme. Referring to FIG. 12, FIG. 12 is a structural schematic diagram of a simulation map generation apparatus provided by the embodiments of the present application, the simulation map generation apparatus 1200 comprises: an acquisition module 1201 configured to acquire navigation data, the navigation data comprising topology data and electronic horizon data EHP, the topology data comprising data of road segments in a navigation path, the electronic horizon data comprising first description information, the first description information being description information of a first road corresponding to a vehicle position, the vehicle position being a position in the navigation path; and a generation module 1202 configured to generate a simulation map corresponding to the navigation path according to the topology data and the electronic horizon data.

[0147] Optionally, the electronic horizon data further comprises second description information, the second description information being description information of an intersection corresponding to the first road.

[0148] Optionally, the navigation data further comprises turning data, the turning data indicating drivable directions of each lane in a second road, the second road being a road in the navigation path, the navigation data indicating that the vehicle has a turning behavior at an intersection connected by the second road; and the generation module 1202 is specifically configured to generate the simulation map according to the topology data, the electronic horizon data and the turning data.

[0149] Optionally, the topology data comprises data of each first road segment in at least one first road segment in the navigation path, and the electronic horizon data comprises at least one first description information; the simulation map generation apparatus 1200 further comprises a determination module 1203 configured to determine a first matching relationship, the first matching relationship indicating a matching relationship between the at least one first description information and the at least one first road segment; and the generation module 1202 is specifically configured to generate the simulation map according to the topology data, the first description information and the first matching relationship.

[0150] Optionally, the navigation data further comprises turning data, the turning data indicating drivable directions of each lane in a second road, the second road being a road in the navigation path, the vehicle having a turning behavior at an intersection connected by the second road; and the simulation map generation apparatus 1200 further comprises a determination module 1203 configured to determine a second matching relationship, the second matching relationship indicating a matching relationship between the turning data and the at least one first road segment; and the generation module 1202 is specifically configured to generate the simulation map according to the topology data, the first description information, the turning data, the first matching relationship and the second matching relationship.

[0151] Optionally, the determination module 1203 is specifically configured to determine the first matching relationship according to a length of the first road segment and a length of the first road, the length of the first road being obtained based on the first description information.

[0152] Optionally, the simulation map comprises a first map element, the first map element is generated according to the electronic horizon data and a preset rule, or the first map element is generated according to the electronic horizon data by a machine learning model; and description information of the first map element does not exist in the navigation data.

[0153] It should be noted that the information interaction and execution process between the modules / units in the simulation map generation apparatus 1200 are based on the same concept as the corresponding method embodiments of FIGS. 1 to 11 of the present application, and the specific content can be referred to the description of the method embodiments in the foregoing description of the present application, which will not be repeated here.

[0154] The present application also provides a device, as shown in FIG. 13, which is a structural schematic diagram of the device provided by the embodiments of the present application. Optionally, the device 1300 performs the functions of the first device in the corresponding method embodiments of FIGS. 1 to 11.

[0155] The device 1300 comprises a memory 1302 and at least one processor 1301. Optionally, the processor 1301 realizes the method in the above embodiments by reading the instructions saved in the memory 1302, or the processor 1301 can also realize the method in the above embodiments by internally stored instructions. In the case where the processor 1301 realizes the method in the above embodiments by reading the instructions saved in the memory 1302, the memory 1302 saves the instructions for realizing the method provided by the above embodiments of the present application.

[0156] Optionally, the at least one processor 1301 is one or more CPUs, or a single core CPU, or a multi-core CPU. The memory 1302 includes but is not limited to a random access memory (RAM), a read-only memory (ROM), a flash memory, or an optical memory, etc. The memory 1302 saves instructions of an operating system. After the program instructions stored in the memory 1302 are read by the at least one processor 1301, the device 1300 performs the corresponding operations in the foregoing embodiments.

[0157] Optionally, the device 1300 further comprises a network interface 1303, which can be a wired interface or a wireless interface, and the network interface 1303 is used for transmitting and receiving data in the corresponding method embodiments of FIGS. 1 to 11.

[0158] It should be understood that the network interface 1303 has the function of receiving data and the function of sending data, and the function of receiving data and the function of sending data can be integrated in the same transceiver interface, or the function of receiving data and the function of sending data can be implemented in different interfaces respectively, which is not limited here. In other words, the network interface 1303 can include one or more interfaces for implementing the function of receiving data and the function of sending data.

[0159] After the processor 1301 reads the program instructions in the memory 1302, the device 1300 can perform other functions described in the foregoing method embodiments.

[0160] Optionally, the device 1300 further includes a bus 1304, and the above processor 1301 and memory 1302 are usually connected with each other through the bus 1304, and other connection modes can also be used.

[0161] The device 1300 provided by the embodiments of the present application is used to execute the method executed by the first device in the foregoing method embodiments, and realizes the corresponding beneficial effects. The specific implementation modes of the device 1300 shown in FIG. 13 can all refer to the descriptions in the foregoing method embodiments, which will not be repeated here.

[0162] In the embodiments of the present application, a computer readable storage medium is also provided, and the computer readable storage medium stores a program, and when the program runs on a computer, the computer executes the steps executed by the first device in the method described in the foregoing embodiments shown in FIG. 1 to FIG. 11.

[0163] In the embodiments of the present application, a computer program product is also provided, and the computer program product includes a program, and when the program runs on a computer, the computer executes the steps executed by the first device in the method described in the foregoing embodiments shown in FIG. 1 to FIG. 11.

[0164] In the embodiments of the present application, a circuit system is also provided, and the circuit system includes processing circuitry, and the processing circuitry is configured to execute the steps executed by the first device in the method described in the foregoing embodiments shown in FIG. 1 to FIG. 11.

[0165] The device provided by the embodiments of the present application can be a chip. The chip includes a processing unit, for example, a processor, and a communication unit, for example, an input / output interface, a pin, or a circuit, etc. The processing unit can execute computer execution instructions stored in a storage unit, so that the chip executes the method described in the embodiments shown in FIG. 1 to FIG. 11. Optionally, the storage unit is a storage unit in the chip, such as a register, a cache, etc. The storage unit can also be a storage unit outside the chip in the wireless access device, such as a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM), etc.

[0166] In addition, it should be noted that the apparatus embodiments described above are merely illustrative, and the units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on multiple network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the embodiments of the present application. In addition, in the apparatus embodiments provided by the present application, the connection relationship between the modules indicates that there is a communication connection between them, which can be implemented as one or more communication buses or signal lines.

[0167] Through the description of the above embodiments, those skilled in the art can clearly understand that the present application can be implemented by means of software and necessary general hardware, and of course, it can also be implemented by special hardware including special integrated circuits, special CLUs, special memories, special components, etc. Generally, functions completed by computer programs can be easily implemented by corresponding hardware, and the specific hardware structure for implementing the same function can also be various, such as analog circuits, digital circuits, or special circuits, etc. However, for the present application, software program implementation is a better embodiment. Based on this understanding, the technical solutions of the present application can be embodied in the form of a software product, which is stored in a readable storage medium, such as a computer's floppy disk, U disk, mobile hard disk, ROM, RAM, magnetic disk or optical disk, etc., including a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods described in the embodiments of the present application.

[0168] In the above embodiments, all or part can be implemented by software, hardware, firmware, or any combination thereof. When implemented by software, it can be implemented in the form of a computer program product in whole or in part.

[0169] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another, for example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center through wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) mode. The computer-readable storage medium can be any available medium that a computer can store or a data storage device such as a server, data center, etc. integrated with one or more available media. The available media can be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, a solid state disk (SSD)), etc.

Claims

1. A method of generating a simulation map, characterized by, The method comprises: obtaining navigation data, the navigation data comprising topological data and electronic horizon data EHP, the topological data comprising data of road segments in a navigation path, the electronic horizon data comprising first description information, the first description information being description information of a first road corresponding to a vehicle position, the vehicle position being a position in the navigation path; generating a simulation map corresponding to the navigation path according to the topological data and the electronic horizon data.

2. The method of claim 1, wherein, The electronic horizon data further comprises second description information, the second description information being description information of an intersection corresponding to the first road.

3. The method according to claim 1 or 2, characterized in that, The navigation data further comprises turning data, the turning data indicating drivable directions of each lane in a second road, the second road being a road in the navigation path, the navigation data indicating that there is a turning behavior of a vehicle at an intersection to which the second road connects, and the generating of the simulation map corresponding to the navigation path according to the topological data and the electronic horizon data comprises: generating the simulation map according to the topological data, the electronic horizon data and the turning data.

4. The method according to claim 1 or 2, characterized in that, The topological data comprises data of each of at least one first road segment in the navigation path, and the electronic horizon data comprises at least one first description information; The method further comprises determining a first matching relationship, the first matching relationship indicating a matching relationship between the at least one first description information and the at least one first road segment; The generating of the simulation map corresponding to the navigation path according to the topological data and the electronic horizon data comprises generating the simulation map according to the topological data, the first description information and the first matching relationship.

5. The method of claim 4, wherein, The navigation data further comprises turning data, the turning data indicating drivable directions of each lane in a second road, the second road being a road in the navigation path, and there being a turning behavior of a vehicle at an intersection to which the second road connects; The method further comprises determining a second matching relationship, the second matching relationship indicating a matching relationship between the turning data and the at least one first road segment; The generating of the simulation map according to the topological data, the first description information and the first matching relationship comprises generating the simulation map according to the topological data, the first description information, the turning data, the first matching relationship and the second matching relationship.

6. The method of claim 4, wherein, The determining of the first matching relationship comprises: determining the first matching relationship according to a length of the first road segment and a length of the first road, the length of the first road being obtained based on the first description information.

7. The method according to claim 1 or 2, characterized in that, The simulation map comprises a first map element, the first map element being generated according to the electronic horizon data and a preset rule, or the first map element being generated according to the electronic horizon data by a machine learning model; and description information of the first map element is not present in the navigation data.

8. An apparatus for generating a simulation map, characterized by comprising: The device comprises: The acquisition module is configured to acquire navigation data, the navigation data comprising topological data and electronic horizon data (EHP), the topological data comprising data of road segments in a navigation path, and the electronic horizon data comprising first description information, the first description information being description information of a first road corresponding to a vehicle position in the navigation path; The generation module is configured to generate a simulation map corresponding to the navigation path according to the topological data and the electronic horizon data.

9. The apparatus of claim 8, wherein, The electronic horizon data further comprises second description information, the second description information being description information of an intersection corresponding to the first road.

10. The apparatus of claim 8 or 9, wherein, The navigation data further comprises turning data, the turning data indicating drivable directions of each lane in a second road, the second road being a road in the navigation path, and the navigation data indicating that a vehicle has a turning behavior at an intersection where the second road connects; The generation module is specifically configured to generate the simulation map according to the topological data, the electronic horizon data, and the turning data.

11. The apparatus of claim 8 or 9, wherein, The topological data comprises data of each of at least one first road segment in the navigation path, and the electronic horizon data comprises at least one first description information. The device further comprises a determination module configured to determine a first matching relationship, the first matching relationship indicating a matching relationship between the at least one first description information and the at least one first road segment. The generation module is specifically configured to generate the simulation map according to the topological data, the first description information, and the first matching relationship.

12. The apparatus of claim 11, wherein, The navigation data further comprises turning data, the turning data indicating drivable directions of each lane in a second road, the second road being a road in the navigation path, and a vehicle having a turning behavior at an intersection where the second road connects; The device further comprises a determination module configured to determine a second matching relationship, the second matching relationship indicating a matching relationship between the turning data and the at least one first road segment. The generation module is specifically configured to generate the simulation map according to the topological data, the first description information, the turning data, the first matching relationship, and the second matching relationship.

13. The apparatus of claim 11, wherein, The determination module is specifically configured to determine the first matching relationship according to a length of the first road segment and a length of the first road, the length of the first road being obtained based on the first description information.

14. The apparatus of claim 8 or 9, wherein, The simulation map comprises a first map element, the first map element being generated according to the electronic horizon data and a preset rule, or the first map element being generated according to the electronic horizon data by using a machine learning model; and description information of the first map element is not present in the navigation data.

15. An apparatus, comprising: The device comprises a processor and a memory, the processor and the memory being coupled, and the memory storing program instructions, which, when executed by the processor, implement the method in any one of claims 1 to 7. The device comprises a processor and a memory, the processor and the memory being coupled, and the memory storing program instructions, which, when executed by the processor, implement the method in any one of claims 1 to 7.

16. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a program, and when the program runs on the computer, the computer executes the method in any one of claims 1 to 7.

17. A computer program product, characterised in that, The computer program product comprises a program, and when the program runs on the computer, the computer executes the method in any one of claims 1 to 7.

Images