Simulation high-precision map generation method, device and computer-readable storage medium

Abstract

A method, device and computer-readable storage medium for generating a simulated high-precision map, which are used to generate a simulated high-precision map used in an autonomous driving simulation system. In the present application, a map generating device obtains the demand for generating a high-precision map. According to the demand, a plurality of primitives that meet the demand are selected from a primitive library, and the simulated high-precision map is generated by splicing the plurality of primitives. The primitives are high-precision map fragments with classification labels. Since a plurality of primitives are stored in the primitive library in advance, a plurality of primitives that meet the demand can be selected from the primitive library when needed, and the plurality of primitives can be spliced ​​to generate a simulated high-precision map, thereby saving manpower in the process of generating the simulated high-precision map, speeding up the generation of the simulated high-precision map, and reducing the cost of the simulated high-precision map.

Description

Technical Field

[0001] The present application relates to the field of intelligent transportation technology, and in particular to a method, device and computer-readable storage medium for generating a simulated high-precision map. Background Art

[0002] The autonomous driving simulation system is an important module for studying autonomous driving. Autonomous driving software can be developed and tested through the autonomous driving simulation system, thus reducing the cost and risk of actual vehicle testing.

[0003] In real-world autonomous driving scenarios, high-definition maps (HDMaps) are essential for lane-level planning and vehicle positioning within road sections. Similarly, autonomous driving simulation systems also rely on HDMaps to simulate real roads, enabling the development and testing of autonomous driving software based on these simulated roads.

[0004] One way to obtain high-precision maps for use in autonomous driving simulation systems is to purchase them from professional mapping companies. However, high-precision maps are expensive, which increases the cost of autonomous driving research. Another approach is to collect data from real vehicles and then create maps based on the collected data. However, this method is time-consuming and labor-intensive, requiring a large amount of manpower. Summary of the Invention

[0005] The present application provides a method, device and computer-readable storage medium for generating a simulated high-precision map, which are used to select multiple primitives that meet the requirements from a primitive library, and splice the multiple primitives to generate a simulated high-precision map, thereby saving manpower in the process of generating the simulated high-precision map, speeding up the generation of the simulated high-precision map, and reducing the cost of the simulated high-precision map.

[0006] In the first aspect, the present application provides a method for generating a simulated high-precision map, in which the demand for generating a high-precision map is obtained. According to the demand, multiple primitives that meet the demand are selected from a primitive library, and the simulated high-precision map is generated by splicing the multiple primitives. The primitive is a high-precision map fragment with a classification label. Since multiple primitives are stored in the primitive library in advance, multiple primitives that meet the demand can be selected from the primitive library when needed, and the multiple primitives are spliced ​​to generate a simulated high-precision map, thereby saving manpower in the process of generating the simulated high-precision map, speeding up the generation of the simulated high-precision map, and reducing the cost of the simulated high-precision map.

[0007] In one possible implementation, high-precision map segments matching the classification labels are segmented from an existing high-precision map; and the segmented high-precision map segments are added to the primitive library as primitives. The existing high-precision map can be an existing high-precision map derived from data collected from actual roads. Primitives obtained in this manner can better conform to real-world road construction specifications.

[0008] In another possible implementation, vector map segments matching the classification labels are segmented from an existing vector map; high-precision map information corresponding to the vector map segments is obtained by performing image detection on satellite cloud images corresponding to the vector map segments; the vector map segments are converted into high-precision map segments using the high-precision map information; and the high-precision map segments obtained through the conversion are added to the primitive library as primitives. Because lane-level information corresponding to the vector map segments can be determined based on satellite cloud images, the high-precision map segments corresponding to the vector map segments can also be determined. This increases the diversity of primitive acquisition methods.

[0009] In one possible implementation, the selecting of multiple primitives that meet the requirements from the primitive library according to the requirements includes: determining at least one classification label required for generating the simulated high-precision map and the number of primitives corresponding to each classification label in the at least one classification label according to the requirements; and selecting the multiple primitives with the at least one classification label from the primitive library according to the number of primitives. In this way, the user can select the required primitives based on the classification labels, thereby simplifying the user's operation, improving the convenience of the simulated high-precision map generation process, and contributing to the promotion and use of the solution. On the other hand, since the user can also input the number of primitives, the convenience of the user inputting the requirements is improved, and in the case where a large number of the same primitives are required, the requirements can be input by entering the quantity, which can simplify the user's operation.

[0010] In order to improve the flexibility of the solution, in one possible implementation, for one of the at least one classification label, when the number of primitives corresponding to the classification label required to generate the simulated high-precision map determined according to the requirements is greater than 1: the selecting of the multiple primitives with the at least one classification label from the primitive library according to the number of primitives includes: randomly selecting the multiple primitives with the classification label from the primitive library according to the number of primitives.

[0011] In another possible implementation, for one of the at least one classification labels, when the number of primitives corresponding to the classification label required to generate the simulated high-precision map is greater than 1 as determined by the requirements: selecting the multiple primitives with the at least one classification label from the primitive library according to the number of primitives includes: selecting the multiple primitives with the classification label from the primitive library by sampling with replacement according to the number of primitives. By selecting primitives by sampling with replacement, the multiple primitives may include two primitives belonging to the same primitive in the primitive library, so that when the number of primitives stored in a classification label is less than the required number, primitives that meet the required number can still be selected.

[0012] In one possible implementation, the plurality of primitives include a first primitive and a second primitive, the first primitive including a first road segment, and the second primitive including a second road segment. Generating the simulated high-precision map by stitching the plurality of primitives includes: generating a transition road segment between the first road segment and the second road segment, the transition road segment including at least one transition lane, the at least one transition lane being used to connect at least one first lane in the first road segment with at least one second lane in the first road segment; establishing a link relationship between the at least one first lane and the at least one transition lane; and establishing a link relationship between the at least one second lane and the at least one transition lane. Because the two primitives are stitched together using the transition road segment, stitching the two primitives can be achieved even when the lanes or driving directions of the two primitives differ.

[0013] In one possible implementation, generating the simulated high-precision map by stitching together the multiple primitives further includes: determining at least one exit lane from the at least one first lane; determining at least one entry lane from the at least one second lane; and the at least one transition lane connecting the at least one exit lane and the at least one entry lane. This ensures that lane information on the stitched simulated high-precision map matches, thereby paving the way for simulated vehicles to operate on the simulated high-precision map.

[0014] In one possible implementation, the number of the at least one exit lane is different from the number of the at least one entry lane, and the transition road segment includes a lane segment for merging the two lanes into a single lane. In this manner, the two road segments with different numbers of lanes can be joined using the transition road segment.

[0015] In one possible implementation, the orientation of the at least one exit lane is different from the orientation of the at least one entrance lane, and the at least one transition lane comprises a curved lane. In this way, two road segments with different lane orientations can be spliced ​​together using a transition road segment.

[0016] In one possible implementation, the classification tag is used to identify at least one of the following for the HD map segment: geometric topology information of the road in the HD map segment; information about the lane usage in the HD map segment; or information about the type of site in the HD map segment. This allows users to access primitives commonly used in simulation environments based on the set classification tags, and this method of setting classification tags better meets the actual needs of the autonomous driving simulation field.

[0017] In one possible implementation, the geometric topology information includes at least one of a curve, a straight road, a roundabout, an intersection, a T-junction, an L-shaped intersection, a U-shaped intersection, or a ramp. In one possible implementation, the lane usage information includes at least one of a bus lane, a pedestrian crossing, a bicycle lane, an expressway, a temporary parking lane, or an emergency parking lane. In one possible implementation, the site type information includes at least one of an urban road, a highway, and a parking lot. This method of setting classification labels can better match the actual needs of the autonomous driving simulation field.

[0018] Corresponding to the simulated high-precision map generation method in the first aspect, this application also provides a map generation device. The map generation device can be a communication chip, a terminal device, or a network device. For example, the map generation device can be a chip for a network device; in another example, it can be a chip for a terminal device.

[0019] In a second aspect, a map generation device is provided, comprising an acquisition unit and a processing unit, configured to execute any of the embodiments of the simulated high-precision map generation methods described in any of aspects 1 to 14. The acquisition unit is configured to perform functions related to sending and receiving. Optionally, the acquisition unit includes a receiving unit and a sending unit. In one design, the map generation device is a communication chip, and the acquisition unit may be an input / output circuit or port of the chip.

[0020] In another design, the acquisition unit may be a transmitter and a receiver, or the acquisition unit is a transmitter and a receiver.

[0021] Optionally, the map generation device further includes modules that can be used to execute any implementation of any of the simulated high-precision map generation methods of the first to fourteenth aspects above.

[0022] In a third aspect, a map generation device is provided. The map generation device is the aforementioned terminal device or network device. The device includes a processor and a memory. Optionally, the device further includes a transceiver. The memory is configured to store computer programs or instructions, and the processor is configured to retrieve and execute the computer programs or instructions from the memory. When the processor executes the computer programs or instructions in the memory, the map generation device executes any of the implementations of any of the simulated high-precision map generation methods described in the first aspect.

[0023] Optionally, there are one or more processors and one or more memories.

[0024] Optionally, the memory may be integrated with the processor, or the memory may be provided separately from the processor.

[0025] Optionally, the transceiver may include a transmitter (transmitter) and a receiver (receiver).

[0026] In a fourth aspect, a map generation device is provided, comprising a processor. The processor is coupled to a memory and is configured to execute the method of any possible implementation of the first aspect. Optionally, the map generation device further comprises a memory. Optionally, the map generation device further comprises a communication interface, the processor being coupled to the communication interface.

[0027] In one implementation, the map generation device is a terminal device. When the map generation device is a terminal device, the communication interface may be a transceiver or an input / output interface. Alternatively, the transceiver may be a transceiver circuit. Alternatively, the input / output interface may be an input / output circuit.

[0028] In another implementation, the map generation device is a network device. When the map generation device is a network device, the communication interface may be a transceiver or an input / output interface. Alternatively, the transceiver may be a transceiver circuit. Alternatively, the input / output interface may be an input / output circuit.

[0029] In another implementation, the map generation device is a chip or a chip system. When the map generation device is a chip or a chip system, the communication interface may be an input / output interface, interface circuit, output circuit, input circuit, pin, or related circuit on the chip or chip system. The processor may also be embodied as a processing circuit or a logic circuit.

[0030] In a fifth aspect, a computer program product is provided, which includes: a computer program (also referred to as code, or instructions), which, when run, enables a computer to execute a method in any possible implementation of the first aspect, or enables a computer to execute a method in any implementation of the first aspect.

[0031] In a sixth aspect, a computer-readable storage medium is provided, which stores a computer program (also referred to as code, or instructions) which, when run on a computer, enables the computer to execute a method in any possible implementation of the first aspect, or enables the computer to execute a method in any implementation of the first aspect.

[0032] In a seventh aspect, a chip system is provided, which may include a processor. The processor is coupled to a memory and may be used to execute any aspect of the first aspect, and the method in any possible implementation of any aspect of the first aspect. Optionally, the chip system also includes a memory. The memory is used to store a computer program (also referred to as code, or instructions). The processor is used to call and run the computer program from the memory, so that the device equipped with the chip system executes any aspect of the first aspect, and the method in any possible implementation of any aspect of the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 A flowchart of a method for generating a simulated high-precision map is provided for an embodiment of the present application;

[0034] Figure 2 A schematic diagram of a classification label setting is provided for an embodiment of the present application;

[0035] Figure 3 A structural diagram of splicing a first primitive and a second primitive is provided for an embodiment of the present application;

[0036] Figure 4 A schematic diagram of a possible splicing of a first primitive and a second primitive is provided for an embodiment of the present application;

[0037] Figure 5 A schematic diagram of another possible splicing of a first primitive and a second primitive is provided for an embodiment of the present application;

[0038] Figure 6 A schematic diagram of the structure of a map generating device provided in an embodiment of the present application;

[0039] Figure 7 A schematic diagram of the structure of another map generating device provided in an embodiment of the present application;

[0040] Figure 8 A schematic diagram of the structure of another map generation device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0041] The embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0042] First, the application scenarios of the embodiments of the present application are introduced. The embodiments of the present application provide a method for generating a simulated high-precision map, and the simulated high-precision map generated by this method can be applied to an autonomous driving simulation system. Vehicles in the autonomous driving simulation system can implement traffic services based on the simulated high-precision map. The traffic services of the embodiments of the present application can be various autonomous driving and assisted driving services, such as: path planning, and providing driving risk warnings for manual driving. The above traffic services are only examples. In the autonomous driving simulation system, the simulated high-precision map provided by the embodiments of the present application can also provide technical preparations for communication between vehicles and other devices (vehicle to everything, V2X), such as vehicle to vehicle (V2V) and vehicle to installation (V2I).

[0043] The high-precision map generation method provided in the embodiments of the present application can be executed by a map generation device, which can be a network-side device or a terminal device, or a chip within a network-side device or a chip within a terminal device. The network-side device includes a computing platform or server. The specific deployment form of the computing platform and server is not limited in this application. For example, it can be a cloud deployment or an independent computer device or chip. The terminal device includes a hardware device that supports scientific computing, such as a personal computer, a server, a mobile terminal, an embedded device, etc.

[0044] Based on the above, Figure 1 The following is a flow chart of a method for generating a simulated high-precision map according to an embodiment of the present application. Figure 1 As shown, the method includes:

[0045] S101: A map generating device obtains a demand for generating a high-precision map.

[0046] In a possible implementation, the user may input a requirement, and the format of the requirement is not limited, for example, it may be a table, a program segment, a piece of text, a file, a voice, etc.

[0047] S102: The map generating device selects a plurality of primitives that meet the requirements from a primitive library according to the requirements, where the primitives are high-precision map segments with classification labels.

[0048] In one possible implementation, a primitive can also be understood as a high-precision map file corresponding to a high-precision map segment.

[0049] S103: The map generating device generates the simulated high-precision map by splicing the multiple primitives.

[0050] Since multiple primitives are stored in the primitive library in advance, multiple primitives that meet the needs can be selected from the primitive library when needed, and the multiple primitives can be spliced ​​to generate a simulated high-precision map, which can save manpower in the process of generating the simulated high-precision map, speed up the generation of the simulated high-precision map, and reduce the cost of the simulated high-precision map.

[0051] The following describes several possible ways to obtain primitives from the primitive library.

[0052] Method 1: Obtain primitives based on an existing high-precision map.

[0053] High-precision maps include both road-level and lane-level information. Lane-level information indicates lane information within a road network, such as lane curvature, lane heading, lane centerline, lane width, lane markings, lane speed limits, lane splits, and lane merges. Lane-level information also includes lane markings (dashed, solid, single, or double), lane color (white or yellow), road medians, median material, road arrows, text content, and location.

[0054] Specifically, high-precision map segments that match the classification labels can be segmented from existing high-precision maps, and the high-precision map segments obtained through segmentation (high-precision map segments can also be understood as high-precision map segment files) are added to the primitive library as primitives. The existing high-precision map can refer to an existing high-precision map obtained based on data collected from actual roads.

[0055] For example, a classification mark is "crossroads". The existing high-precision map is detected, and one or more high-precision map segments including "crossroads" are cut. The obtained high-precision map segments are used as primitives and added to the primitive library.

[0056] Method 2: Obtain primitives based on existing vector maps and satellite cloud images.

[0057] Vector maps, such as open-source vector maps, include road-level information. This information can provide navigational information for users, meeting their driving route needs. For example, road-level information can include the number of lanes on the road, speed limits, and turn information.

[0058] The satellite cloud in the embodiments of this application can be understood as a satellite map. Lane-level information, such as lane width, number of lanes, lane direction, and lane usage, can be identified through the satellite cloud. Therefore, based on the satellite cloud image, the lane-level information corresponding to the vector map segment can be determined, thereby determining the high-precision map segment corresponding to the vector map segment.

[0059] In one possible implementation, vector map segments matching the classification labels can be segmented from an existing vector map. High-precision map information corresponding to the vector map segments can be obtained by performing image detection on satellite cloud images corresponding to the vector map segments. The high-precision map information can be used to convert the vector map segments into high-precision map segments. The high-precision map segments obtained through the conversion are then added to the primitive library as primitives.

[0060] The classification tag in the embodiment of the present application is used to identify at least one of the following items of the high-precision map segment:

[0061] Parameter item a1: type information of the site in the high-precision map segment;

[0062] Parameter a2: geometric topology information of the road in the high-precision map segment; or

[0063] Parameter item a3: lane usage information in the high-precision map segment.

[0064] The following is an introduction to each parameter item.

[0065] Parameter item a1: The classification label is used to identify the type information of the site in the high-precision map segment.

[0066] In one possible implementation, the type information of the venue may include several preset types, such as urban roads, highways, and parking lots. Classification labels may be added to the venues in the high-precision map segments based on the type information of the venues.

[0067] For example, if a high-definition map segment includes a parking lot, the category label for the high-definition map segment will include parking lot. For another example, if a road in a high-definition map segment is a highway, the category label for the high-definition map segment will include highway.

[0068] Parameter item a2: The classification label is used to identify the geometric topology information of the road in the high-precision map segment.

[0069] Geometric elements can be represented by two important types of information: geometric information and topological information. Geometric information refers to the position of an object in three-dimensional Euclidean space. Geometric information reflects the size and position of an object, such as vertex coordinates and specific coefficients in surface mathematical expressions. Topological information refers to the number, type, and interrelationships of an object's topological elements (vertices, edges, and surfaces).

[0070] In an embodiment of the present application, the geometric topology information of the road in the high-precision map segment may include: at least one of: a curve, a straight road, a roundabout, an intersection, a T-junction, an L-shaped intersection, a U-shaped intersection or a ramp.

[0071] If the geometric topology information of a road is "curve", then the road is an arc with a certain curvature.

[0072] If the geometric topology information of a road is "straight road", then the geometric shape of the road is a straight line.

[0073] If the geometric topology information of the road is "roundabout", the geometric shape of the road is circular, and the roundabout in the road section r6 has an exit and an entrance.

[0074] If the geometric topology information of a road is "T-junction", then the geometric shape of the road is T-shaped.

[0075] If the geometric topology information of a road is "crossroad", the geometric shape of the road is a cross.

[0076] If the geometric topology information of a road is "L-shaped intersection", then the geometric shape of the road is L-shaped.

[0077] If the geometric topology information of a road is "U-shaped intersection", the geometric shape of the road is U-shaped.

[0078] In one possible implementation, the classification label used to identify the type information of the site in the high-precision map segment can be called a primary classification label, and the geometric topology information used to identify the road in the high-precision map segment can be called a secondary classification label.

[0079] Figure 2 The schematic diagram of the classification label setting is shown as an example. Figure 2 For example, three first-level classification tags can be set: "Urban Road," "Highway," and "Parking Lot." Second-level classification tags can be set under the first-level classification tags. For example, the second-level classification tags under the first-level classification tag "Urban Road" can include at least one of the following: curve, straight road, roundabout, intersection, T-junction, L-shaped intersection, U-shaped intersection, or ramp.

[0080] For another example, the secondary classification labels under the primary classification label “highway” may include at least one of the following: curve, straight road, or ramp.

[0081] An HD map segment can correspond to a primary classification label, such as a HD map segment with the classification label "parking lot." An HD map segment can also correspond to a primary classification label and at least one secondary classification label. For example, if the road in an HD map segment is a straight road under a city road, the classification labels for the HD map segment might include "city road" and "straight road."

[0082] In a possible implementation, one or more third-level tags can be set under the second-level tag. The third-level tags can be key parameter items that can identify geometric topology information. The following are some examples of third-level classification identification:

[0083] For example, the third-level classification label corresponding to the second-level classification label "curve" may be: curvature, and then high-precision map fragments corresponding to multiple curves with different curvatures can be stored under the second-level classification label "curve".

[0084] For example, the third-level classification label corresponding to the second-level classification label "roundabout" can be: the radius of the roundabout, and then high-precision map fragments corresponding to multiple roundabouts of different radii can be stored under the second-level classification label "roundabout".

[0085] For example, the third-level classification label corresponding to the second-level classification label "U-shaped intersection" can be: the opening size of the U-shaped intersection, and then high-precision map fragments corresponding to multiple U-shaped intersections with different opening sizes can be stored under the second-level classification label "U-shaped intersection".

[0086] For example, the third-level classification label corresponding to the second-level classification label "ramp" can be: the type of ramp, and then multiple high-precision map fragments corresponding to different types of ramps can be stored under the second-level classification label "ramp".

[0087] The type of ramp may include at least one of the following:

[0088] Entrance and exit ramps: auxiliary connecting road sections entering and exiting the main line, which can be "level crossing ramps" or "overpass ramps".

[0089] On and off ramps: Auxiliary connecting slopes for entering and exiting elevated roads, driving up or down, usually "interchange ramps".

[0090] Directional Ramp / Road: Place the right turn lane on the right.

[0091] Non-directional Ramp / Road: The left-turn lane is located on the right, and a loop is set up to connect to other roads.

[0092] Semi-Directional Ramp / Road: Similar to an indirect ramp, but instead of a loop, a longer, more undulating elevated road is used as the connecting ramp.

[0093] U-Turn Ramp / Road: A ramp with a U-turn.

[0094] Note: The above terms are based on right-hand driving road design.

[0095] It should be noted that the high-precision map fragment corresponding to a three-level classification label can be one or more. For example, the high-precision map fragment corresponding to the same curvature can be one or more. This embodiment of the present application does not limit this.

[0096] Parameter item a3: The classification label is used to identify the usage information of the lane in the high-precision map segment.

[0097] The lane usage information may include at least one of: a bus lane, a pedestrian crossing, a bicycle lane, an expressway, a temporary parking lane, or an emergency parking lane.

[0098] Lane usage information is also called a secondary classification label. An HD map segment can include one or more secondary classification labels. For example, if the road in an HD map segment is a straight road, and one of the lanes in the HD map segment is a bus lane, the classification labels for the HD map segment may include: Straight Road and Bus Lane. If the road in the HD map segment is an urban road, the classification label for the HD map segment may also include Urban Road.

[0099] When the usage information of a lane is "bus lane", the lane is mainly used for buses. Specifically, it can be used only for buses at all times, or it can be used only for buses during specified time periods (such as morning rush hour and evening rush hour).

[0100] When the usage information of a lane is "bicycle lane", the lane can only be used for bicycles.

[0101] When the usage information of a lane is "expressway", the lane has requirements for the vehicle's driving speed, for example, the driving speed of vehicles driving in the lane must not be less than 80 kilometers per hour.

[0102] When the usage information of a lane is "crosswalk", the lane is a lane for pedestrians.

[0103] When the usage information of a lane is "emergency lane", the lane can only be used for emergency purposes, such as allowing traffic police vehicles to drive in order to quickly handle various traffic accidents on the road.

[0104] When the usage information of a lane is "temporary parking lane", the lane can only be used for temporary parking and cannot be occupied for long-term parking.

[0105] In the embodiment of the present application, the above-mentioned classification label items are merely examples. In actual applications, other classification label items can also be set according to the road information in the high-precision map fragment. For example, at least one of the following items can also be set as a classification label item: lane height limit, lane maximum speed limit, presence or absence of electronic eyes, lane restricted direction, prohibited time period for restricted direction, lane restricted vehicle type, and prohibited time period for restricted vehicles, etc.

[0106] In one possible implementation, in S102, the map generation device may determine, based on the requirements, at least one classification label required for generating the simulated high-precision map, and the number of primitives corresponding to each of the at least one classification label. The plurality of primitives having the at least one classification label may be selected from the primitive library based on the number of primitives.

[0107] For example, a requirement can be a program entered by the user, as shown below:

[0108]

[0109] In this example, it can be determined that the classification labels required to generate the simulated high-precision map include: 1 roundabout and 1 intersection. In this example, the number of primitives corresponding to each classification label is included.

[0110] For a classification label under the at least one classification label, when the number of primitives of the classification label to be selected from the primitive library is equal to 1, a primitive that satisfies the classification label can be randomly selected from the primitive library. When the number of primitives of the classification label to be selected from the primitive library is greater than 1, a random selection can be performed.

[0111] For example, sampling with replacement can be used to select multiple primitives from the primitive library that satisfy the classification label. "Sampling with replacement" is a simple random sampling method. The sampling units in the population are numbered from 1 to K, and each number is drawn and then returned to the population. For any single draw, since the population size remains constant, all K numbers have an equal chance of being drawn.

[0112] For example, if the primitive to be selected has the classification label "roundabout" and the number of primitives corresponding to the classification label "roundabout" is "2", we can first extract a primitive from all primitives corresponding to the classification label "roundabout" in the primitive library, and then extract another primitive from all primitives corresponding to the classification label "roundabout" in the primitive library. The two primitives selected through sampling with replacement may be the same or different.

[0113] In an embodiment of the present application, when the selected multiple primitives are spliced ​​in S103, the splicing order of the multiple primitives can be randomly generated or specified by the user, for example, the obtained requirements include indication information for indicating the splicing order of at least two primitives among the multiple primitives.

[0114] There are multiple ways to splice two primitives from the plurality of primitives, each of which is described below. For clarity, the following uses a first primitive and a second primitive from the plurality of primitives as an example. The first primitive includes a first road segment, and the second primitive includes a second road segment.

[0115] Method 1: No need to generate transition road segments.

[0116] If the number of lanes included in the first road segment is the same as the number of lanes included in the second road segment, and the lane orientations (also referred to as lane driving directions) are consistent, the first road segment and the second road segment may be spliced.

[0117] Figure 3 A schematic diagram of a structure for splicing a first primitive and a second primitive is shown as an example. Figure 3 (a) in FIG. 1 shows a schematic diagram of a roundabout 301 (the roundabout 301 may be a first primitive). Figure 3 (b) in FIG. 3 shows a crossroads 302 (the crossroads 302 may be a second primitive). Figure 3 (c) in FIG. 1 shows a schematic diagram of a simulated high-precision map obtained after the map generation device splices the first primitive and the second primitive. Figure 3 As shown, the first road segment and the second road segment can be spliced ​​according to the driving direction of the lane in the high-precision map segment without generating a transition road segment.

[0118] If all lanes in at least one first lane of a first road segment have the same driving direction, and all lanes in at least one second lane of a second road segment have the same driving direction, then the exit lane in the first road segment may be joined with the entry lane in the second road segment.

[0119] In another possible implementation, if a first road segment has two first lanes with different orientations, and a second road segment has two second lanes with different orientations, the exit lane in the first road segment is spliced ​​with the entry lane in the second road segment, and the entry lane in the first road segment is spliced ​​with the exit lane in the second road segment.

[0120] Method 2: It is necessary to generate transition road segments.

[0121] The map generating device may generate a transition road segment between the first road segment and the second road segment.

[0122] The transition road segment includes at least one transition lane, the at least one transition lane being used to connect at least one first lane in the first road segment with at least one second lane in the first road segment. A link relationship is established between the at least one first lane and the at least one transition lane. A link relationship is also established between the at least one second lane and the at least one transition lane.

[0123] Specifically, the map generating device may determine at least one exit lane of the at least one first lane, at least one entry lane of the at least one second lane, and at least one transition lane connecting the at least one exit lane and the at least one entry lane.

[0124] A transition road segment is generated based on the number and orientation of exit lanes of the first road segment and the number and orientation of entrance lanes of the second road segment.

[0125] In example 1, the number of exit lanes of the first road segment is different from the number of entry lanes of the second road segment, and the transition road segment includes a lane segment for merging multiple (for example, two) lanes into one lane.

[0126] Figure 4 A possible structural diagram of splicing the first primitive and the second primitive is shown as an example. Figure 4 As shown, the two primitives that need to be spliced ​​are Figure 4 The second primitive 401 shown in (a) of FIG. , and Figure 4 The first primitive 402 is shown in (b) of FIG. The second primitive 401 is a two-lane road, and the first primitive 402 is a single lane road. The entrance lane of the second primitive 401 can be determined based on the lane information of the second primitive 401, and the exit lane of the first primitive 402 can be determined based on the lane information of the first primitive 402. The following is generated between the second primitive 401 and the first primitive 402: Figure 4The transition road segment 403 shown in (c) has one end connected to the exit lane of the first primitive 402 and the other end connected to the entrance lane of the second primitive 401, and is used to resolve the transition of the change in the number of lanes (increase / decrease in the number of lanes).

[0127] Example 2: In a possible implementation, the orientation of the at least one exit lane of the first road segment is different from the orientation of the at least one entrance lane of the second road segment, and then at least one transition lane in the transition road segment includes a curved lane.

[0128] The direction of the lane can be understood as the direction of lane travel. Figure 5 A schematic diagram showing another possible splicing of the first primitive and the second primitive is shown as an example. Figure 5 As shown, the two primitives that need to be spliced ​​are Figure 5 The second primitive 501 shown in (a) of FIG. , and Figure 5 The first primitive 502 is shown in (b) of FIG. Wherein, the vehicle driving direction of the second primitive 501 differs by 90 degrees from the vehicle driving direction of the first primitive 502, and a transition lane (a curve) in the transition road segment is generated to connect the second primitive 501 and the first primitive 502.

[0129] Due to the huge demand for high-precision maps in the field of autonomous driving simulation, relying on purchasing or manual annotation to generate high-precision maps is not only costly, time-consuming, but also very inefficient. Therefore, there is a strong demand for technologies that can quickly and automatically generate virtual high-precision maps for simulation. The high-precision map generation method provided in the embodiment of the present application can construct a large number of high-precision maps that meet the requirements of simulation testing, and has the characteristics of wide coverage and rich road conditions, and can relatively easily cover all simulation testing needs.

[0130] On the other hand, since the road sections stored in the map library in the embodiment of the present application are all intercepted from existing maps, that is, they are derived from real road conditions, the high-precision maps generated in the embodiment of the present application comply with the road construction specifications in reality and are reasonable. Moreover, compared with real high-precision maps, there is no need for on-site surveying and mapping, which reduces labor costs and improves generation efficiency. The accuracy is relatively low and is not synchronized with the actual roads. Under the premise of meeting the simulation test requirements, a large number of simulation maps can be generated to meet the demand for the number of simulation maps. Compared with the existing methods of obtaining high-precision maps, it is significantly ahead in speed and efficiency. Furthermore, in the embodiment of the present application, user-customized high-precision maps can be automatically generated according to user intentions, so as to better match simulation needs.

[0131] It should be noted that the solution provided in the embodiment of the present application is not limited to the generation of virtual high-precision maps for simulation, but can be applied to the generation of other simulation scenarios. The generation process is similar and will not be repeated here.

[0132] "At least one" in the embodiments of the present application refers to one or more, and "more" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: the existence of A alone, the existence of A and B at the same time, and the existence of B alone, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0133] Furthermore, unless otherwise specified, ordinal numbers such as "first" and "second" in the embodiments of this application are used to distinguish multiple objects and are not used to define the order, timing, priority, or importance of multiple objects. For example, the first data type and the second data type are only used to distinguish different data types and do not indicate a difference in priority or importance between the two data types.

[0134] It should be noted that the names of the above-mentioned messages are merely examples. With the evolution of communication technology, the names of any of the above-mentioned messages may change. However, no matter how the names change, as long as their meanings are the same as those of the above-mentioned messages in this application, they fall within the scope of protection of this application.

[0135] The above mainly introduces the solution provided by the present application from the perspective of the interaction between various network elements. It can be understood that in order to realize the above functions, the above-mentioned network elements include hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present invention can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in a hardware or computer software-driven hardware manner depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0136] According to the above method, Figure 6 Provide executable examples for this application Figure 1The structural diagram of the map generating device of the simulation map generating method is shown as follows: Figure 6 As shown, the map generating device can be a device on the network device side, a device on the terminal device side, or a chip or circuit, such as a chip or circuit that can be set on the network device side, or a chip or circuit that can be set on the terminal device side.

[0137] Furthermore, the map generating device 1301 may further include a bus system, wherein the processor 1302 , the memory 1304 , and the transceiver 1303 may be connected via the bus system.

[0138] It should be understood that the processor 1302 may be a chip. For example, the processor 1302 may be a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on chip (SoC), a central processor unit (CPU), a network processor (NP), a digital signal processor (DSP), a microcontroller unit (MCU), a programmable logic device (PLD), or other integrated chips.

[0139] During implementation, each step of the above method can be completed by an integrated logic circuit of the hardware in the processor 1302 or by instructions in the form of software. The steps of the method disclosed in conjunction with the embodiments of the present application can be directly embodied as being executed by a hardware processor, or can be executed by a combination of hardware and software modules in the processor 1302. The software module can be located in a storage medium mature in the art, such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 1304, and the processor 1302 reads the information in the memory 1304 and completes the steps of the above method in conjunction with its hardware.

[0140] It should be noted that the processor 1302 in the embodiment of the present application can be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method embodiment can be completed by hardware integrated logic circuits in the processor or software instructions. The above processor can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component. The various methods, steps, and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the embodiment of the present application can be directly embodied as being executed by a hardware decoding processor, or can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium mature in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, or electrically erasable programmable memory, registers, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0141] It is understood that the memory 1304 in the embodiment of the present application can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct RAM bus RAM (DR RAM). It should be noted that the memory of the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0142] The map generating device may include a processor 1302, a transceiver 1303 and a memory 1304. The memory 1304 is used to store instructions, and the processor 1302 is used to execute the instructions stored in the memory 1304 to achieve the above Figures 1 to 5 A related solution of the map generating device in any one or more corresponding methods shown in .

[0143] In one possible implementation, transceiver 1303 is configured to obtain a requirement for generating a high-precision map. Processor 1302 is configured to select, based on the requirement, multiple primitives from a primitive library that meet the requirement, where the primitives are high-precision map segments with classification labels; and generate the simulated high-precision map by splicing the multiple primitives.

[0144] In one possible implementation, the processor 1302 is configured to segment high-precision map segments that conform to the classification labels from an existing high-precision map; and add the high-precision map segments obtained by the segmentation as primitives to the primitive library.

[0145] In one possible implementation, the processor 1302 is used to segment vector map segments that meet the classification label from an existing vector map; obtain high-precision map information corresponding to the vector map segment by performing image detection on a satellite cloud image corresponding to the vector map segment; use the high-precision map information to convert the vector map segment into a high-precision map segment; and add the high-precision map segment obtained by the conversion as a primitive to the primitive library.

[0146] In one possible implementation, the processor 1302 is specifically used to: determine, according to the requirements, at least one classification label required to generate the simulated high-precision map, and the number of primitives corresponding to each classification label in the at least one classification label; and select the multiple primitives with the at least one classification label from the primitive library according to the number of primitives.

[0147] In one possible implementation, the multiple primitives include a first primitive and a second primitive, the first primitive includes a first road segment, and the second primitive includes a second road segment. The processor 1302 is specifically configured to: generate a transition road segment between the first road segment and the second road segment, the transition road segment including at least one transition lane, the at least one transition lane being used to connect at least one first lane in the first road segment with at least one second lane in the first road segment; establish a link relationship between the at least one first lane and the at least one transition lane; and establish a link relationship between the at least one second lane and the at least one transition lane.

[0148] In one possible implementation, the processor 1302 is further used to: determine at least one exit lane of the at least one first lane; determine at least one entrance lane of the at least one second lane; and the at least one transition lane is used to connect the at least one exit lane with the at least one entrance lane.

[0149] For other related descriptions, please refer to the contents of the aforementioned method embodiment, which will not be repeated here. The concepts, explanations, detailed descriptions and other steps involved in the map generation device and related to the technical solutions provided in the embodiments of this application can be found in the descriptions of these contents in the aforementioned method or other embodiments, which will not be repeated here.

[0150] According to the above method, Figure 7 A schematic diagram of the structure of the map generation device provided in the embodiment of the present application is shown in FIG. Figure 7As shown, the map generating device 1401 may include a communication interface 1403, a processor 1402, and a memory 1404. The communication interface 1403 is used to input and / or output information; the processor 1402 is used to execute computer programs or instructions so that the map generating device 1401 can achieve the above Figures 1 to 5 In the related scheme, the map generating device 1401 realizes the above Figures 1 to 5 In the embodiment of the present application, the communication interface 1403 can implement the above-mentioned Figure 6 The solution implemented by the transceiver 1303, the processor 1402 can implement the above Figure 6 The processor 1302 implements the solution, and the memory 1404 can implement the above Figure 6 The solution implemented by the memory 1304 will not be described in detail here.

[0151] Based on the above embodiments and the same concept, Figure 8 The embodiments of the present application provide the following Figure 1 Schematic diagram of a map generating device of a simulation map generating method shown in FIG. Figure 8 As shown, the map generating device 1501 can be a device on the network device side, a device on the terminal device side, or a chip or circuit, such as a chip or circuit that can be set on a device on the network device side, or a chip or circuit that can be set on a device on the terminal device side.

[0152] The acquisition unit 1503 is configured to acquire requirements for generating a high-precision map. The processing unit 1502 is configured to select, based on the requirements, multiple primitives that meet the requirements from a primitive library, wherein the primitives are high-precision map segments with classification labels; and generate the simulated high-precision map by splicing the multiple primitives.

[0153] For the concepts, explanations, detailed descriptions and other steps involved in the map generation device and related to the technical solutions provided in the embodiments of the present application, please refer to the descriptions of these contents in the aforementioned methods or other embodiments, which will not be repeated here.

[0154] It is understandable that the functions of the various units in the above-mentioned map generating device 1501 can be referred to the implementation of the corresponding method embodiment, and will not be repeated here.

[0155] It should be understood that the division of the units of the above map generation device is only a division of logical functions. In actual implementation, they can be fully or partially integrated into one physical entity, or they can be physically separated. In the embodiment of the present application, the acquisition unit 1503 can be composed of the above Figure 6 The transceiver 1303 is implemented, and the processing unit 1502 can be implemented by the above Figure 6 The processor 1302 is implemented.

[0156] According to the method provided in the embodiment of the present application, the present application also provides a computer program product, which includes: computer program code or instructions, which, when the computer program code or instructions are executed on a computer, causes the computer to execute Figures 1 to 5 A method according to any one of the embodiments shown.

[0157] According to the method provided in the embodiment of the present application, the present application also provides a computer-readable storage medium, which stores a program code, and when the program code is run on a computer, the computer executes Figures 1 to 5 A method according to any one of the embodiments shown.

[0158] According to the method provided in the embodiment of the present application, the present application also provides a chip system, which may include a processor. The processor is coupled to the memory and can be used to execute Figures 1 to 5 The method of any one of the embodiments shown. Optionally, the chip system also includes a memory. The memory is used to store computer programs (also called codes or instructions). The processor is used to call and run the computer program from the memory so that the device equipped with the chip system executes Figures 1 to 5 A method according to any one of the embodiments shown.

[0159] In the above embodiments, all or part of the embodiments can be implemented by software, hardware, firmware or any combination thereof. When implemented using software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, all or part of the processes or functions according to the embodiments of the present application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media integrated therein. Available media may be magnetic media (eg, floppy disks, hard disks, tapes), optical media (eg, high-density digital video discs (DVDs)), or semiconductor media (eg, solid state discs (SSDs)).

[0160] Note: A portion of this patent application contains material which is subject to copyright protection. The copyright owner reserves all rights reserved except for copies of the materials in the patent file or patent record in the Patent Office.

[0161] The map generation devices in the aforementioned apparatus embodiments correspond to the map generation devices in the method embodiments, with corresponding modules or units performing corresponding steps. For example, the acquisition unit (transceiver) performs the receiving or sending steps in the method embodiments, while all other steps except sending and receiving may be performed by the processing unit (processor). The functions of the specific units can be found in the corresponding method embodiments. There may be one or more processors.

[0162] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0163] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0164] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0165] In addition, each functional unit in each embodiment of the present application may be integrated into one unit, each unit may exist physically separately, or two or more units may be integrated into one unit.

[0166] The above are only specific embodiments of the present application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A method for generating a simulated high-precision map, characterized in that: include: Obtaining a requirement for generating a high-precision map, where the requirement indicates at least one classification label; According to the requirements, a plurality of primitives that meet the requirements are selected from a primitive library, where the primitives are high-precision map segments with classification labels; Generate the simulated high-precision map by splicing the plurality of primitives, the plurality of primitives including a first primitive and a second primitive, the first primitive including a first road segment, and the second primitive including a second road segment; The step of generating the simulated high-precision map by splicing the multiple primitives includes: A transition road segment is generated between the first road segment and the second road segment, the transition road segment including at least one transition lane, the at least one transition lane being used to connect at least one exit lane of at least one first lane in the first road segment with at least one entry lane of at least one second lane in the second road segment, the number of the at least one exit lane being different from the number of the at least one entry lane, and the transition road segment including a lane segment for merging two lanes into one lane.

2. The method according to claim 1, wherein The primitives in the primitive library are obtained by at least one of the first method and the second method; The first method includes: Segmenting high-precision map segments that match the classification labels from the existing high-precision map; and Adding the high-precision map segments obtained by the segmentation as primitives to the primitive library; The second method includes: Segmenting vector map segments that match the classification labels from an existing vector map; Acquiring high-precision map information corresponding to the vector map segment by performing image detection on a satellite cloud image corresponding to the vector map segment; converting the vector map segments into high-precision map segments using the high-precision map information; and The high-precision map fragments obtained through the conversion are added to the primitive library as primitives.

3. The method according to claim 1 or 2, wherein: The selecting, according to the requirement, a plurality of primitives that meet the requirement from a primitive library comprises: Determining, based on the requirements, at least one classification label required to generate the simulated high-precision map, and the number of primitives corresponding to each classification label in the at least one classification label; The plurality of primitives having the at least one classification label are selected from the primitive library according to the number of primitives.

4. The method according to any one of claims 1 to 3, wherein: The at least one transition lane is used to connect at least one first lane in the first road segment with at least one second lane in the first road segment; Generating the simulated high-precision map by splicing the multiple primitives includes: Establishing a link relationship between the at least one first lane and the at least one transition lane; A link relationship between the at least one second lane and the at least one transition lane is established.

5. The method according to any one of claims 1 to 4, characterized in that The generating of the simulated high-precision map by splicing the plurality of primitives further comprises: determining at least one exit lane of the at least one first lane; At least one entry lane to the at least one second lane is determined.

6. The method according to any one of claims 1 to 5, wherein: The orientation of the at least one exit lane is different from the orientation of the at least one entrance lane, and the at least one transition lane includes a curved lane.

7. The method according to any one of claims 1 to 6, wherein: The classification tag is used to identify at least one of the following items of the high-precision map segment: Geometric topological information of roads in the high-precision map segment; lane usage information in the high-precision map segment; or The type information of the venue in the high-precision map segment.

8. The method according to claim 7, wherein The geometric topology information includes at least one of a curve, a straight road, a roundabout, a crossroads, a T-junction, an L-shaped intersection, a U-shaped intersection, or a ramp; The lane usage information includes at least one of: a bus lane, a pedestrian crossing, a bicycle lane, an expressway, a temporary parking lane, or an emergency parking lane; The type information of the site includes at least one of: a city road, a highway, and a parking lot.

9. A simulation high-precision map generation device, characterized in that: include: an acquiring unit, configured to acquire a requirement for generating a high-precision map, wherein the requirement indicates at least one classification label; a processing unit configured to select, based on the requirement, a plurality of primitives that meet the requirement from a primitive library, the primitives being high-precision map segments with classification labels; and generate the simulated high-precision map by splicing the plurality of primitives, the plurality of primitives comprising a first primitive and a second primitive, the first primitive comprising a first road segment, and the second primitive comprising a second road segment; The processing unit is specifically configured to: A transition road segment is generated between the first road segment and the second road segment, the transition road segment including at least one transition lane, the at least one transition lane being used to connect at least one exit lane of at least one first lane in the first road segment with at least one entry lane of at least one second lane in the second road segment, the number of the at least one exit lane being different from the number of the at least one entry lane, and the transition road segment including a lane segment for merging two lanes into one lane.

10. The device according to claim 9, wherein The processing unit is configured to obtain the primitives in the primitive library by using at least one of the first method and the second method; The first method includes: Segmenting high-precision map segments that match the classification labels from the existing high-precision map; and Adding the high-precision map segments obtained by the segmentation as primitives to the primitive library; The second method includes: Segmenting vector map segments that match the classification labels from an existing vector map; Acquiring high-precision map information corresponding to the vector map segment by performing image detection on a satellite cloud image corresponding to the vector map segment; converting the vector map segments into high-precision map segments using the high-precision map information; and The high-precision map fragments obtained through the conversion are added to the primitive library as primitives.

11. The device according to claim 9 or 10, characterized in that The processing unit is specifically configured to: Determining, based on the requirements, at least one classification label required to generate the simulated high-precision map, and the number of primitives corresponding to each classification label in the at least one classification label; The plurality of primitives having the at least one classification label are selected from the primitive library according to the number of primitives.

12. The device according to any one of claims 9 to 11, characterized in that The at least one transition lane is used to connect at least one first lane in the first road segment with at least one second lane in the first road segment; The processing unit is specifically configured to: Establishing a link relationship between the at least one first lane and the at least one transition lane; A link relationship between the at least one second lane and the at least one transition lane is established.

13. The device according to any one of claims 9 to 12, characterized in that The processing unit is further configured to: determining at least one exit lane of the at least one first lane; At least one entry lane to the at least one second lane is determined.

14. The device according to any one of claims 9 to 13, characterized in that The orientation of the at least one exit lane is different from the orientation of the at least one entrance lane, and the at least one transition lane includes a curved lane.

15. The device according to any one of claims 9 to 14, characterized in that The classification tag is used to identify at least one of the following items of the high-precision map segment: Geometric topological information of roads in the high-precision map segment; lane usage information in the high-precision map segment; or The type information of the venue in the high-precision map segment.

16. The device according to claim 15, characterized in that The geometric topology information includes at least one of a curve, a straight road, a roundabout, a crossroads, a T-junction, an L-shaped intersection, a U-shaped intersection, or a ramp; The lane usage information includes at least one of: a bus lane, a pedestrian crossing, a bicycle lane, an expressway, a temporary parking lane, or an emergency parking lane; The type information of the site includes at least one of: a city road, a highway, and a parking lot.

17. A map generating device, characterized in that: The method comprises a processor and a memory, wherein the memory is used to store a computer-executable program, and the processor executes the computer-executable program in the memory, so that the method according to any one of claims 1 to 8 is executed.

18. A map generating device, characterized in that: Including processor and communication interface, The communication interface is used to input and / or output information; The processor is configured to execute a computer-executable program so that the method according to any one of claims 1 to 8 is performed.

19. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer-executable program, and when the computer-executable program is executed by a processor, the method according to any one of claims 1 to 8 is executed.

20. A computer program product, characterized in that When the computer program product is run on a processor, the method according to any one of claims 1 to 8 is executed.

Images