A road generalization method, device and electronic equipment for a high-precision map

Abstract

This application relates to the field of autonomous driving technology, specifically to a method, apparatus, and electronic device for road generalization of high-precision maps. The method involves obtaining modification instructions for a specified road in a high-precision map, then determining lane modification information based on the modification instructions, and modifying the number of lanes in the same direction on the specified road to a target number of lanes based on the modification instructions. Next, from a set of candidate driving rules, the target driving rule corresponding to the target number of lanes is determined. Finally, the target driving rule is applied to the specified road to generate a target high-precision map generalized for the specified road. Based on this method, high-precision maps can be automatically and quickly generalized, achieving the technical effect of automatic generalization of simulation scenarios and maximizing the value of high-precision maps.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and in particular to a road generalization method, device and electronic device for high-precision maps. Background Technology

[0002] With the widespread application of high-definition maps in the field of autonomous driving technology, they are receiving increasing attention. Specifically, because high-definition maps contain detailed and rich road and lane information, they are widely used in the construction of simulation scenarios for autonomous driving testing or verification.

[0003] Currently, the construction of simulation scenarios typically involves directly using original high-definition maps to create static simulation scenes. For example, the road information of each road in the high-definition map is first analyzed, and then a road network model is rendered based on the road information to construct the static simulation scene.

[0004] However, in the construction of simulation scenarios, the relevant technologies still lack a solution for generalizing the roads and lanes in high-precision maps at the high-precision map level. Consequently, it is impossible to achieve a greater degree of generalization of the simulation scenarios built on the high-precision map, and it is also impossible to maximize the value of the high-precision map. Summary of the Invention

[0005] This application provides a method, apparatus, and electronic device for road generalization of high-precision maps, which can automatically and quickly generalize high-precision maps to achieve the technical effect of automatic generalization of simulation scenarios, thereby maximizing the value of high-precision maps.

[0006] Firstly, this application provides a method for road generalization on high-precision maps, the method comprising:

[0007] Get modification instructions for a specified road in a high-precision map;

[0008] Based on the modification instruction, lane modification information is determined, and based on the lane modification information, the number of lanes in the same direction on the specified road is modified to the target number of lanes.

[0009] From the candidate travel rule set, the target travel rule corresponding to the target number of travel lanes is determined; wherein, the travel rules in the candidate travel rule set are related to the number of travel lanes.

[0010] The target travel rules are applied to the specified road to generate a target high-precision map that is generalized to the specified road.

[0011] In some possible implementations, modifying the number of lanes in the same direction of travel on the specified road to the target number of lanes based on lane modification information includes:

[0012] If the designated road is a first two-way traffic lane, and the modification instruction indicates modification to a second two-way traffic lane, then the number of lanes traveling in the same direction in the first two-way traffic lane is modified to be consistent with the number of lanes traveling in the same direction in the second two-way traffic lane; wherein, the number of lanes in the first two-way traffic lane and the number of lanes in the second two-way traffic lane are inconsistent; or

[0013] If the designated road is a first one-way traffic lane, and the modification instruction indicates modification to a second one-way traffic lane, then the number of lanes in the first one-way traffic lane is modified to be the same as the number of lanes in the second one-way traffic lane; wherein, the number of lanes in the first one-way traffic lane and the number of lanes in the second one-way traffic lane are not the same; or

[0014] If the designated road is a first two-way traffic lane, and the modification instruction indicates that it should be modified to a second one-way traffic lane, then for the first two-way traffic lane, the number of traffic lanes that are not in the same direction as the second one-way traffic lane will be set to zero, and the number of traffic lanes that are in the same direction as the second one-way traffic lane will be modified to be the same.

[0015] If the designated road is a first one-way traffic lane, and the modification instruction indicates that it should be modified to a second two-way traffic lane, then for the first one-way traffic lane, the direction and number of lanes of the first one-way traffic lane will be modified to be consistent with the second two-way traffic lane.

[0016] In some possible implementations, determining the target travel rule corresponding to the target number of lanes includes:

[0017] In response to the target number of driving lanes being a first value, it is determined that the target driving rule includes the first driving rule;

[0018] In response to the target number of driving lanes being a second value, it is determined that the target driving rule includes a second driving rule and a third driving rule;

[0019] In response to the target number of driving lanes being greater than or equal to a third value, it is determined that the target driving rule includes the second driving rule, the third driving rule, and the fourth driving rule.

[0020] In some possible implementations, applying the target travel rule to the specified road to generate a target high-precision map generalized for the specified road includes:

[0021] Obtain the connecting roads of the specified road;

[0022] Based on the target travel rules, the connection relationship between the designated road and the connecting road is determined;

[0023] Using the aforementioned connection relationship, the connection logic between the specified road and the connecting road in the high-precision map is modified to obtain a target high-precision map that generalizes to the specified road.

[0024] Secondly, this application provides an apparatus for road generalization of high-precision maps, the apparatus comprising:

[0025] The acquisition module retrieves modification instructions for a specified road in a high-precision map;

[0026] The modification module determines lane modification information based on the modification instruction, and modifies the number of lanes in the same lane direction on the specified road to the target number of lanes based on the lane modification information; wherein, the lane modification information includes lane number information and lane direction information;

[0027] The determination module determines the target travel rule corresponding to the target number of driving lanes from the candidate travel rule set; wherein the travel rules in the candidate travel rule set are related to the number of driving lanes.

[0028] The generation module applies the target travel rules to the specified road to generate a high-precision target map that is generalized to the specified road.

[0029] In some possible implementations, the modification module, which modifies the number of lanes in the same direction on the specified road to the target number of lanes based on the lane modification information, is specifically used for:

[0030] If the designated road is a first two-way traffic lane, and the modification instruction indicates modification to a second two-way traffic lane, then the number of lanes traveling in the same direction in the first two-way traffic lane is modified to be consistent with the number of lanes traveling in the same direction in the second two-way traffic lane; wherein, the number of lanes in the first two-way traffic lane and the number of lanes in the second two-way traffic lane are inconsistent; or

[0031] If the designated road is a first one-way traffic lane, and the modification instruction indicates modification to a second one-way traffic lane, then the number of lanes in the first one-way traffic lane is modified to be the same as the number of lanes in the second one-way traffic lane; wherein, the number of lanes in the first one-way traffic lane and the number of lanes in the second one-way traffic lane are not the same; or

[0032] If the designated road is a first two-way traffic lane, and the modification instruction indicates that it should be modified to a second one-way traffic lane, then for the first two-way traffic lane, the number of traffic lanes that are not in the same direction as the second one-way traffic lane will be set to zero, and the number of traffic lanes that are in the same direction as the second one-way traffic lane will be modified to be the same.

[0033] If the designated road is a first one-way traffic lane, and the modification instruction indicates that it should be modified to a second two-way traffic lane, then for the first one-way traffic lane, the direction and number of lanes of the first one-way traffic lane will be modified to be consistent with the second two-way traffic lane.

[0034] In some possible implementations, the determining module, which determines the target travel rule corresponding to the target number of lanes, is specifically used for:

[0035] In response to the target number of driving lanes being a first value, it is determined that the target driving rule includes the first driving rule;

[0036] In response to the target number of driving lanes being a second value, it is determined that the target driving rule includes a second driving rule and a third driving rule;

[0037] In response to the target number of driving lanes being greater than or equal to a third value, it is determined that the target driving rule includes the second driving rule, the third driving rule, and the fourth driving rule.

[0038] In some possible implementations, the step of applying the target travel rule to the specified road to generate a target high-precision map generalized for the specified road, the generation module is specifically used for:

[0039] Obtain the connecting roads of the specified road;

[0040] Based on the target travel rules, the connection relationship between the designated road and the connecting road is determined;

[0041] Using the aforementioned connection relationship, the connection logic between the specified road and the connecting road in the high-precision map is modified to obtain a target high-precision map that generalizes to the specified road.

[0042] Thirdly, this application provides an electronic device, the electronic device comprising:

[0043] Memory, used to store computer programs;

[0044] When the processor executes the computer program stored in the memory, it implements the above-described method steps for road generalization of high-precision maps.

[0045] Fourthly, this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method steps for road generalization of high-precision maps.

[0046] In this embodiment, firstly, the number of driving lanes on a specified road in a high-definition map is modified to achieve automatic generalization of road driving lanes. Secondly, based on a determined target travel rule, the connection logic of driving lanes on a specified road in the high-definition map is modified to achieve automatic generalization of road connection logic. Based on this, this scheme can automatically modify the number of driving lanes on a specified road in an existing high-definition map and the connection logic between driving lanes, thereby achieving automatic generalization of the driving lane portion of the high-definition map. Furthermore, by automatically and quickly generalizing the high-definition map, the technical effect of automatically generalizing the simulation scene is achieved, maximizing the value of the high-definition map.

[0047] Other features and advantages of this application will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the application. The objectives and other advantages of this application may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings. Attached Figure Description

[0048] Figure 1 A schematic diagram illustrating a possible implementation environment for this application;

[0049] Figure 2 This application provides a schematic diagram illustrating the description of a specified road in a high-precision map.

[0050] Figure 3 A flowchart of a road generalization method for high-precision maps provided in this application;

[0051] Figure 4 A schematic diagram illustrating one possible driving lane provided in this application;

[0052] Figure 5a A schematic diagram of a possible target movement rule provided for this application Figure 1 ;

[0053] Figure 5b A schematic diagram of a possible target movement rule provided for this application Figure 2 ;

[0054] Figure 5c A schematic diagram of a possible target movement rule provided for this application Figure 3 ;

[0055] Figure 5dA schematic diagram of a possible target movement rule provided for this application Figure 4 ;

[0056] Figure 6 A schematic diagram of a road generalization device for high-precision maps provided in this application;

[0057] Figure 7 A schematic diagram of the structure of an electronic device provided in this application. Detailed Implementation

[0058] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings.

[0059] First, some terms used in the embodiments of this application will be explained to facilitate understanding by those skilled in the art.

[0060] Generalization: expanding from specific and individual to general. In the embodiments of this application, generalization can be understood as making changes and derivations on real-world data such as high-precision maps.

[0061] Lane generalization: In this embodiment, lane generalization can be understood as generalizing the number of lanes on a specified road and the connection logic between the specified road and connecting roads. For example, generalization is performed on the number of lanes on a specified road. For instance, if the specified road in a real scenario is a two-way four-lane road, after generalization, it becomes a two-way six-lane road. It is easy to understand that as the number of lanes increases or decreases, new travel logic needs to be assigned to the lanes after the change in number, that is, the connection logic between roads. This is mainly applicable to application scenarios such as intersections and other road junctions, thereby realizing the generalization of lane connection logic.

[0062] It should be noted that this solution can be applied to road generalization of high-precision maps in various application scenarios such as intelligent driving, smart cities, and simulation scenarios. This solution is also suitable for tasks requiring automatic and rapid generalization of high-precision maps.

[0063] The implementation subject of this solution can be computing devices such as computing terminals, remote servers, and intelligent vehicles. By deploying on relevant computing devices and automatically modifying the lane information of specified roads in high-precision maps, it solves the problem of the lack of generalization schemes for road lanes in high-precision maps at the high-precision map level. This enables automatic and rapid generalization to high-precision maps, thereby achieving automatic generalization to simulation scenarios. Of course, this is only an illustrative example of the subject of application of this solution and does not specifically limit it.

[0064] The design concept of the road generalization method for high-precision maps provided in the embodiments of this application will be briefly introduced below.

[0065] As research into autonomous driving technology deepens, high-definition maps have become a key element guiding its development. However, the collection and production of high-definition maps is a highly complex process, requiring the application of various sensors and algorithms during the data collection phase to generate usable high-definition maps. Consequently, current high-definition map production suffers from high costs and significant challenges.

[0066] Against this backdrop, simulation scenarios built based on high-definition maps also face challenges such as high production costs and difficulties. Generally, the construction of simulation scenarios involves building the scenario based on high-definition map data through modeling and rendering by a simulation engine. In related technologies, the original high-definition map is typically used directly for constructing static simulation scenarios. For example, first, the road information of each road in the high-definition map is analyzed, and then a road network model is rendered based on the road information to construct the static simulation scenario.

[0067] It is evident that the relevant technologies, in terms of constructing simulation scenarios, do not generalize the lanes of designated roads in high-precision maps at the high-precision map level. In other words, they lack an automatic generalization scheme for lanes in high-precision maps, thus failing to generalize to a greater extent in simulation scenarios and failing to maximize the value of high-precision maps.

[0068] To achieve automatic and rapid generalization for high-definition maps, this application proposes a method for road generalization of high-definition maps. The method involves obtaining a modification instruction for a specified road in the high-definition map; then, based on the lane modification information in the modification instruction, modifying the number of lanes in the same direction on the specified road to a target number of lanes; next, determining the target travel rule corresponding to the target number of lanes from a set of candidate travel rules; and finally, applying the target travel rule to the specified road to generate a target high-definition map generalized for the specified road.

[0069] The lane modification information includes the number of lanes and the direction of the lanes; the driving rules in the candidate driving rule set are related to the number of lanes.

[0070] In this embodiment, firstly, the number of driving lanes on a specified road in a high-definition map is modified to achieve automatic generalization of road driving lanes. Secondly, based on a determined target travel rule, the connection logic of driving lanes on a specified road in the high-definition map is modified to achieve automatic generalization of road connection logic. Based on this, this scheme can automatically modify the number of driving lanes on a specified road in an existing high-definition map and the connection logic between driving lanes, thereby achieving automatic generalization of the driving lane portion of the high-definition map. Furthermore, by automatically and quickly generalizing the high-definition map, the technical effect of automatically generalizing the simulation scene is achieved, maximizing the value of the high-definition map.

[0071] The road generalization method for high-precision maps provided in this application can be applied to… Figure 1 The implementation environment shown may include at least compute nodes, operation nodes, and storage nodes.

[0072] The computing nodes are used to create high-precision maps that meet industry standards in file format based on road data collection information. Currently, the industry standard is OpenDRIVE (a file format). Furthermore, in this embodiment, the OpenDRIVE format high-precision map can be written using XML (a programming language). Of course, this solution does not impose specific restrictions on file format or programming language; this example is provided to help those skilled in the art better understand the description of high-precision maps.

[0073] For example, see Figure 2 The diagram shows a description of a specified road in a high-precision map. The left side represents the code description, while the right side represents the legend. Specifically, the codes marked in red on the left correspond to the lanes of the specified road on the right, with lane numbers 2, 1, -1, and -2. Lanes 2 and 1 represent the left lane, while lanes -1 and -2 represent the right lane. Positive and negative numbers indicate different lane directions for differentiation. However, this scheme does not impose specific restrictions on this rule.

[0074] It should also be noted that the specified road has at least one lane with a width greater than 0, and there is no limit to the number of lanes on the specified road. In addition, a center lane is used to define and describe each lane of the specified road in the high-precision map. This center lane has no width and is used as a reference for lane numbering. The center lane itself has a lane number of 0.

[0075] The operation node is used to interact with the user, enabling the user to deploy, configure, and run road generalization tasks for high-precision maps. The operation node can also obtain user-preset modification instructions for specified roads through the network. In this case, based on user-preset trigger events or default trigger cycles, the operation node can automatically deploy, configure, and run road generalization tasks for high-precision maps.

[0076] Storage nodes are used to store high-precision maps created by computing nodes, as well as various correspondences generated during the road generalization process of operation nodes on high-precision maps, for traceability.

[0077] It should be noted that the aforementioned compute nodes, operation nodes, and storage nodes are different devices, or any two or three of these nodes can be integrated into the same device. The aforementioned compute nodes are not mandatory, and this solution does not impose specific limitations on them.

[0078] The road generalization method for high-precision maps provided in this application will be described in detail below. (Reference) Figure 3 The method includes steps 31-34, as detailed below.

[0079] Step 31: Obtain modification instructions for a specified road in the high-precision map;

[0080] In this embodiment of the application, the high-precision map is a map that defines lanes. Each lane in the high-precision map is defined with a lane type. The lane type defines the main purpose of the lane and its corresponding traffic rules. For example, type=driving indicates that the lane is a driving lane.

[0081] The modification command receives user interaction instructions or preset instructions to be triggered. The modification command contains lane modification information, which mainly carries the number of lanes on the specified road in the high-precision map and information to ensure that the connection logic of the lanes after the modification meets the laws, regulations or traffic rules.

[0082] Step 32: Determine the lane modification information based on the modification instruction, and modify the number of lanes in the same direction of the specified road to the target number of lanes based on the lane modification information;

[0083] Among them, the lane modification information is the information included in the modification instruction. The lane modification information is mainly used to indicate the modification of the number of lanes for a specified road. Of course, the lane modification information can also be used to indicate the modification of the lane direction information for a specified road. The lane modification information includes the number of lanes and the lane direction information.

[0084] In this embodiment, lane modification information for a specified road is determined from the modification instruction. Then, the number of lanes on the specified road is modified to the target number of lanes based on the lane modification information. This mainly covers four scenarios, as follows.

[0085] Scenario 1: If the specified road is a first two-way traffic lane, and the modification command indicates that it should be changed to a second two-way traffic lane, then the number of lanes in the same direction in the first two-way traffic lane should be changed to be the same as the number of lanes in the same direction in the second two-way traffic lane. However, the number of lanes in the first two-way traffic lane and the number of lanes in the second two-way traffic lane are different. For example, changing a two-way 6-lane road to a two-way 4-lane road.

[0086] Scenario 2: If the specified road is the first one-way lane, and the modification command indicates that it should be changed to the second one-way lane, then the number of lanes in the first one-way lane should be changed to be the same as the number of lanes in the second one-way lane. However, the number of lanes in the first one-way lane and the number of lanes in the second one-way lane should not be the same. For example, changing a two-way lane to a three-way lane.

[0087] Scenario 3: If the specified road is a first two-way traffic lane, and the modification command indicates that it should be changed to a second one-way traffic lane, then for the first two-way traffic lane, the number of lanes in the opposite direction to the second one-way traffic lane will be set to zero, and the number of lanes in the same direction as the second one-way traffic lane will be changed to be the same. For example, a two-way 4-lane road will be changed to a one-way 2-lane road.

[0088] It should be noted that in scenario three, even if the number of lanes in the first two-way traffic lane and the second one-way traffic lane is the same, the number of lanes in the same direction will also be different due to the difference in their directions, which means that the same applies.

[0089] Scenario 4: If the specified road is a first one-way traffic lane, and the modification command indicates that it should be changed to a second two-way traffic lane, then for the first one-way traffic lane, the direction and number of lanes of the first one-way traffic lane will be modified to be consistent with the second two-way traffic lane. For example, change a two-way one-way lane to a three-way two-way lane.

[0090] It should be noted that in scenario four, even if the number of lanes in the first one-way lane and the second two-way lane are the same, the number of lanes in the same direction will also differ due to the difference in their directions, which means that the same applies.

[0091] For example, to facilitate understanding, the above situations are summarized in two tables, as detailed below.

[0092] As shown in Table 1.

[0093]

[0094]

[0095] Table 1

[0096] This step, based on the lane modification information in the modification instruction, modifies the number of lanes in the same direction on the designated road to the target number of lanes.

[0097] Step 33: Determine the target driving rule corresponding to the target number of driving lanes from the candidate driving rule set;

[0098] Among them, the travel rules in the candidate travel rule set are related to the number of driving lanes.

[0099] Before detailing the determination of target driving rules, a brief explanation of driving rules is necessary. Driving rules can be understood as a redefinition of the connection relationship, or connection logic, between a specified road and its connecting roads, to ensure that the driving rules of the specified road still comply with traffic regulations after generalization. In other words, for the same specified road, if there are different numbers of lanes in the same driving direction, the driving rules for each lane may differ. This difference is reflected in the connection relationship between that lane and other lanes on other roads. The connection relationship of lanes will be explained in detail below.

[0100] For example, at an intersection where roads intersect, the driving lanes can be described using the `junction` tag. For instance, as shown below... Figure 4 The image shows a section of junction code representing a traffic lane at an intersection. Further, within this junction, a connection is used to describe different connecting roads to the traffic lane. The `laneLink` section describes the connection relationship between the incoming road and the connecting road. In the `connection` section, the first `id` is the ID of the traffic lane within the junction; `incomingRoad` is the ID of the incoming road for this traffic lane; `connectingRoad` is the ID of the connecting road for this traffic lane; and `contactPoint` represents the contact point of the traffic lane, with a value of either `start` or `end`: when the value is `start`, the connection starts from `incomingRoad`; when the value is `end`, the connection ends at `connectingRoad`. In `laneLink`, `from` is the lane ID of the incoming road, and `to` is the lane ID of the connecting road it connects to.

[0101] As one possible implementation, the connection relationships between roads at intersections can be modified by altering the junction code. Of course, the junction code is just one possible implementation and is not specifically limited here. This solution aims to obtain information describing the connection relationships between each lane and adjacent lanes in a specified road, so as to automatically generalize the connection logic between roads using target travel rules.

[0102] Therefore, after briefly explaining the information that needs to be obtained, the following three scenarios will be used to specifically explain how to determine the target driving rules corresponding to the target number of driving lanes.

[0103] Scenario 1: In response to the target number of driving lanes being a first value, it is determined that the target driving rule includes a first driving rule, which includes at least going straight, turning left, turning right, and making a U-turn.

[0104] For example, such as Figure 5a The diagram shows the target driving rules corresponding to the first value. The number of target driving lanes is 1, and the first driving rules corresponding to this driving lane include at least going straight, turning left, turning right, and making a U-turn.

[0105] Scenario 2: In response to the target number of driving lanes being the second value, it is determined that the target driving rules include the second driving rule and the third driving rule. The second driving rule includes at least straight, left turn, and U-turn, and the third driving rule includes at least straight and right turn.

[0106] For example, such as Figure 5b The diagram shows the target driving rules corresponding to the second value. The target number of driving lanes is 2. The driving lane closest to the center lane (one-way lanes are not judged) corresponds to the second driving rule, which includes at least going straight, turning left, and making a U-turn. The other lane corresponds to the third driving rule, which includes at least going straight and turning right.

[0107] Scenario 3: In response to the target number of driving lanes being greater than or equal to the third value, it is determined that the target driving rules include the second driving rule, the third driving rule, and the fourth driving rule. The second driving rule includes at least straight, left turn, and U-turn; the third driving rule includes at least straight and right turn; and the fourth driving rule includes at least straight.

[0108] Example 1, such as Figure 5c The diagram shows the target driving rules corresponding to the third value. The target number of driving lanes is 3. The driving lane closest to the center lane (or one edge for a one-way lane) corresponds to the second driving rule, which includes at least going straight, turning left, and making a U-turn. The driving lane furthest from the center lane (or another edge for a one-way lane) corresponds to the third driving rule, which includes at least going straight and turning right. The remaining driving lanes correspond to the fourth driving rule, which includes at least going straight.

[0109] Example 2, such as Figure 5d The diagram shows the target driving rules corresponding to the third value. The number of target driving lanes is a positive number greater than 3. The driving lane closest to the center lane (or one edge for a one-way lane) corresponds to the second driving rule, which includes at least going straight, turning left, and making a U-turn. The driving lane furthest from the center lane (or another edge for a one-way lane) corresponds to the third driving rule, which includes at least going straight and turning right. The remaining driving lanes correspond to the fourth driving rule, which includes at least going straight.

[0110] It should be noted that the above three scenarios are some possible implementation methods. The purpose here is to illustrate that the first, second, third, and fourth travel rules are rules that include different travel methods, including but not limited to going straight, turning left, turning right, and making a U-turn as mentioned above.

[0111] In this embodiment, several candidate travel rule sets are set up. Based on the travel direction indicated in the travel lane modification information, the target travel rule corresponding to the target number of travel lanes is determined. The connection relationship between each travel lane in the specified road and the connecting road (of the specified road) can be obtained, thereby enabling the automatic generalization of the connection logic between roads.

[0112] Step 34: Apply the target travel rules to the specified roads to generate a high-precision target map that is generalized to the specified roads.

[0113] In this embodiment of the application, applying the target travel rule to the designated road can be understood as modifying the connection relationship between the designated road and the connecting road in the high-precision map according to the target travel rule.

[0114] Specifically, the process begins by identifying the connecting roads of a specified road, such as a crossroads or fork in the road. If this crossroads has four branching roads, and one of these branches is designated as the specified road, the other three become its connecting roads. Then, based on the target travel rules, the connection relationships between the specified road and its connecting roads are determined. These relationships are then used to modify the connection logic between the specified road and its connecting roads in the high-definition map, resulting in a target high-definition map that generalizes to the specified road.

[0115] In summary, by modifying the driving lanes of a specified road using this solution, a target high-definition map can be obtained with changes in the number of driving lanes and corresponding changes in the connection logic between driving lanes. In other words, it achieves generalization of the number of driving lanes and the driving lane connection logic in the high-definition map. Compared with the existing method of recreating the high-definition map, this method can effectively improve generalization efficiency, especially when applied to complex scenarios or large-scale high-definition map scenarios, achieving better technical results.

[0116] Furthermore, roads in the simulation scenario are generated based on the target high-definition map. This addresses the current lack of generalization schemes for roads and lanes in high-definition maps at the high-definition map level, allowing for greater generalization to the simulation scenario and maximizing the value of the high-definition map.

[0117] Based on the same inventive concept, this application also provides a device for road generalization of high-precision maps, for use in, see [link to relevant documentation]. Figure 6 The device includes:

[0118] Module 61 retrieves modification instructions for a specified road in a high-precision map;

[0119] Modification module 62 determines lane modification information based on the modification instruction, and modifies the number of lanes in the same lane direction in the specified road to the target number of lanes based on the lane modification information;

[0120] The determining module 63 determines the target travel rule corresponding to the target number of travel lanes from the candidate travel rule set; wherein the travel rules in the candidate travel rule set are related to the number of travel lanes.

[0121] The generation module 64 applies the target travel rules to the specified road to generate a target high-precision map that is generalized to the specified road.

[0122] In some possible implementations, the modification module 62, which modifies the number of lanes in the same direction of travel on the specified road to the target number of lanes based on the lane modification information, is specifically used for:

[0123] If the designated road is a first two-way traffic lane, and the modification instruction indicates modification to a second two-way traffic lane, then the number of lanes traveling in the same direction in the first two-way traffic lane is modified to be consistent with the number of lanes traveling in the same direction in the second two-way traffic lane; wherein, the number of lanes in the first two-way traffic lane and the number of lanes in the second two-way traffic lane are inconsistent; or

[0124] If the designated road is a first one-way traffic lane, and the modification instruction indicates modification to a second one-way traffic lane, then the number of lanes in the first one-way traffic lane is modified to be the same as the number of lanes in the second one-way traffic lane; wherein, the number of lanes in the first one-way traffic lane and the number of lanes in the second one-way traffic lane are not the same; or

[0125] If the designated road is a first two-way traffic lane, and the modification instruction indicates that it should be modified to a second one-way traffic lane, then for the first two-way traffic lane, the number of traffic lanes that are not in the same direction as the second one-way traffic lane will be set to zero, and the number of traffic lanes that are in the same direction as the second one-way traffic lane will be modified to be the same.

[0126] If the designated road is a first one-way traffic lane, and the modification instruction indicates that it should be modified to a second two-way traffic lane, then for the first one-way traffic lane, the direction and number of lanes of the first one-way traffic lane will be modified to be consistent with the second two-way traffic lane.

[0127] In some possible implementations, the determining module 63, which determines the target travel rule corresponding to the target number of driving lanes, is specifically used for:

[0128] In response to the target number of driving lanes being a first value, it is determined that the target driving rule includes the first driving rule;

[0129] In response to the target number of driving lanes being a second value, it is determined that the target driving rule includes a second driving rule and a third driving rule;

[0130] In response to the target number of driving lanes being greater than or equal to a third value, it is determined that the target driving rule includes the second driving rule, the third driving rule, and the fourth driving rule.

[0131] In some possible implementations, the step of applying the target travel rule to the specified road to generate a target high-precision map generalized for the specified road, the generation module 64, is specifically used for:

[0132] Obtain the connecting roads of the specified road;

[0133] Based on the target travel rules, the connection relationship between the designated road and the connecting road is determined;

[0134] Using the aforementioned connection relationship, the connection logic between the specified road and the connecting road in the high-precision map is modified to obtain a target high-precision map that generalizes to the specified road.

[0135] Based on the same inventive concept, this application also provides an electronic device that can realize the function of the aforementioned device for road generalization of high-precision maps. (Refer to...) Figure 7 The electronic device includes:

[0136] At least one processor 71 and a memory 72 connected to at least one processor 71. In this embodiment, the specific connection medium between the processor 71 and the memory 72 is not limited. Figure 7 The example shown is the connection between processor 71 and memory 72 via bus 70. Bus 70 is... Figure 7The connections between other components are indicated by thick lines and are for illustrative purposes only, not as limiting information. Bus 70 can be divided into address bus, data bus, control bus, etc., for ease of representation. Figure 7 The term 71 is represented by a single thick line, but this does not imply that there is only one bus or one type of bus. Alternatively, the processor 71 can also be called a controller; there is no restriction on the name.

[0137] In this embodiment, memory 72 stores instructions executable by at least one processor 71. By executing the instructions stored in memory 72, at least one processor 71 can perform the road generalization method for high-precision maps discussed above. Processor 71 can implement... Figure 6 The functions of each module in the device / system shown.

[0138] The processor 71 is the control center of the device / system. It can connect to various parts of the control device through various interfaces and lines. By running or executing instructions stored in memory 72 and calling data stored in memory 72, it can monitor the various functions and data processing of the device / system as a whole.

[0139] In one possible design, processor 71 may include one or more processing units. Processor 71 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understood that the modem processor may also not be integrated into processor 71. In some embodiments, processor 71 and memory 72 may be implemented on the same chip; in some embodiments, they may also be implemented on separate chips.

[0140] The processor 71 can be a general-purpose processor, such as a central processing unit (CPU), digital signal processor, application-specific integrated circuit, field-programmable gate array or other programmable logic device, discrete gate or transistor logic device, or discrete hardware component, capable of implementing or executing the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the road generalization method for high-precision maps disclosed in the embodiments of this application can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0141] Memory 72, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules. Memory 72 may include at least one type of storage medium, such as flash memory, hard disk, multimedia card, card-type memory, random access memory (RAM), static random access memory (SRAM), programmable read-only memory (PROM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), magnetic memory, magnetic disk, optical disk, etc. Memory 72 can be any other medium capable of carrying or storing desired program code in the form of instructions or data structures that can be accessed by a computer, but is not limited thereto. In the embodiments of this application, memory 72 may also be a circuit or any other device / system capable of implementing storage functions for storing program instructions and / or data.

[0142] By designing and programming the processor 71, the code corresponding to the road generalization method for high-precision maps described in the foregoing embodiments can be embedded into the chip, enabling the chip to execute it during runtime. Figure 3 The steps of the road generalization method for high-precision maps in the illustrated embodiment are described below. How to design and program the processor 71 is a technique well-known to those skilled in the art and will not be elaborated upon here.

[0143] Based on the same inventive concept, embodiments of this application also provide a storage medium storing computer instructions that, when executed on a computer, cause the computer to perform the road generalization method for high-precision maps described above.

[0144] In some possible implementations, the various aspects of the road generalization method for high-precision maps provided in this application can also be implemented in the form of a program product, which includes program code that, when the program product is run on a device, causes the control device to perform the steps in the road generalization method for high-precision maps according to the various exemplary embodiments of this application described above.

[0145] Those skilled in the art will understand that embodiments of this application can be provided as methods, apparatus / systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0146] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0147] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0148] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0149] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A road generalization method for high-precision maps, characterized in that, The method includes: Get modification instructions for a specified road in a high-precision map; Based on the modification instruction, lane modification information is determined, and based on the lane modification information, the number of lanes in the same lane direction on the specified road is modified to the target number of lanes; wherein, the lane modification information includes lane number information and lane direction information; From the candidate travel rule set, the target travel rule corresponding to the target number of travel lanes is determined; wherein, the travel rules in the candidate travel rule set are related to the number of travel lanes. Obtain the connecting roads of the specified road, and determine the connection relationship between the specified road and the connecting roads based on the target travel rule; Using the aforementioned connection relationship, the connection logic between the specified road and the connecting road in the high-precision map is modified to obtain a target high-precision map that generalizes to the specified road.

2. The method as described in claim 1, characterized in that, The step of modifying the number of lanes in the same direction on the specified road to the target number of lanes based on the lane modification information includes: If the designated road is a first two-way traffic lane, and the modification instruction indicates modification to a second two-way traffic lane, then the number of lanes traveling in the same direction in the first two-way traffic lane is modified to be consistent with the number of lanes traveling in the same direction in the second two-way traffic lane; wherein, the number of lanes in the first two-way traffic lane and the number of lanes in the second two-way traffic lane are inconsistent; or If the designated road is a first one-way traffic lane, and the modification instruction indicates modification to a second one-way traffic lane, then the number of lanes in the first one-way traffic lane is modified to be the same as the number of lanes in the second one-way traffic lane; wherein, the number of lanes in the first one-way traffic lane and the number of lanes in the second one-way traffic lane are not the same; or If the designated road is a first two-way traffic lane, and the modification instruction indicates that it should be modified to a second one-way traffic lane, then for the first two-way traffic lane, the number of traffic lanes that are not in the same direction as the second one-way traffic lane will be set to zero, and the number of traffic lanes that are in the same direction as the second one-way traffic lane will be modified to be the same. If the designated road is a first one-way traffic lane, and the modification instruction indicates that it should be modified to a second two-way traffic lane, then for the first one-way traffic lane, the direction and number of lanes of the first one-way traffic lane will be modified to be consistent with the second two-way traffic lane.

3. The method as described in claim 1, characterized in that, The determination of the target travel rule corresponding to the target number of driving lanes includes: In response to the target number of driving lanes being a first value, it is determined that the target driving rule includes the first driving rule; In response to the target number of driving lanes being a second value, it is determined that the target driving rule includes a second driving rule and a third driving rule; In response to the target number of driving lanes being greater than or equal to a third value, it is determined that the target driving rule includes the second driving rule, the third driving rule, and the fourth driving rule.

4. A road generalization device for high-precision maps, characterized in that, The device includes: The acquisition module retrieves modification instructions for a specified road in a high-precision map; The modification module determines lane modification information based on the modification instruction, and modifies the number of lanes in the same lane direction on the specified road to the target number of lanes based on the lane modification information; wherein, the lane modification information includes lane number information and lane direction information; The determination module determines the target travel rule corresponding to the target number of driving lanes from the candidate travel rule set; wherein, the travel rules in the candidate travel rule set are related to the number of driving lanes. The generation module obtains the connecting roads of the specified road and determines the connection relationship between the specified road and the connecting roads based on the target travel rules; using the connection relationship, it modifies the connection logic of the specified road and the connecting roads in the high-precision map to obtain a target high-precision map generalized for the specified road.

5. The apparatus as described in claim 4, characterized in that, The modification module, which modifies the number of lanes in the same direction on the specified road to the target number of lanes based on the lane modification information, is specifically used for: If the designated road is a first two-way traffic lane, and the modification instruction indicates modification to a second two-way traffic lane, then the number of lanes traveling in the same direction in the first two-way traffic lane is modified to be consistent with the number of lanes traveling in the same direction in the second two-way traffic lane; wherein, the number of lanes in the first two-way traffic lane and the number of lanes in the second two-way traffic lane are inconsistent; or If the designated road is a first one-way traffic lane, and the modification instruction indicates modification to a second one-way traffic lane, then the number of lanes in the first one-way traffic lane is modified to be the same as the number of lanes in the second one-way traffic lane; wherein, the number of lanes in the first one-way traffic lane and the number of lanes in the second one-way traffic lane are not the same; or If the designated road is a first two-way traffic lane, and the modification instruction indicates that it should be modified to a second one-way traffic lane, then for the first two-way traffic lane, the number of traffic lanes that are not in the same direction as the second one-way traffic lane will be set to zero, and the number of traffic lanes that are in the same direction as the second one-way traffic lane will be modified to be the same. If the designated road is a first one-way traffic lane, and the modification instruction indicates that it should be modified to a second two-way traffic lane, then for the first one-way traffic lane, the direction and number of lanes of the first one-way traffic lane will be modified to be consistent with the second two-way traffic lane.

6. The apparatus as claimed in claim 4, characterized in that, The module for determining the target travel rule corresponding to the target number of driving lanes is specifically used for: In response to the target number of driving lanes being a first value, it is determined that the target driving rule includes the first driving rule; In response to the target number of driving lanes being a second value, it is determined that the target driving rule includes a second driving rule and a third driving rule; In response to the target number of driving lanes being greater than or equal to a third value, it is determined that the target driving rule includes the second driving rule, the third driving rule, and the fourth driving rule.

7. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor, when executing a computer program stored in the memory, implements the method steps of any one of claims 1-3.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the method described in any one of claims 1-3.

Images