Lane-level navigation method and device, computer equipment, storage medium, program product and mobile platform

Abstract

A lane-level navigation method, apparatus, computer device, storage medium, program product and mobile platform wherein the lane-level navigation method comprises: determining a road-level navigation route from a current position of a vehicle to a destination according to road-level information of a standard map, the road-level navigation route comprising a plurality of road segments (S10); determining a topological map between lanes in the plurality of road segments according to lane level information of the standard precise map (S20); and navigating at least according to the topological map (S30). According to the lane-level navigation method, a road-level navigation route is divided into a plurality of road sections, and a topological relation between lanes of adjacent road sections is established by adopting a preset alignment mode based on lane-level information of a standard map, so that a topological map between the lanes on the whole road-level navigation route is finally determined; therefore, lane-level navigation can be realized on the basis of the method without a high-precision map and a reinforced standard definition map.

Description

Lane-level navigation method and device, computer equipment, storage medium, program product and mobile platform TECHNICAL FIELD

[0001] The present application relates to the technical field of automatic driving, and in particular to a lane-level navigation method and device, computer equipment, storage medium, program product and mobile platform. BACKGROUND

[0002] With the development of automatic driving technology, the city navigation auxiliary driving function is introduced in the related technology. However, all the schemes on the market at present are realized based on high-precision maps or enhanced version of standard-precision maps. The high-precision maps and the enhanced version of standard-precision maps have high cost, small coverage range and low update frequency, so that the city navigation auxiliary driving function has high cost and is unstable.

[0003] SUMMARY

[0004] The present application provides a lane-level navigation method and device, computer equipment, storage medium, program product and mobile platform, which are used to at least solve one of the above technical problems.

[0005] In a first aspect, the present application provides a lane-level navigation method, comprising: determining a road-level navigation route from a current position of a vehicle to a destination according to road-level information of a standard-precision map, the road-level navigation route comprising a plurality of road segments; determining a topological map between lanes in the plurality of road segments according to lane-level information of the standard-precision map; and performing navigation at least according to the topological map.

[0006] In some embodiments, the plurality of road segments comprises adjacent first and second road segments; and determining the topological map between lanes in the plurality of road segments according to the lane-level information of the standard-precision map comprises: connecting lanes of the first and second road segments in a preset alignment manner to form a topological relationship between the lanes of the first and second road segments.

[0007] In some embodiments, connecting lanes of the first and second road segments in a preset alignment manner to form a topological relationship between the lanes of the first and second road segments comprises: connecting the lanes of the first and second road segments in a left-lane alignment manner and / or a right-lane alignment manner to form the topological relationship between the lanes of the first and second road segments.

[0008] In some embodiments, the lane-level navigation method further comprises: in the case that the number of lanes of the first and second road segments is the same, connecting the lanes of the first and second road segments one-to-one to form the topological relationship between the lanes of the first and second road segments.

[0009] In some embodiments, the lane-level navigation method further comprises: determining a local inter-lane topology relationship within a perception range of the vehicle according to the vehicle perception information; and navigating at least according to the topology map, comprising: navigating according to the local inter-lane topology relationship and the topology map.

[0010] In some embodiments, the navigating according to the local inter-lane topology relationship and the topology map comprises: updating the topology map according to the local inter-lane topology relationship; and navigating according to the updated topology map.

[0011] In some embodiments, the navigating according to the updated topology map comprises: determining whether a lane-changing opportunity is met according to road traffic information; and controlling the vehicle to change lanes according to the updated topology map when the lane-changing opportunity is met.

[0012] In a second aspect, the embodiments of the present application provide a lane-level navigation device, comprising:

[0013] a navigation route determination module configured to determine a road-level navigation route from a current position of a vehicle to a destination according to road-level information of a detailed map, the road-level navigation route comprising a plurality of road segments;

[0014] a topology map determination module configured to determine a topology map of inter-lanes in the plurality of road segments according to lane-level information of the detailed map;

[0015] a navigation module configured to navigate at least according to the topology map.

[0016] In a third aspect, the embodiments of the present application provide a computer device, comprising a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of any of the lane-level navigation methods described above.

[0017] In a fourth aspect, the embodiments of the present application provide a computer-readable storage medium, which stores a computer program / instruction, wherein the computer program / instruction is executed by a processor to implement the steps of any of the lane-level navigation methods described above.

[0018] In a fifth aspect, the embodiments of the present application provide a computer program product, comprising a computer program / instruction, wherein the computer program / instruction is executed by a processor to implement the steps of any of the lane-level navigation methods described above.

[0019] In a sixth aspect, the embodiments of the present application provide a mobile platform, which is installed with the computer device described above.

[0020] Firstly, the road-level navigation route from the current position of the vehicle to the destination is determined according to the road-level information of the labeled map in the application; then the topological map between lanes in the road segments on the road-level navigation route is determined according to the lane-level information of the labeled map; finally, the lane-level navigation is realized based on the topological map. The above process of realizing the lane-level navigation does not depend on the high-precision map or the enhanced labeled map, thereby reducing the cost of the lane-level navigation and improving the stability of the lane-level navigation. BRIEF DESCRIPTION OF DRAWINGS

[0021] In order to more clearly illustrate the technical solutions of the embodiments of the application, the drawings needed to be used in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are some embodiments of the application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0022] Fig. 1 is a flowchart of an embodiment of the lane-level navigation method of the application;

[0023] Fig. 2a and Fig. 2b are schematic diagrams of the one-to-one connection method for connecting the topology between lanes in the application;

[0024] Fig. 3a and Fig. 3b are schematic diagrams of the left lane alignment method for connecting the topology between lanes in the application;

[0025] Fig. 4a and Fig. 4b are schematic diagrams of the right lane alignment method for connecting the topology between lanes in the application;

[0026] Fig. 5a and Fig. 5b are schematic diagrams of the left lane alignment method and the right lane alignment method for connecting the topology between lanes in the application;

[0027] Fig. 6 is a flowchart of another embodiment of the lane-level navigation method of the application;

[0028] Fig. 7a is a schematic diagram of the right side growing road in the application;

[0029] Fig. 7b is a schematic diagram of the left side growing road in the application;

[0030] Fig. 8 is a principle block diagram of an embodiment of the lane-level navigation device of the application;

[0031] Fig. 9 is a structural schematic diagram of an embodiment of the computer device of the application. DETAILED DESCRIPTION

[0032] In order to make the purposes, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some but not all of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall into the scope of protection of the present application. It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict.

[0033] It should also be noted that, in this document, the terms "comprising" and "including" not only include those elements, but also include other elements not explicitly listed, or further include elements inherent in the process, method, article, or device. Without more limitations, the elements defined by the statement "comprising" do not exclude the presence of other identical elements in the process, method, article, or device that includes the elements.

[0034] The present application proposes a lane-level navigation method, which is applied to an automatic driving vehicle to realize an automatic driving function. The automatic driving function includes but is not limited to an urban navigation auxiliary driving function.

[0035] As shown in FIG. 1, it is a flowchart of an embodiment of the lane-level navigation method of the present application, which includes the following steps:

[0036] S10, determining a road-level navigation route from a current position of a vehicle to a destination according to road-level information of a standard detailed map, the road-level navigation route including a plurality of road segments.

[0037] Exemplarily, after a user sets a destination on a human-computer interaction screen, a navigation system calculates N routes (N is greater than or equal to 1) from a current position to the destination based on road-level information (including but not limited to: road topological connection relationship, road grade, road speed limit, road length, road congestion degree, etc.) of an SD Map (standard detailed map), and recommends the user to select on the human-computer interaction screen. The method for calculating the N routes from the current position to the destination can adopt any method in existing road-level navigation technology, which is not limited in the present application.

[0038] In response to a selection operation of the user on the human-computer interaction screen, a road-level navigation route is determined from the N routes, and the road-level navigation route includes a plurality of road segments. Exemplarily, the road-level navigation route is divided into a plurality of road segments, and each road segment includes a plurality of lanes.

[0039] S20, determining a topological map between lanes in the plurality of road segments according to lane-level information of the standard detailed map.

[0040] Exemplarily, the lane-level information of the labeled map includes but is not limited to the number of lanes, the left-right adjacency relationship between lanes, lane turning information, etc. Correspondingly, the labeled map includes lane-level information of each road segment (for example, the number of lanes on each lane segment, the left-right adjacency relationship between lanes, lane turning information, etc.); or the lane-level information of each road segment (for example, the number of lanes on each lane segment, the left-right adjacency relationship between lanes, lane turning information, etc.) can be determined according to the lane-level information of the labeled map.

[0041] According to the lane-level information of the labeled map, the topology map between lanes in the plurality of road segments is determined, including: determining the topology map between lanes in the plurality of road segments according to the lane-level information of each road segment. Exemplarily, the topology map between lanes includes but is not limited to lane-level topology: left-right adjacency relationship, front-back successor relationship, split-merge relationship, and lane connection relationship before and after an intersection. The lane-level topology is a necessary element in the high-definition map, and the autonomous vehicle relies on the lane-level road topology to complete lane changing, split-merge, intersection passing, on-ramp and off-ramp behaviors, etc. Exemplarily, the topology relationship between lanes in a first road segment and a second road segment adjacent to the first road segment is determined according to the lane-level information of the first road segment and the second road segment, wherein the topology relationship between lanes includes but is not limited to the left-right adjacency relationship between lanes and the front-back successor relationship between lanes, etc. Determining the topology relationship between lanes in the first road segment and the second road segment adjacent to the first road segment according to the lane-level information of the first road segment and the second road segment includes: determining the left-right adjacency relationship between lanes in the first road segment according to the lane-level information of the first road segment; determining the left-right adjacency relationship between lanes in the second road segment according to the lane-level information of the second road segment; and determining the front-back successor relationship between lanes in the first road segment and the second road segment according to the left-right adjacency relationship between lanes in the first road segment and the left-right adjacency relationship between lanes in the second road segment, and according to a preset alignment mode (including a left lane alignment mode and / or a right lane alignment mode).

[0042] S30, navigating at least according to the topology map.

[0043] Exemplarily, the lane-level navigation of the vehicle is implemented according to the generated topology map between lanes. After obtaining the topology map between lanes, the lane-level navigation route from the current position of the vehicle to the destination can be determined, so as to implement the lane-level navigation. Exemplarily, a plurality of road segments included in the route from the current position of the vehicle to the destination are determined, and then the lane-level navigation route from the current position of the vehicle to the destination is determined according to the topology map between the plurality of road segments. For example, it is determined that the route from the current position of the vehicle to the destination includes one left turn and one right turn, and then the lane-level path for driving to the left turn lane (for example, the leftmost lane) before the left turn is planned according to the topology map between the plurality of road segments (including the left and right adjacency relationship and the predecessor and successor relationship between lanes), the lane-level path for driving to the right turn lane (for example, the rightmost lane) before the right turn is further planned, and the lane-level navigation route from the current position of the vehicle to the destination is generated according to the determined lane-level paths of the segments.

[0044] In the embodiment, first, the road-level navigation route from the current position of the vehicle to the destination is determined according to the road-level information of the landmark map, the road-level navigation route includes a plurality of road segments; then the topology map between lanes of the plurality of road segments on the road-level navigation route is determined according to the lane-level information of the landmark map; finally, the lane-level navigation is implemented based on the topology map. The above process of implementing the lane-level navigation does not depend on the high-precision map or the enhanced landmark map, thereby reducing the cost of the lane-level navigation and improving the stability of the lane-level navigation.

[0045] In some embodiments, the plurality of road segments include adjacent first and second road segments; and determining the topology map between lanes in the plurality of road segments according to the lane-level information of the landmark map includes: connecting the lanes of the first and second road segments in a preset alignment manner to form the topology relationship between the lanes of the first and second road segments.

[0046] Exemplarily, the number of lanes of the first road segment and the second road segment can be the same or different. When the number of lanes of the first road segment and the second road segment is the same, one-to-one corresponding connection between the lanes of the first road segment and the second road segment is achieved according to a preset alignment mode (for example, the preset alignment mode includes a left lane alignment mode and / or a right lane alignment mode). When the number of lanes of the first road segment and the second road segment is different, one-to-one corresponding connection and one-to-many corresponding connection between the lanes of the first road segment and the second road segment are achieved according to the preset alignment mode (for example, when the first road segment includes three lanes and the second road segment includes four lanes, the first to third lanes in the first road segment are connected to the first to third lanes in the second road segment one-to-one according to the preset alignment mode, and the third lane in the first road segment is connected to the fourth lane in the second road segment, then the first to second lanes of the first road segment and the second road segment are one-to-one corresponding connection, and the third lane of the first road segment and the third to fourth lanes of the second road segment are one-to-many corresponding connection).

[0047] The present application finally determines the topological map between the lanes on the entire road-level navigation route by dividing the road-level navigation route into multiple road segments and establishing the topological relationship between the lanes of adjacent road segments based on the lane-level information of the high-definition map, so that lane-level navigation can be achieved without high-definition map and enhanced standard-definition map.

[0048] In some embodiments, the lane-level navigation method of the present application further includes: in the case where the number of lanes of the first road segment and the second road segment is the same, connecting the lanes of the first road segment and the second road segment one-to-one to form the topological relationship between the lanes of the first road segment and the second road segment.

[0049] As shown in FIGS. 2a and 2b, they are schematic diagrams of one-to-one connection between lanes. In the figure, the circles represent lanes, and the connection lines between the circles represent the topological relationship between the lanes of two road segments. Among them, FIG. 2a takes the first road segment including three lanes (corresponding to three circles, N1=3) and the second road segment including three lanes (corresponding to three circles, N2=3) as an example; FIG. 2b takes the first road segment including four lanes (corresponding to four circles, N1=4) and the second road segment including four lanes (corresponding to four circles, N2=4) as an example.

[0050] In some embodiments, connecting the lanes of the first road segment and the second road segment according to a preset alignment mode to form the topological relationship between the lanes of the first road segment and the second road segment includes: connecting the lanes of the first road segment and the second road segment according to a left lane alignment mode and / or a right lane alignment mode to form the topological relationship between the lanes of the first road segment and the second road segment.

[0051] Exemplarily, the preset alignment manners include a left-lane alignment manner and / or a right-lane alignment manner. In some embodiments, the left-lane alignment manner is adopted to connect the lanes of the first road segment and the second road segment to form the topological relationship between the lanes of the first road segment and the second road segment.

[0052] As shown in FIG. 3a and FIG. 3b, the schematic diagrams of the topological connection between the lanes in the left-lane alignment manner are shown. In the diagrams, the circles represent the lanes, and the lines between the circles represent the topological relationship between the lanes of the two road segments. Taking an example in which the first road segment includes three lanes (corresponding to three circles) and the second road segment includes four lanes (corresponding to four circles), FIG. 3a is a right-growth-type road (i.e., three lanes change to four lanes, and a new lane is added to the right side of the road segment), and FIG. 3b is a left-growth-type road (i.e., three lanes change to four lanes, and a new lane is added to the left side of the road segment).

[0053] The left-lane alignment manner refers to that, starting from the leftmost lane in the first road segment and the second road segment, the left first lane of the first road segment is connected to the left first lane of the second road segment, the left second lane of the first road segment is connected to the left second lane of the second road segment, the left third lane of the first road segment is connected to the left third lane of the second road segment, and the left fourth lane of the first road segment is connected to the left fourth lane of the second road segment.

[0054] The topological relationship between the lanes of the adjacent road segments is constructed in the manner of the above embodiments, so that the construction of the entire lane topological map can be completed, and the lane-level navigation can be implemented.

[0055] However, the inventors have found in the implementation of the present application that, according to the road-level lane information, it is only known that the first road segment includes three lanes and the second road segment includes four lanes, but it cannot be determined whether the road is a left-growth-type road or a right-growth-type road. If the road is a right-growth-type road, the topological relationship between the lanes in FIG. 3a constructed according to the left-lane alignment manner is correct. If the road is a left-growth-type road, the topological relationship between the lanes in FIG. 3b constructed according to the left-lane alignment manner is incorrect (only the incorrect topological relationship is constructed), which will lead to the incorrect topological relationship between the lanes of the first road segment and the second road segment constructed based thereon. Finally, the accuracy and stability of the lane-level navigation will be affected.

[0056] In some embodiments, the right-lane alignment manner is adopted to connect the lanes of the first road segment and the second road segment to form the topological relationship between the lanes of the first road segment and the second road segment.

[0057] As shown in FIG. 4a and FIG. 4b, a schematic diagram of lane inter-topology connection in right lane alignment mode is shown. Circles in the diagram represent lanes, and the connection between the circles represents the topology relationship between the lanes of two road segments. Taking a first road segment including three lanes (corresponding to three circles) and a second road segment including four lanes (corresponding to four circles) as an example. In FIG. 4a, a left growing type road (i.e., three lanes become four lanes, and a new lane is added on the left side of the road segment) is shown, and in FIG. 4b, a right growing type road (i.e., three lanes become four lanes, and a new lane is added on the right side of the road segment) is shown.

[0058] The right lane alignment mode refers to that, starting from the rightmost lanes in the first road segment and the second road segment, the right first lane of the first road segment is connected to the right first lane of the second road segment, the right second lane of the first road segment is connected to the right second lane of the second road segment, the right third lane of the first road segment is connected to the right third lane of the second road segment, and the right fourth lane of the first road segment is connected to the right fourth lane of the second road segment.

[0059] The topology relationship between the lanes of adjacent road segments is constructed through the above-mentioned embodiments, so that the construction of the entire lane topology map can be completed, and lane-level navigation can be implemented.

[0060] However, the inventors found in the process of implementing the present application that according to the road-level lane information, it is only known that the first road segment includes three lanes and the second road segment includes four lanes, but it cannot be determined whether the road is a left growing type road or a right growing type road. If the road is a left growing type road, the topology relationship between the lanes in FIG. 4a constructed according to the right lane alignment mode is correct. If the road is a right growing type road, the topology relationship between the lanes in FIG. 4b constructed according to the right lane alignment mode is incorrect (only incorrect topology relationship is constructed), which will lead to incorrect topology relationship between the lanes of the first road segment and the second road segment based on the construction. Finally, the accuracy and stability of lane-level navigation will be affected.

[0061] Further, in order to improve the accuracy and stability of lane-level navigation, for the incorrect topology relationship between the lanes of the first road segment and the second road segment caused by only using the left lane alignment mode or the right lane alignment mode in the above-mentioned embodiments, and only incorrect topology relationship exists, the following embodiments are proposed: connecting the lanes of the first road segment and the second road segment by using the left lane alignment mode and the right lane alignment mode to form the topology relationship between the lanes of the first road segment and the second road segment.

[0062] As shown in FIG. 5a and FIG. 5b, schematic diagrams for lane-to-lane topology connection using both left lane alignment and right lane alignment are shown. Circles in the diagrams represent lanes, and lines between the circles represent the topology relationship between the lanes of two road segments. Taking an example of a first road segment including three lanes (corresponding to three circles) and a second road segment including four lanes (corresponding to four circles), in FIG. 5a, the topology connection relationship corresponds to the superposition of FIG. 3a and FIG. 4b, which is a right-side growing road (i.e., three lanes become four lanes, and a new lane is added to the right side of the road segment). In FIG. 5b, the topology connection relationship corresponds to the superposition of FIG. 3b and FIG. 4a, which is a left-side growing road (i.e., three lanes become four lanes, and a new lane is added to the left side of the road segment).

[0063] In this embodiment, since both left lane alignment and right lane alignment are used for lane-to-lane topology connection, whether the road is a left-side growing road or a right-side growing road, the constructed topology relationship between the lanes of the first road segment and the second road segment ensures the existence of correct topology relationship consistent with the actual situation, and guarantees that the real topology connection relationship has a non-zero connection probability.

[0064] In some embodiments, the lane-level navigation method of the present application further includes: determining a local lane-to-lane topology relationship within the vehicle perception range according to vehicle perception information; and navigating at least according to the topology map, including: navigating according to the local lane-to-lane topology relationship and the topology map.

[0065] For example, vehicle perception information includes but is not limited to image information captured by vehicle cameras, detection information obtained by vehicle radars, etc. Taking image information captured by vehicle cameras as an example, the vehicle can collect image information within the visual range of the camera, identify the lanes according to the image information, and determine the topology relationship between the lanes on the road segment within the visual range according to the identified lanes, i.e., the local lane-to-lane topology relationship.

[0066] In this embodiment, the local lane-to-lane topology relationship within the vehicle perception range is determined according to vehicle perception information, and lane-level navigation is performed in combination with the constructed topology map. This method is based on the accurate local lane-to-lane topology relationship determined by vehicle perception information, which makes up for the problem of incorrect lane topology relationship introduced by the simultaneous use of left lane alignment and right lane alignment, and improves the accuracy and stability of lane-level navigation.

[0067] In some embodiments, navigating according to the local lane-to-lane topology relationship and the topology map includes: updating the topology map according to the local lane-to-lane topology relationship; and navigating according to the updated topology map.

[0068] Exemplarily, after the local inter-lane topological relationship is determined, the corresponding inter-lane topological relationship in the topological map is updated according to the local inter-lane topological relationship, and lane-level navigation is performed according to the updated topological map. Exemplarily, the topological map contains the inter-lane topological relationship of a plurality of road segments and the position information of each road segment. Here, the position information corresponding to the local inter-lane topological relationship can be determined according to the current positioning information of the vehicle, so as to further determine the inter-lane topological relationship of the corresponding road segment (for example, the inter-lane topological relationship of the road segment where the vehicle is currently located).

[0069] For example, redundant and erroneous topological relationship in the corresponding inter-lane topological relationship in the topological map is deleted according to the local inter-lane topological relationship, that is, the inter-lane topological relationship with redundant and erroneous topological relationship is collapsed into an inter-lane topological relationship containing only correct topological relationship.

[0070] As shown in FIG. 6, it is a flowchart of another embodiment of the lane-level navigation method of the present application. In this embodiment, navigation is performed according to the updated topological map, which includes:

[0071] S31, determining whether to meet a lane-changing occasion according to road traffic information. The road traffic information includes at least one of the following: road passable distance, road congestion degree, road level, road speed limit and road length. The lane-changing occasion refers to a lane-changing condition. When the lane-changing condition is met, the vehicle is controlled to change lanes, and when the lane-changing condition is not met, the vehicle is controlled to keep lanes.

[0072] Exemplarily, the first cost of keeping lanes of the vehicle and / or the second cost of changing lanes of the vehicle are determined according to the road traffic information; and whether to meet the lane-changing occasion is determined according to the first cost and / or the second cost.

[0073] Exemplarily, when the road level is a preset level and the road passable distance is less than a preset distance (for example, the road level is an expressway and the preset distance is 2km; or the road level is an urban expressway and the preset distance is 1km), it is determined that the lane-changing occasion is met, and the vehicle is controlled to change lanes.

[0074] Exemplarily, when the road level is a preset level, the road passable distance is less than a preset distance, and the road ahead is relatively congested (for example, the road level is an expressway and the preset distance is 3km; or the road level is an urban expressway and the preset distance is 1.5km), it is determined that the lane-changing occasion is met, and the vehicle is controlled to change lanes. In this embodiment, under the condition of the same road level, the preset distance for lane-changing control is increased according to the road congestion condition, so as to ensure that there is enough distance to complete lane-changing. It should be noted that the above judgment method for lane-changing control is only an example, and the present application is not limited thereto.

[0075] S32, when the lane changing opportunity is met, controlling the vehicle to change lane according to the updated topological map.

[0076] Illustratively, determining whether the lane changing opportunity is met according to the first cost and / or the second cost comprises: comparing the first cost and the second cost, and determining that the lane changing opportunity is met when the first cost is greater than the second cost; or comparing the first cost and a first threshold and / or comparing the second cost and a second threshold, and determining that the lane changing opportunity is met when the first cost is greater than the first threshold and / or the second cost is less than the second threshold.

[0077] In the embodiment, whether the vehicle is controlled to change lane can be determined according to only the first cost of keeping lane. For example, when the first cost of keeping lane is large enough (exceeds a set threshold), the vehicle is controlled to change lane. For example, the vehicle needs to change lane to the right once at a certain place to turn right at the most right lane of the front intersection, and is currently in the second right lane. When the distance to the intersection is far, the passable distance is large, and the cost of keeping lane is small, the system does not urge to change lane. As the distance to the intersection gradually decreases, the passable distance becomes small, and the cost of keeping lane becomes large (exceeds the set threshold), the system initiates the right lane change.

[0078] In the embodiment, whether the vehicle is controlled to change lane can be determined according to only the second cost of changing lane. For example, when the second cost of changing lane is small enough (less than a set threshold), the vehicle is controlled to change lane. For example, the vehicle needs to change lane to the right once at a certain place to turn right at the most right lane of the front intersection, and is currently in the second right lane. When the distance to the intersection is far, the passable distance is large, and the cost of changing lane to the right is large, the system does not urge to change lane. As the distance to the intersection gradually decreases, the passable distance becomes small, and the cost of changing lane to the right becomes small, the system initiates the right lane change.

[0079] In the embodiment, whether the vehicle is controlled to change lane can be determined according to both the first cost of keeping lane and the second cost of changing lane. For example, when the first cost of keeping lane is large enough (exceeds the second cost of changing lane), the vehicle is controlled to change lane. For example, the vehicle needs to change lane to the right once at a certain place to turn right at the most right lane of the front intersection, and is currently in the second right lane. When the distance to the intersection is far, the passable distance is large, and the cost of keeping lane is small, the system does not urge to change lane. As the distance to the intersection gradually decreases, the passable distance becomes small, and the cost of keeping lane becomes large, which is greater than the cost of changing lane to the right, the system initiates the right lane change.

[0080] In some embodiments, the updated topology map comprises points representing lanes and edges representing connection relationships between lanes; and determining the first cost of the vehicle keeping the lane and the second cost of the vehicle changing the lane according to the road traffic information comprises: assigning weights to edges in the updated topology map according to the road traffic information; and determining the first cost of the vehicle keeping the lane and the second cost of the vehicle changing the lane based on the topology map with the assigned weights by using a graph search algorithm.

[0081] For example, the road traffic information comprises at least one of the following: road passable distance, road congestion degree, road level, road speed limit and road length. The road traffic information can be obtained by real-time sensing of the vehicle and / or by road map data. For example, the road level, road speed limit and road length are obtained by real-time sensing of road level signs, road speed limit signs and road length by sensors of the vehicle, and the passable distance and road congestion degree are obtained by road map data. It should be noted that the above is only an example, and the present application is not limited in this regard.

[0082] For example, the longer the road passable distance, the smaller the first cost of the vehicle keeping the lane, and vice versa; the longer the road passable distance, the greater the second cost of the vehicle changing the lane, and vice versa; the greater the road congestion degree, the greater the first cost of the vehicle keeping the lane, and vice versa; the greater the road congestion degree, the smaller the second cost of the vehicle changing the lane, and vice versa; the higher the road level, the smaller the first cost of the vehicle keeping the lane, and vice versa; the higher the road level, the greater the second cost of the vehicle changing the lane, and vice versa; the lower the road speed limit, the greater the second cost of the vehicle changing the lane, and vice versa; the lower the road speed limit, the smaller the first cost of the vehicle keeping the lane, and vice versa; the longer the road length, the smaller the first cost of the vehicle keeping the lane, and vice versa; the shorter the road length, the greater the second cost of the vehicle changing the lane, and vice versa. It should be noted that at least one of the road traffic information and the first cost and the second cost is associated, and the present application is not limited in this regard.

[0083] After the edges in the topology map are weighted based on the above traffic information, the updated topology map includes points representing lanes and edges representing the connection relationship between lanes, and the edges in the topology map are weighted based on one or more of the above road traffic information. For example, the edges in the topology map are given weight values (a, b, c, d, e) of different sizes ranging from 0 to 1 according to the road passable distance, the road congestion degree, the road level, the road speed limit and the road length, respectively. Among them, the road passable distance, the road congestion degree and the road congestion degree are strong related factors, and the corresponding weight value is large; the road level, the road speed limit and the road length are weak related factors, and the corresponding weight value is small.

[0084] For the road passable distance A, the corresponding weight a is: when A is greater than 5 km, the weight a is 0.5; when A is less than 5 km and greater than 2 km, the weight a is 0.6; when A is less than 1 km, the weight a is 0.7.

[0085] For the road congestion degree B, the corresponding weight b is: when the road is smooth, the weight b is 0.6; when the road is slow, the weight b is 0.8; when the road is congested, the weight b is 0.9 (it should be noted that the above road smooth, slow and congested can correspond to the current navigation field route marking as green, red, deep red respectively, that is, the above information can be obtained according to the prior art, and the specific acquisition method is not limited by the present application).

[0086] For the road level C, the corresponding weight c is: when the road level is expressway, the weight c is 0.6; when the road level is urban expressway, the weight c is 0.5; when the road level is ordinary road, the weight c is 0.4.

[0087] For the road speed limit D, the corresponding weight d is: when the road speed limit is 120 km / h, the weight d is 0.6; when the road speed limit is 100 km / h, the weight d is 0.5; when the road speed limit is 80 km / h, the weight d is 0.4.

[0088] For the road length E, the corresponding weight e is: when the road length is more than 15 km, the weight e is 0.2; when the road length is more than 10 km, the weight e is 0.3; when the road length is more than 5 km, the weight e is 0.4.

[0089] After the weight values (a, b, c, d, e) of the above road traffic information are determined, they can be directly assigned to the corresponding edges in the topology map, or the weight values are added and then assigned to the corresponding edges in the topology map, or the weight values are multiplied and then assigned to the corresponding edges in the topology map. The above is only an example, and the present application does not limit this.

[0090] Then, a graph search algorithm is used to determine a first cost for the vehicle to stay in the lane and a second cost for the vehicle to change lanes. The graph search algorithm includes, but is not limited to, A* algorithm and Dijkstra algorithm, etc.

[0091] The lane-level navigation method provided by the present application can be implemented as a navigation scheme of a high-level assisted driving function based on an SD Map in an urban area, and can be applied to a high-level assisted driving system of an autonomous vehicle. The lane-level navigation method includes the following steps:

[0092] ①After the user sets a navigation end point, the system calculates N routes based on road-level information of the SD Map (including but not limited to road topological connection relationship, road grade, road speed limit, road length, road congestion degree, etc.), and recommends the routes to the user for selection on a human-computer interaction screen.

[0093] ②When the user selects a certain route, the system makes a navigation lane-changing decision within and outside the perception range (for example, within and outside the sight distance) based on lane-level information of the SD Map (including but not limited to the number of lanes, lane adjacency relationship, lane turning information, etc.) and real-time perception information (such as lane lines, road edges, other road users, traffic lights, ground markings, etc.).

[0094] The above navigation scheme of the present application includes global route planning at the road level and local lane-changing decision at the lane level. Based on the method of the present application, lane-changing decision can support the system to robustly select a navigation route for driving in complex traffic environments such as urban areas, highways, urban expressways, etc. based on the SD Map, and avoid missing intersections, ramp entrances, etc. due to selection of a wrong lane. Among them,

[0095] Global route planning: after the starting point and the target point are given, the system obtains a nearby road network from the SD Map, the road network is composed of nodes and connections between nodes, the system constructs the road network into a directed graph, each edge is given a weighted cost according to the road grade, road speed limit, road length, road congestion degree, etc. given by the SD Map, and then a minimum-cost route is solved based on the A* search algorithm.

[0096] Local lane-changing decision: the main difference between a high-precision map and a high-precision map is that the former can provide accurate points or coordinates of lanes and topological relationships between lanes, while the latter does not contain such information. The lane topological relationship is essential information for lane-level navigation, and the present application innovatively proposes a robust method for filling in lane topological relationships to make up for the deficiency of the original information of the high-precision map.

[0097] After obtaining the number of lanes in front of the vehicle from the SD Map, the lane topology connection relationship is supplemented according to a preset rule. The preset rule can be a mapping algorithm, the input of the algorithm being the number of lanes N1 and N2 of two sections of lanes and the traffic direction of each lane, and the output being the topology connection relationship of the two sections of lanes.

[0098] When N1=N2, the lane connection mode is "one-to-one" direct connection. Taking N1=N2=3 and N1=N2=4 as examples, the topology connection relationship is shown in FIG. 2a and FIG. 2b.

[0099] When N1+1=N2, there are two cases of actual roads, i.e. right side growth type road and left side growth type road. The lane is abstracted as a point, represented by a circle in the figure, and taking N1=3, N2=4 as an example, the scene can be visualized as FIG. 7a and FIG. 7b. Among them, FIG. 7a is a schematic diagram of a right side growth type road, and FIG. 7b is a schematic diagram of a left side growth type road.

[0100] The connection mode adopted by the algorithm is left lane alignment mode and right lane alignment mode. The left lane alignment mode is "left 1 to left 1", "left 2 to left 2", "left 3 to left 3", and "left 3 to left 4", and the right lane alignment mode is the same, as shown in FIG. 3a and FIG. 4a.

[0101] However, the algorithm cannot know which actual road condition is, and when the guess is wrong, the topology connection diagram is shown in FIG. 3b and FIG. 4b.

[0102] When the topology relationship is supplemented incorrectly, it will cause the vehicle to not change lanes in time or change lanes unnecessarily. To solve this problem, the present application proposes a multi-hypothesis matching topology mode, i.e. not using a single topology connection relationship, but superimposing multiple possibilities, and the combination effect is shown in FIG. 5a and FIG. 5b.

[0103] The multi-hypothesis topology contains connection probability, i.e. the connection relationship between two lanes appears in how many possibilities. In the above example, "left 1 connects left 1" exists in two cases, so the connection probability is 100%; "left 1 connects left 2" exists in only one case, so the connection probability is 50%. The scheme of "multi-hypothesis topology" ensures that the real topology connection relationship has a non-zero connection probability. And when the ego vehicle gradually approaches the lane number change point, the topology connection relationship will converge to the correct connection mode due to the in-visibility range observation. However, since the topology connection relationship that does not actually exist is also added, the ego vehicle will have a situation of "should change lanes but does not initiate lane change" during the super-visibility range navigation. When the ego vehicle can observe the real road condition in front (i.e. after entering the in-visibility range), the multi-hypothesis topology connection relationship can be collapsed into a single-hypothesis topology connection relationship according to the detected lane line condition, at which time the system can accurately identify whether the lane change is missing during the super-visibility range navigation, and if so, will immediately initiate lane change to the target lane to prevent driving into the wrong lane of the traffic direction.

[0104] After completing the topology connection relationship brain supplement, the road can be abstracted into a directed graph, and the node of the graph is the point (such as the circle in the figure) abstracted from the lane, and the edge of the graph is the topology connection relationship. Each edge is given a weighted cost (Weighted Cost) according to the passable distance, road grade, road speed limit, road length, road congestion degree, etc. given by the SD Map to obtain the total cost, and then the best lane change opportunity is calculated by the graph search algorithm (Graph Search) to initiate navigation lane change. The above total cost integrates various weighted costs, wherein the larger the passable distance, the smaller the total cost (Cost); the higher the road grade and the lower the congestion degree, the smaller the Cost. For example, when the ego vehicle needs to turn right at the rightmost lane at the front intersection, and is currently in the second lane on the right, it needs to complete a right lane change at a certain place. When the distance to the intersection is very far, the passable distance is large, the cost of lane keeping is small, and the system does not rush to change lanes; as the distance to the intersection gradually decreases, the passable distance becomes smaller, and the cost of lane keeping becomes larger than the cost of right lane change, at which time the system will initiate right lane change.

[0105] The entire navigation route is split into in-visibility range and out-of-visibility range parts according to the observation condition, the in-visibility range lane is connected according to the single-hypothesis topology connection of the observed lane line, the out-of-visibility range lane is connected according to the multi-hypothesis topology connection, the topology of the missing lane in the SD Map is completed, and then the best lane change opportunity is calculated based on the graph search algorithm.

[0106] As shown in FIG. 8, it is a principle block diagram of an embodiment of the lane-level navigation device of the present application. In this embodiment, the lane-level navigation device 800 includes:

[0107] The navigation route determination module 810 is configured to determine a road-level navigation route from a current position of a vehicle to a destination according to road-level information of a high-definition map, the road-level navigation route including a plurality of road segments.

[0108] The topology map determination module 820 is configured to determine a topology map between lanes in the plurality of road segments according to lane-level information of the high-definition map. For example, the topology map between lanes in the plurality of road segments is determined according to lane-level information of the high-definition map, including: determining the topology map between lanes in the plurality of road segments according to lane-level information of each road segment. For example, the topology map between lanes includes, but is not limited to, lane-level topology: left-right adjacent relationship, front-back successive relationship, split-merge relationship, and connection relationship between lanes before and after an intersection. The lane-level topology is a necessary element in a high-definition map, and an autonomous vehicle relies on the lane-level topology to complete lane changing, split-merge, intersection passing, on-ramp and off-ramp behaviors. For example, the topology relationship between lanes in a first road segment and a second road segment adjacent to the first road segment is determined according to lane-level information of the first road segment and the second road segment, and the topology relationship between lanes includes, but is not limited to, left-right adjacent relationship between lanes and front-back successive relationship between lanes. The topology relationship between lanes in the first road segment and the second road segment adjacent to the first road segment is determined according to lane-level information of the first road segment and the second road segment, including: determining left-right adjacent relationship between lanes in the first road segment according to lane-level information of the first road segment; determining left-right adjacent relationship between lanes in the second road segment according to lane-level information of the second road segment; and determining front-back successive relationship between lanes in the first road segment and the second road segment according to the left-right adjacent relationship between lanes in the first road segment and the left-right adjacent relationship between lanes in the second road segment, and according to a preset alignment mode (including a left-lane alignment mode and / or a right-lane alignment mode).

[0109] The navigation module 830 is configured to navigate at least according to the topology map.

[0110] Exemplarily, the lane-level navigation of the vehicle is implemented according to the generated topology map between lanes. After obtaining the topology map between lanes, the lane-level navigation route from the current position of the vehicle to the destination can be determined, so as to implement the lane-level navigation. Exemplarily, a plurality of road segments on the route from the current position of the vehicle to the destination are determined, and then the lane-level navigation route from the current position of the vehicle to the destination is determined according to the topology map between the plurality of road segments. For example, it is determined that the route from the current position of the vehicle to the destination includes one left turn and one right turn, and then the lane-level path of driving to the left turn lane (for example, the leftmost lane) before the left turn and the lane-level path of driving to the right turn lane (for example, the rightmost lane) before the right turn are planned according to the topology map between the plurality of road segments (including the left and right neighborhood relationship and the front and rear succession relationship between lanes), and the lane-level navigation route from the current position of the vehicle to the destination is generated according to the determined lane-level paths of each segment.

[0111] In the embodiment, first, the road-level navigation route from the current position of the vehicle to the destination is determined according to the road-level information of the high-definition map by the navigation route determination module 810; then, the topology map between lanes in the plurality of road segments on the road-level navigation route is determined according to the lane-level information of the high-definition map by the topology map determination module 820; and finally, the lane-level navigation is implemented based on the topology map. The above process of implementing the lane-level navigation does not depend on the high-definition map or the enhanced high-definition map, thereby reducing the cost of the lane-level navigation and improving the stability of the lane-level navigation.

[0112] In some embodiments, the plurality of road segments includes a first road segment and a second road segment adjacent to each other; and the topology map between lanes in the plurality of road segments is determined according to the lane-level information of the high-definition map, including connecting the lanes of the first road segment and the second road segment in a preset alignment manner to form the topology relationship between the lanes of the first road segment and the second road segment.

[0113] In some embodiments, the lanes of the first road segment and the second road segment are connected in a preset alignment manner to form the topology relationship between the lanes of the first road segment and the second road segment, including connecting the lanes of the first road segment and the second road segment in a left lane alignment manner and / or a right lane alignment manner to form the topology relationship between the lanes of the first road segment and the second road segment.

[0114] In some embodiments, the topology map determination module is further configured to, in a case where the number of lanes of the first road segment and the second road segment is the same, connect the lanes of the first road segment and the second road segment one by one to form the topology relationship between the lanes of the first road segment and the second road segment.

[0115] In some embodiments, the topological map determining module is further configured to: determine, according to the vehicle perception information, a local inter-lane topological relationship within a vehicle perception range; and navigate at least according to the topological map, including: navigating according to the local inter-lane topological relationship and the topological map.

[0116] In some embodiments, the navigating according to the local inter-lane topological relationship and the topological map includes: updating the topological map according to the local inter-lane topological relationship; and navigating according to the updated topological map.

[0117] In some embodiments, the navigating according to the updated topological map includes: determining, according to road traffic information, whether a lane-changing occasion is met; and controlling the vehicle to change lanes according to the updated topological map when the lane-changing occasion is met. The road traffic information includes at least one of: a road passable distance, a road congestion degree, a road level, a road speed limit, and a road length. The lane-changing occasion refers to a lane-changing condition. When the lane-changing condition is met, the vehicle is controlled to change lanes. When the lane-changing condition is not met, the vehicle is controlled to keep lanes.

[0118] In some embodiments, the determining, according to the road traffic information, whether the lane-changing occasion is met includes:

[0119] determining, according to the road traffic information, a first cost of the vehicle keeping lanes; and / or determining, according to the road traffic information, a second cost of the vehicle changing lanes;

[0120] determining, according to the first cost and / or the second cost, whether the lane-changing occasion is met.

[0121] For example, when the road level is a preset level and the road passable distance is less than a preset distance (e.g., the road level is an expressway and the preset distance is 2 km; or the road level is an urban expressway and the preset distance is 1 km), it is determined that the lane-changing occasion is met, and the vehicle is controlled to change lanes.

[0122] For example, when the road level is a preset level, the road passable distance is less than a preset distance, and the road ahead is relatively congested (e.g., the road level is an expressway and the preset distance is 3 km; or the road level is an urban expressway and the preset distance is 1.5 km), it is determined that the lane-changing occasion is met, and the vehicle is controlled to change lanes. In this embodiment, under the same road level, the preset distance for lane-changing control is increased according to the road congestion condition, to ensure that there is enough distance to complete lane changing. It should be noted that the above judgment method for lane-changing control is only an example, and the present application is not limited in this regard.

[0123] In some embodiments, the determining, according to the first cost and / or the second cost, whether the lane-changing occasion is met includes:

[0124] The first cost and the second cost are compared in size, and when the first cost is greater than the second cost, it is determined that the lane changing opportunity is met; or, the first cost and a first threshold are compared in size and / or the second cost and a second threshold are compared in size, and when the first cost is greater than the first threshold and / or the second cost is less than the second threshold, it is determined that the lane changing opportunity is met.

[0125] In some embodiments, the updated topology map includes points representing lanes and edges representing connection relationships between lanes; and the first cost of the vehicle keeping the lane and the second cost of the vehicle changing the lane are determined according to the road traffic information, including:

[0126] The edges in the updated topology map are assigned weights according to the road traffic information;

[0127] Based on the topology map with the assigned weights, a graph search algorithm is used to determine the first cost of the vehicle keeping the lane and the second cost of the vehicle changing the lane.

[0128] In some embodiments, the road traffic information includes at least one of the following: road passable distance, road congestion degree, road grade, road speed limit, and road length. The road traffic information can be obtained in real time by the vehicle and / or obtained through road map data. For example, the road grade, road speed limit, and road length are obtained by real-time sensing of road speed limit signs, road grade signs, and road lengths through sensors of the vehicle, and the passable distance and road congestion degree are obtained through road map data. It should be noted that the above are only examples, and the present application is not limited in this regard.

[0129] The lane-level navigation device in the above embodiments can be used to perform the lane-level navigation method described in any embodiment of the present application and achieve the corresponding effects, which will not be described here.

[0130] It should be noted that, for the above-mentioned method embodiments, in order to simply describe, they are all expressed as a series of actions, but those skilled in the art should know that the present application is not limited to the order of the actions described, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification all belong to preferred embodiments, and the actions and modules involved are not necessarily required by the present application. In the above embodiments, the description of each embodiment is focused on, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0131] In some embodiments, the embodiments of the present application provide a computer device, comprising a memory, a processor and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of any of the lane-level navigation methods described above.

[0132] In some embodiments, the embodiments of the present application provide a computer readable storage medium, having stored thereon a computer program / instruction, which is executed by a processor to implement the steps of any of the lane-level navigation methods described above.

[0133] In some embodiments, the embodiments of the present application provide a computer program product, comprising a computer program / instruction, which is executed by a processor to implement the steps of any of the lane-level navigation methods described above.

[0134] The computer device, computer readable storage medium and computer program product of the embodiments of the present application described above can be used to implement the lane-level navigation method of the embodiments of the present application, and accordingly achieve the technical effects of the lane-level navigation method of the embodiments of the present application, which will not be described here. In the embodiments of the present application, the related function modules can be implemented by a hardware processor.

[0135] FIG. 9 is a schematic diagram of the hardware structure of a computer device for implementing the lane-level navigation method according to another embodiment of the present application. As shown in FIG. 9, the device comprises one or more processors 910 and a memory 920, and in FIG. 9, the processor 910 is taken as an example.

[0136] The device for implementing the lane-level navigation method can further comprise an input device 930 and an output device 940. The processor 910, the memory 920, the input device 930 and the output device 940 can be connected through a bus or other means, and in FIG. 9, the connection through the bus is taken as an example.

[0137] The memory 920 is a non-volatile computer readable storage medium, which can be used to store non-volatile software programs, non-volatile computer executable programs and modules, such as the program instructions / modules corresponding to the lane-level navigation method in the embodiments of the present application. The processor 910 executes the various function applications and data processing of the server by running the non-volatile software programs, instructions and modules stored in the memory 920, i.e. implements the lane-level navigation method of the above method embodiments.

[0138] The memory 920 can include a program storage area and a data storage area. The program storage area can store an operating system, application programs required by at least one function, and the like. The data storage area can store data created according to the use of the lane-level navigation device, and the like. In addition, the memory 920 can include a high-speed random access memory, and can also include a non-volatile memory such as at least one of a magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 920 can optionally include a memory disposed remotely with respect to the processor 910, which can be connected to the lane-level navigation device through a network. Examples of the network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0139] The input device 930 can receive input digital or character information, and generate signals related to user settings and function control of the lane-level navigation device. The output device 940 can include a display device such as a display screen. One or more modules are stored in the memory 920 and, when executed by the one or more processors 910, perform the lane-level navigation method in any of the method embodiments described above.

[0140] The above products can perform the methods provided in the embodiments of the present application, and have the corresponding function modules and beneficial effects of performing the methods. Technical details not described in detail in the embodiments can be referred to the methods provided in the embodiments of the present application.

[0141] The computer device of the embodiments of the present application exists in various forms, including but not limited to: a vehicle-mounted computer device, a mobile communication device, an ultra-mobile personal computer device, a server, and other electronic devices with data interaction functions, and the like.

[0142] In some embodiments, the present application also provides a mobile platform installed with the computer device described in any of the embodiments of the present application. The mobile platform includes but is not limited to a vehicle, a tracked robot, a biped robot, a quadruped robot, and the like, wherein the vehicle can be a passenger car, a pickup truck, a van, and the like. It should be noted that the above are only examples, and the present application does not limit the specific form of the mobile platform.

[0143] The device embodiments described above are only schematic, and the units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units, i.e., can be located in one place, or can be distributed on multiple network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the embodiments of the present application.

[0144] Those skilled in the art can clearly understand the technical solutions of the various embodiments from the above description of the embodiments, and the various embodiments can be implemented by means of software plus a general hardware platform, and of course, can also be implemented by hardware. Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, rather than limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand: the technical solutions recorded in the foregoing embodiments can still be modified, or some technical features can be replaced by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for lane-level navigation, comprising: determining a road-level navigation route from a current location of a vehicle to a destination according to road-level information of a landmark map, the road-level navigation route comprising a plurality of road segments; determining a topology map between lanes in the plurality of road segments according to lane-level information of the landmark map; navigating at least according to the topology map.

2. The method of claim 1, wherein, the plurality of road segments comprise a first road segment and a second road segment adjacent to each other; determining a topology map between lanes in the plurality of road segments according to lane-level information of the landmark map, comprises: connecting lanes of the first road segment and the second road segment according to a preset alignment mode to form a topology relationship between lanes of the first road segment and the second road segment.

3. The method of claim 2, wherein, connecting lanes of the first road segment and the second road segment according to a preset alignment mode to form a topology relationship between lanes of the first road segment and the second road segment, comprises: connecting lanes of the first road segment and the second road segment according to a left lane alignment mode and / or a right lane alignment mode to form a topology relationship between lanes of the first road segment and the second road segment.

4. The method of claim 2, wherein, further comprising: in a case where the first road segment and the second road segment have the same number of lanes, connecting lanes of the first road segment and the second road segment one-to-one to form a topology relationship between lanes of the first road segment and the second road segment.

5. The method of claim 2, wherein, further comprising: determining a local topology relationship between lanes within a perception range of the vehicle according to vehicle perception information; navigating at least according to the topology map, comprises: navigating according to the local topology relationship between lanes and the topology map.

6. The method of claim 5, wherein, navigating according to the local topology relationship between lanes and the topology map, comprises: updating the topology map according to the local topology relationship between lanes; navigating according to the updated topology map.

7. The method of claim 6, wherein, navigating according to the updated topology map, comprises: determining whether a lane-changing opportunity is met according to road traffic information; controlling the vehicle to change lanes according to the updated topology map when the lane-changing opportunity is met.

8. The method of claim 7, wherein, determining whether a lane-changing opportunity is met according to road traffic information, comprises: determining a first cost of the vehicle keeping lanes according to the road traffic information; and / or determining a second cost of the vehicle changing lanes according to the road traffic information; determining whether the lane-changing opportunity is met according to the first cost and / or the second cost.

9. The method of claim 8, wherein, determining whether the lane-changing opportunity is met according to the first cost and / or the second cost, comprises: comparing the first cost and the second cost, and determining that the lane-changing opportunity is met when the first cost is greater than the second cost; or comparing the first cost and a first threshold value and / or comparing the second cost and a second threshold value, and determining that the lane-changing opportunity is met when the first cost is greater than the first threshold value and / or the second cost is less than the second threshold value.

10. The method of claim 8, wherein, the updated topology map comprises points representing lanes and edges representing connection relationships between lanes; determining a first cost of the vehicle keeping lanes according to road traffic information and determining a second cost of the vehicle changing lanes according to road traffic information, comprises: assigning weights to edges in the updated topology map according to the road traffic information; Based on the weighted topological map, a graph search algorithm is used to determine a first cost for the vehicle to keep the lane and a second cost for the vehicle to change the lane.

11. The method according to any one of claims 7-10, characterized in that, The road traffic information comprises at least one of the following: road passable distance, road congestion degree, road level, road speed limit and road length. 12.A lane-level navigation device, comprising: a navigation route determining module configured to determine a road-level navigation route from a current position of a vehicle to a destination according to road-level information of a detailed map, the road-level navigation route comprising a plurality of road segments; a topological map determining module configured to determine a topological map between lanes in the plurality of road segments according to lane-level information of the detailed map; a navigation module configured to navigate at least according to the topological map.

13. The apparatus of claim 12, wherein, The plurality of road segments comprises a first road segment and a second road segment adjacent to each other; The topological map determining module is further configured to determine the topological map between lanes in the plurality of road segments according to lane-level information of the detailed map, comprising: connecting lanes of the first road segment and the second road segment in a preset alignment manner to form a topological relationship between the lanes of the first road segment and the second road segment.

14. The apparatus of claim 13, wherein, connecting lanes of the first road segment and the second road segment in a preset alignment manner to form a topological relationship between the lanes of the first road segment and the second road segment, comprising: connecting lanes of the first road segment and the second road segment in a left lane alignment manner and / or a right lane alignment manner to form a topological relationship between the lanes of the first road segment and the second road segment.

15. The apparatus of claim 13, wherein, The topological map determining module is further configured to, in a case where the first road segment and the second road segment have the same number of lanes, connect lanes of the first road segment and the second road segment one-to-one to form a topological relationship between the lanes of the first road segment and the second road segment.

16. The apparatus of claim 13, wherein, The topological map determining module is further configured to determine a local inter-lane topological relationship within a perception range of the vehicle according to vehicle perception information; and the navigation module is configured to navigate according to the local inter-lane topological relationship and the topological map.

17. A computer device comprising a memory, a processor, and a computer program stored on the memory, wherein the computer program comprises instructions that, when executed by the processor, cause the processor to perform the method of any one of claims 1-16. The processor executes the computer program to implement the steps of the method of any one of claims 1-11.

18. A computer readable storage medium having stored thereon computer programs / instructions, characterized in that, The computer program / instruction is executed by the processor to implement the steps of the method of any one of claims 1-11.

19. A computer program product comprising computer programs / instructions, characterized in that, The computer program / instruction is executed by the processor to implement the steps of the method of any one of claims 1-11.

20. A mobile platform, comprising: The computer equipment of claim 17 is installed. The computer equipment of claim 17 is installed.

Images