A lane combination screening method, device, equipment and storage medium
By receiving high-precision map information to screen lane combinations, using scene features to optimize lane combinations, and generating flexible and safe lane reference lines, the problem of insufficient reliability and accuracy of lane reference lines generation in the prior art is solved, and more efficient navigation path planning is achieved.
Patent Information
- Application Number
- CN202310169745.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-02-27
- Publication Date
- 2025-08-05
- Estimated Expiration
- 2043-02-27
AI Technical Summary
When generating lane reference lines, the prior art lacks reliability and accuracy, lacks flexibility, and cannot meet the fine needs of autonomous driving navigation.
By receiving high-precision map information, generating road ids and determining vehicle locations, planning several sets of lane combinations, filtering out the optimal lane combination using preset evaluation methods and scene features, extracting the center line for smoothing, and generating lane reference lines.
It improves the redundancy and flexibility of lane reference line generation, ensures the safety and diversity of paths, and adapts to navigation needs of different scenarios.
Smart Images

Figure CN116147650B_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the field of intelligent driving technology, and specifically relates to a lane combination screening method, device, equipment and storage medium. Background Art
[0002] Reference lines are generated based on navigation results from high-precision maps. The navigation results are a sequence of connected road segments, each of which is also called a link. Each link consists of multiple lanes. Map information also provides the connection between the preceding and following lanes.
[0003] Autonomous driving navigation routes require lane-level precision. Based on the link sequence and lane link relationships generated by navigation, all candidate lane combinations within a certain length range are generated, and the optimal lane combination is screened. Based on the lane centerline and boundary of the optimal combination, basic reference line information of a certain length is provided.
[0004] Chinese patent CN108801273B proposes a method for generating road reference lines. This method is relatively simple, generating a single reference line, meeting simple route requirements and providing support for decision-making and planning modules. However, its reliability and accuracy are limited. Furthermore, this single reference line strategy lacks flexibility and cannot guarantee optimality for subsequent optimization. Summary of the Invention
[0005] The purpose of the present invention is to provide a lane combination screening method, device, equipment and storage medium, which generates several groups of lane combinations based on high-precision map information, performs preliminary evaluation and screening of the lane combinations, and further uses scene features to screen them to obtain at least one group of optimal lane combinations, which can be simultaneously provided to downstream parallel optimization to improve the redundancy and flexibility of the reference line generation process.
[0006] In order to achieve the above technical objectives, the technical solutions adopted by the present invention are as follows:
[0007] In a first aspect, embodiments of the present application provide a lane combination screening method, which is applied to a lane combination device. The device includes a signal transceiver module and a processing module. The processing module is configured to screen out a preferred lane combination. The method includes:
[0008] The signal transceiver module receives high-precision map information, generates a road ID to label the road, and determines the location of the vehicle;
[0009] Based on the high-precision map information, the processing module plans several groups of lane combinations in which the vehicle may travel;
[0010] Based on a preset evaluation method, the processing module evaluates and screens the plurality of lane combinations to obtain at least one optimal lane combination;
[0011] The center lines of all lanes in each group of the optimal lane combination are extracted and smoothed to obtain at least one lane reference line.
[0012] In conjunction with the first aspect, in some optional implementations, the signal transceiver module receives high-precision map information, generates a road ID to label the road, and determines the location of the vehicle, including:
[0013] Based on the high-precision map information, the roads are modularized, different lanes are marked with different road IDs, the distances from the center position of the vehicle to the center lines of different lanes are calculated, and the lane corresponding to the minimum value of the distance is determined as the lane where the vehicle is located.
[0014] In conjunction with the first aspect, in some optional implementations, based on the high-precision map information, the processing module plans several groups of possible lane combinations for the vehicle, including:
[0015] Within a preset lane planning distance range in front of the vehicle's location, the processing module searches in the high-precision map in an iterative combination manner to plan several groups of lane combinations in which the vehicle may travel.
[0016] In conjunction with the first aspect, in some optional implementations, based on a preset evaluation method, the processing module evaluates and screens the plurality of lane combinations to obtain at least one optimal lane combination, including:
[0017] A preliminary evaluation and screening is performed on the lane combinations to obtain an intermediate lane combination; the preliminary evaluation and screening criteria are:
[0018] The lane sequence in the lane combination exceeds a preset first threshold;
[0019] The number of lane changes in the lane combination is less than a preset second threshold.
[0020] In conjunction with the first aspect, in some optional implementations, based on a preset evaluation method, the processing module evaluates and screens the plurality of lane combinations to obtain at least one optimal lane combination, including:
[0021] The processing module identifies scene features based on high-precision map information and further screens the middle lane combinations to obtain at least one optimal lane combination; the scene features include:
[0022] When it is recognized that the vehicle is passing through the ramp, a lane combination for driving on the right is selected;
[0023] When it is recognized that the vehicle passes through a curve, the bifurcation point in the lane combination is extracted, and the curvature of the bifurcation point connection line is calculated after connection and compared with the preset minimum curvature, and the lane combination whose bifurcation point connection line curvature exceeds the preset minimum curvature is selected.
[0024] In conjunction with the first aspect, in some optional implementations, the method further includes:
[0025] determining whether the vehicle changes lanes by determining whether a road ID of a preceding lane and a road ID of a succeeding lane in the lane sequence of the lane combination are consistent;
[0026] When the road ID of the previous lane is consistent with the road ID of the next lane, the vehicle does not change lanes;
[0027] When the road ID of the previous lane is inconsistent with the road ID of the next lane, the host vehicle changes lanes once.
[0028] In conjunction with the first aspect, in some optional implementations, the method further includes:
[0029] The lane sequence in the optimal lane combination is judged, and at least two of the three consecutive road IDs in the lane sequence are the same.
[0030] In a second aspect, embodiments of the present application further provide a lane combination screening device, which is applied to a lane combination device. The device includes a signal transceiver module and a processing module. The processing module is used to screen out a preferred lane combination. The device includes:
[0031] Lane combination generation unit: used to generate several lane combinations based on high-precision map information;
[0032] Screening unit: used to screen out at least one optimal lane combination from several lane combinations.
[0033] On the third aspect, an embodiment of the present application also provides a lane combination screening device, including a signal transceiver module, a processing module and a storage module. The processing module is used to screen out a preferred lane combination. The storage module stores a computer program. When the computer program is executed by the signal transceiver module or the processing module, the lane combination screening device performs the above method.
[0034] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program runs on a computer, the computer executes the above method.
[0035] The invention adopting the above technical solution has the following advantages:
[0036] In this solution, the processing module processes and analyzes the high-precision map information received by the signal transceiver module to generate several possible lane combinations for the vehicle. Initially, these combinations are screened based on the principles of extending the drivable lane sequence and minimizing the number of lane changes. Further screening is then performed based on scenario characteristics to select at least one optimal lane combination. The optimal lane combination determined by scenario characteristics is more accurate, and the planned lane reference line path is safer. Multiple optimal lane combinations can be selected, providing multiple options and greater flexibility in lane reference line generation. BRIEF DESCRIPTION OF THE DRAWINGS
[0037] The present invention can be further illustrated by the non-limiting examples given in the accompanying drawings;
[0038] Figure 1 A block diagram of a lane combination screening device provided in an embodiment of the present application;
[0039] Figure 2 A schematic diagram of the process of the lane combination screening method provided in an embodiment of the present application;
[0040] Figure 3 Schematic diagram of high-precision map segmentation and road ID marking of the lane combination screening method provided in an embodiment of the present application;
[0041] Figure 4 A block diagram of the lane combination screening device provided in an embodiment of the present application.
[0042] The main component symbols are described as follows:
[0043] 10. Lane combination screening equipment; 11. Signal transceiver module; 12. Processing module;
[0044] 200. Lane combination screening device; 210. Lane combination generating unit; 220. Screening unit. DETAILED DESCRIPTION
[0045] The present application will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that similar or identical parts in the drawings or descriptions are numbered the same. Implementations not shown or described in the drawings are known to those of ordinary skill in the art. In the description of this application, the terms "first," "second," etc. are used solely to distinguish descriptions and are not to be construed as indicating or implying relative importance.
[0046] like Figure 1 As shown, an embodiment of the present application provides a lane combination screening device 10. The lane combination screening device 10 may include a signal transceiver module 11, a processing module 12 and a storage module. The processing module 12 is used to screen out a preferred lane combination.
[0047] In this embodiment, the signal transceiver module 11 is used to receive high-precision map information, generate road IDs to label roads, and determine the vehicle's current position on the road. Based on the high-precision map information, the processing module 12 generates several possible lane combinations for the vehicle. The lane combinations are initially screened based on the principles of increasing the length of the drivable lane sequence and minimizing the number of lane changes. Further screening is then performed based on scenario characteristics to select at least one optimal lane combination. The optimal lane combination determined by scenario characteristics is more accurate, and the planned lane reference line path is safer. Multiple optimal lane combinations can be selected, providing multiple options and greater flexibility in lane reference line generation.
[0048] The storage module stores a computer program. When the computer program is executed by the signal transceiver module 11 or the processing module 12 , the lane combination screening device 10 executes the following method.
[0049] like Figure 2 As shown, an embodiment of the present application further provides a lane combination screening method, which may include the following steps:
[0050] Step 110: The signal transceiver module 11 receives high-precision map information, generates a road ID to label the road, and determines the location of the vehicle;
[0051] Step 120: Based on the high-precision map information, the processing module 12 plans a plurality of possible lane combinations for the vehicle;
[0052] Step 130: Based on a preset evaluation method, the processing module 12 evaluates and screens the lane combinations to obtain at least one optimal lane combination.
[0053] Step 140: extract the center lines of all lanes in each group of the optimal lane combination, perform smoothing processing, and obtain at least one lane reference line.
[0054] In this embodiment, the signal transceiver module 11 receives high-precision map information and determines the vehicle's position on the road. The processing module 12 analyzes and processes the high-precision map information to plan several possible lane combinations for the vehicle. It first selects lane combinations with long lane sequences and few lane changes. This selection is further refined using scene characteristics to obtain at least one optimal lane combination. The centerlines of all lanes in this optimal lane combination are extracted and smoothed to obtain at least one lane reference line. Multiple optimal lane combinations can be selected, providing multiple options for generating lane reference lines and greater flexibility.
[0055] As an optional implementation, the signal transceiver module 11 receives high-precision map information, generates a road ID to label the road, and determines the location of the vehicle, including:
[0056] Based on the high-precision map information, the roads are modularized, different lanes are marked with different road IDs, the distances from the center position of the vehicle to the center lines of different lanes are calculated, and the lane corresponding to the minimum value of the distance is determined as the lane where the vehicle is located.
[0057] like Figure 3 As shown, in this embodiment, lanes are numbered using road IDs based on high-precision maps. The road IDs of the same lanes have the same number, and the roads are modularized, and different lanes on the road are divided into modules of equal length.
[0058] It can be understood that when determining the position of the vehicle, a vehicle coordinate system is established with the vehicle as the coordinate origin, the lane centerline position coordinates in the high-precision map are extracted, the lane centerline position coordinates in the high-precision map are converted to the vehicle coordinate system, and the distances from different lane centerlines to the vehicle are calculated. Among them, the lane corresponding to the minimum distance from the lane centerline to the vehicle is the lane where the vehicle is located.
[0059] As an optional implementation, based on the high-precision map information, the processing module 12 plans several groups of possible lane combinations for the vehicle, including:
[0060] Within a preset lane planning distance range in front of the vehicle's location, the processing module 12 searches in the high-precision map in an iterative combination manner to plan several groups of lane combinations in which the vehicle may travel.
[0061] In this embodiment, when planning lanes, the current module of the vehicle's current lane is used as the starting lane sequence ID. The next module that the vehicle may move to includes the next module of the current lane and the next module of the adjacent lane of the current lane. Based on this logic, within the preset lane planning distance range, several groups of possible lane combinations for the vehicle are generated through iterative search. For example, Figure 3 The generated lane combinations may be: G1(0, 0, 0, 0, 0, 0); G2(1, 1, 1, 1, 1, 1, 1); G3(2, 2, 2, 2, 2, 2, 2); G4(2, 2, 2, 2, 2, 3, 3, 3).
[0062] As an optional implementation, based on a preset evaluation method, the processing module 12 evaluates and screens the plurality of lane combinations to obtain at least one optimal lane combination, including:
[0063] A preliminary evaluation and screening is performed on the lane combinations to obtain an intermediate lane combination; the preliminary evaluation and screening criteria are:
[0064] The lane sequence in the lane combination exceeds a preset first threshold;
[0065] The number of lane changes in the lane combination is less than a preset second threshold.
[0066] In this embodiment, the lane sequence exceeding the preset first threshold means that the distance of the path planned in the lane combination is long enough to avoid the situation where the planned path distance is insufficient due to road narrowing caused by road construction, merging into intersections, etc.
[0067] From the perspective of driving safety, the more lane changes there are, the higher the possibility of encountering safety risks. The number of lane changes in a lane combination is limited so that it does not exceed a second threshold to improve driving safety.
[0068] As an optional implementation, based on a preset evaluation method, the processing module 12 evaluates and screens the plurality of lane combinations to obtain at least one optimal lane combination, including:
[0069] Based on the high-precision map information, the processing module 12 identifies scene features and further screens the middle lane combinations to obtain at least one optimal lane combination; the scene features include:
[0070] When it is recognized that the vehicle is passing through the ramp, a lane combination for driving on the right is selected;
[0071] When it is recognized that the vehicle passes through a curve, the bifurcation point in the lane combination is extracted, and the curvature of the bifurcation point connection line is calculated after connection and compared with the preset minimum curvature, and the lane combination whose bifurcation point connection line curvature exceeds the preset minimum curvature is selected.
[0072] In this embodiment, when the vehicle is passing through some special scenarios, such as a highway ramp, if the planned path still recommends the vehicle to drive in the left fast lane, it may cause the vehicle to miss the exit or change lanes continuously near the exit, posing a serious safety hazard. Therefore, when the vehicle is identified as passing the ramp, the right lane combination is preferred;
[0073] When the vehicle is traveling at high speed and is about to pass a curve, it is necessary to consider the curvature of the planned lane combination, extract the bifurcation points in the lane combination, connect them, and calculate the curvature of the bifurcation point connection line and compare it with the preset minimum curvature. The curvature of the bifurcation point connection line is preferred, that is, the planned lane combination with a curvature exceeding the preset minimum curvature is selected to ensure the vehicle's cornering safety.
[0074] As an optional implementation, the method further includes:
[0075] determining whether the vehicle changes lanes by determining whether a road ID of a preceding lane and a road ID of a succeeding lane in the lane sequence of the lane combination are consistent;
[0076] When the road ID of the previous lane is consistent with the road ID of the next lane, the vehicle does not change lanes;
[0077] When the road ID of the previous lane is inconsistent with the road ID of the next lane, the host vehicle changes lanes once.
[0078] In this embodiment, the road IDs of the lanes in the lane combination are traversed, and whenever the road ID of the subsequent lane is different from the road ID of the previous lane, a lane change of the vehicle is recorded.
[0079] As an optional implementation, the method further includes:
[0080] The lane sequence in the optimal lane combination is judged, and at least two of the three consecutive road IDs in the lane sequence are the same.
[0081] In this implementation, continuous lane changes are prohibited during normal driving. If three consecutive road IDs in a lane sequence are different, the vehicle is considered to have changed lanes continuously. Therefore, it is necessary to restrict the number of consecutive road IDs in a lane sequence to at least two of the same.
[0082] like Figure 4 As shown, an embodiment of the present application further provides a lane combination screening device 200, which includes at least one software functional module that can be stored in the form of software or firmware in a storage module or embedded in the operating system (OS) of the lane combination screening device 10. The signal transceiver module 11 and the processing module 12 are used to execute the executable modules stored in the storage module, such as the software functional modules and computer programs included in the lane combination screening device 200.
[0083] The lane combination screening device 200 may include a lane combination generating unit 210 and a screening unit 220. The functions of each unit are as follows:
[0084] Lane combination generation unit 210: used to generate a plurality of lane combinations based on high-precision map information;
[0085] Screening unit 220: used to screen out at least one optimal lane combination from a plurality of lane combinations.
[0086] In this embodiment, the storage module may be, but is not limited to, a random access memory, a read-only memory, a programmable read-only memory, an erasable programmable read-only memory, an electrically erasable programmable read-only memory, etc. In this embodiment, the storage module may be used to store high-precision map information, lane combinations generated by the processing module 12, a preset first threshold, a preset second threshold, a preset minimum curvature, and the generated optimal lane combination. Of course, the storage module may also be used to store programs, which the executor executes upon receiving an execution instruction.
[0087] It is understandable that Figure 1 The lane combination screening device 10 shown in FIG is only a schematic diagram of a structure. The lane combination screening device 10 may also include Figure 1 More components shown. Figure 1 Each component shown in the figure can be implemented by hardware, software or a combination thereof.
[0088] It should be noted that, those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the lane combination screening equipment 10 and the lane combination screening device 200 described above can refer to the corresponding processes of each step in the aforementioned method, and will not be elaborated here.
[0089] The present application also provides a computer-readable storage medium that stores a computer program, which, when executed on a computer, causes the computer to execute the lane combination screening method described in the above embodiment.
[0090] Through the description of the above implementation methods, those skilled in the art can clearly understand that the present application can be implemented through hardware or by means of software plus a necessary general hardware platform. Based on this understanding, the technical solution of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), including a number of instructions for enabling a computer device (which can be a personal computer, a screening device, or a network device, etc.) to execute the methods described in each implementation scenario of the present application.
[0091] In summary, the embodiments of the present application provide a lane combination screening method, apparatus, device, and storage medium. In this solution, the processing module 12 processes and analyzes the high-precision map information received by the signal transceiver module 11 to generate several groups of possible lane combinations for the vehicle. The lane combinations are initially screened based on the principles of making the drivable lane sequence longer and reducing the number of lane changes. Further screening is then performed based on scene features to select at least one optimal lane combination. The optimal lane combination obtained through scene feature screening is more accurate, and the planned lane reference line path is safer. There can be multiple groups of optimal lane combinations screened, providing multiple options for the generation of lane reference lines and greater flexibility.
[0092] In the embodiments provided in the present application, it should be understood that the disclosed devices, systems and methods can also be implemented in other ways. The device, system and method embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems, methods and computer program products according to the multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of code, and a part of the module, program segment or code includes one or more executable instructions for implementing the specified logical function. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart can be implemented by a dedicated hardware-based system that performs the specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions. In addition, the functional modules in the various embodiments of the present application can be integrated together to form an independent part, or each module can exist alone, or two or more modules can be integrated to form an independent part.
[0093] The foregoing is merely an embodiment of the present application and is not intended to limit the scope of protection of the present application. Persons skilled in the art will readily appreciate that various modifications and variations are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present application shall be included within the scope of protection of the present application.
Claims
1. A lane combination screening method, characterized by: Applied to a lane combination device, the device includes a signal transceiver module and a processing module, the processing module is used to screen out a preferred lane combination, and the method includes: The signal transceiver module receives high-precision map information, generates a road ID to label the road, and determines the location of the vehicle; Based on the high-precision map information, the processing module plans several groups of lane combinations in which the vehicle may travel; Based on a preset evaluation method, the processing module evaluates and screens the plurality of lane combinations to obtain at least one optimal lane combination; The center lines of all lanes in each group of the optimal lane combination are extracted and smoothed to obtain at least one lane reference line.
2. The lane combination screening method according to claim 1, characterized in that: The signal transceiver module receives high-precision map information, generates a road ID to label the road, and determines the location of the vehicle, including: Based on the high-precision map information, the roads are modularized, different lanes are marked with different road IDs, the distances from the center position of the vehicle to the center lines of different lanes are calculated, and the lane corresponding to the minimum value of the distance is determined as the lane where the vehicle is located.
3. The lane combination screening method according to claim 1, characterized in that: Based on the high-precision map information, the processing module plans several groups of possible lane combinations for the vehicle, including: Within a preset lane planning distance range in front of the vehicle's location, the processing module searches in the high-precision map in an iterative combination manner to plan several groups of lane combinations in which the vehicle may travel.
4. The lane combination screening method according to claim 3, characterized in that: Based on a preset evaluation method, the processing module evaluates and screens the lane combinations to obtain at least one optimal lane combination, including: A preliminary evaluation and screening is performed on the lane combinations to obtain an intermediate lane combination; the preliminary evaluation and screening criteria are: The lane sequence in the lane combination exceeds a preset first threshold; The number of lane changes in the lane combination is less than a preset second threshold.
5. The lane combination screening method according to claim 4, characterized in that: Based on a preset evaluation method, the processing module evaluates and screens the lane combinations to obtain at least one optimal lane combination, including: The processing module identifies scene features based on the high-precision map information and further screens the middle lane combinations to obtain at least one optimal lane combination; the scene features include: When the host vehicle is identified as passing through a ramp, a lane combination for driving on the right is selected; When it is recognized that the vehicle passes through a curve, the bifurcation point in the lane combination is extracted, and the curvature of the bifurcation point connection line is calculated after connection and compared with the preset minimum curvature, and the lane combination whose bifurcation point connection line curvature exceeds the preset minimum curvature is selected.
6. The lane combination screening method according to claim 4, characterized in that: The method further comprises: determining whether the vehicle changes lanes by determining whether a road ID of a preceding lane and a road ID of a succeeding lane in the lane sequence of the lane combination are consistent; When the road ID of the previous lane is consistent with the road ID of the next lane, the vehicle does not change lanes; When the road ID of the previous lane is inconsistent with the road ID of the next lane, the host vehicle changes lanes once.
7. The lane combination screening method according to claim 1, characterized in that: The method further comprises: The lane sequence in the optimal lane combination is judged, and at least two of the three consecutive road IDs in the lane sequence are the same.
8. A lane combination screening device, characterized by: The lane combination screening device includes a signal transceiver module, a processing module and a storage module. The processing module is used to screen out a preferred lane combination. The storage module stores a computer program. When the computer program is executed by the signal transceiver module or the processing module, the lane combination screening device performs the method as described in any one of claims 1 to 7.
9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is run on a computer, the computer is caused to execute the method according to any one of claims 1 to 7.
Citation Information
Patent Citations
A method and apparatus for generating road reference lines
CN108801273B
Unmanned vehicle trajectory prediction method and device
CN114371703A