Map road line construction method, vehicle, equipment and product

The dot-line clustering method combines the road route information collected multiple times, solving the problem of low precision of light map data, improving the accuracy and completeness of map construction, and is suitable for road changes and real-time map updates in urban environments.

CN119085635AInactive Publication Date: 2024-12-06BEIJING JIDU TECH CO LTD
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202411564763.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-11-04
Publication Date
2024-12-06
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

In the prior art, the production of light maps relies on real-time perception of the vehicle's own sensor, resulting in poor data accuracy and the inability to effectively build high-accurate maps. Especially in the case of road reconstruction or urban demolition, the real-time and accuracy of the map are difficult to ensure. .

Method used

By obtaining the route information in the multiple map construction results, using the point-line clustering method to fuse the position point information collected multiple times, determine the traversal point and search direction, form a fusion route, and improve the accuracy and completeness of map construction.

Benefits of technology

It effectively improves the accuracy and completeness of road construction in the map, and ensures the construction effect of map roads. Especially in road changes or urban environments, it improves the alignment consistency between the map and actual scenes.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119085635A_ABST
    Figure CN119085635A_ABST
Patent Text Reader

Abstract

The invention provides a method for constructing road lines in a map, a vehicle, equipment and a product, and relates to the field of intelligent driving, and the method comprises the steps: obtaining multiple mapping results for a target road section; for each road line, determining the position information of one traversal point and the search direction of the next traversal point every other preset step length according to the pose information of each position point indicated in the road line information acquired for multiple times; and based on the obtained position information of each traversal point, determining the fused road line information corresponding to the road line in the target road section, so that multiple mapping results can be fused based on a point-line clustering mode, and the position information of each position point in the multiple mapping results is fully considered when each traversal point is determined, so that the accuracy of mapping is improved. According to the fusion road line formed by the traversal points obtained in this way, the accuracy and integrity of construction of the road lines in the map are effectively improved, and the map road line construction effect is guaranteed.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the field of intelligent driving technology, and in particular to a method, vehicle, equipment and product for constructing road lines in a map. Background Art

[0002] In the process of vehicle driving, in order to facilitate vehicle planning and control, most of the time, maps are constructed to assist in controlling the vehicle. For high-precision maps, their production requires high-precision true value equipment for data collection, which is costly, difficult to cover all scenarios, and difficult to update data. In the case of road reconstruction, urban demolition, etc., the real-time nature of the map is difficult to guarantee. Therefore, non-high-precision maps that focus on perception and neglect maps have gradually become the main maps used in vehicle driving.

[0003] The production of light maps mainly relies on the vehicle's own sensors to perceive the surrounding environment in real time and construct the main road geometry and traffic rules information. Since the original data for light map construction comes from the vehicle's own sensors, the data accuracy is poor and the credibility is low, resulting in poor map results. Summary of the invention

[0004] The embodiments of the present disclosure at least provide a method, vehicle, equipment and product for constructing road lines in a map.

[0005] The present disclosure provides a method for constructing a road line in a map, the method comprising: Acquire multiple mapping results for the target road section; the multiple mapping results include road line information respectively collected when the vehicle passes through the target road section multiple times; the road line information includes position information of multiple position points; the road line includes lane lines and / or road edge lines; For each of the road lines, according to the position information of each position point indicated in the road line information collected multiple times, the position information of a traversal point and the search direction of the next traversal point are determined at every preset step length; the position information of the traversal point is determined based on the position information of the multiple position points after searching the multiple position points according to the corresponding search direction and the preset step length; Based on the obtained position information of each traversal point, the fused road line information corresponding to the road line in the target road section is determined.

[0006] The present disclosure also provides a vehicle, including a controller, wherein the controller includes: a memory for storing machine-readable instructions, and; The processor is used to call and execute the machine-readable instructions stored in the memory to implement the steps in any possible implementation of the above-mentioned method for constructing road lines in a map.

[0007] An embodiment of the present disclosure also provides an electronic device, including: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the machine-readable instructions are executed by the processor to perform steps in any possible implementation of the above-mentioned method for constructing road lines in a map.

[0008] The embodiment of the present disclosure further provides a computer program product, on which a computer program is stored. When the computer program is executed by a processor, the computer program executes the steps in any possible implementation of the above-mentioned method for constructing road lines in a map.

[0009] The method, vehicle, equipment and product for constructing road lines in a map provided by the embodiments of the present disclosure can determine the position information of a traversal point and the search direction of the next traversal point at every preset step length for multiple mapping results of a target road section through the posture information of each position point indicated in the road line information collected multiple times. Here, the position information of each traversal point is determined based on the position information of multiple position points after searching for multiple position points according to the corresponding search direction and the preset step length, so that the fused road line information corresponding to the target road section can be determined based on the obtained position information of each traversal point; in this way, for each road line, the multiple mapping results can be fused based on the point-line clustering method, and the position information of each position point in the multiple mapping results is fully considered when determining each traversal point. The fused road line formed by each traversal point thus obtained effectively improves the accuracy and completeness of the construction of the road lines in the map and ensures the effect of the map road line construction.

[0010] It should be understood that the above general description and the following detailed description are merely exemplary and explanatory, and are not intended to limit the technical solutions of the present disclosure.

[0011] In order to make the above-mentioned objectives, features and advantages of the present disclosure more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the following is a brief introduction to the drawings required for use in the embodiments. The drawings herein are incorporated into the specification and constitute a part of the specification. These drawings illustrate embodiments consistent with the present disclosure and are used together with the specification to illustrate the technical solutions of the present disclosure. It should be understood that the following drawings only illustrate certain embodiments of the present disclosure and should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can also be obtained based on these drawings without creative work.

[0013] Figure 1A flow chart of a method for constructing road lines in a map provided by an embodiment of the present disclosure is shown; Figure 2 A schematic diagram of determining a traversal point provided by an embodiment of the present disclosure is shown; Figure 3 A flow chart of a method for constructing and optimizing road lines in a map provided by an embodiment of the present disclosure is shown; Figure 4 A flowchart of a method for constructing and merging road lines in a map provided by an embodiment of the present disclosure is shown; Figure 5 A schematic diagram of a fused road line provided by an embodiment of the present disclosure is shown; Figure 6 Shows Figure 5 A partial enlarged view of the fused road line shown in; Figure 7 One of the schematic diagrams of a device for constructing road lines in a map provided by an embodiment of the present disclosure is shown; Figure 8 A second schematic diagram of a device for constructing road lines in a map provided by an embodiment of the present disclosure is shown; Fig. 9 A schematic structural diagram of an electronic device provided by an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0014] In order to make the purpose, technical scheme and advantages of the embodiments of the present disclosure clearer, the technical scheme in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all of the embodiments. The components of the embodiments of the present disclosure generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present disclosure provided in the drawings is not intended to limit the scope of the present disclosure for protection, but merely represents the selected embodiments of the present disclosure. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present disclosure.

[0015] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0016] The term "and / or" herein only describes an association relationship, indicating that three relationships may exist. For example, A and / or B may represent the following three situations: A exists alone, A and B exist at the same time, and B exists alone. In addition, the term "at least one" herein represents any combination of at least two of any one or more of a plurality of. For example, including at least one of A, B, and C may represent including any one or more elements selected from the set consisting of A, B, and C.

[0017] Research has found that the production of light maps mainly relies on the vehicle's own sensors to perceive the surrounding environment in real time and construct key road geometry and traffic rules information, which mainly includes basic road topology, lane lines, road edges, traffic lights, signs and other key information. Since the original data for light map construction comes from the vehicle's own sensors, the data accuracy is poor and the credibility is low, resulting in poor map effects and difficulty in mass production.

[0018] Based on the above research, the present disclosure provides a method for constructing road lines in a map, which can fuse multiple mapping results based on point and line clustering, and fully consider the position information of each location point in the multiple mapping results when determining each traversal point. The fused road line formed by each traversal point obtained in this way effectively improves the accuracy and completeness of the road line construction in the map, and ensures the map road line construction effect.

[0019] To facilitate understanding of this embodiment, a method for constructing road lines in a map disclosed in the embodiment of the present disclosure is first introduced in detail. The execution subject of the method for constructing road lines in a map provided in the embodiment of the present disclosure is generally an electronic device with certain computing capabilities, and the electronic device may be a server or a terminal device or other processing device. If it is a server, the server may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud storage, big data and artificial intelligence platforms. If it is a terminal device, the terminal device may be a user equipment (UserEquipment, UE), a mobile device, a terminal, a computing device, and a vehicle-mounted device. If it is other processing devices, the other processing devices may be devices including a processor and a memory, which is not limited here. In some possible implementations, the method for constructing road lines in a map may be implemented by a processor calling computer-readable instructions stored in a memory.

[0020] A method for constructing road lines in a map provided by an embodiment of the present disclosure is described below in conjunction with the accompanying drawings.

[0021] See also Figure 1As shown, it is a flow chart of a method for constructing road lines in a map provided by an embodiment of the present disclosure, such as Figure 1 As shown in , the method for constructing road lines in a map provided by the embodiment of the present disclosure includes steps S101 to S103, wherein: S101: Acquire multiple mapping results for a target road section; the multiple mapping results include road line information respectively collected when a vehicle passes through the target road section multiple times; the road line information includes position information of multiple position points; the road line includes lane lines and / or road edge lines.

[0022] In this step, the road line information that records the posture information of multiple position points collected when the vehicle passes through the target section once can be used as a single mapping result for the target section. By performing multiple collections in the above manner, multiple mapping results of the vehicle passing through the target section multiple times can be obtained.

[0023] Specifically, any mapping result for the target road section is obtained according to the following steps: Acquire multiple frames of road line images continuously collected by the vehicle and the vehicle posture information during the collection; Determine the road line segment information corresponding to the multiple frames of road line images according to the vehicle posture information when each frame of road line image is collected, wherein the road line segment information includes posture information of multiple position points; The road line fragment information corresponding to multiple frames of road line images is spliced ​​to obtain the road line information corresponding to the current mapping result.

[0024] In the above steps, multiple frames of road line images continuously collected when the vehicle passes through the target road section and the vehicle posture information when each frame of road line image is collected can be obtained.

[0025] Here, since the vehicle posture information is collected by the vehicle's own sensors, and since the vehicle's own sensor data collection accuracy is poor, in order to reduce the problem of inaccurate vehicle posture positioning, the vehicle posture information may be optimized and improved vehicle posture information.

[0026] Specifically, the factor graph optimization algorithm can be used to optimize and improve the posture information of multiple vehicles, and the vehicle posture information can also be optimized and improved by other means to achieve smoothing of the posture information of multiple vehicles, reduce the deviation between the posture information of each vehicle, and further help to improve the accuracy of the road line segment information determined according to the vehicle posture information.

[0027] Then, according to each vehicle posture information, road line segment information associated with each vehicle posture information can be determined from the multiple frames of road line images.

[0028] Here, in order to facilitate the processing of the posture information determined from the road line images of different frames, the posture information of each position point can be converted to the same coordinate system. Optionally, the posture information of each position point in the corresponding road line image can be converted to a unified target coordinate system, such as a world coordinate system or a navigation coordinate system (such as a northeast celestial coordinate system), so as to obtain the posture information of each position point.

[0029] In practical applications, vehicles are often equipped with various sensor components such as cameras, radars, global positioning systems (GPS), inertial measurement units (IMUs), etc. Before continuously acquiring multiple frames of road line images through the vehicle camera, the various sensor components can be calibrated and registered in advance to obtain calibration and registration parameters. The calibration and registration parameters include the conversion relationship between the camera coordinate system and the vehicle coordinate system, and the conversion relationship between the vehicle coordinate system and the world coordinate system.

[0030] Correspondingly, based on the calibration registration parameters, the position and posture information of each position point in the corresponding camera coordinate system in the road line image can be converted into position and posture information in the target coordinate system.

[0031] Specifically, based on the calibration and registration parameters, the conversion relationship between the camera coordinate system and the vehicle coordinate system can be obtained, so that the pose information in the camera coordinate system can be converted into the pose information in the vehicle coordinate system (for example, the coordinate system with the center of the vehicle body as the coordinate origin), and then combined with the vehicle positioning position information, the pose information in the vehicle coordinate system can be converted into the pose information in the target coordinate system. The vehicle positioning position information is the vehicle position information when the road line image is collected.

[0032] Then, the road line information of each road line segment is spliced ​​in the order of acquisition time to obtain the road line information corresponding to the current mapping result. Specifically, the position points in the road line segment information are spliced ​​in the order of acquisition time to obtain the road line corresponding to the current mapping result.

[0033] In this way, by splicing the road line segment information obtained from multiple frames of road line images, the road line information corresponding to the current mapping result is obtained, which helps to make the single-pass mapping result have a more stable alignment effect.

[0034] In some possible implementations, the obtaining of multiple mapping results for the target road segment includes: Obtaining the road line information collected by the vehicle multiple times; Determine the maximum distance and average distance between different road lines and the direction of the road line according to the information of each road line, and determine the information of each road line corresponding to the same road section according to the maximum distance, average distance and direction of the road line; The road line information corresponding to the same road section is used as multiple mapping results for the target road section.

[0035] In the above steps, when obtaining the road line information collected by the vehicle multiple times, it can be distinguished according to the type of the road line. For example, when the road line includes lane lines and road edge lines, the lane line information collected multiple times and the road edge line information collected multiple times are screened separately to obtain the lane line information corresponding to the same road section and the road edge line information corresponding to the same road section, thereby avoiding the situation where different types of road lines are merged.

[0036] Optionally, when obtaining each road line information collected by the vehicle multiple times, in order to speed up the road line screening efficiency, an RTree can be constructed to store each road line information collected by the vehicle multiple times. For example, when the road line includes lane lines and road edge lines, two RTrees can be constructed to respectively store each lane line information collected multiple times and each road edge line information collected multiple times. The RTree is used to traverse and search each road line information to determine the road line information corresponding to the same road section.

[0037] For any road line, if there are other road lines whose maximum distance from the road line is less than the first threshold, whose average distance is less than the second threshold, and whose directions are the same, the other road lines and the road line can be divided into the same road line group. In the above manner, the road lines are compared, and the road lines in the same road line group are determined as the road lines corresponding to the same road section, so as to obtain the information of the road lines corresponding to the same road section.

[0038] Here, the maximum distance and average distance between two road lines can be determined by the following steps: determining the distance between each position point on one of the road lines and the corresponding projection point on the other road line, determining the maximum value among the respective distances as the maximum distance between the two road lines, and determining the average value of the respective distances as the average distance between the two road lines.

[0039] The specific values ​​of the first threshold and the second threshold can be determined according to the needs of road line screening, and are not specifically limited here.

[0040] In this way, when determining multiple mapping results for a target road section, the maximum distance, average distance and road direction between different road lines are fully considered to ensure the integrity and accuracy of the multiple mapping results.

[0041] S102: For each of the road lines, according to the position information of each position point indicated in the road line information collected multiple times, determine the position information of a traversal point and the search direction of the next traversal point at every preset step; the position information of the traversal point is determined based on the position information of multiple position points after searching for the multiple position points according to the corresponding search direction and the preset step.

[0042] In this step, for each of the road lines, during the traversal process, the position information of the current traversal point and the search direction of the next traversal point can be determined based on the posture information of multiple position points searched according to the corresponding search direction and the preset step size, thereby obtaining the traversal points corresponding to the road line.

[0043] Specifically, the method of determining the position information of a traversal point and the search direction of the next traversal point at every preset step length according to the position information of each position point indicated in the road line information collected multiple times includes: Determine an initial search direction and an initial traversal point according to the position information of each initial position point indicated in the road line information collected multiple times; the initial position point is the first position point on the road line; Taking the initial traversal point as the current traversal point and the initial search direction as the current search direction, determining a target search point; the position information of the target search point is the position information of a preset step length from the current traversal point in the current search direction; According to the position information of each position point within a preset distance range around the target search point in the road line information collected multiple times, determine the updated current search direction and the current traversal point, and return to the step of determining the target search point until the current traversal point is determined to be the last traversal point.

[0044] In the above steps, the first position point on each road line collected multiple times can be determined as the initial position point of each road line, and the initial search direction and initial traversal point can be determined according to the position information of each initial position point.

[0045] Then, the initial traversal point is used as the current traversal point, and the initial search direction is used as the current search direction, the position information of a point in the current search direction with a preset step length away from the current traversal point is determined, and the point is used as the target search point.

[0046] The specific value of the preset step size may be determined according to the needs of road line fusion and is not specifically limited here.

[0047] Next, based on the position information of the target search point, a preset distance range around the target search point is determined, and for the multiple position points included in the road line information collected multiple times, each position point within the preset distance range around the target search point is determined, and based on the posture information of each position point within the preset distance range around the target search point, an updated current search direction and a current traversal point are determined, and the step of determining the target search point is returned to determine the next target search point that is a preset step length away from the current traversal point in the current search direction, and determine the next current traversal point, until the current traversal point is determined to be the last traversal point.

[0048] The specific value of the surrounding preset distance range may be determined according to the need to determine the traversal point, and is not specifically limited here.

[0049] In this way, the target search point can be determined based on the current traversal point according to the current search direction and the preset step size, and then the updated current search direction and current traversal point can be determined according to the posture information of each position point within the preset distance range around the target search point. The edge calculation in the fusion process is fully considered to ensure the accuracy and continuity of the fused road line.

[0050] When determining the initial search direction and the initial traversal point, in some possible implementations, the initial search direction can be determined based on the posture information of each initial position point indicated in the road line information collected multiple times; the initial search direction is determined based on the average value of the posture information of each initial position point; the initial traversal point is determined based on the projection point of each initial position point in the initial search direction; the initial traversal point is the projection point with the smallest coordinate value along the initial search direction among the projection points.

[0051] In the above steps, the average value of the posture information of each initial position point can be determined to obtain the average posture information of each initial position point, and the direction indicated by the average posture information of each initial position point is determined as the initial search direction.

[0052] Then, the projection points of each initial position point in the initial search direction are determined respectively. It can be understood that the smaller the coordinate value of the projection point along the initial search direction, the closer the projection point is to the starting part of the road line. Therefore, the projection point with the smallest coordinate value along the initial search direction among the projection points is determined as the initial traversal point, which helps to avoid missing position points during the traversal process.

[0053] In this way, determining the initial search direction and initial traversal point in the above manner helps to ensure the integrity of the fused lane line.

[0054] In some possible implementations, determining the updated current search direction and the current traversal point according to the position information of each position point within a preset distance range around the target search point in the road line information collected multiple times includes: The updated posture information of the current traversal point is determined according to the average value of the posture information of each position point within a preset distance range around the target search point, and the direction indicated by the posture information of the current traversal point is used as the updated current search direction.

[0055] In this step, the average value of the posture information of each position point within a preset distance range around the target search point can be determined, and the average posture information of each position point within a preset distance range around the target search point can be obtained. The average posture information can be determined as the posture information of the updated current traversal point, thereby obtaining the updated position information of the current traversal point, and the direction indicated by the posture information of the updated current traversal point can be used as the updated current search direction.

[0056] In this way, when determining the updated current search direction and current traversal point, the position information of each position point within a preset distance range around the target search point is fully considered, thereby achieving the fusion of the position points, which helps to ensure the accuracy of the fused road line.

[0057] To clearly demonstrate the process of determining each traversal point, you can also refer to Figure 2 , Figure 2 A schematic diagram of determining a traversal point provided by an embodiment of the present disclosure. Figure 2 As shown in , according to the embodiment of the present disclosure, the initial traversal point A1 is determined, and according to the initial search direction and the preset step length, the target search point B1 is determined on the basis of the initial traversal point A1. According to the road line information collected multiple times, it can be seen that there are 8 position points C1~C8 around the target search point B1. The surrounding preset distance range D is determined with the target search point B1 as the center. The position points within the preset distance range D around the target search point B1 are C1~C6, and the position points C7~C8 are not within the preset distance range D around the target search point B1. According to the posture information of the position points C1~C6, the updated current traversal point A2 and the current search direction can be determined. According to the updated current search direction and the preset step length, the next target search point B2 is determined on the basis of the current traversal point A2, so that the updated current traversal point and the current search direction can continue to be determined until the current traversal point is determined to be the last traversal point.

[0058] S103: Based on the obtained position information of each traversal point, determine the fused road line information corresponding to the road line in the target road section.

[0059] In this step, based on the obtained position information of each traversal point, each traversal point is used as a position point, and each traversal point is connected in series, so as to obtain the fused road line information corresponding to the road line in the target section.

[0060] Here, the road line includes a lane line and / or a road edge line. Accordingly, each lane line and each road edge line of the target road section can respectively obtain a corresponding fused road line.

[0061] The method for constructing road lines in a map provided by the embodiments of the present disclosure can determine the position information of a traversal point and the search direction of the next traversal point at every preset step length for multiple mapping results of a target road section through the posture information of each position point indicated in the road line information collected multiple times. Here, the position information of each traversal point is determined based on the position information of multiple position points after searching for multiple position points according to the corresponding search direction and the preset step length, so that the fused road line information corresponding to the target road section can be determined based on the obtained position information of each traversal point; in this way, for each road line, the multiple mapping results can be fused based on the point-line clustering method, and the position information of each position point in the multiple mapping results is fully considered when determining each traversal point. The fused road line formed by each traversal point obtained in this way effectively improves the accuracy and completeness of the construction of the road lines in the map, and ensures the map road line construction effect.

[0062] See also Figure 3 As shown, it is a flow chart of a method for constructing and optimizing road lines in a map provided by an embodiment of the present disclosure, such as Figure 3 As shown in , it includes steps S301 to S305, wherein: S301: Acquire multiple mapping results for a target road section; the multiple mapping results include road line information respectively collected when a vehicle passes through the target road section multiple times; the road line information includes position information of multiple position points; the road line includes lane lines and / or road edge lines.

[0063] S302: For each of the road lines, according to the position information of each position point indicated in the road line information collected multiple times, determine the position information of a traversal point and the search direction of the next traversal point at every preset step; the position information of the traversal point is determined based on the position information of multiple position points after searching for the multiple position points according to the corresponding search direction and the preset step.

[0064] S303: Based on the obtained position information of each traversal point, determine the fused road line information corresponding to the road line in the target road section.

[0065] Among them, the description of step S301 to step S303 can refer to the description of step S101 to step S103, and can achieve the same technical effects and solve the same technical problems, and will not be repeated here.

[0066] S304: Based on the fused road line information corresponding to each of the road lines, determine a candidate problem road line pair from the fused road lines corresponding to each of the road lines; the candidate problem road line pair includes a first candidate problem road line and a second candidate problem road line, the number of target position points on the first candidate problem road line is greater than a first number, and the target position point is a position point whose distance from the corresponding projection point on the second candidate problem road line is less than a first distance threshold.

[0067] In actual applications, after determining the fused road line information corresponding to each road line of the target road section, in the case of a fork in the road or a change in the number of lanes, there may be a problem that some road lines cannot be fused. For example, in the case of a fork in the road, the actual scene is a turning road line, but through the above embodiment, two fused road lines are obtained, and a part of the two fused road lines cannot be fused, generally in the shape of a "person" or "entry".

[0068] In order to avoid this problem, the embodiment of the present disclosure can detect whether there are candidate problem road line pairs in the fused road lines corresponding to each road line, and when the existence of candidate problem road line pairs is detected, the candidate problem road line pairs can be extracted from the fused road line information corresponding to each of the road lines.

[0069] For any fused road line, if there are position points on other fused road lines whose distances to corresponding projection points on the fused road line are less than a first distance threshold, and the number of such position points is greater than a first number, it is considered that the fused road line and the other fused road lines may have common parts, and therefore the fused road line and the other fused road lines are combined into a candidate problem road line pair.

[0070] Optionally, the first candidate problematic road line may be any candidate problematic road line in the pair of candidate problematic road lines.

[0071] Optionally, in order to improve the effect of optimizing the candidate problem road line pair, the first candidate problem road line may be the longer candidate problem road line in the candidate problem road line pair, that is, the length of the first candidate problem road line is greater than the length of the second candidate problem road line.

[0072] The specific values ​​of the first number and the first distance threshold can be determined according to the need for screening problematic road lines, and are not specifically limited here.

[0073] S305: Determine an optimized fused road line according to the position and posture information of each target position point on the first candidate problematic road line and the position and posture information of the projection point of the target position point on the second candidate problematic road line.

[0074] In this step, the result of optimizing the candidate problem road line pair can be obtained based on the pose information of each target position point on the first candidate problem road line and the pose information of the projection point of the target position point on the second candidate problem road line, that is, the optimized fused road line.

[0075] In order to determine the optimized fused road line, in some possible implementations, the optimized position point can be determined based on the pose information of each target position point on the first candidate problem road line and the pose information of the projection point of the target position point on the second candidate problem road line; the pose information of the optimized position point is the average of the pose information of the target position point on the first candidate problem road line and the projection point of the target position point on the second candidate problem road line; based on each optimized position point, the optimized fused road line is obtained.

[0076] Specifically, for each target position point on the first candidate problem road line, the average of the pose information of the target position point and the pose information of the projection point on the second candidate problem road line corresponding to the target position point is determined as the pose information of the optimized position point. The optimized position points are connected in series to obtain the optimized fused road line.

[0077] In order to determine the optimized fused road line, in some other possible implementations, among the two endpoints of the first candidate problem road line, the endpoint with a larger distance to the corresponding projection point on the second candidate problem road line can be determined as the target endpoint; starting from the target endpoint, the target merge point is searched for in sequence on the first candidate problem road line; the target merge point belongs to the target position point, and the distance between a second number of consecutive position points after the target merge point and the corresponding projection point on the second candidate problem road line is less than a second distance threshold; based on the target merge point and its projection point on the second candidate problem road line, a fused position point is obtained; the posture information of the fused position point is the average of the posture information of the target merge point and its corresponding projection point; based on each fused position point, the optimized fused road line is determined.

[0078] In the above steps, the distances between the two endpoints of the first candidate problem road line and the corresponding projection points on the second candidate problem road line can be determined, and the endpoint of the first candidate problem road line with the larger distance from the corresponding projection point on the second candidate problem road line is taken as the target endpoint, and the target merging point is searched from the target endpoint. In this way, the search for the target merging point starts from the end of the first candidate problem road line where the fork is larger relative to the second candidate problem road line, avoiding the loss of the forked part of the first candidate problem road line and ensuring the integrity of the optimized fused road line.

[0079] Starting from the target endpoint of the first candidate problem road line, each position point of the first candidate problem road line is searched. When a position point whose distance to the corresponding projection point on the second candidate problem road line is less than a first distance threshold is determined, and the distances between a second number of consecutive position points after the position point and the corresponding projection point on the second candidate problem road line are less than a second distance threshold, the position point can be determined as the target merging point.

[0080] The specific values ​​of the second number and the second distance threshold can be determined according to the optimization requirements of the problematic road line, and are not specifically limited here.

[0081] Exemplarily, the second number may be ten.

[0082] Here, the second distance threshold is greater than the first distance threshold. Exemplarily, the second distance threshold may be twice the first distance threshold.

[0083] Based on the pose information of the target merging point and the average of the pose information of the projection point of the target merging point on the second candidate problem road line, the pose information of the fused position point is determined, and based on each fused position point, the first candidate problem road line and the second candidate problem road line are optimized to determine the optimized fused road line.

[0084] In this way, the target endpoint can be determined in the above manner, and the target merging point can be searched out, as well as the fusion position point can be determined, so that the common part of the first candidate problem road line and the second candidate problem road line can be fused, which helps to ensure the effect of optimizing the fusion of the first candidate problem road line and the second candidate problem road line, thereby effectively solving the problem of unmerged fused road lines in scenarios such as forks in the road or changes in the number of lanes.

[0085] In some possible implementations, determining an optimized fused road line based on each fused position point includes: Using the fused position point to replace the corresponding target position point on the first candidate problematic road line, and marking the projection point on the second candidate problematic road line corresponding to the fused position point as an error point; For the second candidate problematic road line, if the number of position points between two erroneous points on the second candidate problematic road line is less than a third number, all position points between the two erroneous points are marked as erroneous points, and position points on the second candidate problematic road line other than the erroneous points are marked as correct points; If the number of position points between two correct points on the second candidate problematic road line is less than a third number, marking all position points between the two correct points as correct points; Based on the fused position point and the correct point of the second candidate problematic road line, an optimized fused road line is obtained.

[0086] In the above steps, the fused position point is used to replace the corresponding target position point on the first candidate problem road line, and the projection point on the second candidate problem road line corresponding to the fused position point is marked as an error point, thereby ensuring the fusion of the first candidate problem road line and the second candidate problem road line at the target merging point.

[0087] It can be understood that the target position point on the first candidate problem road line corresponding to the fused position point is the target merging point.

[0088] For the second candidate problem road line, all position points between two error points whose number of position points is less than the third number are first marked as error points, and the position points on the second candidate problem road line except the error points are marked as correct points, and then all position points between two correct points whose number of position points is less than the third number are marked as correct points. In this way, the first candidate problem road line and the second candidate problem road line can be merged as much as possible, which helps to ensure the integrity of the optimized fused road line.

[0089] The fused road line information includes the position point labels of each position point on the fused route. When the optimized fused road line is obtained based on the fused position points and the correct points of the second candidate problem road line, a judgment can be made based on the position point labels corresponding to each point. If the position point labels corresponding to two adjacent correct points are not continuous, the second candidate problem road line can be interrupted to obtain multiple new fused road lines.

[0090] The specific value of the third number may be determined according to the optimization requirements of the problematic road line and is not specifically limited here.

[0091] Exemplarily, the third number may be ten.

[0092] In this way, through the above method, the position information of some position points can be optimized, and the position points that do not need to be retained can be deleted to form a new fused road line, which helps to ensure the optimization effect of the fused road line and improve the consistency between the fused road line and the actual scene.

[0093] The above-mentioned method for constructing and optimizing road lines in the map fuses multiple mapping results based on point-line clustering, and fully considers the position information of each location point in the multiple mapping results when determining each traversal point. The fused road lines formed by each traversal point thus obtained effectively improve the accuracy and completeness of the construction of road lines in the map, ensure the effect of the map road line construction, and effectively solve the problem of incomplete merging of fused road lines in scenarios with forks or changes in the number of lanes, which helps to improve the consistency between the construction of road lines in the map and the actual scene, and ensure the stable alignment of the constructed map with the actual scene.

[0094] See also Figure 4 As shown, it is a flowchart of a method for constructing road lines in a map and merging road lines provided by an embodiment of the present disclosure, such as Figure 4 As shown in , it includes steps S401 to S405, wherein: S401: Acquire multiple mapping results for a target road section; the multiple mapping results include road line information respectively collected when a vehicle passes through the target road section multiple times; the road line information includes position information of multiple position points; the road line includes lane lines and / or road edge lines.

[0095] S402: For each of the road lines, according to the position information of each position point indicated in the road line information collected multiple times, determine the position information of a traversal point and the search direction of the next traversal point at every preset step; the position information of the traversal point is determined based on the position information of multiple position points after searching for the multiple position points according to the corresponding search direction and the preset step.

[0096] S403: Based on the obtained position information of each traversal point, determine the fused road line information corresponding to the road line in the target road section.

[0097] Among them, the description of step S401 to step S403 can refer to the description of step S101 to step S103, and can achieve the same technical effects and solve the same technical problems, and will not be repeated here.

[0098] S404: Determine whether there is a target road line group corresponding to the target road segment; and whether there is a fused road line pair in opposite directions and with a distance less than a third distance threshold in the target road line group.

[0099] In actual applications, after determining the fused road line information corresponding to the target road section, in the scenario of a two-way lane, the two lanes are generally not separated by a road edge line, but by a single yellow line or a double yellow line, so the same road line may be collected twice.

[0100] Exemplarily, taking the case where the road line includes the lane line, when the target road section is a two-way lane running east-west, four mapping results are obtained, two of which are collected when the vehicle is driving in the up lane (i.e., from west to east), and the other two are collected when the vehicle is driving in the down lane (i.e., from east to west). It can be understood that in the actual scenario, there are actually two lane lines for the road section, one lane line in the up lane with a direction from west to east, and one lane line in the down lane with a direction from east to west. However, due to the different driving directions of the vehicle in different acquisition processes, the fused road line information may include four lane lines, two lane lines in the up lane and two lane lines in the down lane, one from west to east and one from east to west.

[0101] In order to avoid this problem, the embodiment of the present disclosure can detect whether there is a target road line group corresponding to the target road section in each fused road line, that is, whether there is a fused road line pair with opposite directions and a distance less than a third distance threshold, and when the existence of the fused road line pair is detected, the fused road line pair can be extracted from the fused road line information.

[0102] The specific value of the third distance threshold may be determined according to the need for merging the fused road lines, and is not specifically limited here.

[0103] S405: If the number of the fused road line pairs meets a preset condition, the two fused road lines indicated by each fused road line pair are merged, and a bidirectional flag of the merged fused road line is output, where the bidirectional flag is used to indicate that the merged fused road line has a bidirectional attribute.

[0104] Here, the preset condition may be that the number of the fused road line pairs in the target road line group is greater than two pairs, thereby effectively solving the problem that the uplink and downlink road lines in a two-way lane are not unique.

[0105] When merging the two fused road lines respectively indicated by each fused road line pair, the merged fused road line may be obtained according to the average value of the position information of each two position points corresponding to the two fused road lines.

[0106] The above-mentioned method for constructing and merging road lines in the map fuses multiple mapping results based on point-line clustering, and fully considers the position information of each position point in the multiple mapping results when determining each traversal point. The fused road lines formed by each traversal point thus obtained effectively improve the accuracy and completeness of the construction of road lines in the map, ensure the effect of map road line construction, and effectively solve the problem of road line separation due to different uplink and downlink directions when mapping two-way lanes, ensure the uniqueness of the road lines in the lanes, and set the two-way flag to help improve the consistency of road line construction in the map with the actual scene, and ensure the stable alignment of the constructed map with the actual scene.

[0107] For example, through the embodiments of the present disclosure, the following can be obtained: Figure 5 The fused road lines shown in Figure 5 It can be seen that the fused road edge lines 51 and the fused lane lines 52 between the fused road edge lines 51 are included.

[0108] To show the map construction effect more clearly, you can also refer to Figure 6 , Figure 6 for Figure 5 A partial enlarged view of the fused road line shown in Figure 6 As shown in FIG. , there are four road edge lines 51 and eight fused lane lines 52 , and there are four fused lane lines 52 between every two road edge lines 51 .

[0109] Those skilled in the art will appreciate that, in the above method of specific implementation, the order in which the steps are written does not imply a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of the steps should be determined by their functions and possible internal logic.

[0110] Based on the same inventive concept, a device for constructing road lines in a map corresponding to the method for constructing road lines in a map is also provided in the embodiment of the present disclosure. Since the principle of solving the problem by the device for constructing road lines in a map in the embodiment of the present disclosure is similar to the method for constructing road lines in a map mentioned above in the embodiment of the present disclosure, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0111] See also Figure 7 and Figure 8 , Figure 7 This is one of the schematic diagrams of a device for constructing road lines in a map provided by an embodiment of the present disclosure, Figure 8 The second schematic diagram of a device for constructing a road line in a map provided by an embodiment of the present disclosure. Figure 7 As shown in FIG. 7 , the apparatus 700 for constructing a road line in a map provided by an embodiment of the present disclosure includes: A mapping acquisition module 710 is used to acquire multiple mapping results for a target road section; the multiple mapping results include road line information collected when the vehicle passes through the target road section multiple times; the road line information includes position information of multiple position points; the road line includes lane lines and / or road edge lines; The position traversal module 720 is used to determine the position information of a traversal point and the search direction of the next traversal point at every preset step length according to the position information of each position point indicated in the road line information collected multiple times; the position information of the traversal point is determined based on the position information of multiple position points after searching for the multiple position points according to the corresponding search direction and the preset step length; The position fusion module 730 is used to determine the fused road line information corresponding to the target road section based on the obtained position information of each traversal point; the fused road line information includes the fused road line corresponding to each of the road lines.

[0112] In an optional implementation, Figure 8 As shown in FIG. 7 , the device 700 for constructing road lines in a map further includes a road line optimization module 740, and the road line optimization module 740 is used to: Based on the fused road line information, determining a candidate problematic road line pair from each fused road line; the candidate problematic road line pair includes a first candidate problematic road line and a second candidate problematic road line, the number of target position points on the first candidate problematic road line is greater than a first number, and the target position point is a position point whose distance from a corresponding projection point on the second candidate problematic road line is less than a first distance threshold; An optimized fused road line is determined based on the position and posture information of each target position point on the first candidate problem road line and the position and posture information of the projection point of the target position point on the second candidate problem road line.

[0113] In an optional implementation, if Figure 8 As shown in FIG. 7 , the device 700 for constructing road lines in a map further includes a road line merging module 750, and the road line merging module 750 is used to: Determining that there is a target road line group corresponding to the target road section; and that there is a fused road line pair in opposite directions and with a distance less than a third distance threshold in the target road line group; If the number of the fused road line pairs meets a preset condition, the two fused road lines indicated by each fused road line pair are merged, and a bidirectional flag of the merged fused road line is output, where the bidirectional flag is used to indicate that the merged fused road line has a bidirectional attribute.

[0114] For descriptions of the processing flow of each module in the device and the interaction flow between each module, reference may be made to the relevant descriptions in the above method embodiment, which will not be described in detail here.

[0115] The device for constructing road lines in a map provided by the embodiment of the present disclosure can determine the position information of a traversal point and the search direction of the next traversal point at every preset step length for multiple mapping results of a target road section through the posture information of each position point indicated in the road line information collected multiple times. Here, the position information of each traversal point is determined based on the position information of multiple position points after searching for multiple position points according to the corresponding search direction and the preset step length, so that the fused road line information corresponding to the target road section can be determined based on the obtained position information of each traversal point; in this way, for each road line, the multiple mapping results can be fused based on the point-line clustering method, and the position information of each position point in the multiple mapping results is fully considered when determining each traversal point. The fused road line formed by the traversal points obtained in this way effectively improves the accuracy and completeness of the construction of the road lines in the map, and ensures the map road line construction effect.

[0116] The disclosed embodiment also provides a vehicle, including a controller, the controller including: a memory for storing machine-readable instructions; and a processor for calling and executing the machine-readable instructions stored in the memory to implement the steps of the method for constructing a road line in a map as described in the above method embodiment. The vehicle may be a vehicle equipped with a variety of sensor components such as a camera, a radar, a global positioning system (GPS), an inertial measurement unit (IMU), etc.

[0117] Corresponding to the above-mentioned method for constructing a road line in a map, the embodiment of the present disclosure further provides an electronic device 900, such as Fig. 9 As shown in FIG. , it is a schematic diagram of the structure of an electronic device 900 provided in an embodiment of the present disclosure, including: Processor 910, memory 920, and bus 930. The memory 920 is used to store execution instructions, including internal memory 921 and external memory 922; the internal memory 921 is also called internal memory, which is used to temporarily store the operation data in the processor 910 and the data exchanged with the external memory 922 such as a hard disk. The processor 910 exchanges data with the external memory 922 through the internal memory 921.

[0118] In the embodiment of the present application, the memory 920 is specifically used to store the application code for executing the solution of the present application, and the execution is controlled by the processor 910. That is, when the electronic device 900 is running, the processor 910 communicates with the memory 920 through the bus 930, or the processor 910 communicates with the memory 920 in other ways, so that the processor 910 executes the application code stored in the memory 920, and then executes the steps of the method for constructing road lines in a map described in any of the above embodiments.

[0119] Among them, the memory 920 can be, but is not limited to, a random access memory (RAM), a read only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable read-only memory (EEPROM), etc.

[0120] The processor 910 may be an integrated circuit chip with signal processing capabilities. The above-mentioned processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The disclosed methods, steps and logic block diagrams in the embodiments of the present invention may be implemented or executed. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0121] It is to be understood that the structure illustrated in the embodiment of the present application does not constitute a specific limitation on the electronic device 900. In other embodiments of the present application, the electronic device 900 may include more or fewer components than shown in the figure, or combine some components, or split some components, or arrange the components differently. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0122] The present disclosure also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method for constructing a road line in a map described in the above method embodiment are executed. The storage medium may be a volatile or non-volatile computer-readable storage medium.

[0123] In addition, an embodiment of the present disclosure also provides a computer program product, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method for constructing road lines in a map provided by any of the above embodiments of the present disclosure are executed. For details, please refer to the above method embodiments, which will not be repeated here.

[0124] The computer program product may be implemented in hardware, software or a combination thereof. In an optional embodiment, the computer program product is embodied as a computer storage medium, which may be a volatile or non-volatile computer-readable storage medium. In another optional embodiment, the computer program product is embodied as a software product, such as a software development kit (SDK) and the like.

[0125] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, the specific working process of the above-described equipment and devices can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here. In the several embodiments provided in the present disclosure, it should be understood that the disclosed equipment, devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0126] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0127] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0128] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present disclosure, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present disclosure. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0129] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present disclosure, which are used to illustrate the technical solutions of the present disclosure, rather than to limit them. The protection scope of the present disclosure is not limited thereto. Although the present disclosure is described in detail with reference to the above-described embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-described embodiments within the technical scope disclosed in the present disclosure, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes 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 disclosure, and should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure shall be based on the protection scope of the claims.

Claims

1. A method for constructing road lines in a map, characterized in that: The method comprises: Acquire multiple mapping results for the target road section; the multiple mapping results include road line information respectively collected when the vehicle passes through the target road section multiple times; the road line information includes position information of multiple position points; the road line includes lane lines and / or road edge lines; For each of the road lines, according to the position information of each position point indicated in the road line information collected multiple times, the position information of a traversal point and the search direction of the next traversal point are determined at every preset step length; the position information of the traversal point is determined based on the position information of the multiple position points after searching the multiple position points according to the corresponding search direction and the preset step length; Based on the obtained position information of each traversal point, the fused road line information corresponding to the road line in the target road section is determined.

2. The method according to claim 1, characterized in that The method of determining the position information of a traversal point and the search direction of the next traversal point at every preset step length according to the position information of each position point indicated in the road line information collected multiple times includes: Determine an initial search direction and an initial traversal point according to the position information of each initial position point indicated in the road line information collected multiple times; the initial position point is the first position point on the road line; Taking the initial traversal point as the current traversal point and the initial search direction as the current search direction, determining a target search point; the position information of the target search point is the position information of a preset step length from the current traversal point in the current search direction; According to the position information of each position point within a preset distance range around the target search point in the road line information collected multiple times, determine the updated current search direction and the current traversal point, and return to the step of determining the target search point until the current traversal point is determined to be the last traversal point.

3. The method according to claim 2, characterized in that The step of determining the initial search direction and the initial traversal point according to the position information of each initial position point indicated in the road line information collected multiple times includes: Determine an initial search direction according to the posture information of each initial position point indicated in the road line information collected multiple times; the initial search direction is determined based on the average value of the posture information of each initial position point; The initial traversal point is determined according to the projection points of each initial position point in the initial search direction; the initial traversal point is the projection point with the smallest coordinate value along the initial search direction among the projection points.

4. The method according to claim 2, characterized in that: The step of determining the updated current search direction and the current traversal point based on the position information of each position point within a preset distance range around the target search point in the road line information collected multiple times includes: The updated posture information of the current traversal point is determined according to the average value of the posture information of each position point within a preset distance range around the target search point, and the direction indicated by the posture information of the current traversal point is used as the updated current search direction.

5. The method according to claim 1, characterized in that Follow the steps below to obtain any mapping result for the target road segment: Acquire multiple frames of road line images continuously collected by the vehicle and the vehicle posture information during the collection; Determine the road line segment information corresponding to the multiple frames of road line images according to the vehicle posture information when each frame of road line image is collected, wherein the road line segment information includes posture information of multiple position points; The road line fragment information corresponding to multiple frames of road line images is spliced ​​to obtain the road line information corresponding to the current mapping result.

6. The method according to claim 1, characterized in that The obtaining of multiple mapping results for the target road section includes: Obtaining information of each road line collected by the vehicle multiple times; Determine the maximum distance and average distance between different road lines and the direction of the road line according to the information of each road line, and determine the information of each road line corresponding to the same road section according to the maximum distance, average distance and direction of the road line; The road line information corresponding to the same road section is used as multiple mapping results for the target road section.

7. The method according to any one of claims 1 to 6, characterized in that After determining the fused road line information, the method further includes: Based on the fused road line information corresponding to each of the road lines, a candidate problematic road line pair is determined from the fused road lines corresponding to each of the road lines; the candidate problematic road line pair includes a first candidate problematic road line and a second candidate problematic road line, the number of target position points on the first candidate problematic road line is greater than a first number, and the target position point is a position point whose distance from a corresponding projection point on the second candidate problematic road line is less than a first distance threshold; An optimized fused road line is determined based on the position and posture information of each target position point on the first candidate problem road line and the position and posture information of the projection point of the target position point on the second candidate problem road line.

8. The method according to claim 7, characterized in that The step of determining the optimized fused road line according to the position and posture information of each target position point on the first candidate problematic road line and the position and posture information of the projection point of the target position point on the second candidate problematic road line comprises: Among the two endpoints of the first candidate problematic road line, determine the endpoint having a larger distance from the corresponding projection point on the second candidate problematic road line as the target endpoint; Starting from the target endpoint, searching for a target merging point on the first candidate problematic road line in sequence; the target merging point belongs to the target position point, and the distances between a second number of consecutive position points after the target merging point and the corresponding projection points on the second candidate problematic road line are less than a second distance threshold; Based on the target merged point and its projection point on the second candidate problem road line, a fused position point is obtained; the pose information of the fused position point is the average pose information of the target merged point and its corresponding projection point; Based on each fused position point, determine the optimized fused road line.

9. The method according to claim 8, characterized in that The step of determining an optimized fused road line based on each fused position point includes: Using the fused position point to replace the corresponding target position point on the first candidate problematic road line, and marking the projection point on the second candidate problematic road line corresponding to the fused position point as an error point; For the second candidate problematic road line, if the number of position points between two erroneous points on the second candidate problematic road line is less than a third number, all position points between the two erroneous points are marked as erroneous points, and position points on the second candidate problematic road line other than the erroneous points are marked as correct points; If the number of position points between two correct points on the second candidate problematic road line is less than a third number, marking all position points between the two correct points as correct points; Based on the fused position point and the correct point of the second candidate problematic road line, an optimized fused road line is obtained.

10. The method according to claim 1, characterized in that After determining the fused road line information, the method further includes: Determining that there is a target road line group corresponding to the target road section; and that there is a fused road line pair in opposite directions and with a distance less than a third distance threshold in the target road line group; If the number of the fused road line pairs meets a preset condition, the two fused road lines indicated by each fused road line pair are merged, and a bidirectional flag of the merged fused road line is output, where the bidirectional flag is used to indicate that the merged fused road line has a bidirectional attribute.

11. A vehicle, characterized in that: A controller is included, the controller comprising: a memory for storing machine-readable instructions, and; A processor is used to call and execute the machine-readable instructions stored in the memory to implement the steps of the method for constructing road lines in a map as described in any one of claims 1 to 10.

12. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the machine-readable instructions are executed by the processor to perform the steps of the method for constructing road lines in a map as described in any one of claims 1 to 10.

13. A computer program product, characterized in that The computer program product stores a computer program, and when the computer program is executed by a processor, the steps of the method for constructing road lines in a map as claimed in any one of claims 1 to 10 are executed.

Citation Information

Patent Citations

  • Intelligent agricultural machine transition and operation fusion path planning method and system

    CN114326717A

  • Intelligent electric power inspection robot for self-adaptive environment path planning and inspection method

    CN115877855A

  • Method for global positioning of vehicle based on laser radar

    CN118549939A

  • Travel route planning method and travel route recommendation method

    US20230075758A1

  • Path Fusing and Planning Method for Passing Region, Robot, and Chip

    US20240272643A1