Map construction method and device, vehicle, medium and product

Abstract

The invention relates to a map construction method and device, a vehicle, a medium and a product. Acquiring lane line data of a target road and a driving track of a vehicle on the target road; determining a road boundary line of the target road according to the lane line data and the driving track; and constructing a target map according to the road boundary line and the driving track.

Description

Technical Field

[0001] This disclosure relates to the field of map building, and more particularly to a map building method, apparatus, vehicle, medium, and product. Background Technology

[0002] In the development of autonomous driving, high-definition maps play a crucial role in vehicle localization, environmental perception, and path planning. Among these, road surfaces are one of the most important components, containing information such as road geometry, road type, and lane markings, which are essential for tasks like autonomous driving. Therefore, road surface extraction is a key step in constructing high-definition maps. Summary of the Invention

[0003] To overcome the problems existing in related technologies, this disclosure provides a map construction method, apparatus, vehicle, medium, and product.

[0004] According to a first aspect of the present disclosure, a map construction method is provided, comprising:

[0005] Acquire lane line data of the target road and the driving trajectory of the vehicle on the target road; determine the road boundary line of the target road based on the lane line data and the driving trajectory; construct a target map based on the road boundary line and the driving trajectory.

[0006] Optionally, the driving trajectory includes multiple routes, and determining the road boundary line of the target road based on the lane line data and the driving trajectory includes:

[0007] A main trajectory is determined from the plurality of driving trajectories, wherein the main trajectory includes the longest trajectory among the plurality of driving trajectories;

[0008] Multiple boundary line recognition windows are established based on the main trajectory;

[0009] Based on the lane line data and multiple driving trajectories, the road boundary lines of the target road are determined through multiple boundary line recognition windows.

[0010] Optionally, establishing multiple boundary line recognition windows based on the main trajectory includes:

[0011] Multiple consecutive trajectory points are determined from the main trajectory;

[0012] For each trajectory point, a boundary line recognition window is established with the trajectory point as the center and the length direction perpendicular to the tangent of the trajectory point on the main trajectory as the length direction.

[0013] Optionally, the lane line data includes data for multiple lane lines, and determining the road boundary line of the target road through multiple boundary line recognition windows based on the lane line data and multiple driving trajectories includes:

[0014] Obtain the driving direction for each of the aforementioned driving trajectories;

[0015] Based on the lane line data of multiple lane lines and the driving direction of each driving trajectory, the lane line direction corresponding to each lane line is determined through multiple boundary line recognition windows;

[0016] The road boundary line is determined through multiple boundary line recognition windows based on the lane line data of multiple lane lines and the lane line direction corresponding to each lane line.

[0017] Optionally, determining the road boundary line through multiple boundary line recognition windows based on the lane line data of multiple lane lines and the lane line direction corresponding to each lane line includes:

[0018] For each lane line, the boundary type of the lane line is determined based on the lane line direction and the lane line data. The boundary type represents whether the corresponding lane line belongs to the lane boundary and the boundary type when it belongs to the lane boundary.

[0019] The road boundary line is determined through multiple boundary line recognition windows based on the boundary type corresponding to each lane line.

[0020] Optionally, determining the lane direction corresponding to each lane line through multiple boundary line recognition windows based on the lane line data of multiple lane lines and the driving direction of each driving trajectory includes:

[0021] For each of the boundary line recognition windows, at least one first trajectory intersecting with the boundary line recognition window is determined from the plurality of driving trajectories;

[0022] For each of the first trajectories, determine the relative direction between the first trajectory and the main trajectory, and the position of the first trajectory within the boundary line recognition window;

[0023] Based on the lane line data of multiple lane lines, the relative direction of each first trajectory to the main trajectory, and the position of each first trajectory within the boundary line recognition window, the lane line direction corresponding to each lane line is determined.

[0024] Optionally, for each lane line, the lane line data includes the preceding and following relationships corresponding to the lane line, and the preceding and following relationships represent the preceding lane line and / or the following lane line corresponding to the lane line.

[0025] The lane line data of the multiple lane lines, the relative direction of each first trajectory to the main trajectory, and the position of each first trajectory within the boundary line recognition window are used to determine the lane line direction corresponding to each lane line, including:

[0026] Based on the relative direction of each first trajectory to the main trajectory, the position of each first trajectory within the boundary line identification window, and the successor relationship of each lane line, the lane line direction corresponding to each lane line is determined.

[0027] Optionally, determining the lane direction corresponding to each lane line based on the relative direction of each first trajectory to the main trajectory, the position of each first trajectory within the boundary line identification window, and the successive relationship of each lane line includes:

[0028] Based on the relative direction of each of the first trajectories to the main trajectory and the position of each of the first trajectories within the boundary line recognition window, the lane line direction of at least one lane line is determined;

[0029] Based on the successor-successor relationship of each lane line and the lane line direction of the at least one lane line, the direction of the lane lines is propagated to determine the lane line direction corresponding to each of the multiple lane lines.

[0030] Optionally, determining the lane direction of at least one lane line based on the relative direction of each of the first trajectories to the main trajectory and the position of each of the first trajectories within the boundary line recognition window includes:

[0031] For each of the first trajectories, based on the position of the first trajectory within the boundary line recognition window, the lane lines located on both sides of the first trajectory are traversed.

[0032] For at least one lane line on each side, starting from the lane line closest to the first trajectory, traverse each lane line on the current side in sequence and repeatedly execute the lane line direction determination step until the first loop termination condition of the current side is met.

[0033] The lane direction determination step includes:

[0034] For the first lane line currently being traversed, the lane line direction of the first lane line is determined based on the relative direction between the first trajectory and the main trajectory.

[0035] Based on the lane line type of the first lane line, determine whether the first lane line is a road boundary line;

[0036] If the first lane line is determined to be the road boundary line, the first loop termination condition is satisfied, and the traversal of the lane lines on the current side ends.

[0037] If it is determined that the first lane line is not the road boundary line, the next lane line of the first lane line on the current side is taken as the updated first lane line.

[0038] Optionally, determining the lane direction of the first lane line based on the relative direction between the first trajectory and the main trajectory for the currently traversed first lane line includes:

[0039] When the relative directions of the first trajectory and the main trajectory are in the same direction, the count value of the first lane line in the first preset direction is increased by a preset update value; when the relative directions of the first trajectory and the main trajectory are in opposite directions, the count value of the first lane line in the second preset direction is increased by the preset update value; wherein, the first preset direction is in the same direction as the main trajectory, and the second preset direction is in the opposite direction to the main trajectory.

[0040] If the count value of the target preset direction of the first lane line is greater than or equal to the preset count threshold, the lane line direction of the first lane line is determined to be the target preset direction, and the target preset direction includes the first preset direction or the second preset direction.

[0041] Optionally, the step of propagating the direction of lane lines based on the successive relationship of each lane line and the lane line direction of the at least one lane line to determine the lane line direction corresponding to each of the multiple lane lines includes:

[0042] Iterate through each lane line stored in the preset lane line set in turn, and repeatedly execute the lane line direction propagation step until the preset lane line set has been completely traversed;

[0043] The lane line direction propagation step includes:

[0044] Use the currently traversed lane line as the second lane line;

[0045] If the second lane line meets the preset direction propagation conditions, the preceding lane line and / or the following lane line corresponding to the second lane line are determined according to the preceding and following relationship of the second lane line, and the lane line direction of the second lane line is taken as the direction of the preceding lane line and / or the direction of the following lane line. The next lane line of the second lane line is then traversed, and the next lane line is taken as the updated second lane line.

[0046] If the second lane line does not meet the preset direction propagation condition, skip the second lane line, continue to traverse the next lane line of the second lane line, and use the next lane line as the updated second lane line.

[0047] Optionally, the preset direction propagation conditions include:

[0048] The second lane line has a defined direction, the second lane line has a corresponding preceding lane line and / or following lane line, and the preceding lane line and / or following lane line corresponding to the second lane line has a lane line with an undefined direction.

[0049] Optionally, for each lane line, the lane line data includes the lane line type of the lane line, and determining the boundary type of the lane line based on the lane line direction and the lane line data includes:

[0050] The boundary type of the lane line is determined based on the lane line direction and the lane line type.

[0051] Optionally, determining the road boundary line through multiple boundary line recognition windows based on the boundary type corresponding to each lane line includes:

[0052] Multiple boundary lane lines are determined from the multiple lane lines according to the boundary type;

[0053] By re-traversing each of the boundary line identification windows, and connecting the boundary lane lines with successive relationships, multiple road boundary lines are generated.

[0054] Optionally, constructing the target map based on the road boundary line and the driving trajectory includes:

[0055] Based on the road boundary lines and the driving trajectory, road surface information is extracted from the target road.

[0056] The target map is constructed based on the extracted road surface information.

[0057] Optionally, the road boundary lines include multiple lines; the step of extracting road surface information of the target road based on the road boundary lines and the driving trajectory includes:

[0058] A main trajectory is determined from the plurality of driving trajectories, wherein the main trajectory includes the longest trajectory among the plurality of driving trajectories;

[0059] For each of the road boundary lines, multiple boundary line cutting windows are generated based on the endpoints of the road boundary lines and the main trajectory;

[0060] Based on the boundary type of the road boundary line and the lane direction corresponding to the road boundary line, the road surface information of the target road is extracted through the multiple boundary line cutting windows.

[0061] Optionally, the step of extracting road surface information of the target road through the multiple boundary line cutting windows based on the boundary type of the road boundary line and the lane direction corresponding to the road boundary line includes:

[0062] For each pair of adjacent boundary line cutting windows in the plurality of boundary line cutting windows, according to the boundary type of the road boundary line and the lane line direction corresponding to the road boundary line, each pair of adjacent road boundary lines between the two adjacent boundary line cutting windows is matched, and the road surface between the two adjacent road boundary lines that meet the preset matching rules is taken as the candidate road surface.

[0063] The target road surface information is extracted based on the candidate road surfaces between each pair of adjacent boundary line cutting windows and the two boundaries of each candidate road surface.

[0064] Optionally, the preset matching rules include:

[0065] The combination of the boundary types of two adjacent road boundary lines is a preset type combination;

[0066] The positions of the two adjacent road boundaries satisfy a preset position strategy corresponding to the lane line direction of the two adjacent road boundary lines.

[0067] Optionally, the step of extracting road surface information of the target road based on the candidate road surface between each pair of adjacent boundary lines and the two boundaries of each candidate road surface includes:

[0068] The candidate road surface between each pair of adjacent boundary line cutting windows is traversed sequentially according to the order of the multiple boundary line cutting windows, and the road surface merging step is executed cyclically until all the multiple boundary line cutting windows have been traversed.

[0069] The road surface to be merged at the end of the loop is taken as the target road surface to be extracted;

[0070] The road surface merging step includes:

[0071] At least one candidate road surface between two preset adjacent boundary line cutting windows is taken as the road surface to be merged. The next two adjacent boundary line cutting windows adjacent to the preset two adjacent boundary line cutting windows are taken as the two adjacent boundary line cutting windows currently being traversed. At least one candidate road surface between the two adjacent boundary line cutting windows currently being traversed is taken as the road surface currently being traversed.

[0072] For each of the road surfaces to be merged, a first road surface with two boundaries that are the same as the two boundaries of the road surface to be merged is determined from at least one of the currently traversed road surfaces, and the road surface to be merged is merged with the first road surface to be merged as the updated road surface to be merged;

[0073] The next two adjacent boundary line cutting windows that are adjacent to the two adjacent boundary line cutting windows of the current traversal are used as the updated two adjacent boundary line cutting windows of the current traversal.

[0074] Optionally, the method further includes:

[0075] For non-boundary lane lines on the target road surface, the direction of the target road surface is taken as the direction of the non-boundary lane lines.

[0076] Optionally, generating multiple boundary line cutting windows for each road boundary line based on the endpoints of the road boundary line and the main trajectory includes:

[0077] For each of the road boundary lines, determine the projection point of each endpoint of the road boundary line on the main trajectory;

[0078] For each of the projection points, a boundary line cutting window is established with the projection point as the center and the length direction perpendicular to the tangent of the projection point on the main trajectory as the length direction.

[0079] According to a second aspect of the present disclosure, a map building apparatus is provided, comprising:

[0080] The acquisition module is configured to acquire lane line data of the target road and the driving trajectory of the vehicle on the target road;

[0081] The determination module is configured to determine the road boundary line of the target road based on the lane line data and the driving trajectory;

[0082] The construction module is configured to construct a target map based on the road boundary lines and the driving trajectory.

[0083] According to a third aspect of the present disclosure, a vehicle is provided, comprising:

[0084] processor;

[0085] Memory used to store processor-executable instructions;

[0086] The processor is configured to perform the steps of the method described in the first aspect of this disclosure.

[0087] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided that stores computer program instructions thereon, which, when executed by a processor, implement the steps of the map construction method provided in the first aspect of the present disclosure.

[0088] According to a fifth aspect of the present disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the method described in the first aspect of the present disclosure.

[0089] The technical solutions provided by the embodiments of this disclosure can include the following beneficial effects: Based on the lane line data of the target road and the driving trajectory of the vehicle on the target road, the road boundary line of the target road is determined. Then, a target map can be constructed based on the road boundary line and the driving trajectory of the vehicle on the target road. Compared with using road surface images to extract road surface information based on color segmentation, texture analysis, and combined with machine learning algorithms to construct a target map, this avoids the problem that the accuracy of road surface information extraction based on images is low due to factors such as lighting conditions, complex road surface conditions, etc., and improves the accuracy of the constructed target map.

[0090] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0091] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0092] Figure 1 This is a flowchart illustrating a map construction method according to an exemplary embodiment.

[0093] Figure 2 It is based on Figure 1 The illustrated embodiment shows a flowchart of a map construction method.

[0094] Figure 3 It is based on Figure 2 The illustrated embodiment shows a flowchart of a map construction method.

[0095] Figure 4 It is based on Figure 3 The illustrated embodiment shows a flowchart of a map construction method.

[0096] Figure 5 This is a flowchart illustrating a map construction method according to an exemplary embodiment.

[0097] Figure 6 It is based on Figure 5The illustrated embodiment shows a flowchart of a map construction method.

[0098] Figure 7 This is a schematic diagram of a road surface extraction scene according to an exemplary embodiment.

[0099] Figure 8 This is a block diagram illustrating a map building apparatus according to an exemplary embodiment.

[0100] Figure 9 This is a block diagram illustrating a vehicle according to an exemplary embodiment. Detailed Implementation

[0101] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0102] The embodiments described in the following examples of this disclosure are not representative of all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0103] It should be noted that all actions involving the acquisition of signals, information, or data in this disclosure are carried out in compliance with the relevant data protection laws and policies of the country where the location is situated, and with authorization from the owner of the relevant device.

[0104] Road surface extraction refers to segmenting a road surface into several sections from a pre-modeled lane line. Related technologies typically employ visual algorithms, using color segmentation and texture analysis of acquired road surface images, combined with machine learning algorithms to extract road surface information. However, considering the influence of factors such as lighting conditions, complex road surface conditions, and other factors, the accuracy of road surface information extracted by existing image recognition-based methods needs improvement, which in turn affects the accuracy of the constructed high-precision maps.

[0105] To address the aforementioned problems, this disclosure provides a map construction method, apparatus, vehicle, medium, and product. The specific embodiments of this disclosure will be described in detail below with reference to the accompanying drawings.

[0106] Figure 1 This is a flowchart illustrating a map construction method according to an exemplary embodiment. The method can be applied to vehicles or terminals. Figure 1 As shown, the method includes the following steps:

[0107] In step S11, lane line data of the target road and the vehicle's driving trajectory on the target road are acquired.

[0108] The target road can be a pre-defined road used for lane line modeling and pavement information extraction. The lane line data can include lane line data corresponding to multiple lane lines on the target road. For example, the lane line data can include lane line identification, lane line type, and lane line succession relationships. Lane line types include, for example, solid white lines, dashed white lines, single yellow lines, double yellow lines, dashed yellow lines, guide lines, and deceleration markings. The lane line succession relationship indicates whether a lane line has a corresponding preceding and / or succeeding lane line. The preceding or succeeding lane line of the current lane line refers to a lane line that is in the same longitudinal direction as the current lane line and is adjacent to it in a connected position.

[0109] It should be noted that the lane lines used in this disclosure to construct the target map can be pre-modeled lane lines. For example, visual lane lines can be obtained by performing image recognition on road surface images, and then multiple complete lane lines can be obtained after performing operations such as deduplication, matching, and connection on the visual lane lines. Subsequently, the type of each lane line and its successor-successor relationships can be determined based on the lane line modeling results.

[0110] Furthermore, this disclosure can be applied to extract road surface information on a target road in offline scenarios. The target road can be a two-way road, and each direction of the road can include multiple lanes. In practical applications, vehicles can be controlled to travel in each direction on the target road. If the target road includes ramps, vehicles can also be controlled to travel on those ramps, thereby obtaining multiple travel trajectories of the vehicle on the target road.

[0111] In step S12, the road boundary line of the target road is determined based on the lane line data and the driving trajectory.

[0112] The road boundary line may include the left boundary line, right boundary line, and median dividing line of the target road. The median dividing line can be understood as the dividing line between lanes traveling in different directions on the target road.

[0113] In step S13, a target map is constructed based on the road boundary lines and the driving trajectory.

[0114] In this step, road surface information can be extracted from the target road based on the road boundary lines and driving trajectory. This road surface information may include, for example, road shape, lane direction, and lane type. Based on the extracted road surface information, a target map can be constructed. The target map may include a high-precision map, which can be used for services such as autonomous driving and route planning for vehicles.

[0115] Using the above method, the road boundary line of the target road is determined based on the lane line data of the target road and the driving trajectory of the vehicle on the target road. Then, the target map can be constructed based on the road boundary line and the driving trajectory of the vehicle on the target road. Compared with using road surface images to extract road surface information based on color segmentation, texture analysis and machine learning algorithms to construct the target map, this method avoids the problem of low accuracy of road surface information extraction based on images due to factors such as lighting conditions, complex road surface conditions and scenes, and improves the accuracy of the constructed target map.

[0116] Figure 2 It is based on Figure 1 The illustrated embodiment shows a flowchart of a map construction method, such as... Figure 2 As shown, step S12 includes the following sub-steps:

[0117] In step S121, a main trajectory is determined from the plurality of driving trajectories, the main trajectory including the longest trajectory among the plurality of driving trajectories.

[0118] Here, the main trajectory refers to the trajectory with the widest coverage and longest length among the multiple driving trajectories of the vehicle on the target road.

[0119] In one implementation, the longest driving trajectory can be selected as the main trajectory based on the length of each driving trajectory. In another possible implementation, the main trajectory can be determined from multiple driving trajectories using a preset trajectory selection algorithm.

[0120] In step S122, multiple boundary line recognition windows are established based on the main trajectory.

[0121] The boundary line recognition window is used to identify road boundary lines from multiple lane lines on the target road.

[0122] In one possible implementation of this step, multiple consecutive trajectory points can be determined from the main trajectory; then, for each trajectory point, a boundary line recognition window is established with the trajectory point as the center and the length direction perpendicular to the tangent of the trajectory point on the main trajectory as the length direction.

[0123] In determining multiple consecutive trajectory points from the main trajectory, the main trajectory can be sampled at equal intervals to obtain multiple consecutive trajectory points. Furthermore, in practical applications, the number of generated boundary line recognition windows can be controlled by adjusting the sampling interval of the main trajectory, thus balancing the accuracy and efficiency of road surface information extraction.

[0124] In addition, the boundary line recognition window can be a line segment with the trajectory point as the midpoint, the direction perpendicular to the tangent of the trajectory point on the main trajectory as the length direction, and the road width of the target road as the length of the line segment, or it can be a rectangle with the trajectory point as the midpoint, the direction perpendicular to the tangent of the trajectory point on the main trajectory as the length direction, the road width of the target road as the length, and the width as a preset width.

[0125] In step S123, the road boundary line of the target road is determined through multiple boundary line recognition windows based on the lane line data and multiple driving trajectories.

[0126] Figure 3 It is based on Figure 2 The illustrated embodiment shows a flowchart of a map construction method, such as... Figure 3 As shown, step S123 includes the following sub-steps:

[0127] In step S1231, the driving direction of each driving trajectory is obtained.

[0128] In step S1232, based on the lane line data of multiple lane lines and the driving direction of each driving trajectory, the lane line direction corresponding to each lane line is determined through multiple boundary line recognition windows.

[0129] In this disclosure, the direction of the lane line can include three directions: in the same direction as the main trajectory, in the opposite direction to the main trajectory, and unknown direction.

[0130] Figure 4 It is based on Figure 3 The illustrated embodiment shows a flowchart of a map construction method, such as... Figure 4 As shown, step S1232 includes the following sub-steps:

[0131] In step S12321, for each boundary line identification window, at least one first trajectory intersecting with the boundary line identification window is determined from multiple driving trajectories.

[0132] For example, suppose the boundary line recognition window is a line segment with the trajectory point as the midpoint, the direction perpendicular to the tangent of the trajectory point on the main trajectory as the length direction, and the road width of the target road as the length of the line segment. At least one first trajectory that intersects with the boundary line recognition window is the driving trajectory that intersects with the line segment.

[0133] In step S12322, for each first trajectory, the relative direction between the first trajectory and the main trajectory, as well as the position of the first trajectory within the boundary line recognition window, are determined.

[0134] The relative direction can include the first trajectory traveling in the same direction as the main trajectory, or the first trajectory traveling in the opposite direction to the main trajectory. Thus, the relative direction between each first trajectory and the main trajectory can be determined based on the travel direction of each first trajectory and the travel direction of the main trajectory. It should be noted that the first trajectory also includes the main trajectory itself. When the first trajectory is the main trajectory, it can be understood that the relative direction between this trajectory and the main trajectory is that the first trajectory and the main trajectory travel in the same direction. The position of the first trajectory within the boundary line recognition window is the position of the intersection point between the first trajectory and the line segment corresponding to the boundary line recognition window.

[0135] In step S12323, the lane line direction corresponding to each lane line is determined based on the lane line data of multiple lane lines, the relative direction of each first trajectory to the main trajectory, and the position of each first trajectory within the boundary line recognition window.

[0136] As described above, for each lane line, the lane line data includes the preceding and following relationships corresponding to the lane line, where the preceding and following relationships represent the preceding and / or following lane lines. Thus, during this step, the lane line direction corresponding to each lane line can be determined based on the relative direction of each first trajectory to the main trajectory, the position of each first trajectory within the boundary line identification window, and the preceding and following relationships of each lane line.

[0137] In one implementation of this step, the lane direction of at least one lane line can be determined based on the relative direction of each of the first trajectories to the main trajectory and the position of each of the first trajectories within the boundary line identification window; the direction propagation of lane lines is performed based on the successor relationship of each lane line and the lane direction of the at least one lane line to determine the lane direction corresponding to each of the multiple lane lines.

[0138] In other words, the process of determining the lane line direction in this disclosure can be divided into two steps. First, the lane lines can be assigned a direction value based on the relative direction of each first trajectory to the main trajectory and the position of each first trajectory within the boundary line recognition window. Then, based on the lane line direction of at least one lane line after the direction assignment, and combined with the successor relationship of each lane line, the lane line directions corresponding to multiple lane lines are determined respectively.

[0139] In the process of determining the lane direction of at least one lane line (i.e., assigning lane direction values) based on the relative direction of each first trajectory to the main trajectory and the position of each first trajectory within the boundary line recognition window, for each first trajectory, the lane lines located on both sides of the first trajectory can be traversed according to the position of the first trajectory within the boundary line recognition window; for at least one lane line on each side, starting from the lane line closest to the first trajectory, each lane line on the current side is traversed sequentially, and the lane direction determination step is executed cyclically until the first loop termination condition of the current side is met;

[0140] The lane line direction determination step includes: for the currently traversed first lane line, determining the lane line direction of the first lane line based on the relative direction between the first trajectory and the main trajectory; determining whether the first lane line is a road boundary line based on the lane line type of the first lane line; if the first lane line is determined to be the road boundary line, determining that the first loop termination condition is met, and ending the traversal of the lane lines on the current side; if the first lane line is determined not to be the road boundary line, taking the next lane line of the first lane line on the current side as the updated first lane line.

[0141] In determining the lane direction of the first lane line based on the relative direction between the first trajectory and the main trajectory, when the relative directions of the first trajectory and the main trajectory are in the same direction, the count value of the first lane line in the first preset direction is increased by a preset update value; when the relative directions of the first trajectory and the main trajectory are in opposite directions, the count value of the first lane line in the second preset direction is increased by a preset update value. The first preset direction is in the same direction as the main trajectory, and the second preset direction is in the opposite direction. If the count value of the first lane line in the target preset direction is greater than or equal to a preset count threshold, the lane direction of the first lane line is determined to be the target preset direction, where the target preset direction includes either the first preset direction or the second preset direction.

[0142] The preset update value can be, for example, 1. The first preset direction is the same as the driving direction of the main trajectory, and the second preset direction is the opposite to the driving direction of the main trajectory. In this way, after determining the driving direction of the main trajectory, the lane direction of the first lane line can be identified.

[0143] For example, suppose a vehicle has four driving trajectories on the target road, which can be labeled as trajectory 1, trajectory 2, trajectory 3 and trajectory 4 from top to bottom, and the main trajectory is determined to be trajectory 2. Taking the currently traversed boundary line recognition window A as an example, assume that the four trajectories 1, 2, 3 and 4 all intersect with window A, that is, the first trajectory includes trajectory 1, trajectory 2, trajectory 3 and trajectory 4. For trajectory 1, based on its position within window A, the lane lines on both sides of trajectory 1 are traversed. For each lane line, the traversal can begin from the lane line closest to trajectory 1. For example, the lane lines on the left side of trajectory 1 are traversed first. For the first lane line currently traversed, assuming that the relative direction of trajectory 1 and the main trajectory (i.e., trajectory 2) is the same, the count value of the first preset direction (e.g., "SAME_DIRECTION") of the first lane line is incremented by 1. However, if the relative direction of trajectory 1 and the main trajectory is opposite, the count value of the second preset direction (e.g., "REVERSE_DIRECTION") of the first lane line is incremented by 1. Then, based on the lane line type of the first lane line, it can be determined whether the first lane line is a road boundary line (the road boundary line can include the boundary line between lanes in different directions on the target road, or it can include the left and right boundary lines of the entire target road. For example, in practical applications, the road boundary line can be a single / double yellow line, a yellow dashed line, a fence, a curb, a road boundary line, etc.). Understandably, if the first lane line is the road boundary, the traversal of the lane lines on the current side needs to be terminated. Therefore, in this example, if the first lane line is determined to be the road boundary, the first loop termination condition is met, the traversal of the lane lines on the current side ends, and then the lane lines on the other side of trajectory 1 are traversed sequentially, with the direction of each lane line assigned accordingly. If the first lane line is determined not to be the road boundary, the next lane line of the current first lane line can be used as the updated first lane line, and the direction of the lane lines can continue to be assigned. After the above steps, the direction of the lane lines on both sides of each of the four first trajectories intersecting with window A can be assigned. Similarly, by traversing each lane line recognition window in turn, the count value of the first preset direction or the second preset direction corresponding to the lane line can be updated. In this process, when it is determined that the count value of the target preset direction of a certain lane line is greater than or equal to the preset count threshold, the lane line direction of that lane line can be determined as the target preset direction. The target preset direction can be the first preset direction or the second preset direction. The above example is only for illustration and this disclosure does not limit it.

[0144] It should be noted that if the first trajectory includes multiple lane lines, each lane line between two adjacent first trajectories will have two count values ​​for each preset direction (i.e., the first preset direction and the second preset direction) based on the relative directions of the first trajectories on both sides of the lane line to the main trajectory. If the count value corresponding to any preset direction is greater than or equal to a preset count threshold,

[0145] For example, assuming two adjacent first trajectories are denoted as the x-trajectory and the y-trajectory, and a lane line between the x-trajectory and the y-trajectory is denoted as L, then based on the relative direction of the x-trajectory to the main trajectory, the count value of lane line L corresponding to the first preset direction SAME_DIRECTION-1 can be updated, or the count value of lane line L corresponding to the second preset direction REVERSE_DIRECTION-1 can be updated. Based on the relative direction of the y-trajectory to the main trajectory, the count value of lane line L corresponding to the first preset direction SAME_DIRECTION-2 can be updated, or the count value of lane line L corresponding to the second preset direction REVERSE_DIRECTION-2 can be updated.

[0146] As described above, in the process of assigning lane line directions, this disclosure determines the lane line direction of the first lane line as the target preset direction only if the count value of the target preset direction of the first lane line is greater than or equal to a preset count threshold. However, if, after traversing the boundary line recognition window, the count values ​​of both the first and second preset directions corresponding to the lane line are less than the preset count threshold, the direction of the lane line cannot be determined solely based on lane line direction assignment. To address this situation, this disclosure can propagate lane line directions based on the principle that the directions of successive lane lines are consistent, so that based on lane lines whose directions have already been determined, and combined with the successive relationships of lane lines, the lane line directions of more lane lines can be determined.

[0147] In one implementation, all lane lines obtained from modeling can be recorded in a preset lane line set. During the direction propagation process, this disclosure sequentially traverses each lane line stored in the preset lane line set and repeatedly executes the lane line direction propagation steps until the preset lane line set is completely traversed. The lane line direction propagation steps include: taking the currently traversed lane line as the second lane line; if the second lane line meets the preset direction propagation conditions, determining the preceding and / or succeeding lane lines corresponding to the second lane line based on the preceding and succeeding relationships, and taking the lane line direction of the second lane line as the direction of the preceding and / or succeeding lane lines, continuing to traverse the next lane line of the second lane line, and taking the next lane line as the updated second lane line; if the second lane line does not meet the preset direction propagation conditions, skipping the second lane line, continuing to traverse the next lane line of the second lane line, and taking the next lane line as the updated second lane line.

[0148] The preset direction propagation conditions include: the second lane line has a determined lane line direction, the second lane line has a corresponding preceding lane line and / or following lane line, and the preceding lane line and / or following lane line corresponding to the second lane line has a lane line with an undetermined direction.

[0149] For example, the first lane line in the currently traversed preset lane line set (denoted as lane line 1) is taken as the second lane line. If the lane line direction of lane line 1 has been determined (usually based on the lane line direction assignment), and based on the successor relationship of lane line 1, it is determined that lane line 1 has a corresponding successor lane line (let's say lane line 2), and the direction of lane line 2 has not yet been determined, based on the principle that the directions of successor and successor lane lines are consistent, the lane line direction of lane line 1 can be assigned to lane line 2. In this way, the lane line direction of lane line 2 can be determined. Then, the lane lines in the preset lane line set can continue to be traversed, and the currently traversed lane lines that meet the preset direction propagation conditions are updated as the second lane line. The direction propagation is carried out in the above manner until all lane lines in the preset lane line set have been traversed. After that, the lane line directions of more lane lines can be determined. The above example is only for illustration, and this disclosure does not limit it.

[0150] It should be noted that during the traversal of the preset lane line set, if it is determined that the currently traversed lane line does not meet the above-mentioned preset direction propagation conditions, the lane line can be skipped directly until a lane line that meets the preset direction propagation conditions is traversed.

[0151] In step S1233, the road boundary line is determined through multiple boundary line recognition windows based on the lane line data of multiple lane lines and the lane line direction corresponding to each lane line.

[0152] In this step, for each lane line, the boundary type of the lane line can be determined based on the lane line direction and lane line data. The boundary type represents whether the corresponding lane line belongs to the lane boundary and the boundary type when it belongs to the lane boundary. Based on the boundary type corresponding to each lane line, the road boundary line is determined through multiple boundary line recognition windows.

[0153] For each lane line, the lane line data includes the lane line type. Thus, during this step, the lane line boundary type can be determined based on the lane line direction and type. This boundary type includes at least two of the following: left boundary, right boundary, median dividing line, non-boundary, and unknown type. The left boundary is the left boundary line of the target road, the right boundary is the right boundary line of the target road, and the median dividing line is the dividing line between lanes in different directions on the target road (such as single / double yellow lines in the center of the road, median barriers, the edge of green belts, etc.). A non-boundary refers to a situation where the lane line type indicates it does not belong to the road boundary line, but it is impossible to determine whether it belongs to the left boundary, right boundary, or median dividing line.

[0154] For example, for a certain lane line, the lane line is determined to be a boundary line of the target road based on the lane line type. Assuming the direction of the main trajectory is to the right, if the direction of the lane line is the same as the main trajectory, then the direction of the lane line is determined to be to the right, and the boundary type of the lane line is the right boundary; if the direction of the lane line is opposite to the main trajectory, then the direction of the lane line is determined to be to the left, and the boundary type of the lane line is the left boundary. If a lane line is determined to be a boundary line of the target road based on its lane type, but the lane line has two directions—one that is the same as the direction of the main trajectory and the other that is opposite to the direction of the main trajectory—this is clearly a contradictory situation. However, in actual road scenarios, if the lane line is the median dividing line between two lanes, then when assigning lane line directions, the lane line may be assigned two opposite directions. Therefore, in this case, if a lane line is determined to be a boundary line of the target road based on its lane type, but the lane line has two directions, then the boundary type of the lane line can be determined to be a median dividing line. The above example is only for illustration, and this disclosure does not limit it.

[0155] In addition, during the propagation of lane lines, for the guide lines at the center of the road, both will serve as the boundaries of the road surface. For the guide lines at the road boundary, that is, one of them is the road boundary line, only the guide line that serves as the road boundary line needs to be retained as the boundary of the road surface, and the other guide line can be discarded.

[0156] Furthermore, this step can further determine the road boundary lines through multiple boundary line recognition windows based on the boundary type corresponding to each lane line. In one implementation, multiple boundary lane lines can be determined from the multiple lane lines according to the boundary type; by re-traversing each boundary line recognition window, boundary lane lines with successive relationships are connected to generate multiple road boundary lines.

[0157] By performing this step, multiple boundary line recognition windows can be re-traversed, and then, based on the successor relationship of the boundary lines each day, the boundary lane lines with successor relationships can be connected together to generate multiple complete road boundary lines.

[0158] Figure 5 This is a flowchart illustrating a map construction method according to an exemplary embodiment, such as... Figure 5 As shown, step S13 includes the following sub-steps:

[0159] In step S131, road surface information is extracted from the target road based on the road boundary line and the driving trajectory.

[0160] Figure 6 It is based on Figure 5 The illustrated embodiment shows a flowchart of a map construction method, such as... Figure 6 As shown, step S131 includes the following sub-steps:

[0161] In step S1311, a main trajectory is determined from multiple driving trajectories, wherein the main trajectory includes the longest trajectory among the multiple driving trajectories.

[0162] The implementation method of this step can be referred to in the description of step S121, and will not be repeated here.

[0163] In step S1312, for each of the road boundary lines, multiple boundary line cutting windows are generated based on the endpoints of the road boundary lines and the main trajectory.

[0164] In this step, for each road boundary line, the projection points of each endpoint of the road boundary line on the main trajectory can be determined; for each projection point, the boundary line cutting window is established with the projection point as the center and the direction perpendicular to the tangent of the projection point on the main trajectory as the length direction.

[0165] The boundary line cutting window is used to segment the road surface based on the endpoints of each boundary line, so as to extract road surface information such as road shape and lane lines based on the road surface segmentation results.

[0166] It is understandable that establishing a boundary line cutting window centered on the projection point of the endpoint of the road boundary line onto the main trajectory is less efficient than building a boundary line recognition window based on multiple trajectory points sampled on the main trajectory. Since the number of endpoints of the boundary line is significantly less than the number of trajectory points, the number of boundary line cutting windows is also less than the number of boundary line recognition windows.

[0167] In addition, the implementation method for establishing the boundary line cutting window in this step can refer to the specific implementation method for establishing the boundary line recognition window described above, and will not be repeated here.

[0168] In step S1313, road surface information is extracted from the target road through the multiple boundary line cutting windows according to the boundary type of the road boundary line and the lane line direction corresponding to the road boundary line.

[0169] In this step, for each pair of adjacent boundary line cutting windows in the plurality of boundary line cutting windows, the road boundary lines between each pair of adjacent boundary line cutting windows are matched according to the boundary type of the road boundary lines and the lane line direction corresponding to the road boundary lines, and the road surface between the two adjacent road boundary lines that meet the preset matching rules is taken as the candidate road surface; the road surface information of the target road is extracted according to the candidate road surface between each pair of adjacent boundary line cutting windows and the two boundaries of each candidate road surface.

[0170] The preset matching rules include:

[0171] The combination of the boundary types of the two adjacent road boundary lines is a preset type combination; and the positions of the two adjacent road boundaries satisfy a preset position strategy corresponding to the lane line direction of the two adjacent road boundary lines.

[0172] For example, the preset type combination may include "left boundary - right boundary", "left boundary - center dividing line", and "center dividing line - right boundary". The preset position strategy corresponding to the lane line direction of two adjacent road boundary lines may include, for example, the direction of the boundary's direction type (i.e., in the same direction as the main trajectory or in the opposite direction to the main trajectory), the left boundary must be located to the left of the two boundaries, the right boundary must be located to the right of the two boundaries, and in addition, the two road boundaries are adjacent, that is, there are no other boundaries between the two road boundaries.

[0173] In addition, in the process of extracting road surface information of the target road based on the candidate road surface between each pair of adjacent boundary line cutting windows and the two boundaries of each candidate road surface, the candidate road surface between each pair of adjacent boundary line cutting windows can be traversed sequentially according to the order of multiple boundary line cutting windows, and the road surface merging step can be executed cyclically until all the multiple boundary line cutting windows have been traversed; the road surface to be merged at the end of the loop is taken as the target road surface to be extracted.

[0174] The road surface merging step includes: taking at least one candidate road surface between two preset adjacent boundary line cutting windows as the road surface to be merged; taking the next two adjacent boundary line cutting windows adjacent to the preset two adjacent boundary line cutting windows as the currently traversed two adjacent boundary line cutting windows; and taking at least one candidate road surface between the currently traversed two adjacent boundary line cutting windows as the currently traversed road surface; for each road surface to be merged, determining a first road surface from at least one currently traversed road surface whose two boundaries are the same as the two boundaries of the road surface to be merged, and merging the road surface to be merged with the first road surface to obtain the updated road surface to be merged; and taking the next two adjacent boundary line cutting windows adjacent to the currently traversed two adjacent boundary line cutting windows as the updated currently traversed two adjacent boundary line cutting windows.

[0175] For example, Figure 7 This is a schematic diagram illustrating a road surface extraction scene according to an exemplary embodiment, such as... Figure 7 As shown in the figure, the four dashed lines represent four boundary line cutting windows. Looking from left to right, the first and second dashed lines on the left, along with the two topmost road boundary lines, form a rectangular area 1. When the boundary type combination of the upper and lower road boundary lines of rectangular area 1 is determined to be one of three combinations: "left boundary - right boundary," "left boundary - middle dividing line," or "middle dividing line - right boundary," rectangular area 1 is determined to satisfy the preset matching rule. Rectangular area 1 is then used as a candidate road surface. Following a similar method, further determinations can be made for... Figure 7 Regions 2, 3, 4, 5, 6, and 7 shown are all candidate road surfaces. Then, following the order of the multiple boundary line cutting windows, the candidate road surfaces between each pair of adjacent boundary line cutting windows are traversed sequentially, and the road surface merging step is executed iteratively. For example... Figure 7 As shown, the four boundary line cutting windows are traversed from left to right. The preset candidate road surfaces between two adjacent boundary line cutting windows can be, for example, Figure 7The rectangular area 1 between the first and second dashed lines shown on the left can be considered as the road surface to be merged. The second and third dashed lines adjacent to the first and second dashed lines are used as the cutting windows between the two adjacent boundary lines currently being traversed. At least one candidate road surface between these two adjacent boundary line cutting windows is used as the currently traversed road surface. Figure 7 As shown, the currently traversed road surface is... Figure 7 Regions 2, 3, 4, and 5 are used. Thus, for the rectangular area 1 of the road surface to be merged, a first road surface with the same two boundaries as the rectangular area 1 can be determined from regions 2, 3, 4, and 5. For example, this first road surface is region 2. Regions 1 and 2 can be merged to obtain a new road surface to be merged. Then, the traversal can continue to iterate through the next two adjacent boundary line cutting windows adjacent to the currently traversed two adjacent boundary line cutting windows, so as to update the currently traversed two adjacent boundary line cutting windows. This process continues until the loop ends, and the road surface to be merged at the end of the loop is taken as the target road surface to be extracted. The above example is only for illustration and this disclosure does not limit it.

[0176] It should be noted that during the process of matching the road surface to be merged with the candidate road surface, the unmatched candidate road surface can be added to the set of road surfaces to be merged so that it can continue to participate in the matching process in the future.

[0177] Furthermore, for non-boundary lane lines on the target road surface, the direction of the target road surface can be used as the direction of the non-boundary lane line. For example, spatial location information can be used to calculate the target road surface to which the non-boundary lane line belongs, and then the direction of the non-boundary lane line can be set as the direction of the target road surface, where the direction of the target road surface can be understood as the vehicle's travel direction corresponding to the target road surface.

[0178] In step S132, the target map is constructed based on the extracted road surface information.

[0179] The road surface information may include, for example, road shape, lane direction, and lane type, so that the target map can be constructed based on the extracted road surface information.

[0180] By employing the above method, combining lane line direction propagation and the concept of sliding windows (both boundary line recognition windows and boundary line cutting windows belong to sliding windows), it is possible to accurately extract road surface information such as road shape and lane lines of the target road for various complex and diverse road scenarios. The target map can be constructed based on the extracted road surface information, which can also improve map accuracy and thus improve the navigation and positioning accuracy of autonomous vehicles.

[0181] Figure 8This is a block diagram illustrating a map building apparatus according to an exemplary embodiment, such as... Figure 8 As shown, the device includes:

[0182] The acquisition module 801 is configured to acquire lane line data of the target road and the driving trajectory of the vehicle on the target road;

[0183] The determining module 802 is configured to determine the road boundary line of the target road based on the lane line data and the driving trajectory;

[0184] The construction module 803 is configured to construct a target map based on the road boundary lines and the driving trajectory.

[0185] Optionally, the driving trajectory includes multiple trajectories, and the determining module 802 is configured to determine a main trajectory from the multiple driving trajectories, the main trajectory including the longest trajectory among the multiple driving trajectories; establish multiple boundary line recognition windows based on the main trajectory; and determine the road boundary line of the target road through the multiple boundary line recognition windows based on the lane line data and the multiple driving trajectories.

[0186] Optionally, the determining module 802 is configured to determine multiple consecutive trajectory points from the main trajectory; for each trajectory point, a boundary line recognition window is established with the trajectory point as the center and the length direction perpendicular to the tangent of the trajectory point on the main trajectory as the length direction.

[0187] Optionally, the lane line data includes data for multiple lane lines, and the determining module 802 is configured to acquire the driving direction of each driving trajectory; determine the lane line direction corresponding to each lane line through multiple boundary line recognition windows based on the lane line data of multiple lane lines and the driving direction of each driving trajectory; and determine the road boundary line through multiple boundary line recognition windows based on the lane line data of multiple lane lines and the lane line direction corresponding to each lane line.

[0188] Optionally, the determining module 802 is configured to determine the boundary type of each lane line based on the lane line direction and the lane line data, wherein the boundary type represents whether the corresponding lane line belongs to the lane boundary and the boundary type when it belongs to the lane boundary; and determine the road boundary line through multiple boundary line recognition windows based on the boundary type corresponding to each lane line.

[0189] Optionally, the determining module 802 is configured to, for each boundary line identification window, determine at least one first trajectory intersecting with the boundary line identification window from a plurality of driving trajectories; for each first trajectory, determine the relative direction between the first trajectory and the main trajectory, and the position of the first trajectory within the boundary line identification window; and determine the lane line direction corresponding to each lane line based on the lane line data of the plurality of lane lines, the relative direction between each first trajectory and the main trajectory, and the position of each first trajectory within the boundary line identification window.

[0190] Optionally, for each lane line, the lane line data includes the preceding and following relationships corresponding to the lane line, the preceding and following relationships representing the preceding and / or following lane lines corresponding to the lane line; the determining module 802 is configured to determine the lane line direction corresponding to each lane line based on the relative direction of each first trajectory to the main trajectory, the position of each first trajectory within the boundary line identification window, and the preceding and following relationships of each lane line.

[0191] Optionally, the determining module 802 is configured to determine the lane line direction of at least one lane line based on the relative direction of each of the first trajectories to the main trajectory and the position of each of the first trajectories within the boundary line identification window; and to perform lane line direction propagation based on the successor relationship of each of the lane lines and the lane line direction of the at least one lane line to determine the lane line directions corresponding to the multiple lane lines respectively.

[0192] Optionally, the determining module 802 is configured to, for each of the first trajectories, traverse the lane lines located on both sides of the first trajectory according to the position of the first trajectory within the boundary line identification window; for at least one lane line on each side, starting from the lane line closest to the first trajectory, sequentially traverse each lane line on the current side, and repeatedly execute the lane line direction determination step until the first loop termination condition of the current side is met.

[0193] The lane line direction determination step includes: for the currently traversed first lane line, determining the lane line direction of the first lane line based on the relative direction between the first trajectory and the main trajectory; determining whether the first lane line is a road boundary line based on the lane line type of the first lane line; if the first lane line is determined to be the road boundary line, determining that the first loop termination condition is met, and ending the traversal of the lane lines on the current side; if the first lane line is determined not to be the road boundary line, taking the next lane line of the first lane line on the current side as the updated first lane line.

[0194] Optionally, the determining module 802 is configured to, when the relative directions of the first trajectory and the main trajectory are in the same direction, increase the count value of the first lane line in a first preset direction by a preset update value; when the relative directions of the first trajectory and the main trajectory are in opposite directions, increase the count value of the first lane line in a second preset direction by the preset update value; wherein the first preset direction is in the same direction as the main trajectory, and the second preset direction is in opposite direction to the main trajectory; and when the count value of the first lane line in a target preset direction is determined to be greater than or equal to a preset count threshold, the lane line direction of the first lane line is determined to be the target preset direction, wherein the target preset direction includes either the first preset direction or the second preset direction.

[0195] Optionally, the determining module 802 is configured to sequentially traverse each lane line stored in the preset lane line set and repeatedly execute the lane line direction propagation step until the preset lane line set has been traversed.

[0196] The lane line direction propagation step includes: taking the currently traversed lane line as the second lane line; if the second lane line meets the preset direction propagation conditions, determining the preceding and / or following lane lines corresponding to the second lane line according to the preceding and following relationship, and taking the lane line direction of the second lane line as the direction of the preceding and / or following lane lines, continuing to traverse the next lane line of the second lane line, and taking the next lane line as the updated second lane line; if the second lane line does not meet the preset direction propagation conditions, skipping the second lane line, continuing to traverse the next lane line of the second lane line, and taking the next lane line as the updated second lane line.

[0197] Optionally, the preset direction propagation conditions include:

[0198] The second lane line has a defined direction, the second lane line has a corresponding preceding lane line and / or following lane line, and the preceding lane line and / or following lane line corresponding to the second lane line has a lane line with an undefined direction.

[0199] Optionally, for each lane line, the lane line data includes the lane line type of the lane line, and the determining module 802 is configured to determine the boundary type of the lane line based on the lane line direction and the lane line type of the lane line.

[0200] Optionally, the determining module 802 is configured to determine multiple boundary lane lines from multiple lane lines according to the boundary type; and generate multiple road boundary lines by re-traversing each boundary line identification window and connecting boundary lane lines with successive relationships.

[0201] Optionally, the construction module 803 is configured to extract road surface information of the target road based on the road boundary line and the driving trajectory; and construct the target map based on the extracted road surface information.

[0202] Optionally, the road boundary lines include multiple lines; the construction module 803 is configured to determine a main trajectory from the multiple driving trajectories, the main trajectory including the longest trajectory among the multiple driving trajectories; for each road boundary line, multiple boundary line cutting windows are generated based on the endpoints of the road boundary line and the main trajectory; based on the boundary type of the road boundary line and the lane line direction corresponding to the road boundary line, road surface information is extracted from the target road through the multiple boundary line cutting windows.

[0203] Optionally, the construction module 803 is configured to, for each pair of adjacent boundary line cutting windows in the plurality of boundary line cutting windows, match each pair of adjacent road boundary lines between the adjacent two boundary line cutting windows according to the boundary type of the road boundary line and the lane line direction corresponding to the road boundary line, and take the road surface between the adjacent two road boundary lines that meet the preset matching rules as candidate road surfaces; and extract road surface information of the target road based on the candidate road surfaces between each pair of adjacent boundary line cutting windows and the two boundaries of each candidate road surface.

[0204] Optionally, the preset matching rules include:

[0205] The combination of the boundary types of two adjacent road boundary lines is a preset type combination;

[0206] The positions of the two adjacent road boundaries satisfy a preset position strategy corresponding to the lane line direction of the two adjacent road boundary lines.

[0207] Optionally, the construction module 803 is configured to sequentially traverse the candidate road surfaces between every two adjacent boundary line cutting windows according to the order of the plurality of boundary line cutting windows, and repeatedly execute the road surface merging step until all the plurality of boundary line cutting windows have been traversed; the road surface to be merged at the end of the loop is taken as the target road surface to be extracted; the road surface merging step includes:

[0208] At least one candidate road surface between two pre-defined adjacent boundary line cutting windows is taken as the road surface to be merged. The next two adjacent boundary line cutting windows adjacent to the pre-defined adjacent boundary line cutting windows are taken as the currently traversed adjacent boundary line cutting windows. At least one candidate road surface between the currently traversed adjacent boundary line cutting windows is taken as the currently traversed road surface. For each road surface to be merged, a first road surface with two boundaries identical to the two boundaries of the road surface to be merged is determined from at least one currently traversed road surface. The road surface to be merged is merged with the first road surface to be taken as the updated road surface to be merged. The next two adjacent boundary line cutting windows adjacent to the currently traversed adjacent boundary line cutting windows are taken as the updated currently traversed adjacent boundary line cutting windows.

[0209] Optionally, the construction module 803 is configured to use the direction of the target road surface as the direction of the non-boundary lane line for the non-boundary lane line on the target road surface.

[0210] Optionally, the construction module 803 is configured to determine, for each of the road boundary lines, the projection point of each endpoint of the road boundary line on the main trajectory; and for each projection point, establish the boundary line cutting window with the projection point as the center and the direction perpendicular to the tangent of the projection point on the main trajectory as the length direction.

[0211] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0212] This disclosure also provides a computer-readable storage medium having stored thereon computer program instructions that, when executed by a processor, implement the steps of the map construction method provided in this disclosure.

[0213] Figure 9 This is a block diagram illustrating a vehicle according to an exemplary embodiment. For example, vehicle 900 can be a hybrid vehicle, a non-hybrid vehicle, an electric vehicle, a fuel cell vehicle, or other types of vehicle. Vehicle 900 can be an autonomous vehicle, a semi-autonomous vehicle, or a non-autonomous vehicle.

[0214] Reference Figure 9 The vehicle 900 may include various subsystems, such as an infotainment system 910, a perception system 920, a decision control system 930, a drive system 940, and a computing platform 950. The vehicle 900 may also include more or fewer subsystems, and each subsystem may include multiple components. Furthermore, each subsystem and component of the vehicle 900 can be interconnected via wired or wireless means.

[0215] In some embodiments, the infotainment system 910 may include a communication system, an entertainment system, and a navigation system, etc.

[0216] The perception system 920 may include several sensors for sensing information about the environment surrounding the vehicle 900. For example, the perception system 920 may include a global positioning system (which may be GPS, BeiDou, or other positioning systems), an inertial measurement unit (IMU), lidar, millimeter-wave radar, ultrasonic radar, and a camera device.

[0217] The decision control system 930 may include a computing system, a vehicle controller, a steering system, a throttle, and a braking system.

[0218] The drive system 940 may include components that provide powered motion to the vehicle 900. In one embodiment, the drive system 940 may include an engine, an energy source, a transmission system, and wheels. The engine may be one or a combination of internal combustion engines, electric motors, and compressed air engines. The engine is capable of converting energy provided by the energy source into mechanical energy.

[0219] Some or all of the functions of the vehicle 900 are controlled by a computing platform 950. The computing platform 950 may include at least one processor 951 and a memory 952, the processor 951 being able to execute instructions 953 stored in the memory 952.

[0220] Processor 951 can be any conventional processor, such as a commercially available CPU. Processors may also include graphics processing units (GPUs), field-programmable gate arrays (FPGAs), systems-on-chips (SoCs), application-specific integrated circuits (ASICs), or combinations thereof.

[0221] The memory 952 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0222] In addition to instruction 953, memory 952 can also store data, such as road maps, route information, vehicle position, direction, speed, and other data. The data stored in memory 952 can be used by computing platform 950.

[0223] In this embodiment of the disclosure, the processor 951 may execute instructions 953 to complete all or part of the steps of the map construction method described above.

[0224] In another exemplary embodiment, a computer program product is also provided, the computer program product comprising a computer program executable by a programmable device, the computer program having a code portion for performing the map construction method described above when executed by the programmable device.

[0225] Those skilled in the art will also understand that the various illustrative logical blocks and steps listed in the embodiments of this application can be implemented by electronic hardware, computer software, or a combination of both. Whether such functionality is implemented through hardware or software depends on the specific application and the overall system design requirements. Those skilled in the art can implement the described functionality using various methods for each specific application, but such implementation should not be construed as exceeding the scope of protection of the embodiments of this application.

[0226] Furthermore, the term “exemplary” is used herein to mean serving as an example, instance, or illustration. Any aspect or design described herein as “exemplary” is not necessarily to be construed as advantageous compared to other aspects or designs. Rather, the use of the term “exemplary” is intended to present the concept in a concrete manner. As used herein, the term “or” is intended to mean an inclusive “or” rather than an exclusive “or.” That is, unless otherwise specified or clear from the context, “X applies A or B” is intended to mean any of the natural inclusive arrangements. That is, “X applies A or B” satisfies any of the foregoing instances if X applies A; X applies B; or both X applies A and B. Additionally, unless otherwise specified or clear from the context to refer to the singular form, the articles “a” and “an” as used in this application and the appended claims are generally understood to mean “one or more.”

[0227] Similarly, although this disclosure has been shown and described with respect to one or more implementations, equivalent variations and modifications will occur to those skilled in the art upon reading and understanding the specification and drawings. This disclosure includes all such modifications and variations and is limited only by the scope of the claims. In particular, with respect to the various functions performed by the components described above (e.g., elements, resources, etc.), unless otherwise indicated, the terminology used to describe such components is intended to correspond to any component (functionally equivalent) that performs the specific function of the described component, even if structurally not equivalent to the disclosed structure. Furthermore, although specific features of this disclosure may have been disclosed with respect to only one of several implementations, such features may be combined with one or more other features of other implementations, as may be desired and advantageous to any given or particular application. Moreover, with regard to the terms “comprising,” “owning,” “having,” “having,” or variations thereof as used in the detailed description or claims, such terms are intended to be inclusive in a manner similar to the term “including.”

[0228] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the appended claims.

[0229] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

[0230] In the above detailed description, reference has been made to the accompanying drawings, which illustrate specific aspects of this disclosure by way of illustration. In this regard, terms indicating direction or positional relationship, such as “center,” “longitudinal,” “lateral,” “length,” “width,” “thickness,” “upper,” “lower,” “front,” “rear,” “left,” “right,” “vertical,” “horizontal,” “top,” “bottom,” “inner,” “outer,” “clockwise,” “counterclockwise,” “axial,” “radial,” and “circumferential,” are used with reference to the orientation of the described figures. Since components of the described device can be positioned in multiple different orientations, directional terms are used for illustrative purposes and not for limitation. It should be understood that other aspects can be utilized and structural or logical changes can be made without departing from the concept of this disclosure. Therefore, the following detailed description should not be considered limiting.

[0231] It should be understood that, unless otherwise specifically indicated, features of various embodiments of this disclosure described herein can be combined with each other. As used herein, the term “and / or” includes any one of the relevant listed items and any combination of any two or more; similarly, “at least one of…” includes any one of the relevant listed items and any combination of any two or more.

[0232] It should be understood that, unless otherwise expressly specified and limited, the terms "joining," "attaching," "installing," "connecting," "linking," "fixing," etc., used in the embodiments of this disclosure should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection, an electrical connection, or a connection that allows communication between them; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components, unless otherwise expressly limited. Those skilled in the art can understand the specific meaning of the above terms herein based on the specific circumstances.

[0233] Furthermore, the term "above" as used herein with respect to components, elements, or material layers formed or located "above" a surface may be used to indicate that the component, element, or material layer is "indirectly" positioned (e.g., placed, formed, deposited, etc.) on the surface such that one or more additional components, elements, or layers are arranged between the surface and the component, element, or material layer. However, the term "above" as used with respect to components, elements, or material layers formed or located "above" a surface may also optionally have a specific meaning: that the component, element, or material layer is "directly" positioned (e.g., placed, formed, deposited, etc.) on the surface, for example, in direct contact with the surface.

[0234] Although terms such as “first,” “second,” and “third” may be used herein to describe various components, parts, regions, layers, or sections, these components, parts, regions, layers, or sections are not limited to these terms. Rather, these terms are used only to distinguish one component, part, region, layer, or section from another. Therefore, without departing from the teachings of the examples described herein, the first component, part, region, layer, or section mentioned in the examples may also be referred to as the second component, part, region, layer, or section. Furthermore, the terms “first” and “second” are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as “first” or “second” may explicitly or implicitly include at least one of that feature. In the description herein, “a plurality” means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0235] It should be understood that spatial relative terms, such as “above,” “upper,” “below,” and “lower,” are used herein to describe the relationship between one element and another shown in the figures. In addition to the orientation depicted in the figures, these spatial relative terms are also intended to encompass different orientations of the device in use or operation. For example, if the device in the figures is flipped, an element described as “above” or “upper” relative to another element would be “below” or “lower” relative to that other element. Thus, depending on the spatial orientation of the device, the term “above” encompasses both above and below orientations. Devices may have other orientations (e.g., rotated 90 degrees or in other orientations), and the spatial relative terms used herein should be interpreted accordingly.

Claims

1. A map construction method characterized by comprising: The method comprises: acquiring lane line data of a target road and driving trajectories of a vehicle on the target road; determining a road boundary line of the target road according to the lane line data and the driving trajectories; constructing a target map according to the road boundary line and the driving trajectories.

2. The method of claim 1, wherein, The driving trajectories comprise a plurality of driving trajectories, and the determining of the road boundary line of the target road according to the lane line data and the driving trajectories comprises: determining a main trajectory from the plurality of driving trajectories, the main trajectory comprising a longest trajectory in the plurality of driving trajectories; establishing a plurality of boundary line identification windows according to the main trajectory; determining the road boundary line of the target road through the plurality of boundary line identification windows according to the lane line data and the plurality of driving trajectories.

3. The method of claim 2, wherein, The establishing of the plurality of boundary line identification windows according to the main trajectory comprises: determining a plurality of continuous trajectory points on the main trajectory; for each trajectory point, establishing the boundary line identification window with the trajectory point as the center and with a direction perpendicular to a tangent of the trajectory point on the main trajectory as the length direction.

4. The method of claim 2, wherein, The lane line data comprises data of a plurality of lane lines, and the determining of the road boundary line of the target road through the plurality of boundary line identification windows according to the lane line data and the plurality of driving trajectories comprises: acquiring a driving direction of each driving trajectory; determining a lane line direction corresponding to each lane line through the plurality of boundary line identification windows according to the lane line data of the plurality of lane lines and the driving direction of each driving trajectory; determining the road boundary line through the plurality of boundary line identification windows according to the lane line data of the plurality of lane lines and the lane line direction corresponding to each lane line.

5. The method of claim 4, wherein, The determining of the road boundary line through the plurality of boundary line identification windows according to the lane line data of the plurality of lane lines and the lane line direction corresponding to each lane line comprises: for each lane line, determining a boundary type of the lane line according to the lane line direction and the lane line data of the lane line, the boundary type representing whether the corresponding lane line belongs to a lane boundary and a boundary type when belonging to the lane boundary; determining the road boundary line through the plurality of boundary line identification windows according to the boundary type corresponding to each lane line.

6. The method of claim 4, wherein, The determining of the lane line direction corresponding to each lane line through the plurality of boundary line identification windows according to the lane line data of the plurality of lane lines and the driving direction of each driving trajectory comprises: for each boundary line identification window, determining at least one first trajectory intersecting with the boundary line identification window from the plurality of driving trajectories; for each first trajectory, determining a relative direction of the first trajectory with respect to the main trajectory and a position of the first trajectory in the boundary line identification window; determining the lane line direction corresponding to each lane line according to the lane line data of the plurality of lane lines, the relative direction of each first trajectory with respect to the main trajectory, and the position of each first trajectory in the boundary line identification window.

7. The method of claim 6, wherein, The lane line data of each lane line comprises a predecessor and / or successor lane line corresponding to the lane line; The lane line data of the plurality of lane lines, the relative direction of each first trajectory to the main trajectory, and the position of each first trajectory in the boundary line identification window determine the lane line direction corresponding to each lane line, comprising: According to the relative direction of each first trajectory to the main trajectory, the position of each first trajectory in the boundary line identification window, and the predecessor and / or successor relationship of each lane line, the lane line direction corresponding to each lane line is determined.

8. The method of claim 7, wherein, The lane line data of the plurality of lane lines, the relative direction of each first trajectory to the main trajectory, and the position of each first trajectory in the boundary line identification window determine the lane line direction corresponding to each lane line, comprising: According to the relative direction of each first trajectory to the main trajectory and the position of each first trajectory in the boundary line identification window, the lane line direction of at least one lane line is determined. According to the predecessor and / or successor relationship of each lane line and the lane line direction of the at least one lane line, the direction of the lane line is propagated to determine the lane line direction corresponding to the plurality of lane lines.

9. The method of claim 8, wherein, The lane line data of the plurality of lane lines, the relative direction of each first trajectory to the main trajectory, and the position of each first trajectory in the boundary line identification window determine the lane line direction corresponding to each lane line, comprising: For each first trajectory, according to the position of the first trajectory in the boundary line identification window, the lane lines located on both sides of the first trajectory are traversed; For at least one lane line on each side, starting from the lane line closest to the first trajectory, each lane line on the current side is traversed in turn, and the lane line direction determination step is executed in a loop until the first loop termination condition of the current side is met; The lane line direction determination step comprises: For the currently traversed first lane line, the lane line direction of the first lane line is determined according to the relative direction of the first trajectory to the main trajectory; According to the lane line type of the first lane line, it is determined whether the first lane line is a road boundary line; In the case where it is determined that the first lane line is the road boundary line, it is determined that the first loop termination condition is met, and the traversal of the lane line on the current side is ended; In the case where it is determined that the first lane line is not the road boundary line, the next lane line of the first lane line on the current side is taken as the updated first lane line.

10. The method of claim 9, wherein, For the currently traversed first lane line, the lane line direction of the first lane line is determined according to the relative direction of the first trajectory to the main trajectory, comprising: In a case where the relative direction of the first trajectory and the main trajectory is the same direction, a count value of a first preset direction of the first lane line is increased by a preset update value, and in a case where the relative direction of the first trajectory and the main trajectory is the opposite direction, a count value of a second preset direction of the first lane line is increased by the preset update value; wherein the first preset direction is the same direction as the main trajectory, and the second preset direction is the opposite direction as the main trajectory; In a case where a count value of a target preset direction of the first lane line is greater than or equal to a preset count threshold, a lane line direction of the first lane line is determined as the target preset direction, and the target preset direction includes the first preset direction or the second preset direction.

11. The method of claim 8, wherein, The direction propagation of the lane line according to the predecessor-successor relationship of each lane line and the lane line direction of the at least one lane line includes: Each lane line stored in a preset lane line set is sequentially traversed, and the lane line direction propagation step is repeatedly executed until the preset lane line set is traversed completely. The lane line direction propagation step includes: The currently traversed lane line is taken as a second lane line. If the second lane line meets a preset direction propagation condition, a predecessor lane line and / or a successor lane line corresponding to the second lane line is determined according to the predecessor-successor relationship corresponding to the second lane line, and the lane line direction of the second lane line is taken as the direction of the predecessor lane line and / or the direction of the successor lane line, the next lane line of the second lane line is continuously traversed, and the next lane line is taken as an updated second lane line. If the second lane line does not meet the preset direction propagation condition, the next lane line of the second lane line is continuously traversed, and the next lane line is taken as an updated second lane line.

12. The method of claim 11, wherein, The preset direction propagation condition includes: The second lane line has determined a lane line direction, the second lane line has a corresponding predecessor lane line and / or successor lane line, and there is a lane line without a determined direction in the predecessor lane line and / or successor lane line corresponding to the second lane line.

13. The method of claim 5, wherein, For each lane line, the lane line data includes a lane line type of the lane line, and the determination of a boundary type of the lane line according to the lane line direction and the lane line data of the lane line includes: The boundary type of the lane line is determined according to the lane line direction and the lane line type of the lane line.

14. The method of claim 5, wherein, The determination of the road boundary line according to the boundary type of each lane line includes: A plurality of boundary lane lines are determined from the plurality of lane lines according to the boundary type; After the boundary lane lines with the predecessor-successor relationship are connected by re-traversing each boundary line identification window, the plurality of road boundary lines are generated.

15. The method according to any one of claims 1 to 14, characterized in that, The construction of a target map according to the road boundary line and the driving trajectory includes: The road surface information of the target road is extracted according to the road boundary line and the driving trajectory. constructing the target map according to the extracted road surface information.

16. The method of claim 15, wherein, The road boundary lines include a plurality of road boundary lines; and the road surface information extraction of the target road according to the road boundary lines and the driving trajectories includes: determining a main trajectory from the plurality of driving trajectories, the main trajectory including a longest trajectory among the plurality of driving trajectories; generating, for each of the road boundary lines, a plurality of boundary line cutting windows according to endpoints of the road boundary line and the main trajectory; extracting road surface information of the target road through the plurality of boundary line cutting windows according to boundary types of the road boundary lines and lane line directions corresponding to the road boundary lines.

17. The method of claim 16, wherein, The extracting road surface information of the target road through the plurality of boundary line cutting windows according to boundary types of the road boundary lines and lane line directions corresponding to the road boundary lines includes: for each of the plurality of boundary line cutting windows, matching each of two adjacent road boundary lines between the adjacent two boundary line cutting windows according to the boundary types of the road boundary lines and the lane line directions corresponding to the road boundary lines, and taking a road surface between the two adjacent road boundary lines satisfying a preset matching rule as a candidate road surface; extracting road surface information of the target road according to the candidate road surface between each of the adjacent two boundary line cutting windows and two boundaries of each of the candidate road surfaces.

18. The method of claim 17, wherein, The preset matching rule includes: a combination of the boundary types of the two adjacent road boundary lines is a preset type combination; positions of the two adjacent road boundary lines satisfy a preset position strategy corresponding to the lane line directions of the two adjacent road boundary lines.

19. The method of claim 17, wherein, The extracting road surface information of the target road according to the candidate road surface between each of the adjacent two boundary line cutting windows and the two boundaries of each of the candidate road surfaces includes: traversing the candidate road surface between each of the adjacent two boundary line cutting windows in sequence according to an order of the plurality of boundary line cutting windows, and performing a road surface merging step cyclically until the plurality of boundary line cutting windows are traversed; taking a to-be-merged road surface at the end of the cycle as a target road surface to be extracted; the road surface merging step includes: taking at least one candidate road surface between a preset adjacent two boundary line cutting windows as the to-be-merged road surface, taking a next adjacent two boundary line cutting window adjacent to the preset adjacent two boundary line cutting windows as a currently traversed adjacent two boundary line cutting window, and taking at least one candidate road surface between the currently traversed adjacent two boundary line cutting windows as a currently traversed road surface; for each of the to-be-merged road surfaces, determining a first road surface having two boundaries identical to two boundaries of the to-be-merged road surface from at least one of the currently traversed road surfaces, and merging the to-be-merged road surface and the first road surface to obtain an updated to-be-merged road surface; taking the next adjacent two boundary line cutting window adjacent to the currently traversed adjacent two boundary line cutting window as an updated currently traversed adjacent two boundary line cutting window.

20. The method of claim 19, wherein, The method further includes: For the non-boundary lane line on the target road surface, the direction of the target road surface is taken as the direction of the non-boundary lane line.

21. The method of claim 16, wherein, The generating, for each of the road boundary lines, of a plurality of boundary line cutting windows according to the end points of the road boundary line and the main trajectory comprises: For each of the road boundary lines, determining a projection point of each end point of the road boundary line on the main trajectory respectively; For each of the projection points, establishing the boundary line cutting window with the projection point as the center and with a direction perpendicular to a tangent of the main trajectory at the projection point as the length direction.

22. A map construction apparatus characterized by comprising: Comprising: an acquisition module configured to acquire lane line data of a target road and a driving trajectory of a vehicle on the target road; a determination module configured to determine road boundary lines of the target road according to the lane line data and the driving trajectory; a construction module configured to construct a target map according to the road boundary lines and the driving trajectory.

23. A vehicle characterized by comprising: Comprising: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to perform the steps of the method of any one of claims 1-21.

24. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program, when executed by a processor, implements the steps of the method of any one of claims 1-21.

25. A computer program product, characterised in that, The computer program, when executed by a processor, implements the steps of the method of any one of claims 1-21.

Images