A method and device for detecting and updating a lane vector off-center scenario

Abstract

The application provides a lane vector non-centralized scene detection and updating method and device, wherein the method comprises the following steps: collecting ground objects that can cause the shape of lane boundary to change, and storing the ground objects into a data set; acquiring lane boundaries located in the ground objects; updating the shape of the lane vector through the lane boundaries located in the ground objects; acquiring lane boundaries geometrically intersecting with the ground objects; and updating the shape of the lane vector through the lane boundaries geometrically intersecting with the ground objects. The application can automatically detect and identify the situation that the lane vector is not centralized, and automatically update the shape of the lane vector, solve the problem that the lane vector is not updated synchronously although the real lane boundary is updated, ensure the consistency of the geometry of the lane vector and the geometry of the lane boundary, make the updated lane vector located in the center of the lane, avoid the influence on the use of map data for automatic driving, and the detection and updating process does not need manual participation, and the data production and updating efficiency of the high-precision map is greatly improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of high-precision map data production and automatic driving, and in particular to a detection and updating method and device for a lane vector not centered scene in historical data. BACKGROUND

[0002] Automatic driving is the development trend of future travel. Automatic driving relies on artificial intelligence, visual computing, radar, monitoring devices and global positioning system to cooperate, so that the computer can automatically and safely operate the motor vehicle without any human initiative operation.

[0003] Traditional navigation map data cannot meet the needs of automatic driving applications, while high-precision map data is of great significance to automatic driving decision control, active safety and user experience improvement. In the production process of high-precision map data, the lane vector in the high-precision map is a vector layer, which is automatically generated by the program through the geometric shape of the lane boundary line and needs to be located in the center of the lane. It is a fine expression of the lane and is used to realize centimeter-level positioning, lane-level navigation, lane-level guidance and lane keeping, speed control and other contents in the automatic driving process. However, over time, there may be ground objects that cause changes in the shape of the lane boundary line. The high-precision map data production link will update the lane boundary line based on these ground objects, but the lane vector is not updated synchronously, resulting in that the lane vector in the historical data is no longer located in the center of the lane after the position of the updated lane boundary line, and cannot be directly provided to the vehicle end with automatic driving function.

[0004] The traditional method relies on manual identification and updating of the problem of lane vector not centered in historical data. In the identification and updating process, the production of high-precision map data is slow, the production and updating efficiency is low, and at the same time, it is easy to miss.

[0005] Therefore, it is urgent to overcome the defects of the prior art in the technical field. SUMMARY

[0006] The present application provides a solution to the technical problem that the traditional lane vector not centered needs to rely on manual identification and updating, resulting in slow production of high-precision map data, low production and updating efficiency and easy to miss.

[0007] In order to solve the above technical problems, the present application adopts the following technical scheme:

[0008] In a first aspect, the present application provides a lane vector not centered scene detection and updating method, comprising:

[0009] Collect ground objects that can cause changes in the shape of the lane boundary line and store the ground objects in a data set.

[0010] collecting lane boundary lines located in the ground object;

[0011] updating lane vector shape by the lane boundary lines located in the ground object;

[0012] collecting lane boundary lines geometrically intersecting with the ground object;

[0013] updating lane vector shape by the lane boundary lines geometrically intersecting with the ground object.

[0014] Preferably, the collecting lane boundary lines located in the ground object comprises:

[0015] traversing all lane boundary lines in the current data;

[0016] if each shape point of a lane boundary line falls in the shape surface of a ground object in the data set, judging the lane boundary line as a lane boundary line located in the ground object;

[0017] storing the lane boundary line located in the ground object into ld_vec1.

[0018] Preferably, the updating lane vector shape by the lane boundary lines located in the ground object comprises:

[0019] collecting lane boundary lines located in the ground object ld_vec1;

[0020] collecting lane vector lv_vec1 with ld_vec1 as left and right lane boundary lines;

[0021] traversing the lane vector lv_vec1;

[0022] collecting right contour line of the left lane boundary line and left contour line of the right lane boundary line of each lane vector lv_vec1;

[0023] generating new lane vector shape by the left and right contour lines shape through the center axis generation algorithm;

[0024] replacing the original lane vector shape with the new lane vector shape through preset conditions.

[0025] Preferably, the replacing the original lane vector shape with the new lane vector shape through preset conditions comprises:

[0026] judging whether the distance from each shape point of the new lane vector to the original lane vector shape is greater than a preset distance threshold; if yes, replacing the original lane vector shape with the new lane vector shape, if no, continuing to traverse the lane vector lv_vec1.

[0027] Preferably, the collecting lane boundary lines geometrically intersecting with the ground object comprises:

[0028] traversing all lane edges in the current data,

[0029] calculating the number of intersection points between the lane edge and each ground object in the data set, and if the number of intersection points is only one, judging that the lane edge is a lane edge geometrically intersecting with the ground object;

[0030] storing the lane edge geometrically intersecting with the ground object in ld_vec2.

[0031] Preferably, the updating of the lane vector shape through the lane edge geometrically intersecting with the ground object comprises:

[0032] obtaining the lane edge ld_vec2 geometrically intersecting with the ground object;

[0033] obtaining the lane vector lv_vec2 with ld_vec2 as the left and right lane edges;

[0034] traversing the lane vector lv_vec2;

[0035] obtaining the right profile line of the left lane edge and the left profile line of the right lane edge of each lane vector lv_vec2;

[0036] generating a new lane vector shape through the central axis using the shapes of the left and right profile lines;

[0037] replacing the original lane vector shape with the new lane vector shape through a preset condition.

[0038] Preferably, the replacing of the original lane vector shape with the new lane vector shape through the preset condition comprises:

[0039] judging whether the head and tail coordinates of the new lane vector have been updated, if yes, replacing the original lane vector shape with the new lane vector shape, and if no, continuing to traverse the lane vector lv_vec2;

[0040] judging whether the distance from each shape point of the new lane vector to the shape of the original lane vector is greater than a preset distance threshold, if yes, replacing the original lane vector shape with the new lane vector shape, and if no, continuing to traverse the lane vector lv_vec2.

[0041] Preferably, after the replacing of the original lane vector shape with the new lane vector shape, the method further comprises:

[0042] obtaining the coordinates of the original head and tail lane nodes, correcting the shape of the new lane vector, and ensuring the consistency of the original head and tail coordinates with the head and tail coordinates of the lane vectors before and after.

[0043] Preferably, the ground object comprises a guide flow belt and a cement platform.

[0044] In a second aspect, the present application provides a lane vector off-center scenario detection and updating device, comprising:

[0045] at least one processor; and

[0046] a memory in communication with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the processor to perform the lane vector off-center scenario detection and updating method according to the first aspect.

[0047] In view of the deficiencies in the prior art, the present application can achieve the following beneficial effects:

[0048] The present application can automatically detect and identify lane vector off-center scenarios and automatically update the shape of the lane vector, solving the problem of lane vector non-synchronous updating due to real-time lane edge line updating, ensuring the consistency of lane vector geometry and lane edge line geometry, and making the updated lane vector located in the center of the lane, thereby avoiding affecting the use of map data for autonomous driving.

[0049] The present application does not require manual participation in the identification and updating process of the lane vector, greatly improving the data production and updating efficiency of high-precision maps. BRIEF DESCRIPTION OF DRAWINGS

[0050] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments of the present application. Obviously, the drawings described below are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained from these drawings without creative labor.

[0051] Figure 1 is a high-precision map historical data scenario diagram;

[0052] Figure 2 is a scenario diagram of lane edge line change caused by road facility or road condition change;

[0053] Figure 3 is a scenario diagram of lane vector off-center caused by adjustment of lane edge line position;

[0054] Figure 4 is a lane vector off-center scenario detection and updating method overall flow diagram;

[0055] Figure 5 is a lane vector off-center scenario detection and updating method partial flow diagram;

[0056] Figure 6 is Figure 5Schematic diagram of application results;

[0057] Figure 7 This is a partial flowchart of a method for detecting and updating lane vectors in non-centered scenarios;

[0058] Figure 8 yes Figure 7 Schematic diagram of application results;

[0059] Figure 9 This is a schematic diagram of a device for detecting and updating lane vectors in scenarios where the lane vector is not centered. Detailed Implementation

[0060] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention. In addition, the technical features of the various embodiments or individual embodiments provided by the present invention can be arbitrarily combined with each other to form feasible technical solutions. Such combinations are not constrained by the order of steps and / or structural composition patterns, but must be based on the ability of those skilled in the art to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed by the present invention.

[0061] Example 1:

[0062] like Figure 1 The image shown is a schematic diagram of historical data scenes in a high-precision map. Historical data scenes stored in the high-precision map are processed based on historical lane lines. Where the number of lanes changes, the map data is divided into three intervals (S1, S2, S3) for storage. The lane lines and lane vectors in different intervals are disconnected in shape. However, this historical data scene is not static. Over time, changes in road facilities or conditions can cause changes in the shape of the lane lines. For example, during road construction, lane lines may be re-printed with guide strips, or new concrete platforms may be added in some scenarios. These features can cause changes in the lane lines to varying degrees. Figure 2As shown in the figure, it is a schematic diagram of the scenario that the lane boundary changes after the road facility or road condition changes, wherein the shaded part represents the ground object such as the flow guide belt or the cement platform; for the situation that the lane boundary changes, the high-precision map making platform will first adjust the position of the lane boundary based on the road shape, but the lane vector will not be updated synchronously, at this time, the lane vector is no longer located in the center of the lane, such as Figure 3 As shown in the figure, it is a schematic diagram of the scenario that the lane vector is not centered after the position of the lane boundary is adjusted, wherein the pre-adjusted lane boundary includes three segments of LD1 (the starting point is M point, and the ending point is N point), LD2 (the starting point is N point, and the ending point is P point) and LD3 (the starting point is P point, and the ending point is Q point), and the lane vector includes three segments of LV1, LV2 and LV3; if the un-updated lane vector is directly used for tracking driving in the automatic driving process, the situation of line driving or collision with the cement platform may occur, which will not meet the safety requirements of automatic driving.

[0063] In order to solve the technical problems that the traditional lane vector is not centered and needs to rely on manual identification and updating, thereby leading to slow production of high-precision map data, low production and updating efficiency and easy omission, embodiment 1 provides a detection and updating method for the scenario that the lane vector is not centered, as shown in the figure, which comprises: Figure 4 As shown in the figure, it is a schematic diagram of the scenario that the lane vector is not centered after the position of the lane boundary is adjusted, wherein the pre-adjusted lane boundary includes three segments of LD1 (the starting point is M point, and the ending point is N point), LD2 (the starting point is N point, and the ending point is P point) and LD3 (the starting point is P point, and the ending point is Q point), and the lane vector includes three segments of LV1, LV2 and LV3; if the un-updated lane vector is directly used for tracking driving in the automatic driving process, the situation of line driving or collision with the cement platform may occur, which will not meet the safety requirements of automatic driving.

[0064] S10, collect the ground object that will cause the shape of the lane boundary to change, and store the ground object in a data set.

[0065] The ground object refers to the fixed object on the ground surface, including the naturally formed and artificially constructed, and generally refers to the relatively fixed object on the ground.

[0066] At present, the ground object that will cause the shape of the lane boundary to change in the data production process mainly includes the ground object such as the flow guide belt and the cement platform, but is not limited to the cement platform and the flow guide belt; in this embodiment, the collection of the ground object that will cause the shape of the lane boundary to change particularly refers to the collection of the flow guide belt and the cement platform; in the actual implementation process, the data set specifically corresponds to the data set obj_vec.

[0067] S20, acquire the lane boundary located in the ground object.

[0068] In the specific implementation, the collection of the lane boundary located in the ground object comprises:

[0069] S21, traverse all the lane boundaries in the current data.

[0070] S22, if each shape point of a lane boundary falls in the shape surface of a ground object in the data set, it is judged that the lane boundary is the lane boundary located in the ground object.

[0071] Each shape point of the lane edge line falls within the shape surface of a certain feature in the dataset, meaning the lane edge line is entirely surrounded by the shape surface of the feature, and the lane edge line has no intersection with the shape surface of the feature (e.g., Figure 3 The lane edge line shown is LD2). At this time, it is determined that the lane edge line is located within the ground feature.

[0072] S23, store the lane edge lines located within the ground features into ld_vec1.

[0073] Here, ld_vec1 is the set of all lane edges located within the ground features.

[0074] S30 updates the lane vector shape using lane edge lines located within ground features.

[0075] like Figure 5 The diagram shown is a partial flowchart of a method for detecting and updating lane vectors in a non-centered scenario. The step of updating the lane vector shape using lane edge lines located within ground features includes:

[0076] Get the lane edge line ld_vec1 located within the ground features.

[0077] Get the lane vector lv_vec1 with ld_vec1 as the left and right lane edges.

[0078] Here, lv_vec1 is a set of lane vectors with ld_vec1 as the left and right lane edges.

[0079] Iterate through the lane vector lv_vec1.

[0080] Obtain the right contour line of the left lane edge and the left contour line of the right lane edge for each lane vector lv_vec1.

[0081] The shape of the new lane vector is obtained by using the shape of the left and right contour lines through the centerline generation algorithm.

[0082] After the shapes of the left and right contour lines are determined, the new lane vector shape can be obtained through the central axis generation algorithm, and the new lane vector shape is always located at the center of the left and right contour line shapes.

[0083] By using preset conditions, the original lane vector shape is replaced with a new lane vector shape.

[0084] In the implementation process, the step of replacing the original lane vector shape with a new lane vector shape based on preset conditions specifically includes:

[0085] determining whether the distance from each shape point of the new lane vector to the original lane vector shape is greater than a preset distance threshold; if yes, replacing the original lane vector shape with the new lane vector shape, and if no, continuing to traverse the lane vector lv_vec1, wherein the distance from each shape point of the new lane vector to the original lane vector shape is ΔD1, and in combination with the actual application, preferably, the preset distance threshold is 0.2 m, that is, only when the distance ΔD1 from each shape point of the new lane vector to the original lane vector shape is greater than 0.2 m, the system determines that the deviation of each shape point of the new lane vector from the original lane vector shape is large enough to affect the vehicle in automatic driving, at this time, the original lane vector shape is replaced with the new lane vector shape.

[0086] As shown in FIG. 8, which is an application result schematic diagram of the method, for the application scenario of the lane edge line (such as LD2) located in the ground feature, the corresponding lane vector (such as LV2) can be detected and updated. Figure 6 Figure 5 As shown in FIG. 8, which is an application result schematic diagram of the method, for the application scenario of the lane edge line (such as LD2) located in the ground feature, the corresponding lane vector (such as LV2) can be detected and updated.

[0087] S40, acquiring the lane edge line geometrically intersecting the ground feature.

[0088] In the specific implementation, the collecting of the lane edge line geometrically intersecting the ground feature includes:

[0089] S41, traversing all the lane edge lines in the current data.

[0090] S42, calculating the number of intersection points of the lane edge line and each ground feature in the data set, and if the number of intersection points is only one, determining that the lane edge line is the lane edge line geometrically intersecting the ground feature.

[0091] In this step, by limiting the number of intersection points, the lane edge line (such as LD2) located in the ground feature can be excluded, and the lane edge line (such as LD1 and LD3) geometrically intersecting the ground feature can be obtained.

[0092] S43, storing the lane edge line geometrically intersecting the ground feature in ld_vec2.

[0093] ld_vec2 is a set of lane edge lines geometrically intersecting the ground feature.

[0094] S50, updating the lane vector shape through the lane edge line geometrically intersecting the ground feature.

[0095] As shown in FIG. 8, which is an application result schematic diagram of the method, for the application scenario of the lane edge line (such as LD2) located in the ground feature, the corresponding lane vector (such as LV2) can be detected and updated. Figure 7 The updating of the lane vector shape through the lane edge line geometrically intersecting the ground feature includes:

[0096] Acquiring the lane edge line ld_vec2 geometrically intersecting the ground feature.​

[0097] Obtain a lane vector lv_vec2 with ld_vec2 as the left and right lane boundaries.

[0098] Wherein, lv_vec2 is a set of lane vectors with ld_vec2 as the left and right lane boundaries.

[0099] Iterate through the lane vector lv_vec2.

[0100] Obtain the right profile line of the left lane boundary and the left profile line of the right lane boundary of each lane vector lv_vec2.

[0101] Use the left and right profile line shapes to generate a new lane vector shape through the center axis algorithm.

[0102] Similarly, after the left and right profile line shapes are determined, a new lane vector shape can be obtained through the center axis generation algorithm, and the new lane vector shape is always located at the center position of the left and right profile line shapes.

[0103] Replace the original lane vector shape with the new lane vector shape through a preset condition.

[0104] In the implementation process, the replacement of the original lane vector shape with the new lane vector shape through a preset condition specifically includes:

[0105] Determine whether the head and tail coordinates of the new lane vector have been updated, if yes, replace the original lane vector shape with the new lane vector shape, if not, continue to iterate through the lane vector lv_vec2; in one implementation, it can be further determined whether the head and tail point coordinates of the new lane vector are close to those of the original lane vector, for example, when the distance between the head and tail point coordinates of the new lane vector and those of the original lane vector is less than 0.5 m, the next step of determination is continued to be executed, otherwise, the lane vector lv_vec2 is continued to be iterated.

[0106] Determine whether the distance from each shape point of the new lane vector to the shape of the original lane vector is greater than a preset distance threshold; if yes, replace the original lane vector shape with the new lane vector shape, if not, continue to iterate through the lane vector lv_vec2, wherein the distance from each shape point of the new lane vector to the shape of the original lane vector is △D2, and in combination with the actual application, the preset distance threshold is preferably 0.2 m, that is, only when the distance △D2 from each shape point of the new lane vector to the shape of the original lane vector is greater than 0.2 m, the system determines that the deviation of each shape point of the new lane vector from the shape of the original lane vector is large enough to affect the vehicle for automatic driving, at this time, the original lane vector shape is replaced with the new lane vector shape.

[0107] As shown in Figure 8 , it is Figure 7The application results diagram shows that, for the application scenario of lane edges (such as LD1 and LD3) that intersect with ground features, the corresponding lane vectors (such as LV1 and LV3) can be detected and updated.

[0108] As one implementation method, in order to optimize the shape of the new lane vector, in the two application scenarios mentioned above, after replacing the original lane vector shape with the new lane vector shape, the method further includes:

[0109] Obtain the coordinates of the first and last nodes of the original lane vector, correct the shape of the new lane vector, and ensure the consistency between the coordinates of the first and last nodes of the original lane vector and the coordinates of the first and last nodes of the new lane vector.

[0110] This embodiment 1 provides a method for detecting and updating lane vector non-centered scenarios. It can automatically detect and identify lane vector non-centered situations. In different application scenarios, it automatically updates the non-centered lane vectors in historical data to the centered state in a segmented manner. After the update is completed, it can also ensure that the coordinates of the first and last nodes of the updated lane vector are highly consistent with the coordinates of the first and last nodes of the original lane vector.

[0111] Example 2:

[0112] Based on the same overall technical solution as in Embodiment 1, such as Figure 9 The diagram shown is a schematic of a detection and update device for a lane vector non-centering scenario provided in Embodiment 2, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the processor to perform the detection and update method for a lane vector non-centering scenario as described in Embodiment 1.

[0113] In summary, this invention provides a method and apparatus for detecting and updating lane vector misalignment scenarios. It can automatically detect and identify lane vector misalignment and automatically update the shape of the lane vector. This solves the problem that the lane vector is not updated synchronously when the lane edge line is updated, ensuring the consistency between the lane vector geometry and the lane edge line geometry. The detection and updating process does not require manual intervention, greatly improving the efficiency of high-precision map data production and updating.

[0114] It should be noted that the descriptions of each embodiment in the above embodiments have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0115] Those skilled in the art will appreciate that embodiments of the present application can be devised for a method, a system, an electronic device, or a computer software program product. Accordingly, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application can take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage devices, and the like) embodying computer readable program code.

[0116] The present application is described in reference to the flowchart and / or block diagrams of methods, systems, electronic devices, or computer software program products according to embodiments of the present application. It will be understood that each block of the flowchart and / or block diagrams, and combinations of blocks in the flowchart and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks.

[0117] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the function specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks.

[0118] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks.

[0119] While preferred embodiments of the application have been described, those skilled in the art will appreciate that additional modifications and variations can be made to the embodiments without departing from the inventive concepts. Accordingly, the appended claims are intended to cover all such modifications and variations as falling within the scope of the present application.

Claims

1. A method for detecting and updating lane vector misalignment scenarios, characterized in that, The method comprises the following steps: Collecting ground objects that cause lane boundary shape changes and storing the ground objects in a data set; The ground object is located at a road lane number change and exists in different intervals of map data segmentation; Obtaining lane boundary lines in the ground object; Updating lane vector shapes by using the lane boundary lines in the ground object; Obtaining lane boundary lines geometrically intersecting the ground object; Updating lane vector shapes by using the lane boundary lines geometrically intersecting the ground object; The step of obtaining lane boundary lines in the ground object comprises the following steps: Traversing all lane boundary lines in current data; If each shape point of a lane boundary line falls in the shape surface of a ground object in the data set, the lane boundary line is determined as a lane boundary line in the ground object; Storing the lane boundary line in the ground object in ld_vec1; The step of updating lane vector shapes by using the lane boundary lines in the ground object comprises the following steps: Obtaining lane boundary lines ld_vec1 in the ground object; Obtaining lane vectors lv_vec1 with ld_vec1 as left and right lane boundary lines; Traversing the lane vectors lv_vec1; Obtaining right profile lines of left lane boundary lines and left profile lines of right lane boundary lines of each lane vector lv_vec1; Generating new lane vector shapes by using the left and right profile line shapes through a center axis generation algorithm; Replacing original lane vector shapes with the new lane vector shapes through a first preset condition; The step of obtaining lane boundary lines geometrically intersecting the ground object comprises the following steps: Traversing all lane boundary lines in current data, Calculating the number of intersection points of lane boundary lines and each ground object in the data set, and if the number of intersection points is only one, the lane boundary line is determined as a lane boundary line geometrically intersecting the ground object; Storing the lane boundary line geometrically intersecting the ground object in ld_vec2; The step of updating lane vector shapes by using the lane boundary lines geometrically intersecting the ground object comprises the following steps: Obtaining lane boundary lines ld_vec2 geometrically intersecting the ground object; Obtaining lane vectors lv_vec2 with ld_vec2 as left and right lane boundary lines; Traversing the lane vectors lv_vec2; Obtaining right profile lines of left lane boundary lines and left profile lines of right lane boundary lines of each lane vector lv_vec2; Generating new lane vector shapes by using the left and right profile line shapes through a center axis generation algorithm; Replacing original lane vector shapes with the new lane vector shapes through a second preset condition.

2. The method of claim 1, wherein, The step of replacing original lane vector shapes with the new lane vector shapes through the first preset condition specifically comprises the following steps: Determining whether each shape point of the new lane vector to the original lane vector shape is greater than a preset distance threshold; if yes, the new lane vector shape is used to replace the original lane vector shape, and if no, the lane vector lv_vec1 is continuously traversed.

3. The method of claim 1, wherein, The step of replacing original lane vector shapes with the new lane vector shapes through the second preset condition specifically comprises the following steps: Determining whether the first and last coordinates of the new lane vector have been updated; if yes, the new lane vector shape is used to replace the original lane vector shape, and if no, the lane vector lv_vec2 is continuously traversed. If it is judged that the new lane vector first and last coordinates have been updated, and when the distance between the new lane vector and the original lane vector first and last point coordinates is less than 0.5m, it is judged whether the distance between each shape point of the new lane vector and the original lane vector shape is greater than a preset distance threshold; if yes, the original lane vector shape is replaced with the new lane vector shape, and if no, the lane vector lv_vec2 is continuously traversed.

4. The method of claim 2 or 3, wherein, After the original lane vector shape is replaced with the new lane vector shape, the method further comprises: Coordinates of the original first and last lane nodes are acquired, the shape of the new lane vector is corrected, and consistency of the original first and last coordinates and the first and last coordinates of the lane vector before and after is ensured.

5. The method of claim 1, wherein, The ground features include a diversion belt and a cement platform.

6. A device for detecting and updating lane vector misalignment scenarios, characterized in that, Comprise: At least one processor; And The memory is in communication connection with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the processor executes the instructions to execute the lane vector non-centering scene detection and updating method according to any one of claims 1-5.

Images