A prompt layer generation method and device, a vehicle and an electronic device

Abstract

Embodiments of the present application disclose a prompt layer generation method and device, a vehicle and electronic equipment. The method comprises the following steps: obtaining multi-source map element change data; determining a change type and a change element set corresponding to each change type according to the multi-source map element change data; generating a polygon layer corresponding to the multi-source map element change data according to the change type; and controlling the polygon layer to be displayed on a navigation map, wherein the information of the polygon layer comprises a position and a boundary of the polygon layer, the polygon layer is used to prompt that there is a map element change in front of the vehicle, and the multi-source map element change data is determined based on original map data and / or vehicle perception data. Thus, the embodiments combine multi-source change data and change types to generate a corresponding polygon layer for driving risk prompt, thereby improving the accuracy and warning effect of the polygon layer generation, and further improving the driving safety of the vehicle.

Description

Technical Field

[0001] This invention relates to the field of transportation technology, and more specifically, to a method, apparatus, vehicle, and electronic device for generating prompt layers. Background Technology

[0002] During transportation, changes to map elements can significantly impact vehicle safety. Current high-precision maps may perform poorly in real-world scenarios involving such changes, potentially even leading to accidents. Therefore, effectively providing alerts for map element changes is a pressing issue that needs to be addressed. Summary of the Invention

[0003] In view of this, embodiments of the present invention provide a method, apparatus, vehicle, and electronic device for generating a warning layer, which generates a corresponding polygonal layer for driving risk warning by combining multi-source change data and change type, thereby improving the accuracy and warning effect of polygonal layer generation and thus improving vehicle driving safety.

[0004] In a first aspect, embodiments of the present invention provide a method for generating a prompt layer, the method comprising:

[0005] Acquire multi-source map element change data, which is determined based on original map data and / or vehicle perception data, including road element perception data and traffic light perception data.

[0006] Based on the multi-source map element change data, determine the change type and the set of changed elements corresponding to the change type. The change type includes linear element changes and traffic light changes.

[0007] Based on the change type, a polygon layer corresponding to the multi-source map element change data is generated, and the information of the polygon layer includes the position and boundary of the polygon layer;

[0008] Control the display of the polygon layer on the navigation map, the polygon layer is used to indicate changes in map elements ahead.

[0009] Secondly, embodiments of the present invention provide a vehicle, the vehicle comprising:

[0010] The navigation control system is configured to determine a polygon layer according to the method described above, and update the navigation route according to the polygon layer;

[0011] The driving control system is configured to drive according to the updated navigation route;

[0012] The display device is configured to display a navigation map, which includes a polygon layer in the current driving direction and change information corresponding to the polygon layer.

[0013] Thirdly, embodiments of the present invention provide a prompt layer generation device, the device comprising:

[0014] The data acquisition unit is configured to acquire multi-source map element change data, which is determined based on original map data and / or vehicle perception data, and the vehicle perception data includes road element perception data and traffic light perception data.

[0015] The processing unit is configured to determine a change type and a set of changed elements corresponding to the change type based on the multi-source map element change data, wherein the change type includes linear element changes and traffic light changes;

[0016] The generation unit is configured to generate a polygon layer corresponding to the change data of the multi-source map elements according to the change type, wherein the information of the polygon layer includes the position and boundary of the polygon layer.

[0017] The control unit is configured to control the display of the polygon layer on the navigation map, the polygon layer being used to indicate changes in map elements ahead of the vehicle.

[0018] Fourthly, embodiments of the present invention provide an electronic device, including a memory and a processor, wherein the memory is used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method described above.

[0019] Fifthly, embodiments of the present invention provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method described above.

[0020] Sixthly, embodiments of the present invention provide a computer program product that, when run on a computer, causes the computer to perform the method described above.

[0021] This invention, through acquiring multi-source map element change data, determines the change type and the corresponding set of changed elements for each change type based on the multi-source map element change data, generates a polygon layer corresponding to the multi-source map element change data based on the change type, and controls the display of the polygon layer on the navigation map. The information of the polygon layer includes its position and boundaries. The polygon layer is used to indicate changes in map elements ahead. The multi-source map element change data is determined based on original map data and / or vehicle perception data. The vehicle perception data includes road element perception data and traffic light perception data, and the change type includes linear element changes and traffic light changes. Therefore, this embodiment, by combining multi-source change data and change types to generate corresponding polygon layers for driving risk warnings, improves the accuracy and warning effect of polygon layer generation, thereby enhancing vehicle driving safety. Attached Figure Description

[0022] The above and other objects, features and advantages of the present invention will become clearer from the following description of embodiments of the invention with reference to the accompanying drawings, in which:

[0023] Figure 1 This is a flowchart of the prompt layer generation method according to an embodiment of the present invention;

[0024] Figure 2 This is a flowchart of a preprocessing method for changing the linear element type according to an embodiment of the present invention;

[0025] Figure 3 This is a flowchart of a method for generating a polygon layer by linearly changing elements according to an embodiment of the present invention;

[0026] Figures 4-5 This is a schematic diagram of a map layer according to an embodiment of the present invention;

[0027] Figure 6 This is a flowchart of a target point set determination method according to an embodiment of the present invention;

[0028] Figure 7 This is a schematic diagram of a target point set determination process according to an embodiment of the present invention;

[0029] Figure 8 This is a flowchart of a method for generating polygons based on a target point set according to an embodiment of the present invention;

[0030] Figure 9 This is a flowchart of the concave hull generation method according to an embodiment of the present invention;

[0031] Figure 10 This is a flowchart of a method for generating a polygon layer by changing traffic light elements according to an embodiment of the present invention;

[0032] Figure 11This is a flowchart of the method for determining the line element corresponding to the traffic light change element according to an embodiment of the present invention;

[0033] Figure 12 This is a flowchart of another target point set determination method according to an embodiment of the present invention;

[0034] Figure 13 This is a schematic diagram of the prompt layer generation process according to an embodiment of the present invention;

[0035] Figure 14 This is a schematic diagram of the vehicle structure according to an embodiment of the present invention;

[0036] Figure 15 This is a schematic diagram of the prompt layer generation device according to an embodiment of the present invention;

[0037] Figure 16 This is a schematic diagram of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0038] The present application is described below based on embodiments, but it is not limited to these embodiments. In the detailed description of the present application below, certain specific details are described in detail. Those skilled in the art can fully understand the present application without these details. To avoid obscuring the substance of the present application, well-known methods, processes, flows, elements, and circuits are not described in detail.

[0039] Furthermore, those skilled in the art should understand that the accompanying drawings provided herein are for illustrative purposes only and are not necessarily drawn to scale.

[0040] Unless the context explicitly requires it, words such as "including" or "contains" throughout the application should be interpreted as including rather than exclusive or exhaustive; that is, meaning "including but not limited to".

[0041] In the description of this application, it should be understood that the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance. Furthermore, in the description of this application, unless otherwise stated, "a plurality of" means two or more.

[0042] The solutions described in this specification and embodiments, if involving the processing of personal information, will be processed only under the premise of having a legal basis (such as obtaining the consent of the personal information subject, or being necessary for the performance of a contract), and will only be processed within the scope stipulated or agreed upon. A user's refusal to process personal information beyond what is necessary for basic functions will not affect the user's use of basic functions.

[0043] Currently, handling road change scenarios is technically challenging, especially in autonomous vehicle scenarios, posing significant safety and compliance risks. Therefore, when element-level map real-time updates cannot quickly meet requirements, fallback measures are needed for element change scenarios to avoid safety and compliance issues. To address this technical problem, this invention provides a method, apparatus, vehicle, and electronic device for generating warning layers. By combining multi-source change data and change types, corresponding polygon layers for driving risk warnings are generated, improving the accuracy and warning effect of polygon layer generation, thereby enhancing vehicle driving safety.

[0044] Figure 1 This is a flowchart of the prompt layer generation method according to an embodiment of the present invention. Figure 1 As shown, the prompt layer generation method of this invention includes the following steps:

[0045] Step S110: Obtain multi-source map element change data. This multi-source map element change data is determined based on the original map data and / or vehicle perception data, including road element perception data and traffic light perception data.

[0046] Furthermore, this embodiment obtains multi-source map element change data by receiving road change information and traffic light change information. The road change information includes hard boundary change information and trunk element change information.

[0047] This embodiment can acquire element change information from the original high-precision map and element change information determined by differences in elements detected within the same location area based on vehicle perception data and the original high-precision map. Therefore, this embodiment can combine element change information obtained from multiple sources to generate a more accurate prompt layer, thereby guiding subsequent navigation and improving vehicle driving safety.

[0048] Furthermore, the element change information of each source in this embodiment can be detected and determined based on the corresponding element change detection model. For example, the element change detection model uses an image processing network to detect differences in road area images from different periods in the same area to determine whether any elements have changed. As another example, the element change detection model can also detect the distribution map of vehicle historical trajectories (e.g., trajectory heatmaps) to determine whether road elements have changed. For example, if a previously existing trajectory no longer exists, it can indicate that the road segment containing the corresponding trajectory has changed from passable to impassable.

[0049] Furthermore, the change detection model can detect differences between elements in the vehicle's real-time perception data and the original high-precision map during vehicle operation, thereby determining element change information. For example, during vehicle operation, the vehicle acquires perception data within a predetermined range around it through its onboard sensors (such as cameras, radar, etc.). The change detection model can identify element information in this perception data through an element recognition module and compare it with element information within the same range in the original high-precision map to determine whether element changes have occurred in that area.

[0050] It should be understood that this embodiment does not limit the structure of the element change detection model or the element change detection method it adopts; it can be determined using existing or future element change detection models.

[0051] This embodiment obtains element change information from various sources to acquire multi-source map element change data within the required area, thereby generating a prompt layer corresponding to the vehicle's path to guide subsequent navigation and improve vehicle driving safety.

[0052] Step S120: Determine the change type and the set of changed elements corresponding to each change type based on the multi-source map element change data. The change types include linear element changes and traffic light changes.

[0053] In this embodiment, linear element changes include hard boundary changes and backbone element changes. Hard boundaries (HB) can include fixed objects without zone attributes such as medians, fences, pedestrian walkways, construction zone boundaries, posts, and stone spheres, as well as boundaries that define a specific area, such as roundabouts. Backbone elements can include linear elements on the road such as lane lines, lanes, stop lines, intersection waiting areas, and zebra crossings.

[0054] Furthermore, the elements undergoing modification have corresponding modification attributes. For example, the modification attributes of hard-boundary elements can include addition, deletion, and boundary changes. Boundary changes can include shifting, shape changes, and other types of changes that widen or narrow the drivable area. The modification attributes of traffic light elements can include addition, shifting, deletion, operating status, and light attributes. Operating status can include normal and faulty states, and light attributes can characterize attributes such as traffic light type, for example, round light or arrow light. The main elements include interval elements, lane markings, and lanes. The modification attributes of interval elements can include addition, removal, position shifting, and shape changes. The modification attributes of lane markings can include line attributes (e.g., solid lines, dashed lines), position, quantity changes, and direction changes. The modification attributes of lanes can include lane attributes (e.g., motor vehicle lanes, non-motor vehicle lanes), changes in ground arrows, and changes in lane mobility time.

[0055] In this embodiment, at least one changed element is determined from the acquired multi-source map element change data, and a set of changed elements corresponding to each change type is determined according to the change type of each changed element. For example, if the acquired multi-source map element change data includes hard boundary element hb1, hard boundary element hb2, and traffic light element TL1, then the set of changed elements includes the set {hb1, hb2} corresponding to the hard boundary change type and {TL1} corresponding to the traffic light change type.

[0056] Step S130: Generate a polygon layer corresponding to the multi-source map element change data according to the change type. The information of the polygon layer includes its location and boundaries. A polygon is a polygon used on a map to mark areas of concern. This embodiment uses a polygon layer to mark areas corresponding to element changes that can affect vehicle driving, thereby guiding subsequent driving routes and improving driving safety and compliance.

[0057] In one optional implementation, this embodiment generates a corresponding polygon layer based on each changed element in the acquired set of changed elements for each change type. In another optional implementation, since the impact of some element changes on vehicle driving is limited, generating corresponding polygon layers for all changed elements might interfere with vehicle driving. Therefore, this embodiment can also filter each set of changed elements based on corresponding filtering conditions to obtain changed elements that have a significant impact on vehicle driving, and generate corresponding polygon layers based on these changed elements. This reduces information interference and lowers computational resources while ensuring driving safety and compliance.

[0058] Furthermore, in this embodiment, the sets of change elements of different change types are preprocessed according to the corresponding preprocessing methods to obtain at least one target change element of the corresponding change type, and a corresponding polygon layer is generated based on each target change element.

[0059] Optionally, for linear element change types, this embodiment filters each change element in the corresponding change element set based on at least one of the following: confidence level, linear change attribute, location, and vehicle recognition area, to obtain at least one target change element. The confidence level of the change element is the confidence level when the corresponding element change detection model outputs the corresponding change element. The linear change attribute is determined based on the corresponding change element type. For example, the change attributes of the lane lines mentioned above can include addition, deletion, position movement, shape change, etc. Specific examples can be found in the descriptions of the change attributes of various change elements, which will not be listed here. Furthermore, this embodiment can provide a polygonal prompt layer in the navigation map during vehicle operation to improve driving safety. Therefore, this embodiment can only determine change elements within a predetermined range around the vehicle for timely and effective reminders. Therefore, this embodiment can also filter change elements by determining whether the location of the change element is within the vehicle recognition area. Furthermore, the vehicle recognition area can be limited based on a first distance in front of the vehicle and a second distance behind the vehicle. It should be understood that this embodiment does not limit the specific values ​​of the first distance and the second distance. They can be preset according to the actual application scenario, or dynamically adjusted according to the actual application scenario (such as vehicle type, speed limit of the road where the vehicle is located, or real-time speed of the vehicle) and predetermined dynamic adjustment rules.

[0060] Figure 2 This is a flowchart of a preprocessing method for changing the linear element type according to an embodiment of the present invention. Further, as... Figure 2 As shown, the preprocessing method for changing the linear element type in this embodiment includes the following steps:

[0061] Step S210: Obtain the change element. In this embodiment, the change element is obtained from the set of change elements of the corresponding type.

[0062] Step S220: Determine whether the confidence level of the changed element is greater than the first threshold. The confidence level of the changed element is the confidence level when the corresponding element change detection model outputs the changed element. It should be understood that this embodiment does not limit the specific value of the first threshold; it can be set according to specific application scenarios to ensure driving safety. If the confidence level of the changed element is greater than the first threshold, proceed to step S230; if the confidence level of the changed element is not greater than the first threshold, proceed to step S260.

[0063] Step S230: Determine whether the changed element is within the vehicle recognition area. That is, if the confidence level of the changed element is greater than a first threshold, further determine whether the changed element is within the vehicle recognition area. As described above, the vehicle recognition area in this embodiment can be limited based on a first distance in front of the vehicle and a second distance behind the vehicle. Based on whether the position of the changed element is within the vehicle recognition area corresponding to the vehicle's position, if the changed element is within the vehicle recognition area, proceed to step S240; if the changed element is outside the vehicle recognition area, proceed to step S260. In an optional implementation, the changed element being within the vehicle recognition area can mean that at least a portion of the changed element is located within the vehicle recognition area.

[0064] Step S240: Determine whether the change attribute of the changed element meets the conditions. If the confidence level of the changed element is greater than the first threshold and it is within the vehicle recognition area, further determine whether the change attribute of the changed element meets the conditions. Meeting the conditions for the change attribute means that the change attribute of the changed element is among the pre-set necessary change attribute types for generating a polygon layer. It should be understood that this embodiment does not limit the necessary change attribute types; they can be determined based on the degree of influence of each type of changed element on vehicle driving, and will not be illustrated here. Further, if the confidence level of the changed element is greater than the first threshold, its position is within the vehicle recognition area, and its change attribute meets the conditions, then proceed to step S250; otherwise, proceed to step S260.

[0065] Step S250: The changed element is determined as the target changed element. That is, in this embodiment, the changed element with a confidence level greater than the first threshold, located within the vehicle recognition area, and whose changed attributes meet the conditions is determined as the target changed element.

[0066] Step S260: Filter out the changed element. That is, if the changed element does not meet any of the above conditions, it is filtered out.

[0067] Figure 2 The preprocessing process shown is based on the sequential execution of confidence threshold judgment, location judgment, and change attribute judgment. It should be understood that this embodiment does not limit the execution order of each judgment condition. It can be judged in any order or in parallel, and the final judgment result is used to determine whether to filter out the change element.

[0068] Furthermore, this embodiment takes the judgment of the above three conditions as an example. It should be understood that this embodiment does not limit the number of condition judgments. It can also use one or more of the above three conditions in combination, or it can use other filtering conditions to change the filtering of elements based on the actual application scenario. No further examples will be given here.

[0069] Optionally, for traffic light change types, this embodiment filters each change element in the change element set based on the confidence level and / or traffic light change attributes of each change element in the corresponding change element set to obtain at least one target change element.

[0070] Furthermore, since the change in the function of traffic lights from good to bad has a relatively small impact on vehicle movement, a corresponding polygon layer does not need to be generated for traffic light elements with this type of change. Similarly, since temporary lights may have a short operating cycle, no special processing is required for them in this embodiment.

[0071] Furthermore, for traffic lights with changed light attributes, this embodiment can determine whether to take appropriate action based on the confidence level of the changed element. The light attribute can characterize attributes such as traffic light type, for example, round light, arrow light, etc. Optionally, if the confidence level of the changed light attribute is high, vehicles can drive based on real-time traffic light perception data, and its impact on vehicle driving safety is relatively limited. However, for changes in light attributes with low confidence levels (e.g., below the second threshold), due to their inherent uncertainty, this embodiment needs to provide a notification for such changed elements to ensure driving safety.

[0072] It should be understood that the above-mentioned filtering conditions for traffic light change types are merely exemplary. In practical applications, the corresponding filtering conditions can be adjusted according to specific circumstances, and this embodiment does not impose any limitations.

[0073] Furthermore, this embodiment generates a polygon layer based on the acquired changed elements or the target changed elements obtained through filtering. It should be understood that the only difference between the two is the number of changed elements used; their specific execution processes are similar. The following describes in detail the process of generating a polygon layer using the target changed elements determined after filtering.

[0074] Figure 3 This is a flowchart of a method for generating a polygon layer by linearly changing elements according to an embodiment of the present invention. Figures 4-5 This is a schematic diagram of a map layer according to an embodiment of the present invention. Figure 3 As shown, if the target change element is a linear change element, the method for generating a polygon layer from a linear change element in this embodiment includes the following steps:

[0075] Step S310: Obtain the target change element.

[0076] Step S320: Query whether a historical layer matches the target changed element. Optionally, if the historical layer includes the target changed element, or if the distance between the target changed element and the historical layer is less than a preset distance threshold, then the target changed element is determined to match a historical layer. If a historical layer matches the target changed element, proceed to step S330; otherwise, proceed to step S340.

[0077] like Figure 4 As shown, assume the target change element is hb. The map contains a polygon polygon1 corresponding to the historical layer, and the range of polygon1 includes element hb. That is, the historical layer includes the target change element hb, thus confirming that the target change element hb matches the historical layer polygon1.

[0078] Furthermore, such as Figure 5 As shown, assume the target change element is hb. There exists a polygon polygon2 corresponding to the historical layer in the map. The target change element hb is very close to polygon2, less than a preset distance threshold, and is therefore considered a match between the target change element hb and the historical layer polygon1.

[0079] Step S330: In response to the existence of a matching historical layer for the target changed element, the target changed element is added to the element set corresponding to the historical layer, generating a new element set. That is, assuming the element set corresponding to the polygon of the historical layer is cluster1, the target changed element is added to cluster1, and the new element set is the updated element set cluster1.

[0080] In step S340, in response to the absence of a matching historical layer for the target changed element, a new element set is generated based on the target changed element. That is, if no matching historical layer exists for the target changed element, a new element set is created, and the target changed element is added to this new element set.

[0081] In one optional implementation, if the target change element is a hard boundary element change, this embodiment obtains at least one new element set by clustering at least one target change element. Further, this embodiment obtains at least one new element set by clustering based on the distance between line elements in each target change element. Further optionally, if the target change element is a backbone element, then all target elements are added to the same element set.

[0082] Step S350: Generate the corresponding polygon layer based on the new element set.

[0083] In this embodiment, when there is a historical layer that matches the target change element, a new polygon layer is generated based on the polygons corresponding to the newly generated target change element and the historical layer. This avoids the interference problem caused by too much overlap of polygon layers with similar positions and optimizes the polygon layer generation process.

[0084] Alternatively, this embodiment can use a disjoint-set data structure algorithm to merge and update the new target change elements into the polygons corresponding to their matching historical layers, thereby generating a new polygon layer. In another optional implementation, this embodiment regenerates the corresponding polygon layer based on the line elements within the updated new element set, to further improve the accuracy of the polygon layer.

[0085] Since a linear element is a line with no width, in order to make the construction of a polygon convenient and efficient, this embodiment discretizes the line (polyline) corresponding to the linear element to form multiple points, and then constructs a polygon based on these points.

[0086] Figure 6 This is a flowchart of a target point set determination method according to an embodiment of the present invention. Figure 7 This is a schematic diagram illustrating a target point set determination process according to an embodiment of the present invention. In another optional implementation, to further reduce computational overhead, this embodiment performs a downsampling operation on the lines corresponding to each linear element to obtain the corresponding point set, and then constructs a polygon based on these points. Figure 6 As shown, the target point set determination method in this embodiment includes the following steps:

[0087] Step S410: Perform downsampling operation on the line elements in the new element set to obtain the point set corresponding to each line element.

[0088] Further optionally, this embodiment performs equally spaced sampling on the lines corresponding to each linear element. For example, it adds points at a specific distance to the left or right along the normal direction of each point on each line, while deleting some duplicate points or other points that would cause the polygon to be non-compliant, in order to generate a point set corresponding to each linear element. Figure 7 As shown, a linear element L1 is sampled at equal intervals to obtain multiple sampling points p1-p6. Taking sampling points p2 and p3 as examples, normal lines are drawn at sampling points p2 and p3, and points are added at specific distances to the left or right along the direction of the normal lines. Figure 7 As shown, the newly added points in the intermediate region formed by the normals drawn at sampling points p2 and p3 have some duplicate points. This embodiment deletes these duplicate points to avoid non-compliant issues with polygons subsequently created based on these points. It should be understood that... Figure 7The method of obtaining the point set corresponding to the linear element shown is merely exemplary. This embodiment does not limit the sampling method of points on the line or the method of obtaining new points in the area surrounding the line. It is sufficient that the area covered by the points can express the range of areas affected by the change of the linear element. Examples will not be given here.

[0089] Step S420: Merge the point sets of each line element to obtain the target point set. That is, in this embodiment, the point sets corresponding to each line element in the newly obtained element set are merged to form a large point set, which is the target point set.

[0090] Step S430: Construct the polygon layer based on the target point set.

[0091] Figure 8 This is a flowchart of a method for generating polygons based on a target point set according to an embodiment of the present invention. Figure 8 As shown, the method for generating polygons based on a target point set according to an embodiment of the present invention includes the following steps:

[0092] Step S510: Construct the outer convex hull based on the target point set. Optionally, this embodiment can construct the outer convex hull based on the Graham Scan Algorithm. The Graham Scan Algorithm is a convex hull calculation algorithm based on polar angle sorting, used to find the convex hull of a point set on a two-dimensional plane. Given a set of points on a two-dimensional plane, it finds the convex hull formed by these points, that is, the smallest convex polygon enclosing the point set. It should be understood that this embodiment does not limit the algorithm for constructing the outer convex hull; other existing convex hull calculation methods (e.g., Jarvis step method, Andrew algorithm, etc.) or convex hull calculation methods developed in the future can also be used, which will not be described in detail here.

[0093] Step S520: Generate a concave hull based on the outer convex hull and points within it. In this embodiment, to further generate a polygon that conforms to the original obstacle (i.e., the impassable area caused by element changes), this embodiment can generate a concave hull based on the outer convex hull and points within it, and further determine the polygon layer based on this concave hull. In other optional implementations, it should be understood that directly determining the polygon layer based on the convex hull is also within the scope of protection of this invention.

[0094] In one alternative implementation, this embodiment can use a pre-set concave hull calculation method or a concave hull generator configured with a concave hull calculation method to generate a concave hull based on the outer convex hull and the points in the outer convex hull.

[0095] Figure 9This is a flowchart of a concave hull generation method according to an embodiment of the present invention. Further, the concave hull generation method of this embodiment includes the following steps:

[0096] Step S610: Determine the current edge. In this embodiment, the current edge can be determined based on the boundary of the convex hull, or it can be determined based on the boundaries of the already generated concave hull and convex hull. This embodiment does not limit this to either.

[0097] Step S620: Determine whether the current edge is a short edge. The length of a short edge is less than a first predetermined value. If the current edge is not a short edge, proceed to step S630. If the current edge is a short edge, either identify it as the edge of the concave hull or discard the current edge, and proceed to step S610 to redetermine the current edge.

[0098] Step S630: When the current edge is not a short edge, find valid interior points of the current edge based on the points within the convex hull. Valid interior points must satisfy the following conditions: a) They are located inside the current edge. b) They are not close to either end of the current edge. c) The lines connecting interior points do not intersect other edges. d) The lines connecting interior points do not create unnecessary intersections or knots with the lines connecting other points.

[0099] Step S640: Sort the internal points based on the distance between the internal points and the current edge.

[0100] Step S650: Select at least one point based on the sorted sequence of internal points, and determine whether the at least one point satisfies the corresponding matching condition. The matching condition may specifically be: whether the line formed by the at least one point has at least one of the following characteristics: continuity, directional consistency, geometric rationality, and topological correctness. If the at least one point does not satisfy the corresponding matching condition, these points can be discarded, other points can be queried for further judgment, or the current edge can be redefined. If the at least one point satisfies the corresponding matching condition, proceed to step S660.

[0101] Step S660: Determine whether the line formed by at least one selected point is a long edge. If not, add the next point to the internal point sorting sequence and execute steps S650-S660 until the line formed by the selected point is a long edge, or the points in the internal point sorting sequence have been traversed. If the points in the internal point sorting sequence have been traversed but a long edge still cannot be formed, the generated edge can be determined as a concave hull edge or these points can be discarded, and the current edge can be re-determined. If the selected point satisfies the matching condition and the line formed is a long edge, execute step S670. The length of the long edge is greater than a second predetermined value.

[0102] Step S670: Determine whether the depth of the obtained long edge meets the conditions. The depth of the long edge characterizes the degree of concavity of the corresponding long edge, which in this embodiment can be determined based on the distance between the relevant internal points of the long edge and the long edge itself. If the depth of the obtained long edge meets the conditions, then the long edge is used as the boundary of the concave hull, and the current edge is redefined. If the depth of the obtained long edge does not meet the conditions, proceed to step S680.

[0103] Step S680: Determine whether the acquired long edge has a closer neighboring edge. If the acquired long edge has a closer neighboring edge, then use the acquired long edge as the boundary of the concave hull or discard the long edge, and redetermine the current edge. If the acquired long edge has no closer neighboring edge, proceed to step S690.

[0104] In step S690, if the obtained long edge has no closer neighboring edge, use it as the boundary of the concave hull and insert a new edge to determine the current edge.

[0105] In summary, repeat steps S610-S690 until the hull is closed to obtain a polygon that better matches the area affected by the changed element.

[0106] It should be understood that Figure 9 The concave hull generation method shown is merely exemplary. This embodiment does not limit the concave hull calculation method used, as long as it can generate the corresponding concave hull based on the convex hull and the points in the convex hull.

[0107] Step S530: Generate the corresponding polygon layer based on the hull.

[0108] In one alternative implementation, an initial layer is generated based on the hull, and it is determined whether there is a historical layer that is less than a predetermined distance from the initial layer. In response to the existence of a historical layer that is less than a predetermined distance from the initial layer, the initial layer and the historical layer are merged to generate a polygonal layer. In response to the absence of a historical layer that is less than a predetermined distance from the initial layer, the initial layer is determined as the polygonal layer.

[0109] Furthermore, in this embodiment, an initial polygon (i.e., an initial layer) is determined based on the boundary of the humm. If the initial polygon is close to or overlaps with other historical polygons (e.g., layers), the initial polygon and historical polygons can be merged based on the boundary to generate the polygon layer of this embodiment. Thus, this embodiment avoids the complexity of multiple prompt layers within the same area and subsequent navigation guidance. Furthermore, if there are no historical polygons within a predetermined range around the initial polygon, then the initial polygon is determined as the polygon layer of this embodiment.

[0110] Figure 10This is a flowchart illustrating a method for generating a polygon layer from traffic light changing elements according to an embodiment of the present invention. Further, if the target changing element is a traffic light changing element... Figure 10 As shown, the method for generating a polygon layer from traffic light change elements in this embodiment includes the following steps:

[0111] Step S710: Obtain the lane and stop line information corresponding to the traffic light change element. The lanes corresponding to the traffic light change element include all lanes affected by that traffic light.

[0112] Step S720: Using the stop line as the endpoint line, determine the starting line along the lane edge line according to a preset distance. The preset distance can be set according to specific application scenarios; this embodiment does not limit the specific value.

[0113] Step S730: Generate corresponding polygon layers based on the starting line, the ending line, and the lane edges.

[0114] Figure 11 This is a flowchart of a method for determining the line element corresponding to a traffic light modification element according to an embodiment of the present invention. Figure 11 As shown, assuming the traffic light change element is LG0, and its corresponding stop line is Ls, the starting line Le is determined by using the stop line Ls as the endpoint and the lane edge line Lb along a preset distance. This embodiment can generate a corresponding polygon layer based on the endpoint line Ls, the starting line Le, and the lane edge line Lb.

[0115] Figure 12 This is a flowchart of another target point set determination method according to an embodiment of the present invention. Figure 12 As shown, if the target change element is a traffic light change element, the method for determining the corresponding target point set includes the following steps:

[0116] Step S810 involves downsampling the starting line, ending line, and lane edges to obtain the point sets corresponding to the starting line, ending line, and lane edges. The method for determining the point sets corresponding to the lines in this embodiment is similar to... Figure 7 The method shown is similar and will not be described in detail here. However, similarly, the point sets corresponding to the starting line, ending line, and lane edge lines in this embodiment can also be obtained by sampling in other ways, as long as the points in the relevant area are obtained.

[0117] Step S820: Merge the point sets to obtain the target point set.

[0118] Step S830: Construct the polygon layer based on the target point set.

[0119] It should be understood that the method of constructing the polygon layer based on the target point set in this embodiment is the same as that described above. Figure 8 and Figure 9The embodiments shown are similar and will not be described again here.

[0120] Step S140: Display a polygon layer on the navigation map. This polygon layer is used to indicate changes in map elements ahead.

[0121] Furthermore, in this embodiment, if the vehicle detects an element change in the road segment ahead during driving, it generates and sends a corresponding polygon layer, and determines the subsequent navigation route based on the type of element change and the polygon layer, such as controlling the vehicle to detour and avoid the polygon layer, so as to ensure driving safety and compliance.

[0122] Figure 13 This is a schematic diagram illustrating the prompt layer generation process according to an embodiment of the present invention. For example... Figure 13 As shown, in this embodiment, after obtaining multi-source map element change data, the data is processed through a map element change information understanding node to obtain change information that meets the conditions. Change information that can form the same polygon layer is identified as a change element group. Based on this change element group, corresponding polygon information, the change elements corresponding to the polygon information, and the group confidence level corresponding to the change element group are formed. It should be understood that the polygon information formation process in this embodiment is similar to that in the above embodiments and will not be described in detail here.

[0123] This invention, through acquiring multi-source map element change data, determines the change type and the corresponding set of changed elements for each change type based on the multi-source map element change data, generates a polygon layer corresponding to the multi-source map element change data based on the change type, and controls the display of the polygon layer on the navigation map. The information of the polygon layer includes its position and boundaries. The polygon layer is used to indicate changes in map elements ahead. The multi-source map element change data is determined based on original map data and / or vehicle perception data. The vehicle perception data includes road element perception data and traffic light perception data, and the change type includes linear element changes and traffic light changes. Therefore, this embodiment, by combining multi-source change data and change types to generate corresponding polygon layers for driving risk warnings, improves the accuracy and warning effect of polygon layer generation, thereby enhancing vehicle driving safety.

[0124] Figure 14 This is a structural schematic diagram of a vehicle according to an embodiment of the present invention. Figure 14As shown, the vehicle 14 in this embodiment of the invention includes a navigation control system 141, a driving control system 142, and a display device 143. The navigation control system is configured to determine a polygon layer using any of the above implementation methods and update the navigation route based on the polygon layer. The driving control system 142 is configured to drive according to the updated navigation route. The display device 143 is configured to display a navigation map, which includes a polygon layer in the current driving direction and corresponding change information for the polygon layer.

[0125] In this embodiment of the invention, the vehicle navigation control system acquires multi-source map element change data, determines the change type and the corresponding set of changed elements based on the multi-source map element change data, generates a polygon layer corresponding to the multi-source map element change data based on the change type, and controls the display of the polygon layer on the navigation map. The information of the polygon layer includes its position and boundaries. The polygon layer is used to indicate changes in map elements ahead. The multi-source map element change data is determined based on original map data and / or vehicle perception data. The vehicle perception data includes road element perception data and traffic light perception data, and the change type includes linear element changes and traffic light changes. Therefore, this embodiment improves the accuracy and warning effect of polygon layer generation by combining multi-source change data and change types to generate corresponding polygon layers for driving risk warnings, thereby improving vehicle driving safety.

[0126] Figure 15 This is a schematic diagram of the prompt layer generation device according to an embodiment of the present invention. Figure 15 As shown, the prompt layer generation device 15 of this embodiment includes a data acquisition unit 151, a processing unit 152, a generation unit 153, and a control unit 154.

[0127] Data acquisition unit 151 is configured to acquire multi-source map element change data, which is determined based on original map data and / or vehicle perception data, including road element perception data and traffic light perception data. Processing unit 152 is configured to determine a change type and a set of changed elements corresponding to that change type based on the multi-source map element change data, where the change type includes linear element changes and traffic light changes. Generation unit 153 is configured to generate a polygon layer corresponding to the multi-source map element change data based on the change type, where the information of the polygon layer includes its position and boundaries. Control unit 154 is configured to control the display of the polygon layer on the navigation map, where the polygon layer is used to indicate that there are map element changes ahead.

[0128] In this embodiment of the invention, the vehicle navigation control system acquires multi-source map element change data, determines the change type and the corresponding set of changed elements based on the multi-source map element change data, generates a polygon layer corresponding to the multi-source map element change data based on the change type, and controls the display of the polygon layer on the navigation map. The information of the polygon layer includes its position and boundaries. The polygon layer is used to indicate changes in map elements ahead. The multi-source map element change data is determined based on original map data and / or vehicle perception data. The vehicle perception data includes road element perception data and traffic light perception data, and the change type includes linear element changes and traffic light changes. Therefore, this embodiment improves the accuracy and warning effect of polygon layer generation by combining multi-source change data and change types to generate corresponding polygon layers for driving risk warnings, thereby improving vehicle driving safety.

[0129] Figure 16 This is a schematic diagram of an electronic device according to an embodiment of the present invention. (For example...) Figure 16 As shown, electronic device 160 is a general-purpose data processing device, which includes a general-purpose computer hardware structure, including at least a processor 161 and a memory 162. The processor 161 and memory 162 are connected via a bus 163. The memory 162 is adapted to store instructions or programs executable by the processor 161. The processor 161 can be a standalone microprocessor or a collection of one or more microprocessors. Thus, the processor 161 executes the instructions stored in the memory 162 to perform the method flow of the embodiments of the present invention as described above, thereby realizing data processing and control of other devices. The bus 163 connects the aforementioned components together, and also connects the aforementioned components to a display controller 164, a display device, and an input / output (I / O) device 165. The input / output (I / O) device 165 can be a mouse, keyboard, modem, network interface, touch input device, motion-sensing input device, printer, and other devices known in the art. Typically, the input / output device 165 is connected to the system via an input / output (I / O) controller 166.

[0130] Those skilled in the art will understand that embodiments of this application can be provided as methods, apparatus (devices), or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0131] This application is described with reference to flowchart illustrations of methods, apparatus (devices), and computer program products according to embodiments of this application. It should be understood that each step in the flowchart can be implemented by computer program instructions.

[0132] These computer program instructions may be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including an instruction means, the implementation process of which is described in the instruction means. Figure 1 The function specified in one or more processes.

[0133] These computer program instructions may also be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing device, produce instructions for implementing processes. Figure 1 A device for a function specified in one or more processes.

[0134] Another embodiment of the present invention relates to a non-volatile storage medium for storing a computer-readable program for use by a computer to execute some or all of the above-described method embodiments.

[0135] That is, those skilled in the art will understand that all or part of the steps in the methods of the above embodiments can be implemented by a program specifying the relevant hardware. This program is stored in a storage medium and includes several instructions to cause a device (which may be a microcontroller, chip, etc.) or processor to execute all or part of the steps of the methods described in the embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0136] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for generating a prompt layer, characterized in that, The method includes: Acquire multi-source map element change data, which is determined based on original map data and / or vehicle perception data, including road element perception data and traffic light perception data. Based on the multi-source map element change data, determine the change type and the set of changed elements corresponding to the change type. The change type includes linear element changes and traffic light changes. Based on the change type, a polygon layer corresponding to the multi-source map element change data is generated, and the information of the polygon layer includes the position and boundary of the polygon layer; Control the display of the polygon layer on the navigation map, the polygon layer is used to indicate changes in map elements ahead.

2. The method according to claim 1, characterized in that, The acquisition of multi-source map element change data includes: Receive road change information and traffic light change information to obtain the multi-source map element change data. The road change information includes hard boundary change information and main element change information, and the linear element change includes hard boundary change and main element change.

3. The method according to claim 1, characterized in that, The step of generating the polygon layer corresponding to the multi-source map element change data based on the change type includes: Preprocess the sets of change elements of different change types according to the corresponding preprocessing methods to obtain at least one target change element of the corresponding change type; The polygon layer is generated based on each of the target change elements.

4. The method according to claim 3, characterized in that, The step of preprocessing the sets of change elements of different change types according to the corresponding preprocessing methods to obtain at least one target change element of the corresponding change type includes: In response to the change type being a linear element change, each change element in the change element set is filtered based on at least one of the confidence level, linear change attribute, location, and vehicle recognition region of each change element in the corresponding change element set to obtain the at least one target change element.

5. The method according to claim 3, characterized in that, The target change element is a linear change element, and generating the polygon layer based on each target change element includes: In response to the existence of a matching historical layer for the target changed element, the target changed element is added to the element set corresponding to the historical layer, generating a new element set; In response to the absence of a matching historical layer for the target changed element, a new element set is generated based on the target changed element; The corresponding polygon layer is generated based on the new set of elements.

6. The method according to claim 5, characterized in that, The step of generating a new element set based on the target changed element includes: Clustering is performed based on the distance between line elements in the target change elements to obtain at least one new set of elements.

7. The method according to claim 5, characterized in that, The step of generating the corresponding polygon layer based on the new element set includes: A downsampling operation is performed on the line elements in the new element set to obtain the point set corresponding to each line element; Merge the point sets of each line element to obtain the target point set; The polygon layer is constructed based on the target point set.

8. The method according to claim 3, characterized in that, The step of preprocessing the sets of change elements of different change types according to the corresponding preprocessing methods to obtain at least one target change element of the corresponding change type includes: In response to the change type being traffic light change, each change element in the change element set is filtered based on the confidence level and / or traffic light change attribute of each change element in the corresponding change element set to obtain at least one target change element.

9. The method according to claim 3, characterized in that, The target change element is a traffic light change element, and generating the polygon layer based on each target change element includes: Obtain the lane and stop line information corresponding to the traffic light change element; Using the stop line as the endpoint line, the starting line is determined along the edge line of the lane according to a preset distance; The corresponding polygon layer is generated based on the starting line, the ending line, and the edge lines of the lane.

10. The method according to claim 9, characterized in that, The step of generating the corresponding polygon layer based on the starting line, the ending line, and the lane edge lines includes: Downsampling is performed on the starting line, the ending line, and the edge lines of the lanes to obtain the point sets corresponding to the starting line, the ending line, and the edge lines of the lanes; Merge the various point sets to obtain the target point set; The polygon layer is constructed based on the target point set.

11. The method according to claim 7 or 10, characterized in that, The step of constructing the polygon layer based on the target point set includes: Construct the outer convex hull based on the target point set; A concave hull is generated based on the outer convex hull and the points in the outer convex hull; The corresponding polygon layer is generated based on the indentation.

12. The method according to claim 11, characterized in that, The step of generating the corresponding polygon layer based on the indentation includes: An initial layer is generated based on the indentation. In response to the existence of a historical layer that is less than a predetermined distance from the initial layer, the initial layer and the historical layer are merged to generate the polygon layer; In response to the absence of a historical layer whose distance from the initial layer is less than a predetermined distance, the initial layer is determined to be the polygonal layer.

13. A vehicle, characterized in that, The vehicles include: A navigation control system is configured to determine a polygon layer according to the method of any one of claims 1-12, and update a navigation route based on the polygon layer; The driving control system is configured to drive according to the updated navigation route; The display device is configured to display a navigation map, which includes a polygon layer in the current driving direction and change information corresponding to the polygon layer.

14. A prompt layer generation device, characterized in that, The device includes: The data acquisition unit is configured to acquire multi-source map element change data, which is determined based on original map data and / or vehicle perception data, including road element perception data and traffic light perception data. The processing unit is configured to determine a change type and a set of changed elements corresponding to the change type based on the multi-source map element change data, wherein the change type includes linear element changes and traffic light changes; The generation unit is configured to generate a polygon layer corresponding to the change data of the multi-source map elements according to the change type, wherein the information of the polygon layer includes the position and boundary of the polygon layer. The control unit is configured to control the display of the polygon layer on the navigation map, the polygon layer being used to indicate changes in map elements ahead of the vehicle.

15. An electronic device comprising a memory and a processor, characterized in that, The memory is used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method as described in any one of claims 1-12.

16. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method as described in any one of claims 1-12.

17. A computer program product, characterized in that, When the computer program product is run on a computer, it causes the computer to perform the method as described in any one of claims 1-12.

Images