Lane information determination, lane encoding data determination method and device, medium and vehicle

Abstract

This disclosure relates to a method, apparatus, medium, and vehicle for determining lane information and lane coding data. The lane information determination method includes: acquiring the vehicle's position and lane coding data; determining the vehicle's projection vector point from multiple vector points based on the vehicle's position; matching the index information of the projection vector point with index information in a first mapping relationship to determine the index information of other target vector points from the first mapping relationship; matching the index information of the projection vector point and the index information of the other target vector points with index information in a second mapping relationship to determine first lane information corresponding to the projection vector point and second lane information corresponding to the other target vector points; and determining the vehicle's target lane information based on the first lane information and the second lane information. This disclosure can improve the speed and efficiency of determining the vehicle's lane information.

Description

Technical Field

[0001] This disclosure relates to the field of intelligent driving technology, specifically to a method, device, medium, and vehicle for determining lane information and lane coding data. Background Technology

[0002] In intelligent driving scenarios, it is often necessary to determine the vehicle's lane information. Related technologies require complex calculations using lane-coded data to determine this lane information, resulting in slow determination speed and low efficiency. Furthermore, the encoding methods for lane-coded data in these technologies are complex. Summary of the Invention

[0003] To achieve the above objectives, this disclosure provides a method, apparatus, medium, and vehicle for determining lane information and lane coding data.

[0004] Firstly, this disclosure provides a method for determining lane information, including: The vehicle's location and lane coding data are obtained. The lane coding data includes a first mapping relationship between the index information of each vector point and the index information of other vector points, and a second mapping relationship between the index information of each vector point and the lane information corresponding to the vector point. The multiple vector points include at least the vector points on the lane lines in the road where the vehicle is located, and the other vector points include vector points that have a topological relationship with the vector points among the multiple vector points. The projection vector point of the vehicle is determined from the plurality of vector points based on the vehicle position. The projection vector point includes the vector point of the vehicle in a preset projection direction. The index information of the projected vector points is matched with the index information in the first mapping relationship to determine the index information of other target vector points from the first mapping relationship; Based on the index information of the projected vector point and the index information of other target vector points, the index information in the second mapping relationship is matched to determine the first lane information corresponding to the projected vector point and the second lane information corresponding to the other target vector points; The target lane information of the vehicle is determined based on the first lane information and the second lane information.

[0005] Optionally, the lane coding data further includes a third mapping relationship between the index information of each vector point and the vector point's heading angle and position, wherein the index information includes at least the vector point's spatial index in the spatial index coordinate system, and the method further includes: Obtain the vehicle heading angle; Determining the projected vector point of the vehicle from the plurality of vector points based on the vehicle's position includes: Determine the vehicle position spatial index in the spatial index coordinate system; The vehicle position spatial index is matched with the vector point spatial index included in the index information in the third mapping relationship to determine candidate vector points from the plurality of vector points, and the candidate vector point heading angle and candidate vector point position are determined from the third mapping relationship. The projected vector point of the vehicle is determined from the candidate vector points based on the vehicle heading angle, the candidate vector point heading angle, the vehicle position, and the candidate vector point position.

[0006] Optionally, determining the vehicle's projected vector point from the candidate vector points based on the vehicle's heading angle, the candidate vector point's heading angle, the vehicle's position, and the candidate vector point's position includes: Determine the angle difference between the vehicle's heading angle and the candidate vector point's heading angle; The candidate vector point corresponding to the heading angle of the candidate vector point whose angle difference satisfies the preset condition is determined as the first target candidate vector point; The position of the first target candidate vector point is determined from the positions of the candidate vector points; The projection vector point is determined from the first target candidate vector point based on the position of the first target candidate vector point and the position of the vehicle.

[0007] Optionally, the preset projection direction is to the left of the vehicle position; determining the projection vector point from the first target candidate vector points based on the first target candidate vector point position and the vehicle position includes: The position of the first target candidate vector point is compared with the position of the vehicle, and the position of the second target candidate vector point located to the left of the vehicle position is determined from the position of the first target candidate vector point. The first target candidate vector point corresponding to the position of the second target candidate vector point is determined as the projection vector point.

[0008] Optionally, the step of matching the vehicle location spatial index with the vector point spatial index included in the index information of the third mapping relationship to determine candidate vector points from the plurality of vector points includes: In the spatial index coordinate system, determine the adjacent spatial index that is adjacent to the vehicle position spatial index; The candidate vector point is determined from the plurality of vector points by matching the adjacent spatial index with the vector point spatial index in the third mapping relationship.

[0009] Optionally, the topological relationship includes at least one of a preorder relationship, a postorder relationship, a parent relationship, and a child relationship. The preorder relationship reflects that the other vector points are located on the same lane line as the vector point and that the other vector points are ahead of the vector point. The postorder relationship reflects that the other vector points are located on the same lane line as the vector point and that the other vector points are behind the vector point. The parent relationship reflects that the lane line of the other vector points is located to the left of the lane line of the vector point. The child relationship reflects that the lane line of the other vector points is located to the right of the lane line of the vector point.

[0010] Secondly, this disclosure provides a method for determining lane coding data, including: Acquire map data, the map data including roads, the roads including lane lines; Multiple vector points are determined based on the lane lines; Determine the index information of each of the plurality of vector points; Construct a first mapping relationship between the index information of each vector point and the index information of the other vector points, wherein the other vector points include vector points that have a topological relationship with the vector points among the plurality of vector points; Construct a second mapping relationship between the index information of each vector point and the lane information corresponding to the vector point; Lane coding data is determined based at least on the first mapping relationship and the second mapping relationship.

[0011] Thirdly, this disclosure provides a lane information determination device, including: The first acquisition module is configured to acquire the vehicle position and lane coding data of the vehicle. The lane coding data includes a first mapping relationship between the index information of each vector point and the index information of other vector points, and a second mapping relationship between the index information of each vector point and the lane information corresponding to the vector point. The multiple vector points include at least the vector points on the lane lines in the road where the vehicle is located, and the other vector points include vector points that have a topological relationship with the vector points among the multiple vector points. The first determining module is configured to determine the projection vector point of the vehicle from the plurality of vector points based on the vehicle position, wherein the projection vector point includes the vector point of the vehicle in a preset projection direction; The first matching module is configured to match the index information of the projected vector point and the index information of other target vector points with the index information in the second mapping relationship to determine the first lane information corresponding to the projected vector point and the second lane information corresponding to other target vector points. The second determining module is configured to determine the target lane information of the vehicle based on the first lane information and the second lane information.

[0012] Fourthly, this disclosure provides a computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the steps of the method described in any of the first aspects.

[0013] Fifthly, this disclosure provides a vehicle including the lane information determination device described in the third aspect.

[0014] Through the above technical solution, lane coding data is pre-constructed. This lane coding data includes a first mapping relationship between the index information of each vector point and the index information of other vector points, and a second mapping relationship between the index information of each vector point and the lane information corresponding to that vector point. Therefore, the target other vector points matched through the first mapping relationship are vector points that have a topological relationship with the projected vector point of the vehicle. Since the projection direction of the projected vector point and the topological relationship between the target other vector points and the projected vector point are known, the target lane information of the vehicle can be determined based on the first lane information corresponding to the projected vector point and the second lane information corresponding to the target other vector points. This disclosure determines the first lane information corresponding to the projected vector point and the second lane information corresponding to the target other vector points by matching the first and second mapping relationships in the lane coding data, thereby quickly determining the first and second lane information and improving the speed and efficiency of determining the target lane information. In addition, the lane coding data of this disclosure encodes the topological relationship between vector points, making the encoding method simpler and more efficient.

[0015] Other features and advantages of this disclosure will be described in detail in the following detailed description section. Attached Figure Description

[0016] The accompanying drawings are provided to further illustrate the present disclosure and form part of the specification. They are used together with the following detailed description to explain the present disclosure, but do not constitute a limitation thereof. In the drawings: Figure 1 It is lane coding data in the related art as illustrated in an exemplary embodiment.

[0017] Figure 2 This is a schematic diagram of a lane and lane lines according to an exemplary embodiment.

[0018] Figure 3 This is a flowchart illustrating a lane information determination method according to an exemplary embodiment.

[0019] Figure 4 This is a schematic diagram illustrating a road, lanes, and lane lines according to an exemplary embodiment.

[0020] Figure 5 It is field data of a first mapping relationship as illustrated in an exemplary embodiment.

[0021] Figure 6 It is field data of a second mapping relationship as illustrated in an exemplary embodiment.

[0022] Figure 7 This is a schematic diagram illustrating a road, lanes, and lane lines according to an exemplary embodiment.

[0023] Figure 8 This is a flowchart illustrating the determination of the projection vector points of a vehicle according to an exemplary embodiment.

[0024] Figure 9 This is a flowchart illustrating the determination of candidate vector points according to an exemplary embodiment.

[0025] Figure 10 This is a flowchart illustrating the determination of projection vector points according to an exemplary embodiment.

[0026] Figure 11 This is a flowchart illustrating a method for determining lane coding data according to an exemplary embodiment.

[0027] Figure 12 This is a block diagram illustrating a lane information determination device according to an exemplary embodiment.

[0028] Figure 13 This is a block diagram illustrating a vehicle according to an exemplary embodiment. Detailed Implementation

[0029] The specific embodiments of this disclosure will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit this disclosure.

[0030] In applications of intelligent driving systems, such as scenarios using high-precision map data, end-to-end online vector map construction, or line-following, it is necessary to describe or encode each lane on the road. This data is then broadcast to higher-level applications, such as decision-making and planning modules, through map engines and other related modules.

[0031] In related technologies, the following two technical solutions can be used to perform lane coding and obtain lane coding data: 1) Polynomial curve coding method; 2) Lane coding using the geometric point sequence of lane centerline and lane boundary.

[0032] However, technical solution 1) requires sampling to generate a reference line using an absolute starting position and an independent variable, and then generating a sequence of lane boundary shape points and a sequence of lane centerline shape points based on the reference line. This solution has the following drawbacks: 1) It requires sampling based on the starting position, which necessitates a global coordinate system conversion due to the vehicle's use of a vehicle coordinate system, and polynomial sampling results in accuracy loss; 2) It requires sampling the lane boundary curvature based on the lane centerline, leading to high computational complexity, and the calculation of lane boundaries based on the centerline results in point intersection issues.

[0033] Technical solution 2) requires a sequence of coordinate points to represent the lane centerline, which has the following drawbacks: 1) It requires calculating the curvature and resampling according to its own needs; 2) It has the same drawback as technical solution 1) above, namely the problem of intersection of sequence points.

[0034] Furthermore, the data parsing and sampling methods of the aforementioned technical solutions 1) and 2) are complex, resulting in a very complex encoding method for lane coding data and low encoding efficiency.

[0035] For example, see Figure 1 , Figure 1 It is lane coding data in the related art as illustrated in an exemplary embodiment.

[0036] like Figure 1 As shown, lane coding data includes the number of lanes, lane data, number of lane lines, lane lines, number of coordinates, and coordinates (x, y). The number of lanes represents the total number of lanes; lane data represents each lane within that number of lanes; the number of lane lines represents the number of lane lines within a lane; lane lines represent each lane line within that number of lane lines; the number of coordinates represents the number of coordinates within each lane line; and the coordinates (x, y) represent the coordinate values ​​of the coordinates. Furthermore, lane coding data represents lane lines using a coordinate sequence of (x, y) coordinates. For example, according to the road lane direction, lane lines are represented by a coordinate sequence from front to back.

[0037] Combination Figure 1 The lane coding data shown can be found in [reference]. Figure 2 Assuming the position of vehicle CC is represented by the black triangle, the direction of travel of vehicle CC is as indicated by the arrow, lanes include lane1 and lane2, and lane lines include lines 1-5, then the relevant technology can determine the vehicle's lane in the following way: According to the map engine broadcast Figure 1The lane coding data is used to retrieve the coordinates of all lane lines. Distances to the vehicle's current position are calculated, or the position perpendicular to the vehicle's direction of travel is calculated, and projection point sampling is performed. The vehicle position with the shortest distance to the current position on each lane line is then calculated as the projection point of the vehicle's position on that lane.

[0038] For example, taking lane line 3 as an example, calculate the distances between vehicle CC and all coordinate points in line 3, such as the distance between vehicle CC and coordinate point C1, the distance between vehicle CC and coordinate point C2, and the distance between vehicle CC and coordinate point C. The distance between vehicle CC and coordinate point C is the shortest, so coordinate point C is the projection point of vehicle CC on line 3. Similarly, the projection point of vehicle CC on line 1 is coordinate point A, the projection point of vehicle CC on line 2 is coordinate point B, the projection point of vehicle CC on line 4 is coordinate point D, and the projection point of vehicle CC on line 5 is coordinate point E. Therefore, the calculation result of the projection point can be... Figure 2 The numbers A, B, C, D, and E are shown.

[0039] Finally, the distances between these projection points are used to further determine which lane the vehicle is in on the road.

[0040] Therefore, it can be seen that in related technologies, lane coding data can only obtain the coordinate information on the lane line. A series of complex calculations based on this coordinate information are required to determine the vehicle's lane, resulting in slow lane determination and low efficiency.

[0041] Figure 3 This is a flowchart illustrating a lane information determination method according to an exemplary embodiment, such as... Figure 3 As shown, the lane information determination method may include the following steps.

[0042] Step 310: Obtain the vehicle position and lane coding data. The lane coding data includes the index information of each vector point among multiple vector points and the first mapping relationship between the index information of other vector points, as well as the second mapping relationship between the index information of each vector point and the lane information corresponding to the vector point. The multiple vector points include at least the vector points on the lane lines in the road where the vehicle is located, and the other vector points include the vector points among the multiple vector points that have a topological relationship with the vector points.

[0043] In some embodiments, the plurality of vector points includes at least vector points on the lane lines of the road in which the vehicle is located. For example, see reference. Figure 4Assume the vehicle is currently on a road with road ID 10001, which includes lanes 1 and 2. Lanes 1 and 2 each contain lane lines 1-5. Taking lane lines 1-3 as an example, the vector points on each lane line can include... Figure 4 The point is indicated by a circle.

[0044] Understandably, multiple vector points can also include vector points on lane lines in other roads, which can be multiple roads obtained from map data, and these multiple roads may not include the road where the vehicle is located.

[0045] In a possible implementation, multiple vector points can also be determined based on the virtual lane lines in the virtual lane and the lane lines in the road where the vehicle is located. The virtual lane lines can be lane lines constructed to the left of the leftmost lane line in the road where the vehicle is located. For example, with Figure 4 For example, a virtual lane can be lane0, and a virtual lane line can be line0.

[0046] This embodiment of the disclosure determines multiple vector points by using virtual lane lines in the virtual lane and lane lines in the road where the vehicle is located, which facilitates the derivation of the topological relationship between the vector points of the lane lines. Since the virtual lane line is known to be the leftmost lane, the trajectory direction between the vector points can be calculated through the virtual lane and the virtual lane line, which facilitates resampling calculation and lane line refitting.

[0047] In one possible implementation, when there are multiple roads, lane coding data can be constructed for each road. When determining lane information, the lane coding data matching the road where the vehicle is located is obtained, and the vehicle's lane information is determined based on this lane coding data. In another possible implementation, lane coding data can be constructed for multiple roads together, and the vehicle's lane information is determined based on this lane coding data when determining lane information.

[0048] In some embodiments, the index information includes at least the spatial index of the vector point's location in a spatial index coordinate system. In a possible implementation, the spatial index coordinate system can be a coordinate system obtained by dividing the road into spatial index blocks from the origin at horizontal intervals of a first preset distance and vertical intervals of a second preset distance. The origin can be any point in a projected coordinate system or a Cartesian coordinate system. The units for the first and second preset distances can be meters.

[0049] The coordinate form of a vector point spatial index can be (row, col), where row represents the index number of the horizontal column of the spatial index coordinate system, and col represents the index number of the vertical row of the spatial index coordinate system.

[0050] For example, still using Figure 4 For example, the origin of the spatial index coordinate system is located at the top left corner. The horizontal columns of the spatial index coordinate system include index numbers 0-11, and the vertical rows include index numbers 0-8. Figure 4 Taking lane line 1 as an example, the vector point of the second vector point in lane line 1 has a spatial index of (4,4) in the spatial index coordinate system; the vector points of the third and fourth vector points in lane line 1 both have a spatial index of (5,4) in the spatial index coordinate system.

[0051] In some embodiments, the index information includes not only the vector point spatial index but also a spatial index sequence number, which is a unique sequence number assigned to each vector point. In possible implementations, the spatial index sequence number may be set based on the horizontal or vertical position of the vector point's spatial index in the spatial index coordinate system. This disclosure embodiment ensures the global uniqueness of the vector point's index information through the vector point spatial index and spatial index sequence number.

[0052] For example, the above is still the case. Figure 4 For example, the index information of the second vector point in lane line 1 is (4,4,3); the index information of the third vector point in lane line 1 is (5,4,25); and the index information of the fourth vector point in lane line 1 is (5,4,14). Therefore, the third and fourth vector points have different index information through their spatial index numbers, ensuring that the index information of the vector points is globally unique.

[0053] In some embodiments, the topological relationship includes at least one of a preceding relationship, a following relationship, a parent relationship, and a child relationship. The preceding relationship is used to reflect that other vector points are located on the same lane line as the vector point and that other vector points are in front of the vector point. The following relationship is used to reflect that other vector points are located on the same lane line as the vector point and that other vector points are behind the vector point. The parent relationship is used to reflect that the lane line of other vector points is located to the left of the lane line of the vector point. The child relationship is used to reflect that the lane line of other vector points is located to the right of the lane line of the vector point.

[0054] In some embodiments, the direction of travel can be distinguished by lane lines. For example, as described above... Figure 4For example, taking the vector point spatial index and spatial index number as an example, for the vector point (5, 4, 25) in lane line 1, the other vector points of this vector point (5, 4, 25) include vector points (5, 4, 14) and vector points (4, 4, 3), where vector point (5, 4, 14) is a vector point with a preceding order relationship to vector point (5, 4, 25), and vector point (4, 4, 3) is a vector point with a following order relationship to vector point (5, 4, 25). For the vector point (4, 5, 55) in lane line 2, the other vector points of this vector point (4, 5, 55) include vector point (5, 4, 25), where vector point (5, 4, 25) is a vector point with a parent relationship to vector point (4, 5, 55). The method for determining other vector points with child relationships is similar and will not be repeated here.

[0055] In some embodiments, each of the following vector points may be included: other vector points that have a parent relationship with a vector point, other vector points that have a preorder relationship with a vector point, and other vector points that have a suffix relationship with a vector point. Other vector points that have a child relationship with a vector point may be one or more, or the vector point may not have any other vector points that have a child relationship.

[0056] In a possible implementation, the index information of other vector points in the first mapping relationship can be stored as field data. For example, see... Figure 5 Taking other vector points with a preceding order relationship to a vector point as preceding vector points, other vector points with a following order relationship as following vector points, other vector points with a parent relationship as parent vector points, and other vector points with a child relationship as child vector points as child vector points, and assuming that the index information includes the vector point's spatial index and spatial index number, then the index information of other vector points can be... Figure 5 The field data shown is stored.

[0057] The field data can be: [(row, col, idx), (row, col, idx), (row, col, idx), count, (row, col, idx), ... Count-1 ], where row represents the index number of the horizontal column of the spatial index coordinate system, col represents the index number of the vertical row of the spatial index coordinate system, and idx represents the spatial index sequence number. The first (row, col, idx) represents the index information of the previous vector point, the second (row, col, idx) represents the index information of the next vector point, the third (row, col, idx) represents the index information of the parent vector point, count represents the number of child vector points, the fourth (row, col, idx) represents the index information of the first child vector point, and count-1 represents the index information of the second to count-1 child vector points.

[0058] In some embodiments, the index information of vector points in the first mapping relationship and the index information of other vector points can be stored together as field data. For example, still using... Figure 5 As shown, the index information of vector points can be stored before the index information of the preceding vector points.

[0059] This embodiment of the disclosure constructs a first mapping relationship by using other vector points that have a topological relationship with the vector point. The topological relationship of front and back, parent and child can quickly index from the local lane matching position to the relationship of the current position based on the entire road. This allows the vehicle's current lane and the logical relationship between the current lane and other lanes to be quickly located based on the index information of the vector point, improving the efficiency and speed of subsequent determination of the vehicle's lane information.

[0060] In some embodiments, the second mapping relationship between the index information of each vector point and the lane information corresponding to the vector point can be stored as field data. In possible implementations, the corresponding lane information includes the corresponding road, lane, and lane lines. For example, still taking the index information including the aforementioned (row, col, idx) as an example, see [link to relevant documentation]. Figure 6 The second mapping relationship can be used as Figure 6 The data is stored in the format shown, so it can be seen that the lane line, lane and road where the vector point is located can be known based on the index information of the vector point.

[0061] Figure 6 The second mapping relationship shown can achieve the following: all roads are indexed by road ID, and the current road data is represented by the number of lanes following the road ID; the current road data is indexed by the number of lanes and the lane line vector point data is indexed by the number of lane lines.

[0062] Step 320: Determine the vehicle's projection vector point from multiple vector points based on the vehicle's position. The projection vector point includes the vehicle's vector point in a preset projection direction.

[0063] The preset projection direction can be determined according to actual needs. For example, the preset projection direction could be the left side of the vehicle's position. In one possible implementation, projection sampling points can be calculated based on the vehicle's position, and the vehicle's projection vector point can be determined from multiple vector points. In another possible implementation, the vehicle's projection vector point can be determined from candidate vector points based on the vehicle's heading angle, the heading angle of candidate vector points, the vehicle's position, and the positions of candidate vector points. Specific details regarding the determination of the vehicle's projection vector point can be found below. Figure 9 The details and related descriptions will not be repeated here.

[0064] Step 330: Match the index information of the projected vector point and the index information of other target vector points with the index information in the second mapping relationship to determine the first lane information corresponding to the projected vector point and the second lane information corresponding to other target vector points.

[0065] Step 340: Determine the target lane information of the vehicle based on the first lane information and the second lane information.

[0066] In some embodiments, target lane information may be used to reflect at least one piece of information about the vehicle's lane and its sub-lanes within that lane. Sub-lanes may be artificially defined, for example, ... Figure 7 For example, assuming a left-to-right direction, the lane between line 1 and line 2 is defined as the first sub-lane in lane 1, and the lane between line 2 and line 3 is defined as the second sub-lane in lane 1.

[0067] For example, still using Figure 7For example, assuming the index information of the projected vector point is (5,4,25), the index information of other target vector points determined from the first mapping relationship includes: the index information of the rear vector point (4,4,3), the index information of the front vector point (5,4,14), and the index information of the sub-vector point (4,5,55). From the second mapping relationship, the rear vector point (4,4,3), the front vector point (5,4,14), and the sub-vector point (4,5,55) all correspond to road 10001 and lane 1. The rear vector point (4,4,3) and the front vector point (5,4,14) both correspond to lane line 1, and the sub-vector point (4,5,55) corresponds to lane line 2. Since the projection direction of the projection vector point is known, for example, taking the preset projection direction as the left direction, we can directly infer from the first lane information corresponding to the projection vector point and the second lane information corresponding to other target vector points that the lane line on the left side of the vehicle is line1, the lane line on the right side of the vehicle is line2, and the vehicle belongs to lane1. Thus, we know that the vehicle belongs to lane1 and is in the first sub-lane between line1 and line2.

[0068] This disclosure discloses lane-coded data pre-constructed, which includes a first mapping relationship between the index information of each vector point and the index information of other vector points, and a second mapping relationship between the index information of each vector point and the lane information corresponding to that vector point. Therefore, the target other vector points matched through the first mapping relationship are vector points with a topological relationship to the projected vector point of the vehicle. Since the projection direction of the projected vector point and the topological relationship between the target other vector points and the projected vector point are known, the target lane information of the vehicle can be determined based on the first lane information corresponding to the projected vector point and the second lane information corresponding to the target other vector points. This disclosure determines the first lane information corresponding to the projected vector point and the second lane information corresponding to the target other vector points by matching the first and second mapping relationships in the lane-coded data, achieving rapid determination of the first and second lane information, thereby improving the speed and efficiency of determining the target lane information. Furthermore, the lane-coded data of this disclosure encodes the topological relationships between vector points, making the encoding method simpler and more efficient.

[0069] Figure 8 This is a flowchart illustrating the determination of the projected vector points of a vehicle according to an exemplary embodiment, such as... Figure 8 As shown, the process may include the following steps.

[0070] Step 810: Determine the vehicle position spatial index in the spatial index coordinate system.

[0071] In some embodiments, prior to step 810, the method further includes acquiring the vehicle heading angle. In possible implementations, the vehicle heading angle may be acquired simultaneously with the vehicle position and lane coding data. This disclosure does not impose any restrictions on the order of data acquisition.

[0072] In some embodiments, the vehicle position spatial index can be determined based on the vehicle's location, the width of the horizontal column of the spatial index coordinate system, the height of the vertical row of the spatial index coordinate system, and the coordinates of the origin of the spatial index coordinate system. For example, assume the current vehicle's coordinates are ( The coordinates of the origin are ( If the width is m and the height is n, then the index number of the vertical row of the vehicle location spatial index is... = ( - ) / m–1, the index number of the horizontal column of the vehicle location spatial index =( - ) / n–1.

[0073] Step 820: Match the vector point spatial index included in the index information in the third mapping relationship with the vehicle position spatial index to determine candidate vector points from multiple vector points, and determine the heading angle and position of the candidate vector points from the third mapping relationship.

[0074] In some embodiments, the lane coding data further includes a third mapping relationship between the index information of each vector point and the vector point's heading angle and position. The vector point's heading angle can be the heading angle of the vector point, and the vector point's position can be the coordinates of the vector point in the projected coordinate system.

[0075] For example, the above is still the case. Figure 4 For example, Figure 4 In the diagram, H, H1, and H2 represent the heading angles of vector points (5,4,25), (4,5,55), and (4,6,31), respectively. The heading angle is defined as 0 for true north, with values ​​ranging from 0 to π on the left and from 0 to -π on the right.

[0076] In a possible implementation, the third mapping relationship can be stored in the form of metadata fields. For example, taking the vector point index information, which includes the vector point spatial index and spatial index number, as an example, the metadata field of the third mapping relationship can be (row,col,idx,x,y,hdg), where row represents the index number of the horizontal column in the vector point spatial index, col represents the index number of the vertical row in the vector point spatial index, idx represents the spatial index number, (x,y) represents the vector point position, and hdg represents the heading angle of the vector point.

[0077] The lane coding data in this embodiment includes the index information of each vector point and a third mapping relationship between the vector point's heading angle and position. The third mapping relationship provides the vector point's heading angle information, which eliminates the need to calculate the vector point's heading angle based on the preceding and following points. Furthermore, the vector point's heading angle is static information and does not require dynamic calculation, thus facilitating fast data fusion while ensuring the accuracy of the heading angle information.

[0078] Candidate vector points can include vector points around the vehicle, that is, vector points adjacent to the vehicle's position. Specific details regarding the determination of vector points adjacent to the vehicle's position can be found below. Figure 9 The details and related descriptions will not be repeated here.

[0079] Step 830: Determine the vehicle's projected vector point from the candidate vector points based on the vehicle's heading angle, the candidate vector point's heading angle, the vehicle's position, and the candidate vector point's position.

[0080] For specific details regarding step 830, please refer to the following: Figure 10 The details and related descriptions will not be repeated here.

[0081] This embodiment of the disclosure pre-constructs a third mapping relationship in the lane coding data, enabling the direct loading of candidate vector points through the vehicle location spatial index, eliminating the need for calculation and thus improving the speed of acquiring candidate vector points, and consequently, the speed of determining projected vector points. Furthermore, since it loads point data, compared to loading data on a road or road segment basis, less data is loaded, resulting in faster indexing.

[0082] Figure 9 This is a flowchart illustrating the determination of candidate vector points according to an exemplary embodiment, such as... Figure 9 As shown, the process may include the following steps.

[0083] Step 910: Determine the adjacent spatial index that is adjacent to the vehicle position spatial index in the spatial index coordinate system.

[0084] In a possible implementation, the adjacent spatial index can be obtained by increasing or decreasing at least one of the index numbers of the horizontal columns and the vertical rows in the vehicle location spatial index by a preset value. The preset value can be specifically determined according to actual needs. For example, taking a preset value of 1 and a vehicle location spatial index of (5,5), the adjacent spatial index can include: (5,4), (4,4), (4,5), (4,6), (5,6), (6,6), (6,5), and (6,4), where the adjacent spatial index is the adjacent index in the eight directions of the vehicle location spatial index.

[0085] Step 920: Match the adjacent spatial index with the vector point spatial index in the third mapping relationship to determine candidate vector points from multiple vector points.

[0086] In a possible implementation, a vector point that has the same spatial index as its neighboring vector points can be identified as a candidate vector point.

[0087] This embodiment of the disclosure determines the adjacent spatial index based on the vehicle location spatial index, and directly matches candidate vector points from the third mapping relationship based on the adjacent spatial index. The adjacent spatial index further narrows the index range and further improves the speed of obtaining candidate vector points.

[0088] Figure 10 This is a flowchart illustrating the determination of projection vector points according to an exemplary embodiment, such as... Figure 10 As shown, the process may include the following steps.

[0089] Step 1010: Determine the angle difference between the vehicle's heading angle and the candidate vector point's heading angle.

[0090] Step 1020: The candidate vector point corresponding to the heading angle of the candidate vector point whose angle difference meets the preset conditions is determined as the first target candidate vector point.

[0091] In some embodiments, the preset conditions may include the angle difference being within a preset range. The preset range can be specifically determined according to actual needs. For example, the preset range may be [-5,5] or [-10,10], etc.

[0092] In some embodiments, the first target candidate vector point may include a vector point that is the same as or close to the vehicle's direction of travel. This disclosure determines the first target candidate vector point by the angular difference between the vehicle's heading angle and the heading angle of the candidate vector point; that is, by comparing the vehicle's heading angle with the heading angle of the candidate vector point. Since the heading angle of the candidate vector point is pre-constructed data, rapid comparison can be achieved, improving the speed of determining the first target candidate vector point.

[0093] Step 1030: Determine the position of the first target candidate vector point from the candidate vector point positions.

[0094] Step 1040: Determine the projection vector point from the first target candidate vector point based on the position of the first target candidate vector point and the vehicle position.

[0095] As mentioned above, the preset projection direction can be to the left of the vehicle position. In some embodiments, determining the projection vector point from the first target candidate vector point based on the first target candidate vector point position and the vehicle position may include: comparing the first target candidate vector point position and the vehicle position, determining the position of the second target candidate vector point located to the left of the vehicle position from the first target candidate vector point position; and determining the first target candidate vector point corresponding to the position of the second target candidate vector point as the projection vector point.

[0096] In a possible implementation, if there are multiple second target candidate vector point locations, they can be sorted according to the distance between the second target candidate vector point locations and the vehicle location, and the second target candidate vector point location with the smallest distance can be selected.

[0097] This embodiment compares the position of a first target candidate vector point with the vehicle position, determines the position of a second target candidate vector point located to the left of the vehicle position from the first target candidate vector point positions, and determines the first target candidate vector point corresponding to the position of the second target candidate vector point as the projection vector point. This enables the determination of the projection vector point through coordinate comparison, further improving the speed of projection vector point determination.

[0098] Figure 11 This is a flowchart illustrating a method for determining lane coding data according to an exemplary embodiment, such as... Figure 11 As shown, the process may include the following steps.

[0099] Step 1110: Obtain map data, which includes roads, lanes included in the roads, and lane lines included in the lanes.

[0100] Step 1120: Determine multiple vector points based on the lane lines.

[0101] Step 1130: Determine the index information of each vector point among multiple vector points.

[0102] Step 1140: Construct the first mapping relationship between the index information of each vector point and the index information of other vector points, where other vector points include vector points that have a topological relationship with the vector points among multiple vector points.

[0103] Step 1150: Construct a second mapping relationship between the index information of each vector point and the lane information corresponding to the vector point.

[0104] Step 1160: Determine lane coding data based at least on the first mapping relationship and the second mapping relationship.

[0105] In possible implementations, the corresponding lane information may include the corresponding road, lane, and lane lines, wherein each of the road, lane, and lane lines may include one or more. In some embodiments, the method for determining lane coding data further includes: constructing a third mapping relationship between the index information of each vector point and the vector point's heading angle and position; determining lane coding data based at least on the first and second mapping relationships, including: determining lane coding data based on the first, second, and third mapping relationships.

[0106] For specific details regarding steps 1110-1160 above, please refer to the aforementioned method for determining lane information, which will not be repeated here.

[0107] The lane coding data of this disclosure includes a first mapping relationship between the index information of each vector point and the index information of other vector points, and a second mapping relationship between the index information of each vector point and the road, lane, and lane line corresponding to the vector point. The lane coding data of this disclosure encodes the topological relationships between vector points, resulting in a simpler and more efficient encoding method.

[0108] Furthermore, the lane coding data in this embodiment also includes a third mapping relationship between the index information of each vector point and the vector point's heading angle and position. This enables the encoding of vector point data, such as the vector point's heading angle and position, including directional angle information, making it easier to determine the vehicle's lane information. Moreover, the vector point's heading angle and position are easily obtained, making it easier to acquire lane coding data.

[0109] Figure 12 This is a block diagram illustrating a lane information determination device according to an exemplary embodiment, such as... Figure 12 As shown, the lane information determination device 1200 includes: The first acquisition module 1210 is configured to acquire the vehicle position and lane coding data of the vehicle. The lane coding data includes a first mapping relationship between the index information of each vector point and the index information of other vector points, and a second mapping relationship between the index information of each vector point and the lane information corresponding to the vector point. The multiple vector points include at least the vector points on the lane lines in the road where the vehicle is located, and the other vector points include the vector points among the multiple vector points that have a topological relationship with the vector points. The first determining module 1220 is configured to determine the projection vector point of the vehicle from the plurality of vector points based on the vehicle position, wherein the projection vector point includes the vector point of the vehicle in a preset projection direction; The first matching module 1230 is configured to match the index information of the projected vector point and the index information of other target vector points with the index information in the second mapping relationship to determine the first lane information corresponding to the projected vector point and the second lane information corresponding to other target vector points. The second determining module 1240 is configured to determine the target lane information of the vehicle based on the first lane information and the second lane information.

[0110] Optionally, the lane coding data further includes a third mapping relationship between the index information of each vector point and the vector point's heading angle and position, wherein the index information includes at least the vector point spatial index in the spatial index coordinate system, and the device further includes: The second acquisition module is configured to acquire the vehicle heading angle of the vehicle. The first determining module 1220 is further configured as follows: Determine the vehicle position spatial index in the spatial index coordinate system; The vehicle position spatial index is matched with the vector point spatial index included in the index information in the third mapping relationship to determine candidate vector points from the plurality of vector points, and the candidate vector point heading angle and candidate vector point position are determined from the third mapping relationship. The projected vector point of the vehicle is determined from the candidate vector points based on the vehicle heading angle, the candidate vector point heading angle, the vehicle position, and the candidate vector point position.

[0111] Optionally, the first determining module 1220 is further configured to: Determine the angle difference between the vehicle's heading angle and the candidate vector point's heading angle; The candidate vector point corresponding to the heading angle of the candidate vector point whose angle difference satisfies the preset condition is determined as the first target candidate vector point; The position of the first target candidate vector point is determined from the positions of the candidate vector points; The projection vector point is determined from the first target candidate vector point based on the position of the first target candidate vector point and the position of the vehicle.

[0112] Optionally, the preset projection direction is to the left of the vehicle's position; the first determining module 1220 is further configured to: The position of the first target candidate vector point is compared with the position of the vehicle, and the position of the second target candidate vector point located to the left of the vehicle position is determined from the position of the first target candidate vector point. The first target candidate vector point corresponding to the position of the second target candidate vector point is determined as the projection vector point.

[0113] Optionally, the first determining module 1220 is further configured to: In the spatial index coordinate system, determine the adjacent spatial index that is adjacent to the vehicle position spatial index; The candidate vector point is determined from the plurality of vector points by matching the adjacent spatial index with the vector point spatial index in the third mapping relationship.

[0114] Optionally, the topological relationship includes at least one of a preorder relationship, a postorder relationship, a parent relationship, and a child relationship. The preorder relationship reflects that the other vector points are located on the same lane line as the vector point and that the other vector points are ahead of the vector point. The postorder relationship reflects that the other vector points are located on the same lane line as the vector point and that the other vector points are behind the vector point. The parent relationship reflects that the lane line of the other vector points is located to the left of the lane line of the vector point. The child relationship reflects that the lane line of the other vector points is located to the right of the lane line of the vector point.

[0115] This disclosure also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the lane information determination method provided in this disclosure.

[0116] This disclosure also provides a vehicle including the lane information determination device provided herein.

[0117] Figure 13 This is a block diagram illustrating a vehicle 1300 according to an exemplary embodiment. For example, vehicle 1300 may be a hybrid vehicle, a non-hybrid vehicle, an electric vehicle, a fuel cell vehicle, or other types of vehicle. Vehicle 1300 may be an autonomous vehicle, a semi-autonomous vehicle, or a non-autonomous vehicle.

[0118] Reference Figure 13The vehicle 1300 may include various subsystems, such as an infotainment system 1310, a perception system 1320, a decision control system 1330, a drive system 1340, and a computing platform 1350. The vehicle 1300 may also include more or fewer subsystems, and each subsystem may include multiple components. Furthermore, each subsystem and component of the vehicle 1300 can be interconnected via wired or wireless means.

[0119] In some embodiments, the infotainment system 1310 may include a communication system, an entertainment system, and a navigation system, etc.

[0120] The perception system 1320 may include several sensors for sensing information about the environment surrounding the vehicle 1300. For example, the perception system 1320 may include a global positioning system (which may be a GPS system, a BeiDou system, or another positioning system), an inertial measurement unit (IMU), a lidar, a millimeter-wave radar, an ultrasonic radar, and a camera device.

[0121] The decision control system 1330 may include a computing system, a vehicle controller, a steering system, a throttle, and a braking system.

[0122] The drive system 1340 may include components that provide powered motion to the vehicle 1300. In one embodiment, the drive system 1340 may include an engine, an energy source, a transmission system, and wheels. The engine may be one or a combination of internal combustion engines, electric motors, and compressed air engines. The engine is capable of converting energy provided by the energy source into mechanical energy.

[0123] Some or all of the functions of the vehicle 1300 are controlled by a computing platform 1350. The computing platform 1350 may include at least one first processor 1351 and a first memory 1352, the first processor 1351 being able to execute instructions 1353 stored in the first memory 1352.

[0124] The first processor 1351 can be any conventional processor, such as a commercially available CPU. The processor may also include a graphics processing unit (GPU), a field-programmable gate array (FPGA), a system-on-a-chip (SOC), an application-specific integrated circuit (ASIC), or a combination thereof.

[0125] The first memory 1352 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0126] In addition to instruction 1353, the first memory 1352 can also store data, such as road maps, route information, vehicle position, direction, speed, and other data. The data stored in the first memory 1352 can be used by the computing platform 1350.

[0127] In this embodiment of the disclosure, the first processor 1351 may execute instructions 1353 to complete all or part of the steps of the lane information determination method described above.

[0128] The preferred embodiments of this disclosure have been described in detail above with reference to the accompanying drawings. However, this disclosure is not limited to the specific details of the above embodiments. Within the scope of the technical concept of this disclosure, various simple modifications can be made to the technical solutions of this disclosure, and these simple modifications all fall within the protection scope of this disclosure.

[0129] It should also be noted that the various specific technical features described in the above embodiments can be combined in any suitable manner without contradiction. To avoid unnecessary repetition, this disclosure will not describe the various possible combinations separately.

[0130] Furthermore, various different embodiments of this disclosure can be combined in any way, as long as they do not violate the spirit of this disclosure, they should also be regarded as the content disclosed in this disclosure.

Claims

1. A method for determining lane information, characterized in that, include: The vehicle's location and lane coding data are obtained. The lane coding data includes a first mapping relationship between the index information of each vector point and the index information of other vector points, and a second mapping relationship between the index information of each vector point and the lane information corresponding to the vector point. The multiple vector points include at least the vector points on the lane lines in the road where the vehicle is located, and the other vector points include vector points that have a topological relationship with the vector points among the multiple vector points. The projection vector point of the vehicle is determined from the plurality of vector points based on the vehicle position. The projection vector point includes the vector point of the vehicle in a preset projection direction. The index information of the projected vector points is matched with the index information in the first mapping relationship to determine the index information of other target vector points from the first mapping relationship; Based on the index information of the projected vector point and the index information of other target vector points, the index information in the second mapping relationship is matched to determine the first lane information corresponding to the projected vector point and the second lane information corresponding to the other target vector points; The target lane information of the vehicle is determined based on the first lane information and the second lane information.

2. The method according to claim 1, characterized in that, The lane coding data further includes a third mapping relationship between the index information of each vector point and the vector point's heading angle and position, wherein the index information at least includes the vector point's spatial index in a spatial index coordinate system, and the method further includes: Obtain the vehicle heading angle; Determining the projected vector point of the vehicle from the plurality of vector points based on the vehicle's position includes: Determine the vehicle position spatial index in the spatial index coordinate system; The vehicle position spatial index is matched with the vector point spatial index included in the index information in the third mapping relationship to determine candidate vector points from the plurality of vector points, and the candidate vector point heading angle and candidate vector point position are determined from the third mapping relationship. The projected vector point of the vehicle is determined from the candidate vector points based on the vehicle heading angle, the candidate vector point heading angle, the vehicle position, and the candidate vector point position.

3. The method according to claim 2, characterized in that, The step of determining the vehicle's projected vector point from the candidate vector points based on the vehicle's heading angle, the candidate vector point's heading angle, the vehicle's position, and the candidate vector point's position includes: Determine the angle difference between the vehicle's heading angle and the candidate vector point's heading angle; The candidate vector point corresponding to the heading angle of the candidate vector point whose angle difference meets the preset conditions is determined as the first target candidate vector point; The position of the first target candidate vector point is determined from the positions of the candidate vector points; The projection vector point is determined from the first target candidate vector point based on the position of the first target candidate vector point and the position of the vehicle.

4. The method according to claim 3, characterized in that, The preset projection direction is to the left of the vehicle position; determining the projection vector point from the first target candidate vector points based on the first target candidate vector point position and the vehicle position includes: The position of the first target candidate vector point is compared with the position of the vehicle, and the position of the second target candidate vector point located to the left of the vehicle position is determined from the position of the first target candidate vector point. The first target candidate vector point corresponding to the position of the second target candidate vector point is determined as the projection vector point.

5. The method according to claim 2, characterized in that, The step of matching the vector point spatial index with the index information included in the third mapping relationship based on the vehicle location spatial index to determine candidate vector points from the plurality of vector points includes: In the spatial index coordinate system, determine the adjacent spatial index that is adjacent to the vehicle position spatial index; The candidate vector point is determined from the plurality of vector points by matching the adjacent spatial index with the vector point spatial index in the third mapping relationship.

6. The method according to claim 1, characterized in that, The topological relationship includes at least one of a precedence relationship, a follow-up relationship, a parent relationship, and a child relationship. The precedence relationship reflects that the other vector point is located on the same lane line as the vector point and that the other vector point is in front of the vector point. The follow-up relationship reflects that the other vector point is located on the same lane line as the vector point and that the other vector point is behind the vector point. The parent relationship reflects that the lane line of the other vector point is located to the left of the lane line of the vector point. The child relationship reflects that the lane line of the other vector point is located to the right of the lane line of the vector point.

7. A method for determining lane coding data, characterized in that, include: Acquire map data, the map data including roads, the roads including lane lines; Multiple vector points are determined based on the lane lines; Determine the index information of each of the plurality of vector points; Construct a first mapping relationship between the index information of each vector point and the index information of the other vector points, wherein the other vector points include vector points that have a topological relationship with the vector points among the plurality of vector points; Construct a second mapping relationship between the index information of each vector point and the lane information corresponding to the vector point; Lane coding data is determined based at least on the first mapping relationship and the second mapping relationship.

8. A lane information determination device, characterized in that, include: The first acquisition module is configured to acquire the vehicle position and lane coding data of the vehicle. The lane coding data includes a first mapping relationship between the index information of each vector point and the index information of other vector points, and a second mapping relationship between the index information of each vector point and the lane information corresponding to the vector point. The multiple vector points include at least the vector points on the lane lines in the road where the vehicle is located, and the other vector points include vector points that have a topological relationship with the vector points among the multiple vector points. The first determining module is configured to determine the projection vector point of the vehicle from the plurality of vector points based on the vehicle position, wherein the projection vector point includes the vector point of the vehicle in a preset projection direction; The first matching module is configured to match the index information of the projected vector point and the index information of other target vector points with the index information in the second mapping relationship to determine the first lane information corresponding to the projected vector point and the second lane information corresponding to other target vector points. The second determining module is configured to determine the target lane information of the vehicle based on the first lane information and the second lane information.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the steps of the method described in any one of claims 1 to 7.

10. A vehicle, characterized in that, Includes the lane information determination device as described in claim 8.

Images