Path generation method and device, vehicle and storage medium

Abstract

The application discloses a path generation method and device, a vehicle and a storage medium. The method comprises the following steps: acquiring a preceding lane and a subsequent lane of a target intersection to be passed; obtaining a grid intersection corresponding to the target intersection according to the preceding lane and the subsequent lane; determining a plurality of grid points in the grid intersection as a plurality of stage points according to the value of each grid point in the grid intersection; and determining a target path passing through the target intersection according to the plurality of stage points. According to the method, the vehicle turning angle range corresponding to the stage points is more accurate, the target path constructed according to the plurality of stage points is more accurate and smooth, and the safety of the vehicle passing through the target intersection according to the target path is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle control, and more particularly, to a path generation method and device, a vehicle, and a computer readable storage medium. BACKGROUND

[0002] In the field of automatic driving, the intersection without lane lines has always been a place that consumes a lot of manpower and time cost in the process of automatic driving mapping and production. Unlike ordinary lanes, the intersection without lane lines often needs to be manually labeled by technical personnel, but the manual labeling method is low in efficiency.

[0003] At present, an arc-shaped passing path can be constructed for the passing direction and the import and export roads of the target intersection, and the vehicle is controlled to pass through the target intersection according to the constructed arc-shaped passing path.

[0004] However, the accuracy of the passing route determined by this method is low, resulting in low safety of the vehicle passing through the intersection. SUMMARY

[0005] Therefore, the present application provides a path generation method, device, vehicle and computer readable storage medium to solve the above problems.

[0006] In a first aspect, the embodiments of the present application provide a path generation method, which comprises: acquiring a preceding lane and a subsequent lane of a target intersection to be passed; performing grid division on the target intersection according to the preceding lane and the subsequent lane to obtain a grid intersection corresponding to the target intersection; determining a plurality of grid points from the grid intersection as a plurality of stage points according to the generation value of each grid point in the grid intersection, the generation value of the grid point being used to represent the vehicle turning angle range at the grid point; and determining a target path passing through the target intersection according to the plurality of stage points.

[0007] In a second aspect, the embodiments of the present application provide a path generation device, which comprises: an acquisition module configured to acquire a preceding lane and a subsequent lane of a target intersection to be passed; a division module configured to perform grid division on the target intersection according to the preceding lane and the subsequent lane to obtain a grid intersection corresponding to the target intersection; a determination module configured to determine a plurality of grid points from the grid intersection as a plurality of stage points according to the generation value of each grid point in the grid intersection, the generation value of the grid point being used to represent the vehicle turning angle range at the grid point; and a path obtaining module configured to determine a target path passing through the target intersection according to the plurality of stage points.

[0008] In a third aspect, the embodiments of the present application provide a vehicle, which comprises:

[0009] one or more processors;

[0010] Memory;

[0011] One or more applications, wherein the applications are stored in memory and configured to be executed by one or more processors, and the applications are configured to perform the methods of the first aspect described above.

[0012] Fourthly, embodiments of this application provide a computer-readable storage medium storing program code, which can be invoked by a processor to execute the method described in the first aspect.

[0013] This application provides a path generation method, apparatus, vehicle, and computer-readable storage medium. In this application, a grid intersection is determined based on the preceding and following lanes of the target intersection. Multiple stage points are determined based on the value of each grid point within the grid intersection. The turning angle range corresponding to each stage point is more precise, making the target path constructed based on multiple stage points more accurate and smooth, thus improving the safety of vehicles passing through the target intersection according to the target path. Furthermore, in this application, stage points are determined from each grid point within the grid intersection, fully utilizing the passable area of ​​the intersection and flexibly and rationally planning the path.

[0014] These or other aspects of this application will become more apparent in the following description of the embodiments. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 A schematic diagram of a vehicle hardware environment applicable to embodiments of this application is shown.

[0017] Figure 2 A flowchart of a path generation method according to an embodiment of this application is shown.

[0018] Figure 3 A flowchart of a path generation method according to yet another embodiment of this application is shown.

[0019] Figure 4 A schematic diagram of a target intersection is shown in an embodiment of this application.

[0020] Figure 5 It shows Figure 4 A schematic diagram of the stage points corresponding to the target intersection.

[0021] Figure 6 It shows Figure 4 A schematic diagram of the traffic routes corresponding to the target intersection.

[0022] Figure 7 A flowchart of a path generation method according to another embodiment of this application is shown.

[0023] Figure 8 A structural block diagram of a path generation apparatus according to an embodiment of this application is shown.

[0024] Figure 9 A structural block diagram of a computer-readable storage medium provided in an embodiment of this application is shown. Detailed Implementation

[0025] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0026] Reference Figure 1 , Figure 1 A schematic diagram of a vehicle hardware environment applicable to an embodiment of this application is shown. The vehicle 100 includes an autonomous driving system 110. The autonomous driving system 110 can have a variety of built-in autonomous driving functions. The autonomous driving system 110 controls the vehicle to drive autonomously according to the built-in autonomous driving functions. The autonomous driving functions may include, for example, automatic lane changing function, automatic overtaking function, and automatic parking function.

[0027] The autonomous driving system 110 may include an on-board data acquisition device 111, one or more (only one is shown in the figure) processors 112 and memory 113.

[0028] The vehicle-mounted data acquisition device 111 is used to collect various signals from the vehicle in order to obtain the target's travel direction and driving status based on the collected signals.

[0029] The processor 112 may be a microcontroller unit (MCU) with a built-in memory 113 containing a program that can execute the contents of the following embodiments, and the processor 112 can execute the program stored in the memory 113.

[0030] The processor 112 may include one or more processors. The processor 112 connects to various parts of the vehicle 100 via various interfaces and lines, and performs various functions and processes data of the vehicle 10 by running or executing instructions, programs, code sets, or instruction sets stored in the memory 113, and by calling data stored in the memory 113. Optionally, the processor 112 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 12 may integrate one or a combination of several of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the displayed content; and the modem handles wireless communication. It is understood that the modem may also not be integrated into the processor 112, but may be implemented separately using a communication chip.

[0031] Memory 113 may include random access memory (RAM) or read-only memory (ROM). Memory 15 may be used to store instructions, programs, code, code sets, or instruction sets. Memory 15 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (such as touch functionality, sound playback functionality, image playback functionality, etc.), instructions for implementing the various method embodiments described below, etc.

[0032] The vehicle-mounted data acquisition device 111 may include cameras and sensors for collecting information such as the target travel direction and target driving status of the vehicle. Different information can be collected by different sensors. For example, the camera and distance sensor can be used to determine information such as surrounding obstacles or surrounding vehicles in the target driving status of the vehicle.

[0033] Reference Figure 2 , Figure 2 A flowchart of a path generation method according to an embodiment of this application is shown. The method is used for vehicles and includes:

[0034] S110: Obtain the preceding and following lanes of the target intersection to be traversed.

[0035] In this application, the vehicle may be a vehicle with a built-in autonomous driving system (e.g., Figure 1 The 110) electric or gasoline-powered vehicle, which can be a sedan, SUV, bus, or truck, etc. The autonomous driving system can include various autonomous driving functions, through which the vehicle controls its automatic driving.

[0036] The vehicle's autonomous driving function may include a path generation function. Once the path generation function is activated, the vehicle begins to perform a path generation operation to obtain the target path, and controls the vehicle to pass through the target intersection based on the target path.

[0037] A target intersection can refer to an intersection that the vehicle is currently waiting to pass or will soon be waiting to pass (e.g., in 2 minutes) during its journey. During autonomous driving, the vehicle can obtain the user-set starting point and destination, determine the driving route based on these, and identify each intersection to be passed as a target intersection based on the driving route.

[0038] The preceding and following lanes can be determined based on the intersection data of the target intersection and the target traffic direction corresponding to the target intersection.

[0039] The target direction of travel can refer to the direction of travel through the target intersection. For example, turning left from lane a1 to lane a2, where a1 and a2 are two lanes of the target intersection, the target direction of travel is turning left from a1 to a2; going straight from lane a3 to lane a4, where a3 and a4 are two lanes of the target intersection, the target direction of travel is going straight from a3 to a4; turning right from lane a5 to lane a6, where a5 and a6 are two lanes of the target intersection, the target direction of travel is turning right from a5 to a6.

[0040] The intersection data for the target intersection can refer to the set of point coordinates (outline) representing the planar contour of the target intersection, as well as elements such as the IDs of each associated lane (the preceding lane entering the target intersection and the following lane leaving the target intersection), and traffic signals. This intersection data can be obtained from map XML data in an autonomous driving map.

[0041] The following is an example of map XML data;

[0042] <junction id="301">

[0043] <outline>

[0044] <cornerGlobal x="113" y="25">

[0045] <cornerGlobal x="113" y="26">

[0046] <cornerGlobal x="115" y="26">

[0047] …

[0048] < / outline>

[0049] <objectoverlapgroup>

[0050] < objectRef erence id="161_1" type="incoming_lane" >

[0051] < objectRef erence id="161_2" type="incoming_lane" >

[0052] < objectRef erence id="162_1" type="incoming_lane" >

[0053] < objectRef erence id="171_1" type="outcoming_lane" >

[0054] …

[0055] < / objectoverlapgroup>

[0056]

[0057] The target intersection and each lane cluster in the intersection data can be treated as participants. A global search algorithm is used to determine the global planning ID sequence to obtain the preceding and following lanes of the target intersection. Specifically, for the target travel direction, the preceding lane refers to the lane entering the target intersection according to that target travel direction, and the following lane refers to the lane leaving the target intersection according to that target travel direction.

[0058] It is understandable that, for different target traffic directions at a target intersection, the corresponding preceding and following lanes may be different. This application only uses one target traffic direction as an example for explanation. When a vehicle enters the target intersection according to other target directions, the corresponding preceding and following lanes are determined in a similar way.

[0059] S120. Based on the preceding and following lanes, the target intersection is divided into grids to obtain the corresponding grid intersection.

[0060] After determining the preceding and following lanes, the target intersection can be divided into grids based on the preceding and following lanes to obtain a grid-shaped intersection.

[0061] The grid density can be determined based on the traffic flow and size of the target intersection. Then, the target intersection can be divided into grids based on the grid density, the preceding lanes, and the following lanes, thus obtaining the corresponding grid intersection.

[0062] S130. Based on the value of each grid point in the grid intersection, determine multiple grid points from the grid intersection as multiple stage points.

[0063] The cost value of a grid point is used to characterize the turning angle range of a vehicle at that grid point. The gentler the turning angle range, the lower the cost value; the more abrupt the turning angle range, the higher the cost value.

[0064] After identifying the grid intersections, the cost value of each grid point within the intersection can be determined. Based on the cost values ​​of each grid point, the grid points with the lowest cost values ​​are selected as multiple stage points. For example, if there are 40 grid points, the 8 grid points with the lowest cost values ​​are selected as 8 stage points.

[0065] S140. Based on multiple stage points, determine the target path through the target intersection.

[0066] After obtaining multiple stage points, the entry point to the target intersection can be determined based on the preceding lanes, and the exit point to leave the target intersection can be determined based on the following lanes. Based on the entry point, exit point, and multiple stage points, a smooth passage path can be connected as the target path.

[0067] Optionally, the target driving situation at the target intersection can also be obtained, and a traffic strategy can be obtained based on the target route and the target driving situation; and the target intersection can be passed according to the traffic strategy.

[0068] After determining the target route, a strategy for traversing the target intersection is determined based on the target route and the target driving situation, serving as the traffic strategy. The target driving situation refers to the driving situation at the target intersection when the vehicle passes through it, and may include obstructing vehicles, pedestrians, and other obstacles that the vehicle may encounter when passing through the target intersection.

[0069] For example, when the target direction of travel includes going straight, a straight-ahead strategy is adopted based on the target path and the target driving situation: accelerating or yielding is determined based on the speed and situation of each obstacle; as another example, when the target direction of travel includes turning left, a left-turn strategy is adopted based on the target path and the target driving situation: proceeding first at the point where right-turning vehicles meet at the target intersection; as yet another example, when the target direction of travel includes turning right, a right-turn strategy is adopted based on the target path and the target driving situation: yielding to oncoming left-turning vehicles and vehicles or pedestrians going straight in intersecting directions.

[0070] After determining the traffic strategy, the vehicle is controlled to drive automatically to pass through the target intersection.

[0071] In this embodiment, a grid intersection is determined based on the preceding and following lanes of the target intersection. Multiple stage points are then determined based on the value of each grid point within the grid intersection. The turning angle range corresponding to each stage point is more precise, making the target path constructed based on multiple stage points more accurate and smoother, thus improving the safety of vehicles passing through the target intersection according to the target path. Furthermore, in this embodiment, stage points are determined from each grid point within the grid intersection, making full use of the passable area of ​​the intersection and allowing for flexible and reasonable path planning.

[0072] Reference Figure 3 , Figure 3 A flowchart of a path generation method according to another embodiment of this application is shown. The method is used for vehicles and includes:

[0073] S210: Obtain the preceding and following lanes of the target intersection to be traversed.

[0074] The description of S210 is the same as that of S110 above, and will not be repeated here.

[0075] S220. Obtain the end point of the centerline of the preceding lane as the first point, and obtain the beginning point of the centerline of the following lane as the second point; determine the trend vector in the target intersection based on the first point and the second point; determine the grid intersection of the corresponding target intersection based on the trend vector.

[0076] After determining the preceding and following lanes, the end point of the centerline of the preceding lane is taken as the first point, and the beginning point of the centerline of the following lane is taken as the second point. The first and second points can be connected, and the direction pointing to the second point is determined as the direction of the vector to obtain the trend vector.

[0077] like Figure 4 As shown, the target traffic direction is to turn left from L1 into L2. The first point of the preceding lane L1 is P1, and the second point of the following lane L2 is P2. The solid line L with arrows is the trend vector.

[0078] After obtaining the trend vector, the direction of the grid lines for drawing the grid intersection can be determined based on the trend vector, and the grid intersection can be drawn by drawing the grid lines in that direction.

[0079] As one implementation method, determining the grid intersection corresponding to the target intersection based on the trend vector includes: determining the target point based on the center line of the preceding lane and the center line of the following lane; drawing a first grid line in a first direction between the first point and the second point, and drawing a second grid line in a second direction on the target side of the trend vector to obtain the grid intersection, wherein the target point is on the target side of the trend vector, the first direction refers to the direction perpendicular to the trend vector, and the second direction refers to the direction parallel to the trend vector.

[0080] The target point can be determined based on the center line of the preceding lane, the center line of the following lane, and the target direction of travel. For example, if the target direction of travel includes going straight, the midpoint of the line segment connecting the first point and the second point is taken as the target point. Or, if the target direction of travel includes turning left or right, the intersection of the center line of the preceding lane and the center line of the following lane is taken as the target point.

[0081] like Figure 4 As shown, the target direction of travel is a left turn from L1 into L2, and the target point is the intersection P0 of the centerline of L1 and the centerline of L2. Wherein, Figure 4 In the grid, there exists a target point P0 where the intersection of a first grid line and a second grid line is located.

[0082] After obtaining the target point and trend vector, the direction perpendicular to the trend vector is designated as the first direction. A first grid line in the first direction is drawn between the first point and the second point. Then, taking the direction of the trend vector as the second direction, a second grid line in the second direction is drawn on the side of the trend vector closer to the target point. This second grid line, along with the first and second grid lines, divides the intersection outline into an m*n grid, resulting in a grid intersection. Here, m and n are non-zero natural numbers, and the division densities 1 / m and 1 / n depend on the actual size of the target intersection and the traffic flow. Optionally, the higher the traffic flow, the higher the division density can be.

[0083] like Figure 4 As shown, the first grid line includes 6 first grid lines between the first point P1 and the second point P2, and the second grid line includes 15 second grid lines on the side of the trend vector L closer to the target point P0. That is, m is 6 and n is 15 at this time.

[0084] S230. Based on the cost value of each grid point in the grid intersection, determine multiple grid points from the grid intersection as multiple stage points.

[0085] The description of S230 is the same as that of S130 above, and will not be repeated here.

[0086] S240. Obtain the end point of the centerline of the preceding lane as the first point, and obtain the beginning point of the centerline of the following lane as the second point; according to the fifth-order polynomial fitting method, perform fitting processing on the first point, the second point, and multiple stage points to obtain the target path.

[0087] In this application, the cost value of each grid point on each first grid line can be constructed according to the set cost value calculation rules, and the grid point with the lowest cost value on each first grid line can be determined as the stage point corresponding to each first grid line.

[0088] like Figure 5 As shown, according to Figure 4 The value of each grid point on each first grid line is used to determine the stage point corresponding to each first grid line; the stage point is... Figure 5 The intersection of the solid circular markers.

[0089] Starting from the first point and ending at the second point, the curve can be obtained by fitting multiple stage points using the fifth-order polynomial fitting method, which can then be used as the route for the target traffic direction.

[0090] like Figure 6 As shown, with Figure 5 The passage 601, constructed from multiple stage points, the first point, and the second point, is a smooth curve.

[0091] It should be noted that when the target traffic direction at the intersection includes going straight, the first point and the second point can be directly connected, and the straight line connecting the first point and the second point can be used as the target path at the intersection when the target traffic direction is going straight. When the target traffic direction at the intersection includes turning left and turning right, the target path under the target traffic direction is determined according to the methods described in S210-S240 above.

[0092] It should be noted that the above method can be used to obtain a path for each intersection in the autonomous driving map, or the above steps can be performed only for intersections in the autonomous driving map that do not have virtual lane lines to obtain a path.

[0093] In this embodiment, a traffic route is constructed based on the stage point with the lowest cost. The traffic route is smooth, and vehicles traveling along the route exhibit good stability, thus improving traffic safety. Simultaneously, fitting processing is performed on multiple stage points to further improve the smoothness of the obtained traffic route, thereby enhancing traffic safety.

[0094] In this embodiment, there is no need to manually add virtual lane lines at intersections to assist in the generation of paths for autonomous vehicles, which greatly saves manpower and time costs in mapping and facilitates the establishment of an automated map production chain. Furthermore, while saving map production costs, this application can still ensure the input of information for the decision-making and planning module of the autonomous driving system, including the vehicle's driving posture at the intersection and information on the vehicle's passable boundaries. In addition, compared to virtual lane lines, the path planning method adopted in this application can more fully and flexibly utilize the intersection area in real-world conditions for obstacle avoidance planning, without being limited by the constraints of virtual lane lines from map data.

[0095] Reference Figure 7 , Figure 7 A flowchart of a path generation method according to another embodiment of this application is shown. The method is used for vehicles and includes:

[0096] S310. Obtain the preceding and following lanes of the target intersection to be traversed; divide the target intersection into grids based on the preceding and following lanes to obtain the corresponding grid intersection of the target intersection.

[0097] The description of S310 is the same as that of S110-S120 above, and will not be repeated here.

[0098] S320. Obtain the value of the stage point in the previous first grid line for each first grid line, and use it as the historical value of the grid point on each first grid line.

[0099] In this embodiment, the first grid lines in each first direction of the grid intersection are ordered. The first grid lines in each first direction of the grid intersection are arranged according to the target order, with the first grid line closer to the first point appearing earlier in the order. For example... Figure 5 The grid intersections shown are numbered from left to right as follows: 6, 5, 4, 3, 2 and 1. The first point is numbered 0 and the second point is numbered 7.

[0100] For each first grid line, the cost value of the stage points in the preceding first grid line is obtained and used as the historical cost value of the grid points on that first grid line. If the current first grid line is the first first grid line, then the historical cost value of each grid point on that first grid line is 0. If the current first grid line is not the first first grid line, then the cost value of the stage points in the preceding first grid line is obtained and used as the historical cost value of each grid point on that first grid line.

[0101] For example, the historical cost value of each grid point on the second first grid line is the cost value of the stage point on the first first grid line.

[0102] S330. Determine the initial value of each grid point on the first grid line.

[0103] For each grid point on the first grid line, the cost value of the initial stage point is determined according to the cost value calculation rules.

[0104] In this embodiment, the generation value calculation rule may refer to: determining the first generation value of each grid point on each first grid line based on the stage points on each first grid line and the two first grid lines preceding each first grid line; determining the second generation value of each grid point on each first grid line based on the relative distance and relative sequence difference corresponding to each grid point on each first grid line, where the relative distance is the distance between the grid point and the target point, and the relative sequence difference is the difference between the sequence number of the first grid line where the grid point is located and the sequence number of the first grid point where the target point is located, and the target point is determined based on the preceding and following lanes; determining the third generation value of each grid point on each first grid line based on the target point, the starting point of the center line of the following lane, the grid points on each first grid line, the stage points on the preceding first grid line of each first grid line, and the sequence number of each first grid line; and determining the initial generation value corresponding to each grid point on each first grid line based on the first generation value, the second generation value, and the third generation value corresponding to each grid point on each first grid line.

[0105] Specifically, based on the stage points on each first grid line and the two preceding first grid lines, a first vector representing the travel direction of each grid point on each first grid line and a second vector representing the travel direction of the stage points in the preceding first grid line can be determined. Then, according to Formula 1, the first offspring value of each initial stage point can be determined based on the first vector representing the travel direction of each grid point on each first grid line and the second vector representing the travel direction of the stage points in the preceding first grid line. Formula 1 is as follows:

[0106]

[0107] Where c1 is the first child value of a grid point ij (the intersection of the first grid line i and the second grid line j, where the grid intersection includes m first grid lines and n second grid lines) corresponding to a first grid line i in the grid intersection, and the coordinates of the grid point ij are P. cur (x cur ,y cur The coordinates of the stage point on the first grid line preceding the first grid line i are P. pre1 (x pre1 ,y pre1 The coordinates of the stage point on the second first grid line preceding the first grid line i are P. pre2 (x pre2 ,y pre2 ), the first vector is d cur =(x cur -x pre1 ,y cur -y pre1 The second vector is d. pre =(x pre1 -x pre2 ,y pre1 -y pre2 ), where P is the first grid line i when it is the first grid line. pre1 It can refer to the target point P0, P pre2 It could refer to the first point, P1.

[0108] In this embodiment, for each grid point in each first grid line, the first vector corresponding to the grid point represents the travel direction of the grid point.

[0109] The second offspring value of each grid point on each first grid line can be determined according to Formula 2, based on the relative distance and relative sequence difference between each grid point on each first grid line. Formula 2 is as follows:

[0110]

[0111] Where c2 is the second offspring value of a grid point ij on the first grid line i, P0 refers to the target point P0, and the coordinates of P0 are (x0, y0). cur P0 represents the relative distance between grid point ij and the target point. K refers to the sequence number of the first grid line containing the target point, where the sequence number of the first grid line i is i. For example, as... Figure 5 As shown, the value of K is 3.

[0112] The third-generation value of each grid point on each first grid line can be determined based on the target point, the starting point of the centerline of the subsequent lane, the grid points on each first grid line, the stage points on the previous first grid line, and the sequence number of each first grid line. Formula 3 is as follows:

[0113]

[0114] Where c3 is the third offspring value of a grid point ij on the first grid line i, the coordinates of the second point P2 (the starting point of the centerline of the successor lane) are P2(x2,y2), and the coordinates of the first point P1 (the ending point of the centerline of the preceding lane) are P1(x1,y1). The successor direction d... b = (x2-x0, y2-y0).

[0115] Determine the first, second, and third offspring values ​​for each grid point on each first grid line. Based on these values, determine the initial generation value for each grid point on each first grid line.

[0116] As one implementation method, the initial generation value corresponding to each grid point on each first grid line is determined based on the first generation value, the second generation value, and the third generation value corresponding to each grid point on each first grid line. This includes: obtaining a first weight for the first generation value of each grid point on each first grid line, a second weight for the second generation value of each grid point on each first grid line, and a third weight for the third generation cost value of each grid point on each first grid line; and performing a weighted summation of the first generation value, the second generation value, and the third generation value corresponding to each grid point on each first grid line based on the first weight, the second weight, and the third weight to obtain the initial generation value of each grid point on each first grid line.

[0117] The process of determining the initial value described above can be expressed as Formula 4, which is as follows:

[0118] c ij =c1k1+c2k2+c3k3

[0119] Among them, c ij Let k be the initial value of grid point ij, k1 be the first weight, k2 be the second weight, and k3 be the third weight. The first, second, and third weights can be determined through multiple trials or experience, and this application does not limit their specific values.

[0120] S340. Calculate the sum of the initial cost value and the historical cost value corresponding to each grid point on the first grid line, and use it as the cost value of each grid point on the first grid line.

[0121] The calculation process for the cost value of the above grid points can be expressed as Formula 5, which is as follows:

[0122] c = c0 + c ij

[0123] Where c is the cost of grid point ij, and c0 is the historical cost. At this point, formulas four and five can be combined to obtain the formula for calculating the cost of grid points, which is formula six, as follows:

[0124] c = c0 + c1k1 + c2k2 + c3k3

[0125] S350. Determine the grid point with the lowest cost value from each first grid line, and use it as the stage point corresponding to each first grid line.

[0126] For each first grid line, the grid point with the lowest cost value is determined and used as the unique stage point for that first grid line. For example... Figure 5 As shown, the six first grid lines define six stage points (stage points are...). Figure 5 (The intersection of the solid circular markers).

[0127] S360. Based on multiple stage points, determine the target path through the target intersection.

[0128] The description of S360 is the same as that of S140 above, and will not be repeated here.

[0129] In this embodiment, based on the cost value of each grid point on each first grid line, the grid point with the lowest cost value is selected as the stage point. The stage point with the lowest cost value results in a smoother traffic route constructed based on the stage point. When vehicles travel along the traffic route, the stability is better, thus improving traffic safety.

[0130] Reference Figure 8 , Figure 8 This diagram illustrates a structural block diagram of a path generation apparatus according to an embodiment of this application. The apparatus 800 is used in a vehicle and includes:

[0131] The acquisition module 810 is used to acquire the preceding and following lanes of the target intersection to be traversed;

[0132] The segmentation module 820 is used to segment the target intersection into grids based on the preceding and following lanes, thereby obtaining the corresponding grid intersection of the target intersection.

[0133] The determination module 830 is used to determine multiple grid points from the grid intersection based on the cost value of each grid point in the grid intersection, as multiple stage points. The cost value of the grid point is used to characterize the vehicle turning angle range at the grid point.

[0134] The path acquisition module 840 is used to determine the target path through the target intersection based on multiple stage points.

[0135] Furthermore, the segmentation module 820 is also used to obtain the end point of the center line of the preceding lane as the first point and the beginning point of the center line of the following lane as the second point; based on the first point and the second point, a trend vector is determined in the target intersection; based on the trend vector, the grid intersection of the corresponding target intersection is determined.

[0136] Furthermore, the segmentation module 820 is also used to determine the target point based on the center line of the preceding lane and the center line of the following lane; draw a first grid line in a first direction between the first point and the second point, and draw a second grid line in a second direction on the target side of the trend vector to obtain a grid intersection, wherein the target point is on the target side of the trend vector, the first direction refers to the direction perpendicular to the trend vector, and the second direction refers to the direction parallel to the trend vector.

[0137] Furthermore, the determination module 830 is also used to determine the cost value of grid points on each first grid line; and to determine the grid point with the lowest cost value from each first grid line as the stage point corresponding to each first grid line.

[0138] Furthermore, the grid intersection includes multiple ordered first grid lines in the first direction; the determination module 830 is also used to obtain the cost value of the stage point in the previous first grid line of each first grid line as the historical cost value of the grid point on each first grid line; determine the initial cost value of the grid point on each first grid line; and calculate the sum of the initial cost value and the historical cost value corresponding to the grid point on each first grid line as the cost value of the grid point on each first grid line.

[0139] Furthermore, the determining module 830 is also used to determine the first offspring value of each grid point on each first grid line based on the stage points on each first grid line and the two first grid lines preceding each first grid line; to determine the second offspring value of each grid point on each first grid line based on the relative distance and relative sequence difference corresponding to each grid point on each first grid line, where the relative distance refers to the distance between the grid point and the target point, and the relative sequence difference refers to the difference between the sequence number of the first grid line where the grid point is located and the sequence number of the first grid point where the target point is located, and the target point is determined based on the preceding and following lanes; to determine the third offspring value of each grid point on each first grid line based on the target point, the starting point of the centerline of the following lane, the grid points on each first grid line, the stage points on the preceding first grid line of each first grid line, and the sequence number of each first grid line; and to determine the initial generation value corresponding to each grid point on each first grid line based on the first offspring value, the second offspring value, and the third offspring value corresponding to each grid point on each first grid line.

[0140] Furthermore, the determination module 830 is also used to obtain a first weight for the first child value of each grid point on each first grid line, a second weight for the second child value of each grid point on each first grid line, and a third weight for the third child cost value of each grid point on each first grid line; based on the first weight, the second weight, and the third weight, the first child value, the second child value, and the third child value corresponding to each grid point on each first grid line are weighted and summed to obtain the initial generation value of each grid point on each first grid line.

[0141] Furthermore, the path acquisition module 840 is also used to acquire the end point of the centerline of the preceding lane as the first point, and to acquire the beginning point of the centerline of the following lane as the second point; according to the fifth-order polynomial fitting method, the first point, the second point, and multiple stage points are fitted to obtain the target path.

[0142] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the above-described device and module can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0143] In the several embodiments provided in this application, the coupling between modules can be electrical, mechanical, or other forms of coupling.

[0144] Furthermore, the functional modules in the various embodiments of this application can be integrated into a single processing module. The integrated module can be implemented either in hardware or as a software functional module.

[0145] refer to Figure 9 , Figure 9 A structural block diagram of a computer-readable storage medium provided in an embodiment of this application is shown. The computer-readable storage medium 900 stores program code that can be called by a processor to execute the methods described in the above method embodiments.

[0146] The computer-readable storage medium 900 may be an electronic memory such as flash memory, EEPROM (Electrically Erasable Programmable Read-Only Memory), EPROM, hard disk, or ROM. Optionally, the computer-readable storage medium 900 includes a non-transitory computer-readable storage medium. The computer-readable storage medium 900 has storage space for program code 910 that performs any of the method steps described above. This program code can be read from or written to one or more computer program products. The program code 910 may be compressed, for example, in a suitable form.

[0147] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A path generation method, characterized in that, The method includes: Obtain the preceding and following lanes of the target intersection to be traversed; Based on the preceding lane and the following lane, the target intersection is divided into grids to obtain the grid intersections corresponding to the target intersections; the grid intersections include a first grid line; The cost value of each grid point on each first grid line is determined, and the grid point with the lowest cost value is determined from each first grid line as the stage point corresponding to each first grid line, so as to obtain multiple stage points; the cost value of the grid point is used to characterize the vehicle turning angle range at the grid point; the end point of the center line of the preceding lane is obtained as the first point, and the beginning point of the center line of the following lane is obtained as the second point. Using the fifth-order polynomial fitting method, the first point, the second point, and the multiple stage points are fitted to obtain the target path through the target intersection.

2. The method according to claim 1, characterized in that, The step of dividing the target intersection into grids based on the preceding and following lanes to obtain the corresponding grid intersections includes: The end point of the centerline of the preceding lane is taken as the first point, and the beginning point of the centerline of the following lane is taken as the second point. Based on the first point and the second point, determine the trend vector at the target intersection; Based on the trend vector, determine the grid intersection corresponding to the target intersection.

3. The method according to claim 2, characterized in that, The step of determining the grid intersection corresponding to the target intersection based on the trend vector includes: The target point is determined based on the centerline of the preceding lane and the centerline of the following lane; A first grid line in a first direction is drawn between the first point and the second point, and a second grid line in a second direction is drawn on the target side of the trend vector to obtain the grid intersection, wherein the target point is on the target side of the trend vector, the first direction refers to the direction perpendicular to the trend vector, and the second direction refers to the direction parallel to the trend vector.

4. The method according to claim 1, characterized in that, The grid intersection includes multiple ordered first grid lines in a first direction; Determining the cost value of each grid point on the first grid line includes: Obtain the cost value of the stage point in the previous first grid line for each first grid line, and use it as the historical cost value of the grid point on each first grid line; Determine the initial cost value for each grid point on the first grid line; Calculate the sum of the initial cost value and the historical cost value corresponding to each grid point on the first grid line, and use it as the cost value of each grid point on the first grid line.

5. The method according to claim 4, characterized in that, Determining the initial generation value of each grid point on the first grid line includes: Based on the stage points on each of the first grid lines and the two first grid lines preceding each of the first grid lines, determine the first offspring value of each grid point on each of the first grid lines; The second offspring value of each grid point on each of the first grid lines is determined based on the relative distance and relative sequence difference corresponding to each grid point on each of the first grid lines. The relative distance corresponding to each grid point on the first grid line refers to the distance between the grid point and the target point. The relative sequence difference corresponding to each grid point on the first grid line refers to the difference between the sequence number of the first grid line where the grid point is located and the sequence number of the first grid point where the target point is located. The target point is determined based on the preceding lane and the following lane. The third offspring value of each grid point on each first grid line is determined based on the target point, the first endpoint of the centerline of the subsequent lane, the grid point on each first grid line, the stage point on the previous first grid line of each first grid line, and the sequence number of each first grid line. The initial generation value corresponding to each grid point on each of the first grid lines is determined based on the first generation value, the second generation value, and the third generation value corresponding to each grid point on each of the first grid lines.

6. The method according to claim 5, characterized in that, The step of determining the initial generation value corresponding to each grid point on each of the first grid lines based on the first generation value, the second generation value, and the third generation value corresponding to each grid point on each of the first grid lines includes: Obtain a first weight for the first child value of each grid point on each of the first grid lines, a second weight for the second child value of each grid point on each of the first grid lines, and a third weight for the third child cost value of each grid point on each of the first grid lines; Based on the first weight, the second weight, and the third weight, the first offspring value, the second offspring value, and the third offspring value corresponding to each grid point on each first grid line are weighted and summed to obtain the initial generation value of each grid point on each first grid line.

7. A path generation device, characterized in that, The device includes: The acquisition module is used to acquire the preceding and following lanes of the target intersection to be traversed; The segmentation module is used to segment the target intersection into grids based on the preceding lanes and the following lanes, to obtain grid intersections corresponding to the target intersections; the grid intersections include first grid lines; The determination module is used to determine the cost value of grid points on each of the first grid lines, and to determine the grid point with the lowest cost value from each of the first grid lines as the stage point corresponding to each of the first grid lines, so as to obtain multiple stage points; the cost value of the grid point is used to characterize the vehicle turning angle range at the grid point. The path acquisition module is used to obtain the end point of the center line of the preceding lane as the first point and the beginning point of the center line of the following lane as the second point; and to perform fitting processing on the first point, the second point and the multiple stage points according to the fifth-order polynomial fitting method to obtain the target path through the target intersection.

8. A vehicle, characterized in that, The vehicles include: One or more processors; Memory; One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more applications being configured to perform the method as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium contains program code that can be invoked by a processor to execute the method as described in any one of claims 1-6.

Images