Path planning method and device, electronic equipment, vehicle, storage medium and product

Abstract

The invention relates to a path planning method and device, electronic equipment, a vehicle, a storage medium and a program product, and the method comprises the steps: determining the transverse distribution weight of each sampling point through the curvature determined based on each group of adjacent sampling points on a sampling path in a lane, taking the minimum sum of the curvatures as an optimization target, and determining the transverse distribution weight of each sampling point; the transverse distribution weight is used for indicating the offset distance of the sampling point in the direction perpendicular to the sampling path; and generating a target path according to the sampling path and the transverse distribution weight. According to the method, the global optimal path can be generated.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a path planning method, device, electronic device, vehicle, storage medium and product. Background Art

[0002] In a racing competition, an unmanned vehicle can reach its maximum speed when driving in a straight line. However, once it enters a curve, it needs to slow down appropriately to pass safely. The greater the curvature of the curve, the greater the deceleration required to maintain stability and avoid loss of control.

[0003] The ideal path should satisfy the curvature constraints of the vehicle kinematics and be as small as possible to ensure a small deceleration before entering the curve and a high speed when passing the curve.

[0004] Therefore, it is very necessary to plan the optimal driving route and spend less time on the global path. Summary of the Invention

[0005] The embodiments of the present application provide a path planning method, device, electronic device, vehicle, storage medium and program product, which are intended to generate a globally optimal driving path to at least partially solve the above-mentioned technical problems.

[0006] To achieve the above objectives, according to a first aspect of the present application, a path planning method is provided, comprising:

[0007] Based on the curvature determined for each group of adjacent sampling points on the sampling path within the lane, minimizing the sum of the curvatures is used as an optimization goal to determine a lateral distribution weight for each sampling point, wherein the lateral distribution weight is used to indicate an offset distance of the sampling point in a direction perpendicular to the sampling path;

[0008] A target path is generated according to the sampling path and the lateral distribution weight.

[0009] Optionally, before determining the lateral distribution weight of each sampling point based on the curvature determined for each group of adjacent sampling points on the sampling path within the lane, with minimizing the sum of the curvatures as an optimization goal, the method further includes:

[0010] For each group of adjacent sampling points, the initial lateral distribution weight of each sampling point is set as a variable to be optimized to obtain a curvature polynomial, wherein the curvature polynomial is the sum of the curvatures of multiple groups of adjacent sampling points;

[0011] The minimum curvature sum is obtained according to the preset constraint condition of the initial lateral distribution weight and the curvature polynomial.

[0012] Optionally, setting the initial lateral distribution weight of each sampling point as a variable to be optimized to obtain a curvature polynomial includes:

[0013] Obtaining position information corresponding to a plurality of the sampling points according to the lane boundary line of the lane and the initial lateral distribution weights of the adjacent sampling points;

[0014] Determining a target circle based on position information corresponding to adjacent sampling points;

[0015] A curvature polynomial is obtained according to the target circle and the position information.

[0016] Optionally, obtaining a curvature polynomial according to the target circle and the position information includes:

[0017] Acquire a first triangle and a second triangle according to a plurality of adjacent sampling points and the target circle, wherein the first triangle and the second triangle are two similar triangles;

[0018] A curvature polynomial is obtained according to the radius of the target circle, position information corresponding to a plurality of adjacent sampling points, and a similarity relationship between the first triangle and the second triangle.

[0019] Optionally, obtaining position information corresponding to a plurality of the sampling points according to the lane boundary line of the lane and initial lateral distribution weights of adjacent sampling points includes:

[0020] Obtain a reference point on the lane boundary line corresponding to the sampling point;

[0021] The position information of the sampling point is acquired according to the position information of the reference point and the initial lateral distribution weight corresponding to the sampling point.

[0022] Optionally, the reference points include: a first reference point on the left boundary line of the lane corresponding to the sampling point, and a second reference point on the right boundary line of the lane corresponding to the sampling point; the first reference point, the sampling point and the second reference point are in the same straight line.

[0023] Optionally, obtaining the sum of the minimum curvatures according to the preset constraint condition of the initial lateral distribution weight and the curvature polynomial includes:

[0024] Optimizing the initial lateral distribution weight in the curvature polynomial according to preset constraints of the initial lateral distribution weight;

[0025] Until the minimum curvature sum of the curvature polynomial is obtained.

[0026] Optionally, generating a target path according to the sampling path and the lateral distribution weight includes:

[0027] Obtaining an offset distance of the sampling point relative to the sampling path according to the lateral distribution weight;

[0028] A target path is generated according to the offset distance and the sampling path.

[0029] Optionally, before determining the lateral distribution weight of each sampling point based on the curvature determined for each group of adjacent sampling points on the sampling path within the lane and taking minimizing the sum of the curvatures as an optimization goal, the method further includes:

[0030] Acquire a plurality of boundary sampling points on a lane boundary line of the lane;

[0031] Acquire a plurality of centerline sampling points on the centerline of the lane according to the plurality of boundary sampling points;

[0032] A plurality of sampling points on a sampling path are determined according to the centerline sampling point and the lane boundary line.

[0033] Optionally, the lane boundary line includes a left lane boundary line and a right lane boundary line;

[0034] The step of determining a plurality of sampling points on a sampling path according to the centerline sampling point and the lane boundary line includes:

[0035] Obtaining a first intersection point of a perpendicular line of the centerline sampling point and a left lane boundary line, and a second intersection point of a perpendicular line of the centerline sampling point and a right lane boundary line;

[0036] Any point on the line connecting the first intersection point and the second intersection point is set as a sampling point on the sampling path.

[0037] Optionally, acquiring a plurality of centerline sampling points on the centerline of the lane according to the plurality of boundary sampling points includes:

[0038] Acquire, according to a preset sampling step, a first boundary sampling point on the left boundary line of the lane and a second boundary sampling point on the right boundary line of the lane corresponding to the first boundary sampling point;

[0039] Obtain a midpoint of a line connecting the first boundary sampling point and the second boundary sampling point, and use the midpoint as a midline sampling point.

[0040] According to a second aspect of the present application, a path planning device is provided, comprising:

[0041] a determination module configured to determine, based on the curvature determined for each group of adjacent sampling points on the sampling path within the lane, a lateral distribution weight for each sampling point, with minimizing the sum of the curvatures as an optimization objective, wherein the lateral distribution weight is used to indicate an offset distance of the sampling point in a direction perpendicular to the sampling path;

[0042] A generation module is used to generate a target path according to the sampling path and the horizontal distribution weight.

[0043] In a third aspect, this embodiment further provides an electronic device, comprising a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the above method.

[0044] In a fourth aspect, this embodiment further provides a vehicle, which includes the above-mentioned electronic device.

[0045] In a fifth aspect, this embodiment further provides a computer-readable storage medium, which includes a computer program. When the computer program is run on an electronic device, the computer program is used to enable the electronic device to execute the steps of the above method.

[0046] In the sixth aspect, this embodiment also provides a computer program product, including a computer program, which is stored in a computer-readable storage medium; when the processor of an electronic device reads the computer program from the computer-readable storage medium, the processor executes the computer program, so that the electronic device performs the steps of the above method.

[0047] In summary, in the embodiments of the present application, through the above-mentioned technical solution, the vehicle can use the minimum sum of the curvatures of the sampling path as the optimization target, determine the lateral distribution weight of each sampling point, and then, based on the lateral distribution weight and the sampling path, determine the target path with the minimum sum of curvatures. Compared to existing path planning methods, the target path planned in this application can ensure high-speed and stable steering, minimizing the time the vehicle spends on the global path.

[0048] Other features and advantages of the present application will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] To more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present application. Those skilled in the art can also derive other drawings based on these drawings without inventive effort.

[0050] In order to more completely understand the present application and its beneficial effects, the following description will be given in conjunction with the accompanying drawings, wherein the same drawing numbers represent the same parts in the following description.

[0051] Figure 1 is a schematic diagram of a path planning process provided in an exemplary embodiment of the present application;

[0052] Figure 2 is a schematic diagram of a racetrack provided in an exemplary embodiment of the present application;

[0053] Figure 3 is a schematic diagram of track boundary sampling provided in an exemplary embodiment of the present application;

[0054] Figure 4 is a first schematic diagram of a sampling path provided in an exemplary embodiment of the present application;

[0055] Figure 5 is a second schematic diagram of a sampling path provided in an exemplary embodiment of the present application;

[0056] Figure 6 is a schematic diagram of curvature calculation provided in an exemplary embodiment of the present application;

[0057] Figure 7 is a first schematic diagram of a target path provided in an exemplary embodiment of the present application;

[0058] Figure 8 is a second schematic diagram of a target path provided in an exemplary embodiment of the present application;

[0059] Figure 9 Schematic diagram of a path sampling device provided in an exemplary embodiment of the present application.

[0060] Figure 10 Schematic diagram of the electronic device provided in an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0061] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the embodiments described are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0062] In conjunction with the background technology described above, the primary challenge faced by autonomous racecars in racetrack competitions is how to choose the optimal driving path based solely on the track boundaries, without lane markings. This path selection is undoubtedly the key to determining racing results.

[0063] Speed plays a crucial role in track racing. While driving straight, a car can reach its maximum speed. However, once it enters a curve, it must slow down appropriately to safely negotiate it. The greater the curvature of the curve, the greater the deceleration required to maintain stability and avoid loss of control. Tracks offer numerous curves with varying curvatures. To achieve the highest possible performance, autonomous racing cars must carefully choose their paths through these curves.

[0064] The ideal path should satisfy the curvature constraints of the vehicle's kinematics and be as small as possible to ensure minimal deceleration before entering a corner, while maintaining the highest possible speed through the corner. This allows the car to achieve higher speeds and shorter times, ultimately shortening the overall time and laying a solid foundation for excellent track results.

[0065] It can be seen that planning a path with optimal global curvature based on the actual track scenario is the current problem that needs to be solved.

[0066] In related technologies, the use of kinematic models to describe the state of a high-speed vehicle on a track results in large errors. Under high-speed conditions, the tire side panel characteristics are obvious, and the actual motion state is very different from the kinematic model, making it impossible to truly describe the motion of the car.

[0067] Therefore, in order to solve the above problems, the present application proposes a path planning method, device, electronic device, vehicle, computer-readable storage medium and computer program product, aiming to provide a global curvature optimal path planning method for a track scene to improve the driving efficiency and speed of unmanned racing cars on the track.

[0068] Specifically, if Figure 1 As shown, the path planning method in the embodiment of the present application can be applied to a terminal device, which can be a mobile phone, tablet, computer, server, or other device, or a vehicle, without specific limitation. The method can include the following steps:

[0069] S10, based on the curvature determined for each group of adjacent sampling points on the sampling path within the lane, with minimizing the sum of the curvatures as an optimization goal, determining a lateral distribution weight for each sampling point, wherein the lateral distribution weight is used to indicate an offset distance of the sampling point in a direction perpendicular to the sampling path;

[0070] It should be noted that, in this embodiment, the track feature points are collected by GNSS equipment on the track site to generate Figure 2 The two-dimensional plane map of the track is shown, wherein the map may include the coordinate information of the left and right lane boundaries of the track.

[0071] On this basis, the vehicle can calculate the sum of the curvatures of all curvatures based on the curvature determined by each group of adjacent sampling points on the sampling path within the lane, and take the minimum sum of curvatures as the optimization goal to determine the lateral distribution weight of each sampling point.

[0072] It is understandable that there may be multiple sampling points on the sampling path. In this embodiment, the sampling points may be grouped, and multiple adjacent sampling points may be divided into a group of sampling points. The reciprocal of the radius of the circle formed by the multiple sampling points is the curvature of the group of sampling points.

[0073] The sampling path can be understood as the initial driving path. The driving path at this time needs to be further optimized to minimize the sum of the global curvature of the target path.

[0074] In addition, if Figure 3 As shown in the lane boundary, the sampling point on the sampling path may be at any position on the line between the corresponding boundary points of the left boundary line and the right boundary line. Therefore, the lateral distribution weight ω in this embodiment is i It can be used to indicate the offset distance of the sampling point in the direction perpendicular to the sampling path. In this way, this embodiment can determine the position of each sampling point based on the lateral distribution weight to generate the target path.

[0075] S20: Generate a target path according to the sampling path and the horizontal distribution weight.

[0076] In this embodiment, after calculating the lateral distribution weight of each sampling point, the vehicle can generate a target path according to the sampling path and the lateral distribution weight.

[0077] It can be understood that since the lateral distribution weight can represent the offset distance of the sampling point in the direction perpendicular to the sampling path, in this embodiment, the lateral offset distance of each sampling point compared to the sampling path can be determined based on the lateral distribution weight, and the sampling path can be corrected using the lateral offset distance to obtain the target path with the minimum global curvature sum.

[0078] Therefore, in this embodiment of the present application, the vehicle can use the minimum sum of the curvatures of the sampled paths as the optimization goal, determine the lateral distribution weights for each sampling point, and then, based on the lateral distribution weights and the sampled paths, determine the target path with the minimum sum of curvatures. Compared to existing path planning methods, the target path planned in this application ensures high-speed and stable steering, minimizing the time the vehicle spends on the global path.

[0079] In one embodiment, before the step of “determining the lateral distribution weight of each sampling point based on the curvature determined for each group of adjacent sampling points on the sampling path within the lane, with minimizing the sum of the curvatures as an optimization objective” in S10, the following steps may also be included:

[0080] S30, for each group of adjacent sampling points, setting the initial lateral distribution weight of each sampling point as a variable to be optimized, to obtain a curvature polynomial, wherein the curvature polynomial is the sum of the curvatures of the curvatures of each group of adjacent sampling points;

[0081] S40 , obtaining a minimum curvature sum according to the preset constraint condition of the initial lateral distribution weight and the curvature polynomial.

[0082] In this embodiment, if Figure 4 The sampling path shown in FIG. 1 includes multiple sampling points, and the sampling point P i =P i，0 +ω i (P i，1 -P i，0 ), where P i，0 、P i，1 is the edge point of the track, is a constant, and the initial lateral distribution weight ω i It is the key parameter that determines the location of the generated path point. If it is selected as the variable to be optimized, the vector of the variable x=(ω0ω1 … ω n-1 ω n ).

[0083] Then, the vehicle can generate a curvature polynomial curv according to the initial lateral distribution weights of the sampling points. The curvature polynomial is the sum of the curvatures of multiple groups of adjacent sampling points.

[0084] In this embodiment, the optimization goal is to minimize the sum of the curvatures of the global path to ensure the maximum average speed of the car. The curvatures of all sampling points on the track are summed to obtain the following objective function (i.e., the curvature polynomial in this embodiment):

[0085]

[0086] Furthermore, the vehicle can obtain the minimum sum of curvatures according to the preset constraints of the initial lateral distribution weight and the curvature polynomial.

[0087] Among them, since the generated path must be within the track, for each sampling point P i :

[0088] P i =P i，0 +ω i (P i，1 -P i，0 )

[0089] Among them, the initial horizontal distribution weight 0<ω i <1.

[0090] therefore,

[0091] On this basis, this application can be used to calculate the curvature polynomial By solving, we can get the global optimal solution of the horizontal distribution weight, which makes the curvature polynomial obtain the minimum value under the current constraints.

[0092] The coordinates of any sampling point can be obtained according to the global optimal solution of the lateral distribution weights, and the set of all sampling points is the path with the global minimum sum of curvatures.

[0093] In one embodiment, in the above S30, “setting the initial lateral distribution weight of each sampling point as a variable to be optimized to obtain a curvature polynomial” may include:

[0094] S301, obtaining position information corresponding to a plurality of sampling points according to the lane boundary line of the lane and the initial lateral distribution weights of the adjacent sampling points;

[0095] S302, determining a target circle based on position information corresponding to adjacent sampling points;

[0096] S303: Acquire a curvature polynomial according to the target circle and the position information.

[0097] In this embodiment, the vehicle may obtain position information corresponding to a plurality of sampling points based on the lane boundary line and the initial lateral distribution weights of adjacent sampling points.

[0098] It can be understood that, in this embodiment, Figure 5 The sampling path shown in FIG. 1 includes multiple sampling points, and the sampling point P i =P i，0 +ω i (P i，1 -P i，0 ), where P i，0 、P i，1 is the boundary point on the lane boundary line, and the boundary point P on the left boundary line i，0 and the boundary point P on the right boundary line i，1 Any point on the line between is a sampling point, where the initial horizontal distribution weight ω i ∈[0, 1], the initial horizontal distribution weight represents P i At two endpoints P i，0 and P i，1 The ratio of the distance between them.

[0099] The vehicle can then determine the target circle based on the position information corresponding to multiple adjacent sampling points.

[0100] It should be noted that, in this embodiment, if the number of each group of adjacent sampling points is 3, then three adjacent sampling points can determine a circle, such as Figure 6 As shown, three adjacent sampling points P0, P1, and P2 determine the circle O.

[0101] The vehicle can then construct a curvature polynomial based on the radius of the target circle and the location information of the sampling points.

[0102] In a specific embodiment, in the above S303, "obtaining a curvature polynomial according to the target circle and the position information" may include:

[0103] S3031: Obtain a first triangle and a second triangle according to a plurality of sampling points and the center of the target circle, where the first triangle and the second triangle are two similar triangles;

[0104] S3032: Obtain a curvature polynomial according to the radius of the target circle, position information corresponding to a plurality of sampling points, and a similarity relationship between the first triangle and the second triangle.

[0105] Combined with the above description, if Figure 5 The sampling path shown in FIG. 1 includes multiple sampling points, and the sampling point P i =P i，0 +ω i (P i，1 -P i，0 ).

[0106] If the coordinates collected by GNSS are used to identify the sampling point P i To express, such as Figure 6 , then the sampling point P i It can be expressed as:

[0107] x i =x i0 +ω i (x i1 -x i0 )

[0108] y i =y i0 +ω i (y i1 -y i0 )

[0109] It can be understood that, in this embodiment, since the step lengths between sampling points can be fixed and evenly distributed, Figure 6 As shown, any three adjacent points P0, P1, and P2 can determine a circle O.

[0110] at this time, It can be seen that triangle ΔOP0P1 and triangle ΔP0P1P3 are similar triangles to each other. According to the relationship between the corresponding sides of similar triangles, we can get:

[0111]

[0112] Where ΔS is the distance between two adjacent points, R is the radius of the circle determined by three points, and curv is the curvature.

[0113]

[0114]

[0115] For any three points P i-1 、P i 、P i+1

[0116]

[0117] Using road boundary sampling points can be expressed as:

[0118]

[0119] The square of the modulus can be represented by a matrix:

[0120]

[0121] Among them, const is a constant and there is no limitation on it.

[0122] In this embodiment, the standard form of the quadratic programming problem is:

[0123]

[0124] subject l≤Ax≤u

[0125] That is, the quadratic programming optimization problem is of quadratic form, and its constraints are of linear form. x is the variable to be optimized, which is an n-dimensional vector. P is the quadratic term coefficient, which is a positive definite matrix. q is the linear term coefficient, which is an n-dimensional vector. A is an mxn matrix, A is the linear term coefficient of the constraint function, m is the number of constraint functions, and l and u are the lower and upper boundaries of the constraint function, respectively.

[0126] Combined with the above description, the sampling point P i =P i，0 +ω i (P i，1 -P i，0 ), P i，0 、P i，1 is the edge point of the track, is a constant, and the lateral distribution weight ω iIt is the key parameter that determines the location of the generated path point. i is the optimization variable, then the vector of the optimization variable is:

[0127] x=(ω0 ω1 … ω n-1 ω n )

[0128] In this embodiment, the objective function is defined to minimize the sum of the curvatures of the global path to ensure the maximum average speed of the car. Therefore, the curvatures of all sampling points on the track are summed to obtain the following objective function (i.e., the curvature polynomial in this embodiment):

[0129]

[0130] Calculate the curvature at each point:

[0131]

[0132] Get the curvature polynomial:

[0133]

[0134] In one embodiment, in S301 above, “obtaining position information corresponding to the plurality of sampling points according to the lane boundary line of the lane and the initial lateral distribution weights of the adjacent sampling points” may include:

[0135] S3011, obtaining a reference point on the lane boundary line corresponding to the sampling point;

[0136] S3012: Acquire the position information of the sampling point according to the position information of the reference point and the initial horizontal distribution weight corresponding to the sampling point.

[0137] In one embodiment, the reference points include: a first reference point on the left boundary line of the lane corresponding to the sampling point, and a second reference point on the right boundary line of the lane corresponding to the sampling point; the first reference point, the sampling point and the second reference point are on the same straight line.

[0138] In this embodiment, combined with the above embodiment description, combined with the above description, as Figure 5 The sampling path shown in FIG. 1 includes multiple sampling points, and the sampling point P i =P i，0 +ω i (P i，1 -P i，0 ).

[0139] If the coordinates collected by GNSS are used to identify the sampling point P i To express, such as Figure 6 , then the sampling point P i It can be expressed as:

[0140] x i =x i0 +ω i (x i1 -x i0 )

[0141] y i =y i0 +ω i (y i1 -y i0 )

[0142] Among them, P i1 (x i1 ,y i1 ) and P i0 (x i0 ,y i0 ) are respectively on the left boundary line of the lane and the right boundary line of the lane and the sampling point P i The corresponding reference point.

[0143] It is understandable that if Figure 5 As shown, the sampling point P i Located in P i1 (x i1 ,y i1 ) and P i0 (x i0 ,y i0 ), that is, P i1 (x i1 ,y i1 ), P i and P i0 (x i0 ,y i0 ) are on the same straight line, and the initial horizontal distribution weight ω i Characterized by the expression in P i At two endpoints P i，0 and P i，1 The ratio of the distance between them.

[0144] In one embodiment, in the above S40, “obtaining the sum of the minimum curvatures according to the preset constraint conditions of the initial lateral distribution weight and the above” may include:

[0145] S401, optimizing the initial lateral distribution weight in the curvature polynomial according to preset constraints of the initial lateral distribution weight;

[0146] S402, until the minimum curvature sum of the curvature polynomial is obtained.

[0147] In this embodiment, combined with the above description, the sampling point P i =P i，0 +ω i (P i，1 -P i，0 ), P i，0 、P i，1 is the edge point of the track, is a constant, and the initial lateral distribution weight ω corresponding to each sampling point i It is the key parameter that determines the location of the generated path point. i is the optimization variable, then the vector of the optimization variable is:

[0148] x=(ω0 ω1 … ω n-1 ω n )

[0149] The goal of this embodiment is to minimize the sum of the curvatures of the global path to ensure the maximum average speed of the car. Therefore, the following objective function (i.e., the curvature polynomial in this embodiment) can be obtained by summing the curvatures of all sampling points:

[0150]

[0151] In this embodiment, the initial lateral distribution weight in the curvature polynomial can be optimized until the minimum curvature sum of the curvature polynomial is reached.

[0152] In one embodiment, in the above S20, “generating a target path according to the sampling path and the horizontal distribution weight” may include:

[0153] S201, obtaining offset distances of multiple target sampling points on the lane relative to the sampling path;

[0154] S202: Generate a target path according to the offset distance and the sampling path.

[0155] In this embodiment, if Figure 7 As shown, after calculating the lateral distribution weights of the sampling points, the vehicle can obtain the offset distances of multiple sampling points on the lane relative to the sampling path based on the lateral distribution weights, and then generate a target path based on the offset distances and the sampling path.

[0156] It is understandable that since the sampling point P i =P i，0 +ω i (P i，1 -P i，0 ), and P i，0 、P i，1 is the edge point of the track, which is actually a known constant. Therefore, the lateral distribution weight ωi After determining the sampling point P i The position of can be determined, so that the Figure 8 The target path with minimum global curvature is shown.

[0157] In one embodiment, before the above S10, "determining the lateral distribution weight of each sampling point based on the curvature determined for each group of adjacent sampling points on the sampling path within the lane, with minimizing the sum of the curvatures as an optimization goal," the following steps may also be included:

[0158] S50, acquiring a plurality of boundary sampling points on the lane boundary line of the lane;

[0159] S60, acquiring a plurality of centerline sampling points on the centerline of the lane according to the plurality of boundary sampling points;

[0160] S70: Determine a plurality of sampling points on a sampling path according to the centerline sampling point and the lane boundary line.

[0161] In this embodiment, if Figure 3 As shown, the left and right boundary lines of the track can be sampled. In this embodiment, an appropriate distance can be selected as the step length according to the actual scenario to generate a series of track edge sampling points.

[0162] Then, the two points on the left and right boundary lines of the lane are interpolated at equal intervals to obtain the sampling points of the track center line. A cubic polynomial is used to fit the sampling points of the track center to obtain the global center line of the track y = ax 3 +bx 2 +cx+d, such as Figure 4 As shown, the global center line can be sampled at equal intervals to obtain evenly distributed and equally spaced center line sampling points.

[0163] Then, multiple sampling points on the sampling path can be determined based on the centerline sampling point and the lane boundary line.

[0164] In a specific embodiment, in the above S60, “acquiring a plurality of centerline sampling points on the centerline of the lane according to the plurality of boundary sampling points” may include:

[0165] S601, acquiring a first boundary sampling point on the left boundary line of the lane, and a second boundary sampling point on the right boundary line of the lane corresponding to the first boundary sampling point;

[0166] S602: Obtain a midpoint of a line connecting the first boundary sampling point and the second boundary sampling point, and use the midpoint as a midline sampling point.

[0167] In this embodiment, the sampling point P i =P i，0+ω i (P i，1 -P i，0 ), and P i，0 is the first boundary sampling point on the left boundary line, and P i，1 is the second boundary sampling point on the right boundary line. The first boundary sampling point corresponds to the second boundary sampling point, that is, the sampling step lengths of the two boundary points are consistent.

[0168] In a specific embodiment, in the above S70, “determining multiple sampling points on the sampling path according to the centerline sampling point and the lane boundary line” may include:

[0169] S701, obtaining a first intersection point of a perpendicular line of the centerline sampling point and a left lane boundary line, and a second intersection point of a perpendicular line of the centerline sampling point and a right lane boundary line;

[0170] S702: Set any point on the line connecting the first intersection point and the second intersection point as a sampling point on the sampling path.

[0171] In this embodiment, a perpendicular line is drawn from the heading of the centerline sampling point to the left and right lane boundary lines, and two intersection points P on the left and right where the perpendicular line intersects the lane boundary lines are obtained. i，0 and P i，1 , then the two intersection points P i，0 and P i，1 Any point on the line can be represented as:

[0172] P i =P i，0 +ω i (P i，1 -P i，0 )

[0173] P i This is the sampling point in this embodiment.

[0174] Therefore, in the embodiment of the present application, an approximate curvature expression is constructed by the positional relationship of three consecutive sampling points, the lateral distribution weight of each point is selected as the optimization variable, the weight value range is the constraint condition, the cost function is the sum of the curvatures of all points represented by the weight coefficient, and the solution result is the lateral weight of each point, which effectively solves the problem of planning the optimal curvature path in the track scenario. By constructing the cost function and the constraint condition, the path with the optimal global curvature is planned according to the actual characteristics of the track, which improves the speed of the car on the track, effectively shortens the time, and thus effectively improves the overall track performance.

[0175] Accordingly, the present application also provides a path planning device, such as Figure 9 As shown, the device may include:

[0176] Determination module 1001, configured to determine a lateral distribution weight for each sampling point based on the curvature determined for each group of adjacent sampling points on the sampling path within the lane, with minimizing the sum of the curvatures as an optimization objective, wherein the lateral distribution weight indicates an offset distance of the sampling point in a direction perpendicular to the sampling path;

[0177] The generating module 1002 is configured to generate a target path according to the sampling path and the horizontal distribution weight.

[0178] Optionally, the path planning device in the present application further includes:

[0179] A first acquisition module is configured to set, for each group of adjacent sampling points, an initial lateral distribution weight of each sampling point as a variable to be optimized, to obtain a curvature polynomial, wherein the curvature polynomial is the sum of the curvatures of multiple groups of adjacent sampling points;

[0180] The second acquisition module is configured to acquire the sum of the minimum curvatures according to the preset constraint conditions of the initial lateral distribution weights and the curvature polynomial.

[0181] Optionally, the first acquisition module is further configured to:

[0182] Obtaining position information corresponding to a plurality of the sampling points according to the lane boundary line of the lane and the initial lateral distribution weights of the adjacent sampling points;

[0183] Determining a target circle based on position information corresponding to adjacent sampling points;

[0184] A curvature polynomial is obtained according to the target circle and the position information.

[0185] Optionally, the first acquisition module is further configured to:

[0186] Acquire a first triangle and a second triangle according to a plurality of adjacent sampling points and the target circle, wherein the first triangle and the second triangle are two similar triangles;

[0187] A curvature polynomial is obtained according to the radius of the target circle, position information corresponding to a plurality of adjacent sampling points, and a similarity relationship between the first triangle and the second triangle.

[0188] Optionally, the first acquisition module is further configured to:

[0189] Obtain a reference point on the lane boundary line corresponding to the sampling point;

[0190] The position information of the sampling point is acquired according to the position information of the reference point and the initial lateral distribution weight corresponding to the sampling point.

[0191] Optionally, the reference points include: a first reference point on the left boundary line of the lane corresponding to the sampling point, and a second reference point on the right boundary line of the lane corresponding to the sampling point; the first reference point, the sampling point and the second reference point are in the same straight line.

[0192] Optionally, the second acquisition module is further configured to:

[0193] Optimizing the initial lateral distribution weight in the curvature polynomial according to preset constraints of the initial lateral distribution weight;

[0194] Until the minimum curvature sum of the curvature polynomial is obtained.

[0195] Optionally, the generation module is also used to:

[0196] Obtaining an offset distance of the sampling point relative to the sampling path according to the lateral distribution weight;

[0197] A target path is generated according to the offset distance and the sampling path.

[0198] Optionally, the path planning device in the present application further includes:

[0199] a first sampling point acquisition module, configured to acquire a plurality of boundary sampling points on a lane boundary line of the lane;

[0200] a second sampling point acquisition module, configured to acquire a plurality of centerline sampling points on the centerline of the lane according to the plurality of boundary sampling points;

[0201] The sampling point determination module is used to determine multiple sampling points on the sampling path according to the centerline sampling point and the lane boundary line.

[0202] Optionally, the lane boundary line includes a left lane boundary line and a right lane boundary line;

[0203] The sampling point determination module is also used to:

[0204] Obtaining a first intersection point of a perpendicular line of the centerline sampling point and a left lane boundary line, and a second intersection point of a perpendicular line of the centerline sampling point and a right lane boundary line;

[0205] Any point on the line connecting the first intersection point and the second intersection point is set as a sampling point on the sampling path.

[0206] Optionally, the sampling point second acquisition module is further configured to:

[0207] Acquire, according to a preset sampling step, a first boundary sampling point on the left boundary line of the lane and a second boundary sampling point on the right boundary line of the lane corresponding to the first boundary sampling point;

[0208] Obtain a midpoint of a line connecting the first boundary sampling point and the second boundary sampling point, and use the midpoint as a midline sampling point.

[0209] The specific implementation of the above operations can be found in the previous embodiments and will not be repeated here.

[0210] Accordingly, the embodiment of the present application further provides an electronic device, such as Figure 10 As shown, Figure 10 Schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device 1100 includes a processor 1101 having one or more processing cores, a memory 1102 having one or more computer-readable storage media, and a computer program stored in the memory 1102 and executable on the processor. The processor 1101 is electrically connected to the memory 1102. Those skilled in the art will understand that the vehicle structure shown in the figure does not constitute a limitation of the vehicle, and may include more or fewer components than shown, or combine certain components, or arrange the components differently.

[0211] The processor 1101 is the control center of the electronic device 1100. It connects the various parts of the entire electronic device 1100 using various interfaces and lines. By running or loading software programs and / or units stored in the memory 1102 and calling data stored in the memory 1102, it executes various functions of the electronic device 1100 and processes data, thereby monitoring the electronic device 1100 as a whole. The processor 1101 can be a processor (Central Processing Unit, CPU), a graphics processing unit (GPU), a network processor (Network Processor, NP), etc., and can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of this application.

[0212] In the embodiment of the present application, the processor 1101 in the electronic device 1100 loads instructions corresponding to one or more application processes into the memory 1102 according to the following steps, and the processor 1101 runs the application stored in the memory 1102 to implement various functions, such as:

[0213] Based on the curvature determined for each group of adjacent sampling points on the sampling path within the lane, minimizing the sum of the curvatures is used as an optimization goal to determine a lateral distribution weight for each sampling point, wherein the lateral distribution weight is used to indicate an offset distance of the sampling point in a direction perpendicular to the sampling path;

[0214] A target path is generated according to the sampling path and the lateral distribution weight.

[0215] The specific implementation of the above operations can be found in the previous embodiments and will not be repeated here.

[0216] Optional, such as Figure 10 As shown, the electronic device 1100 further includes: a touch screen 1103, a radio frequency circuit 1104, an audio circuit 1105, an input unit 1106, and a power supply 1107. Among them, the processor 1101 is electrically connected to the touch screen 1103, the radio frequency circuit 1104, the audio circuit 1105, the input unit 1106, and the power supply 1107 respectively. Those skilled in the art will understand that Figure 7 The vehicle structure shown in the figure does not constitute a limitation to the vehicle, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0217] The touch display screen 1103 can be used to display a graphical user interface and receive operation instructions generated by the user acting on the graphical user interface. The touch display screen 1103 may include a display panel and a touch panel. Among them, the display panel can be used to display information input by the user or information provided to the user and various graphical user interfaces of the vehicle, which can be composed of graphics, text, icons, videos and any combination thereof. Optionally, the display panel can be configured in the form of a liquid crystal display (LCD), an organic light-emitting diode (OLED), etc. The touch panel can be used to collect user touch operations on or near it (such as operations performed by the user using any suitable object or accessory such as a finger, stylus, etc. on or near the touch panel), and generate corresponding operation instructions, and the operation instructions execute corresponding programs. Optionally, the touch panel may include two parts: a touch display system and a touch controller. Among them, the touch display system detects the user's touch direction, detects the signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch display system, converts it into touch point coordinates, and then sends it to the processor 1101, and can receive commands sent by the processor 1101 and execute them. The touch panel can cover the display panel. When the touch panel detects a touch operation on or near it, it is transmitted to the processor 1101 to determine the type of touch event. The processor 1101 then provides a corresponding visual output on the display panel according to the type of touch event. In an embodiment of the present application, the touch panel and the display panel can be integrated into the touch display screen 1103 to realize input and output functions. However, in some embodiments, the touch panel and the touch panel can be used as two independent components to realize input and output functions. That is, the touch display screen 1103 can also be used as part of the input unit 1106 to realize the input function.

[0218] The RF circuit 1104 may be used to transmit and receive RF signals, thereby establishing wireless communication with network devices or other vehicles through wireless communication, and transmitting and receiving signals with network devices or other vehicles.

[0219] Audio circuit 1105 can be used to provide an audio interface between the user and the vehicle through a speaker and microphone. Audio circuit 1105 converts received audio data into electrical signals and transmits them to the speaker, which then converts them into sound signals for output. The microphone, on the other hand, converts collected sound signals into electrical signals, which are received by audio circuit 1105 and converted into audio data. This audio data is then output to processor 1101 for processing, then transmitted via RF circuit 1104 to, for example, another vehicle, or to memory 1102 for further processing. Audio circuit 1105 may also include an earphone jack to allow communication between an external headset and the vehicle.

[0220] The input unit 1106 may be configured to receive input digital, character information, or user feature information (such as fingerprint, iris, or facial information), and to generate keyboard, mouse, joystick, optical, or trackball signal input related to user settings and function control.

[0221] Power supply 1107 is used to supply power to various components of electronic device 1100. Optionally, power supply 1107 can be logically connected to processor 1101 via a power management device, thereby enabling the power management device to manage charging, discharging, and power consumption. Power supply 1107 can also include one or more DC or AC power supplies, a recharging device, a power failure detection circuit, a power converter or inverter, a power status indicator, and other arbitrary components.

[0222] although Figure 10 Not shown, the electronic device 1100 may further include a camera, a sensor, a wireless fidelity module, a Bluetooth module, etc., which will not be described in detail here.

[0223] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0224] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be accomplished by instructions, or by controlling related hardware through instructions. The instructions may be stored in a computer-readable storage medium and loaded and executed by a processor.

[0225] To this end, an embodiment of the present application provides a computer-readable storage medium storing a plurality of computer programs. The computer programs can be loaded by a processor to execute any one of the path planning methods provided in the embodiments of the present application. The computer programs can execute the following steps of the path planning method:

[0226] Based on the curvature determined for each group of adjacent sampling points on the sampling path within the lane, minimizing the sum of the curvatures is used as an optimization goal to determine a lateral distribution weight for each sampling point, wherein the lateral distribution weight is used to indicate an offset distance of the sampling point in a direction perpendicular to the sampling path;

[0227] A target path is generated according to the sampling path and the lateral distribution weight.

[0228] The specific implementation of the above operations can be found in the previous embodiments and will not be repeated here.

[0229] The computer-readable storage medium may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0230] Since the computer program stored in the computer-readable storage medium can execute any path planning method provided in the embodiments of the present application, the beneficial effects that can be achieved by any path planning method provided in the embodiments of the present application can be achieved. Please refer to the previous embodiments for details and will not be repeated here.

[0231] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0232] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable path planning device to produce a machine, so that the instructions executed by the processor of the computer or other programmable path planning device generate instructions for implementing the process in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0233] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable path planning device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device that implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0234] These computer program instructions may also be loaded onto a computer or other programmable path planning device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable device to implement the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0235] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0236] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0237] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology for information storage. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media such as modulated communication signals and carrier waves.

[0238] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more features. In the description of this application, "plurality" means two or more, unless otherwise specifically defined.

[0239] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0240] The embodiments, implementation methods and related technical features of the present application can be combined and replaced with each other without conflict.

[0241] The above are merely preferred embodiments of the present application and do not constitute any form of limitation to the present application. However, any simple modifications, equivalent changes, and modifications made to the above embodiments based on the technical essence of the present application without departing from the content of the technical solution of the present application are still within the scope of the technical solution of the present application.

Claims

1. A path planning method, characterized in that: The method comprises: Based on the curvature determined for each group of adjacent sampling points on the sampling path within the lane, minimizing the sum of the curvatures is used as an optimization goal to determine a lateral distribution weight for each sampling point, wherein the lateral distribution weight is used to indicate an offset distance of the sampling point in a direction perpendicular to the sampling path; A target path is generated according to the sampling path and the lateral distribution weight.

2. The path planning method according to claim 1, characterized in that: Before determining the lateral distribution weight of each sampling point based on the curvature determined for each group of adjacent sampling points on the sampling path within the lane and taking the minimum sum of the curvatures as the optimization goal, the method further includes: For each group of adjacent sampling points, the initial lateral distribution weight of each sampling point is set as a variable to be optimized to obtain a curvature polynomial, wherein the curvature polynomial is the sum of the curvatures of multiple groups of adjacent sampling points; The minimum curvature sum is obtained according to the preset constraint condition of the initial lateral distribution weight and the curvature polynomial.

3. The path planning method according to claim 2, characterized in that: The initial lateral distribution weight of each sampling point is set as a variable to be optimized to obtain a curvature polynomial, including: Obtaining position information corresponding to a plurality of the sampling points according to the lane boundary line of the lane and the initial lateral distribution weights of the adjacent sampling points; Determining a target circle based on position information corresponding to adjacent sampling points; A curvature polynomial is obtained according to the target circle and the position information.

4. The path planning method according to claim 3, characterized in that: The obtaining of a curvature polynomial according to the target circle and the position information includes: Acquire a first triangle and a second triangle according to a plurality of adjacent sampling points and the target circle, wherein the first triangle and the second triangle are two similar triangles; A curvature polynomial is obtained according to the radius of the target circle, position information corresponding to a plurality of adjacent sampling points, and a similarity relationship between the first triangle and the second triangle.

5. The path planning method according to claim 3, characterized in that: The acquiring, based on the lane boundary line of the lane and the initial lateral distribution weights of the adjacent sampling points, position information corresponding to the plurality of sampling points includes: Obtain a reference point on the lane boundary line corresponding to the sampling point; The position information of the sampling point is acquired according to the position information of the reference point and the initial lateral distribution weight corresponding to the sampling point.

6. The path planning method according to claim 5, characterized in that: The reference points include: a first reference point on the left boundary line of the lane corresponding to the sampling point, and a second reference point on the right boundary line of the lane corresponding to the sampling point; the first reference point, the sampling point, and the second reference point are in the same straight line.

7. The path planning method according to claim 2, characterized in that: The obtaining of the minimum curvature sum according to the preset constraint condition of the initial lateral distribution weight and the curvature polynomial includes: Optimizing the initial lateral distribution weight in the curvature polynomial according to preset constraints of the initial lateral distribution weight; Until the minimum curvature sum of the curvature polynomial is obtained.

8. The path planning method according to any one of claims 1 to 7, characterized in that: Generating a target path according to the sampling path and the lateral distribution weight includes: Obtaining an offset distance of the sampling point relative to the sampling path according to the lateral distribution weight; A target path is generated according to the offset distance and the sampling path.

9. The path planning method according to claim 1, wherein: The curvature determined based on each group of adjacent sampling points on the sampling path within the lane, with the sum of the curvatures being minimized as an optimization goal, before determining the lateral distribution weight of each sampling point, the method includes: Acquire a plurality of boundary sampling points on a lane boundary line of the lane; Acquire a plurality of centerline sampling points on the centerline of the lane according to the plurality of boundary sampling points; A plurality of sampling points on a sampling path are determined according to the centerline sampling point and the lane boundary line.

10. The path planning method according to claim 9, characterized in that: The lane boundary line includes a lane left boundary line and a lane right boundary line; The step of determining a plurality of sampling points on a sampling path according to the centerline sampling point and the lane boundary line includes: Obtaining a first intersection point of a perpendicular line of the centerline sampling point and a left lane boundary line, and a second intersection point of a perpendicular line of the centerline sampling point and a right lane boundary line; Any point on the line connecting the first intersection point and the second intersection point is set as a sampling point on the sampling path.

11. The path planning method according to claim 10, characterized in that: The step of acquiring a plurality of centerline sampling points on the centerline of the lane according to the plurality of boundary sampling points includes: Acquire, according to a preset sampling step, a first boundary sampling point on the left boundary line of the lane and a second boundary sampling point on the right boundary line of the lane corresponding to the first boundary sampling point; Obtain a midpoint of a line connecting the first boundary sampling point and the second boundary sampling point, and use the midpoint as a midline sampling point.

12. A path planning device, characterized in that: The path planning device comprises: a determination module configured to determine, based on the curvature determined for each group of adjacent sampling points on the sampling path within the lane, a lateral distribution weight for each sampling point, with minimizing the sum of the curvatures as an optimization objective, wherein the lateral distribution weight is used to indicate an offset distance of the sampling point in a direction perpendicular to the sampling path; A generation module is used to generate a target path according to the sampling path and the horizontal distribution weight.

13. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor is enabled to perform the method according to any one of claims 1 to 11.

14. A vehicle, characterized in that: The vehicle includes the electronic device according to claim 13.

15. A computer-readable storage medium, characterized in that The method comprises a computer program. When the computer program is run on an electronic device, the computer program is used to enable the electronic device to execute the method according to any one of claims 1 to 11.

16. A computer program product, characterized in that The method comprises a computer program stored in a computer-readable storage medium; when a processor of an electronic device reads the computer program from the computer-readable storage medium, the processor executes the computer program, so that the electronic device executes any one of the methods described in claims 1 to 11.

Images