Intelligent driving simulation road model generation method and related equipment

Abstract

The invention discloses an intelligent driving simulation road model generation method and related equipment, and relates to the field of vehicle simulation, and the method comprises the steps: generating a corresponding offset line based on an offset reference datum line discrete point set and an offset distance through a datum line offset module; generating boundary lines of different lanes based on the offset line through a road generation module; and generating a simulation road model based on all the offset lines and all the boundary lines.

Description

Technical Field

[0001] The present invention relates to the field of vehicle simulation, and more specifically, to a method for generating a road model for intelligent driving simulation and related equipment. Background Art

[0002] With the development of smart cars, driverless and assisted driving have become important functional configurations of vehicles. The development of driverless or assisted driving includes three functional modules: environment perception, path planning and decision-making, and vehicle control. However, when integrating environment perception, path planning and decision-making, and vehicle control, it is necessary to use a road model to test the performance and functions of these three functional modules after integration. The current road model has problems such as complex model, slow generation time, and uneven roads. Summary of the invention

[0003] The present disclosure aims to solve at least one of the technical problems existing in the prior art or related art.

[0004] In view of this, in a first aspect, an embodiment of the present disclosure proposes a method for generating an intelligent driving simulation road model, comprising:

[0005] Generate a corresponding offset line based on the offset reference baseline discrete point set and the offset distance through the baseline offset module;

[0006] Generate boundary lines of different lanes based on the above offset lines through a road generation module;

[0007] A simulated road model is generated based on all of the above offset lines and all of the above boundary lines.

[0008] In a feasible implementation, the above-mentioned baseline offset module generates a corresponding offset line based on the offset reference baseline discrete point set and the offset distance, including:

[0009] Get the offset reference baseline discrete point set and offset distance;

[0010] Detect whether there are any overlapping points in the above-mentioned offset reference baseline discrete point set, and remove redundant overlapping points to form an offset reference optimization baseline discrete point set;

[0011] Calculate the total number of discrete point elements in the above-mentioned offset reference optimization baseline discrete point set;

[0012] Determine an original set by using the normal vectors of all points in the above-mentioned offset reference optimized baseline discrete point set at corresponding points and the above-mentioned offset distance, wherein the above-mentioned normal vectors include a single normal vector and two normal vectors;

[0013] Calculate the minimum distance between each point in the original set after discrete point offset and the offset reference optimized baseline discrete point set, retain the discrete points in the original set after discrete point offset whose minimum distance is greater than or equal to the minimum distance, and form all the retained points into the optimized set after discrete point offset;

[0014] The quadratic programming method is used to optimize and average the above-mentioned optimized set of discrete points after offset to form a final set of offset discrete points, and a corresponding offset line is generated based on the above-mentioned final set of discrete points.

[0015] In a feasible implementation, when the normal vector is a single normal vector,

[0016] The above-mentioned original set is determined by combining the normal vectors of all points in the above-mentioned offset reference optimized baseline discrete point set at the corresponding points and the above-mentioned offset distance, including:

[0017] Selecting each group of three adjacent discrete points of the offset reference optimization baseline in the above-mentioned discrete point set of the offset reference optimization baseline to perform collinearity judgment;

[0018] When the collinearity judgment result is collinear, the offset point coordinates of the middle discrete point of the offset reference optimization baseline in each group are calculated;

[0019] When the middle discrete point of the offset reference optimization baseline in each of the above groups is not the starting point or the end point, the collinearity judgment and offset point coordinate calculation operations of the next group are continued to obtain the first element in the above original set.

[0020] In a feasible implementation, it also includes:

[0021] When the collinearity judgment result is non-collinearity, the outer circle center coordinates of the circumscribed circle formed by each group of three adjacent discrete points of the offset reference optimization baseline are calculated;

[0022] Calculate the vector coordinates and the modulus length of the line connecting the above circumscribed circle and the offset point of the offset reference optimization baseline discrete point in the middle of each group;

[0023] The offset point coordinates of the middle offset reference optimization baseline discrete point in each group are calculated based on the above-mentioned vector coordinates, the above-mentioned modulus, the above-mentioned offset distance and the coordinates of the middle offset reference optimization baseline discrete point in each group to obtain the second element in the above-mentioned original set.

[0024] In a feasible implementation, it also includes:

[0025] When the collinearity judgment result is collinear, the offset point coordinates of the middle discrete point of the offset reference optimization baseline in each group are calculated;

[0026] In the case where the middle discrete point of the offset reference optimization baseline in each of the above groups is the starting point or the end point, the offset point coordinates of the above starting point or the end point are calculated to obtain the third element in the above original set.

[0027] In a feasible implementation, when the normal vector is two normal vectors,

[0028] The above-mentioned original set is determined by combining the normal vectors of all points in the above-mentioned offset reference optimized baseline discrete point set at the corresponding points and the above-mentioned offset distance, including:

[0029] A first vector and a second vector are established based on each group of three adjacent offset reference optimized baseline discrete points in the offset reference optimized baseline discrete point set, wherein the middle point in each group of three adjacent offset reference optimized baseline discrete points is the starting point of the first vector and is the end point of the second vector;

[0030] Calculate a first unit normal vector of the first vector;

[0031] Calculate a second unit normal vector of the second vector;

[0032] Performing an offset based on the offset distance according to the first unit normal vector to obtain a first excessive offset point;

[0033] Performing an offset based on the offset distance according to the second unit normal vector to obtain a second excessive offset point;

[0034] Performing collinearity judgment on the first vector and the second vector to obtain a collinearity judgment result;

[0035] When the collinearity determination result is collinearity, the first over-offset point and the second over-offset point are used as the fourth element of the original set.

[0036] In a feasible implementation, it also includes:

[0037] When the collinearity determination result is non-collinearity, a first straight line is established using the first unit normal vector and the first transition point;

[0038] Establishing a second straight line using the second unit normal vector and the second over-offset point;

[0039] The coordinates of the intersection of the first straight line and the second straight line are calculated, and the coordinates of the intersection are used as the fifth element of the original set.

[0040] In a feasible implementation, it also includes:

[0041] Determine the starting point offset coordinates based on the starting point horizontal coordinate, the offset direction and the above offset distance;

[0042] Determine the end point offset coordinates based on the end point horizontal coordinate, the offset direction and the above offset distance;

[0043] The starting point offset coordinates and the end point offset coordinates are determined as the sixth element of the original set.

[0044] In a feasible implementation manner, the above-mentioned generation of boundary lines of different lanes based on the above-mentioned offset lines by the road generation module includes:

[0045] Generate multiple B-spline curves based on the coordinates of multiple randomly generated control points to generate a lane center reference line;

[0046] Boundary lines of different lanes are generated based on the lane center reference line and the offset line.

[0047] In a second aspect, the present disclosure also provides an intelligent driving simulation road model generation device, including:

[0048] A first generating unit, configured to generate a corresponding offset line based on an offset reference baseline discrete point set and an offset distance through a baseline offset module;

[0049] A second generating unit, configured to generate boundary lines of different lanes based on the offset lines through a road generating module;

[0050] The third generating unit is used to generate a simulated road model based on all the above offset lines and all the above boundary lines.

[0051] In the third aspect, an embodiment of the present disclosure further proposes an electronic device, comprising: a memory, a processor, and a computer program stored in the above-mentioned memory and executable on the above-mentioned processor, wherein the above-mentioned processor is used to implement the steps of the intelligent driving simulation road model generation method as any one of the above-mentioned first aspects when executing the computer program stored in the memory.

[0052] In a fourth aspect, an embodiment of the present disclosure further proposes a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for generating a road model for intelligent driving simulation according to any one of the first aspects is implemented.

[0053] In summary, the intelligent driving simulation road model generation method of the embodiment of the present disclosure includes: generating a corresponding offset line based on a discrete point set and an offset distance of an offset reference baseline by a baseline offset module; generating boundary lines of different lanes based on the above offset line by a road generation module; generating a simulation road model based on all the above offset lines and all the above boundary lines. Compared with the existing road model generation method, the present disclosure generates offset lines and lane boundary lines in steps through a baseline offset module and a road generation module, which effectively reduces the complexity of the model. Through the baseline offset method, a simulation road model that conforms to the actual road can be quickly generated, avoiding the common problem of complex and difficult to manage models in the background technology. Since the present disclosure adopts a combination of a discrete point set and an offset distance, the calculation process of road generation is simplified, and a complete road model can be generated in a short time. Compared with the problem of slow generation time in the background technology, the present disclosure significantly improves the efficiency of model generation, thereby accelerating the development progress of unmanned driving and assisted driving systems. The present disclosure ensures the smoothness of the generated road boundary lines and simulation road models through an offset generation method based on a reference baseline. In the background technology, the problem of uneven roads is prone to occur due to the insufficient optimization of the model generation method. The present disclosure ensures that the generated road model has higher smoothness by accurately controlling the offset distance and the position of discrete points, which is conducive to the integrated testing of environmental perception, path planning and vehicle control modules. The present disclosure not only supports the generation of single-lane roads, but also can easily generate multi-lane boundary lines through the road generation module to adapt to the needs of complex traffic environments. Compared with the traditional method that can only handle simple road models, this solution has a stronger simulation capability for multi-lane and complex traffic conditions, and provides better support for the comprehensive testing of unmanned driving and assisted driving systems. Through the present disclosure, the problems of complex road model generation, long time consumption and unevenness in the current technology can be solved, and a simulation road model suitable for unmanned driving and assisted driving development can be generated more efficiently, thereby improving the efficiency and quality of system development and testing.

[0054] The intelligent driving simulation road model generation method proposed in the present disclosure, and other advantages, objectives and features of the present disclosure will be reflected in part through the following description, and in part will also be understood by technical personnel in the field through research and practice of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present specification. Also, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0056] Figure 1A schematic diagram of a process for generating a road model for intelligent driving simulation provided by an embodiment of the present disclosure;

[0057] Figure 2 A schematic diagram of a reference baseline offset module workflow provided by an embodiment of the present disclosure;

[0058] Figure 3 A schematic diagram of the process of obtaining the original set of discrete points after offset by performing an offset in a single normal vector direction provided in an embodiment of the present disclosure;

[0059] Figure 4 A schematic diagram of the process of obtaining an original set of discrete points after offset by calculating the intersection of two straight lines after offsetting two normal vector directions provided in an embodiment of the present disclosure;

[0060] Figure 5 A schematic diagram of a process for obtaining an optimized set after discrete point offset provided by an embodiment of the present disclosure;

[0061] Figure 6 A schematic diagram of the workflow of a road feature generation module provided in an embodiment of the present disclosure;

[0062] Figure 7 A scenario schematic diagram of a two-lane simulated road model generated according to an embodiment of the present disclosure;

[0063] Figure 8 A structural schematic diagram of an intelligent driving simulation road model generation proposed in an embodiment of the present disclosure;

[0064] Fig. 9 A structural schematic diagram of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0065] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices. The technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments.

[0066] See also Figure 1 , which is a schematic diagram of a process of generating a road model for intelligent driving simulation provided by an embodiment of the present disclosure, and may specifically include:

[0067] S110, generating a corresponding offset line based on the offset reference baseline discrete point set and the offset distance through a baseline offset module;

[0068] Exemplarily, the baseline offset module generates a corresponding offset line based on the input offset reference baseline and its discrete point set, combined with a preset offset distance. The offset reference baseline can be a road centerline or other key design benchmark. A new offset line is constructed by applying the offset distance at each discrete point. The shape of the offset line will depend on the geometric characteristics of the reference baseline and the given offset parameters.

[0069] S120, generating boundary lines of different lanes based on the offset lines by a road generation module;

[0070] Exemplarily, in this step, the road generation module uses the generated offset lines to further construct the boundary lines of different lanes. The specific operation is to set different lane width and other parameters based on each offset line to generate the boundary line of each lane. In this process, the road generation module will adjust the generated boundary line according to the lane type (such as main lane, auxiliary lane, etc.) to make it meet the actual road design requirements.

[0071] S130: Generate a simulated road model based on all the offset lines and all the boundary lines.

[0072] For example, based on all generated offset lines and lane boundary lines, a complete simulated road model is constructed through a simulation tool. This model will integrate all previously generated line data to form a simulation environment with real road geometry features for subsequent simulation or testing.

[0073] In summary, compared with the existing road model generation method, the present disclosure generates offset lines and lane boundary lines in steps through the baseline offset module and the road generation module, which effectively reduces the complexity of the model. Through the baseline offset method, a simulated road model that conforms to the actual road can be quickly generated, avoiding the common problem of complex and difficult to manage models in the background technology. Since the present disclosure adopts a combination of discrete point sets and offset distances, the calculation process of road generation is simplified, and a complete road model can be generated in a short time. Compared with the problem of slow generation time in the background technology, the present disclosure significantly improves the efficiency of model generation, thereby accelerating the development progress of unmanned driving and assisted driving systems. The present disclosure ensures the smoothness of the generated road boundary lines and simulated road models through an offset generation method based on a reference baseline. In the background technology, due to the insufficient optimization of the model generation method, the problem of uneven roads is prone to occur, and the present disclosure ensures that the generated road model has higher smoothness by accurately controlling the offset distance and the position of the discrete points, which is conducive to the integrated testing of environmental perception, path planning and vehicle control modules. The present disclosure not only supports the generation of single-lane roads, but also can easily generate multi-lane boundary lines through the road generation module to adapt to complex traffic environment requirements. Compared with the traditional method that can only handle simple road models, this solution has a stronger simulation capability for multi-lane and complex traffic conditions, providing better support for comprehensive testing of unmanned driving and assisted driving systems. Through this disclosure, the problems of complex, time-consuming and uneven road model generation in current technologies can be solved, and simulation road models suitable for unmanned driving and assisted driving development can be generated more efficiently, thereby improving the efficiency and quality of system development and testing.

[0074] In some examples, such as Figure 2 The figure is a schematic diagram of the workflow of a reference baseline offset module provided by an embodiment of the present disclosure. The above step S110 generates a corresponding offset line based on a discrete point set of the offset reference baseline and an offset distance through the baseline offset module, including:

[0075] S1101. Obtain a discrete point set of an offset reference baseline and an offset distance.

[0076] Exemplarily, the offset reference baseline discrete point set PR={(XR(i), YR(i))} and the offset distance d are obtained.

[0077] Where: PR is the set of discrete points of the offset reference baseline;

[0078] XR(i) is the horizontal coordinate of the i-th discrete point in the discrete point set of the offset reference baseline;

[0079] YR(i) is the ordinate of the i-th discrete point in the discrete point set of the offset reference baseline; d is the offset distance of the offset reference baseline.

[0080] S1102, detecting whether there are any overlapping points in the above-mentioned offset reference baseline discrete point set, and removing redundant overlapping points to form an offset reference optimization baseline discrete point set.

[0081] Exemplarily, it is detected whether there are any overlapping points in the offset reference baseline discrete point set, and redundant overlapping points are eliminated to form the offset reference optimization baseline discrete point set PRR={(XR(j), YR(j))}.

[0082] Where: PRR is the set of discrete points of the offset reference optimization baseline;

[0083] XR(j) is the horizontal coordinate of the jth discrete point in the discrete point set of the offset reference optimization baseline;

[0084] YR(j) is the ordinate of the jth discrete point in the discrete point set of the offset reference optimization baseline.

[0085] Furthermore, we also set PRR = {(XR(k), YR(k))}.

[0086] Where: XR(k) is the horizontal coordinate of the kth discrete point in the discrete point set of the offset reference optimization baseline;

[0087] YR(k) is the ordinate of the kth discrete point in the discrete point set of the offset reference optimization baseline.

[0088] S1103, calculating the total number of discrete point elements in the discrete point set of the offset reference optimization baseline.

[0089] Exemplarily, the total number N of discrete point elements in the offset reference optimization baseline discrete point set PRR={(XR(j), YR(j))} is calculated.

[0090] S1104, determining an original set of normal vectors of all points in the above-mentioned offset reference optimized baseline discrete point set at corresponding points and the above-mentioned offset distance, wherein the above-mentioned normal vector includes a single normal vector and two normal vectors;

[0091] Exemplarily, all points in the offset reference optimized baseline discrete point set PRR = {(XR(j), YR(j))} are offset by d in the single normal vector direction at the corresponding point, or all points in the offset reference optimized baseline discrete point set PRR = {(XR(j), YR(j))} are offset by d in two normal vector directions and then the intersection of two straight lines is calculated to obtain the original set PP after the discrete points are offset. It is preferred to use the method of offsetting the two normal vector directions by d and then calculating the intersection of two straight lines to obtain the original set PP after the discrete points are offset.

[0092] In some examples, when the normal vector is a single normal vector,

[0093] The above-mentioned original set is determined by combining the normal vectors of all points in the above-mentioned offset reference optimized baseline discrete point set at the corresponding points and the above-mentioned offset distance, including:

[0094] Selecting each group of three adjacent discrete points of the offset reference optimization baseline in the above-mentioned discrete point set of the offset reference optimization baseline to perform collinearity judgment;

[0095] When the collinearity judgment result is collinear, the offset point coordinates of the middle discrete point of the offset reference optimization baseline in each group are calculated;

[0096] When the middle discrete point of the offset reference optimization baseline in each of the above groups is not the starting point or the end point, the collinearity judgment and offset point coordinate calculation operations of the next group are continued to obtain the first element in the above original set.

[0097] In some examples, this also includes:

[0098] When the collinearity judgment result is non-collinearity, the outer circle center coordinates of the circumscribed circle formed by each group of three adjacent discrete points of the offset reference optimization baseline are calculated;

[0099] Calculate the vector coordinates and the modulus length of the line connecting the above circumscribed circle and the offset point of the offset reference optimization baseline discrete point in the middle of each group;

[0100] The offset point coordinates of the middle offset reference optimization baseline discrete point in each group are calculated based on the above-mentioned vector coordinates, the above-mentioned modulus, the above-mentioned offset distance and the coordinates of the middle offset reference optimization baseline discrete point in each group to obtain the second element in the above-mentioned original set.

[0101] In some examples, this also includes:

[0102] When the collinearity judgment result is collinear, the offset point coordinates of the middle discrete point of the offset reference optimization baseline in each group are calculated;

[0103] In the case where the middle discrete point of the offset reference optimization baseline in each of the above groups is the starting point or the end point, the offset point coordinates of the above starting point or the end point are calculated to obtain the third element in the above original set.

[0104] For example, Figure 3As shown, a schematic diagram of the process of obtaining the original set after the discrete point offset is obtained by offsetting in the direction of a single normal vector provided by an embodiment of the present disclosure. In the case where the normal vector is a single normal vector, the schematic diagram of the process of determining the original set, step S1104 specifically includes steps S11041-1-1 to step S1104-1-14:

[0105] Step S11041-1-1: Set the initial value of the offset point number k in the offset reference optimization baseline discrete point set to 2.

[0106] Step S11041-1-2: Determine whether the offset point sequence number k is not greater than the difference of the total number of discrete point elements N minus 1. If not, the offset point coordinates corresponding to all discrete points in the offset reference optimization baseline discrete point set are obtained to form the original set of discrete points after offset PP = {(XR1(k), YR1(k))|k∈[1,N]}, and execute step S11041-1-14; if yes, execute step S11041-1-3 to perform collinearity determination of three adjacent discrete points. That is, select each group of three adjacent offset reference optimization baseline discrete points in the above offset reference optimization baseline discrete point set for collinearity determination.

[0107] Wherein: PP is the original set after the discrete points are offset; XR1(k) is the horizontal coordinate of the kth discrete point in the original set after the discrete points are offset; YR1(k) is the vertical coordinate of the kth discrete point in the original set after the discrete points are offset.

[0108] Step S11041-1-3: Determine whether the three discrete points with offset point numbers K-1, K, and K+1 in the offset reference optimization baseline discrete point set are collinear. The determination method is: whether the absolute value of the cosine of the angle between vector 1 composed of the discrete points with offset point numbers K-1 and K and vector 2 composed of the discrete points with offset point numbers K and K+1 is greater than or equal to 0.99. The absolute value of the cosine of the angle between vector 1 and vector 2 is equal to the absolute value of the value obtained by multiplying the dot of vector 1 and vector 2 and dividing it by the modulus of vector 1 and vector 2. If yes, the three discrete points with offset point number K-1, offset point number K, and offset point number K+1 are collinear, then go to step S11041-1-4; if no, the three discrete points with offset point number K-1, offset point number K, and offset point number K+1 are not collinear, then jump to step S11041-1-8.

[0109] Furthermore, the calculation formula of the absolute value of the cosine of the angle between vector 1 and vector 2 is:

[0110] |COSθ|=|(XR(k)-XR(k-1))*(XR(k+1)-XR(k))-(YR(k)-YR(k-1))*(YR(k+1)-YR(k))| / (d1*d2)

[0111] Where: |COSθ|——the absolute value of the cosine of the angle between vector 1 and vector 2. d1——the modulus of vector 1, d2——the modulus of vector 2.

[0112] Where: the coordinates of vector 1 are: (XR(k)-XR(k-1), YR(k)-YR(k-1));

[0113] The coordinates of vector 2 are: (XR(k+1)-XR(k), YR(k+1)-YR(k)).

[0114] Furthermore, we know that: d1^2=(XR(k)-XR(k-1))^2+(YR(k)-YR(k-1))^2;

[0115] d2^2=(XR(k+1)-XR(k))^2+(YR(k+1)-YR(k))^2;

[0116] Step S11041-1-4: Calculate the coordinates of the offset point of the discrete point with sequence number k in the offset reference optimization baseline discrete point set as (XR1(k), YR1(k)), that is, calculate the offset point coordinates of the middle offset reference optimization baseline discrete point in each group. The coordinates of the offset point of the discrete point with sequence number k in the offset reference optimization baseline discrete point set are equal to the offset distance d divided by the modulus d1 of vector 1 multiplied by the obtained value of the normal vector of vector 1 plus the discrete point with sequence number k in the offset reference optimization baseline discrete point set. The calculation formula for the coordinates of the offset point of the discrete point with sequence number k in the offset reference optimization baseline discrete point set is:

[0117] XR1(k)=XR(k)+d / d1*(-(YR(k)-YR(k-1)))

[0118] YR1(k)=YR(k)+d / d1*(XR(k)-XR(k-1))

[0119] Among them: the normal vector of vector 1 is (-(YR(k)-YR(k-1)),XR(k)-XR(k-1))

[0120] Step S11041-1-5: Check whether the offset point number k in the offset reference optimized baseline discrete point set is equal to 2 or equal to N-1. If so, jump to step S11041-1-6; if not, jump to step S11041-1-7, that is, when the middle offset reference optimized baseline discrete point in each of the above groups is not the starting point or the end point, continue with the collinearity judgment and offset point coordinate calculation operations of the next group to obtain the first element in the above original set.

[0121] Step S11041-1-6: Calculate the offset point coordinates of the discrete points with offset point numbers 1 and N in the offset reference optimization baseline discrete point set as (XR1(1), YR1(1)), (XR1(N), YR1(N)). That is, when the above collinearity judgment result is collinearity, calculate the offset point coordinates of the middle offset reference optimization baseline discrete point in each group; when the middle offset reference optimization baseline discrete point in each group is the starting point or end point, calculate the offset point coordinates of the starting point or end point to obtain the third element in the above original set. When k is equal to 2, calculate (XR1(1), YR1(1)); when k is equal to N-1, calculate (XR1(N), YR1(N)). (XR1(1), YR1(1)) is equal to the offset distance d divided by the modulus d1 of vector 1 multiplied by the obtained value of the normal vector of vector 1 plus the discrete point numbered 1 in the offset reference optimization baseline discrete point set; (XR1(N), YR1(N)) is equal to the offset distance d divided by the modulus d1 of vector 1 multiplied by the obtained value of the normal vector of vector 1 plus the discrete point numbered N in the offset reference optimization baseline discrete point set. The calculation formula is:

[0122] XR1(1)=XR(1)+d / d1*(-(YR(k)-YR(k-1))); YR1(1)=YR(1)+d / d1*(XR(k)-XR(k-1))

[0123] XR1(N)=XR(N)+d / d1*(-(YR(k)-YR(k-1))); YR1(N)=YR(N)+d / d1*(XR(k)-XR(k-1))

[0124] Step S11041-1-7: The offset point number k in the offset reference optimization baseline discrete point set is incremented by 1, and the process jumps to step S11041-1-2 for execution.

[0125] Step S11041-1-8: Calculate the center coordinates (XO, YO) of the circumscribed circle of the three discrete points with offset point number k-1, offset point number k, and offset point number k+1 in the offset reference optimized baseline discrete point set. That is, when the collinearity judgment result is not collinear, calculate the external center coordinates of the circumscribed circle composed of each group of three adjacent discrete points of the offset reference optimized baseline. According to the center formula of the circumscribed circle of three points, it can be known that:

[0126] XO=((y2-y1)*(y3*y3-y1*y1+x3*x3-x1*x1)-(y3-y1)*(y2*y2-y1*y1+x2*x2-x1*x1)) / (2.0*((x3-x1)*(y2-y1)-(x2-x1)*(y3-y1)));

[0127] YO=((x2-x1)*(x3*x3-x1*x1+y3*y3-y1*y1)-(x3-x1)*(x2*x2-x1*x1+y2*y2-y1*y1)) / (2.0*((y3-y1)*(x2-x1)-(y2-y1)*(x3-x1)));

[0128] Among them: XO is the horizontal coordinate of the center of the circumscribed circle; YO is the vertical coordinate of the center of the circumscribed circle. X1, Y1, X2, Y2, X3, Y3 are the horizontal and vertical coordinate aliases of the three discrete points with offset point number k-1, offset point number k, and offset point number k+1.

[0129] X1=XR(k-1); Y1=YR(k-1); X2=XR(k); Y2=YR(k); X3=XR(k+1); Y3=YR(k+1).

[0130] Step S11041-1-9: Calculate the vector coordinates (XOK, YOK) and vector modulus r of the line connecting the center coordinates (XO, YO) of the circumscribed circle and the discrete point with offset point number K in the offset reference optimization baseline discrete point set. That is, calculate the vector coordinates and modulus of the line connecting the above circumscribed circle and the offset point of the offset reference optimization baseline discrete point in the middle of each group. The calculation formula of the vector coordinates (XOK, YOK) and the vector modulus r is:

[0131] XOK=XR(k)-XO; YOK=YR(k)-YO; r^2=XOK^2+YOK^2

[0132] Among them: (XOK, YOK) is the vector coordinate of the line connecting the center coordinate of the circumscribed circle and the discrete point with offset point number K in the discrete point set of the offset reference optimized baseline. This vector represents the normal vector of the discrete point with offset point number K in the discrete point set of the offset reference optimized baseline; r is the vector modulus length of the line connecting the center coordinate of the circumscribed circle and the discrete point with offset point number K in the discrete point set of the offset reference optimized baseline, which also represents the radius of the circumscribed circle.

[0133] Step S11041-1-10: Calculate the offset point coordinates of the discrete point with offset point number K in the offset reference optimized baseline discrete point set as (XR1(K), YR1(K)). That is, calculate the offset point coordinates of the middle offset reference optimized baseline discrete point in each group based on the above-mentioned vector coordinates, the above-mentioned modulus, the above-mentioned offset distance and the coordinates of the middle offset reference optimized baseline discrete point in each group to obtain the second element in the above-mentioned original set. (XR1(K), YR1(K)) is equal to the offset distance d divided by the vector modulus r and then multiplied by the value obtained of the vector coordinates of the line connecting the discrete points with offset point number K in the offset reference optimized baseline discrete point set by the coordinates of the center of the circumscribed circle plus the discrete point with offset point number K in the offset reference optimized baseline discrete point set. The calculation formula of (XR1(K), YR1(K)) is:

[0134] XR1(K)=XR(k)+d / r*XOK; YR1(K)=YR(k)+d / r*YOK

[0135] Step S11041-1-11: Check whether the offset point number k in the offset reference optimization baseline discrete point set is equal to 2 or equal to N-1. If so, jump to step S11041-1-12; if not, jump to step S11041-1-13.

[0136] Step S11041-1-12: Calculate the coordinates of the offset points of the discrete points with offset point numbers 1 and N in the offset reference optimization baseline discrete point set as (XR1(1), YR1(1)), (XR1(N), YR1(N)). When K is equal to 2, calculate (XR1(1), YR1(1)); when k is equal to N-1, calculate (XR1(N), YR1(N)). (XR1(1), YR1(1)) is equal to the difference between the coordinates of the center of the circumscribed circle and the discrete point with offset point number 1 in the offset reference optimized baseline discrete point set multiplied by the offset distance d, and then divided by the obtained value of the vector modulus r plus the discrete points with offset point number 1 in the offset reference optimized baseline discrete point set; when K is equal to N-1, XR1(N), YR1(N)) is equal to the difference between the coordinates of the center of the circumscribed circle and the discrete point with offset point number N in the offset reference optimized baseline discrete point set multiplied by the offset distance d, and then divided by the obtained value of the vector modulus r plus the discrete points with offset point number N in the offset reference optimized baseline discrete point set. The calculation formulas of (XR1(1), YR1(1)) and (XR1(N), YR1(N)) are:

[0137] XR1(1)=XR(1)+d / r*(XR(1)-XO); YR1(1)=YR(1)+d / r*(YR(1)-YO);

[0138] XR1(N)=XR(N)+d / r*(XR(N)-XO); YR1(N)=YR(N)+d / r*(YR(N)-YO);

[0139] Step S11041-1-13: The offset point number k in the offset reference optimization baseline discrete point set is incremented by 1, and the process jumps to step S11041-1-2 for execution.

[0140] Step S11041-1-14: The offset point coordinates corresponding to all discrete points in the discrete point set of the offset reference optimization baseline constitute the original set PP after the discrete point offset = {(XR1(k), YR1(k))|k∈[1,N]}, and execute step 5.

[0141] In some examples, when the normal vector is two normal vectors,

[0142] The above-mentioned original set is determined by combining the normal vectors of all points in the above-mentioned offset reference optimized baseline discrete point set at the corresponding points and the above-mentioned offset distance, including:

[0143] A first vector and a second vector are established based on each group of three adjacent offset reference optimized baseline discrete points in the offset reference optimized baseline discrete point set, wherein the middle point in each group of three adjacent offset reference optimized baseline discrete points is the starting point of the first vector and is the end point of the second vector;

[0144] Calculate a first unit normal vector of the first vector;

[0145] Calculate a second unit normal vector of the second vector;

[0146] Performing an offset based on the offset distance according to the first unit normal vector to obtain a first excessive offset point;

[0147] Performing an offset based on the offset distance according to the second unit normal vector to obtain a second excessive offset point;

[0148] Performing collinearity judgment on the first vector and the second vector to obtain a collinearity judgment result;

[0149] When the collinearity determination result is collinearity, the first over-offset point and the second over-offset point are used as the fourth element of the original set.

[0150] In some examples, this also includes:

[0151] When the collinearity determination result is non-collinearity, a first straight line is established using the first unit normal vector and the first transition point;

[0152] Establishing a second straight line using the second unit normal vector and the second over-offset point;

[0153] The coordinates of the intersection of the first straight line and the second straight line are calculated, and the coordinates of the intersection are used as the fifth element of the original set.

[0154] In some examples, this also includes:

[0155] Determine the starting point offset coordinates based on the starting point horizontal coordinate, the offset direction and the above offset distance;

[0156] Determine the end point offset coordinates based on the end point horizontal coordinate, the offset direction and the above offset distance;

[0157] The starting point offset coordinates and the end point offset coordinates are determined as the sixth element of the original set.

[0158] For example, Figure 4As shown, it is a schematic diagram of the process of obtaining the original set after the discrete points are offset by calculating the intersection of two straight lines after the two normal vector directions are offset according to an embodiment of the present disclosure. In the case where the normal vector is two normal vectors, the schematic diagram of the process of determining the original set, step S1104 specifically includes steps S11042-1-1 to step S1104-2-13:

[0159] Furthermore, the method of obtaining the optimized set PPH after the discrete point offset is as follows:

[0160] Step S11041-2-1: Set the initial value of the offset point number k in the offset reference optimization baseline discrete point set to 2.

[0161] Step S11041-2-2: Calculate vector 1 and vector 2 consisting of two adjacent discrete points in the offset reference optimization baseline discrete point set with offset point number k-1, offset point number k, and offset point number k+1, that is, establish a first vector 1 and a second vector 2 based on each group of three adjacent offset reference optimization baseline discrete points in the above offset reference optimization baseline discrete point set, wherein the middle point of each group of three adjacent offset reference optimization baseline discrete points is the starting point of the above first vector and the end point of the above second vector.

[0162] The coordinates of vector 1 (XQ1, YQ1) are: (XR(k)-XR(k-1), YR(k)-YR(k-1))

[0163] The coordinates of vector 2 (XQ2, YQ2) are: (XR(k+1)-XR(k), YR(k+1)-YR(k))

[0164] Step S11041-2-3: Calculate the unit normal vectors of vector 1 and vector 2, namely unit normal vector 1 (XD1, YD1) and unit normal vector 2 (XD2, YD2), calculate the first unit normal vector 1 of the first vector, and calculate the second unit normal vector 2 of the second vector.

[0165] (XD1,YD1)=(-(YR(k)-YR(k-1)),XR(k)-XR(k-1)) / d1

[0166] (XD2,YD2)=(-(YR(k+1)-YR(k)),XR(k+1)-XR(k)) / d2

[0167] Where: d1, d2 are the modulus lengths of vector 1 and vector 2 respectively.

[0168] Step S11041-2-4: The discrete points with offset point number k in the discrete point set of the offset reference optimized baseline are offset according to the offset distance d on the unit normal vector 1 (X1, Y1) and the unit normal vector 2 (X2, Y2) to obtain the transition point 1 (XG1, YG1) and the transition point 2 (XG2, YG2), that is, the first unit normal vector is offset based on the offset distance to obtain the first transition point, and the second unit normal vector is offset based on the offset distance to obtain the second transition point.

[0169] (XG1,YG1)=(XR(k),YR(k))+d*(XD1,YD1)

[0170] (XG2,YG2)=(XR(k),YR(k))+d*(XD2,YD2)

[0171] Step S11041-2-5: Determine whether vector 1 and vector 2 composed of two adjacent discrete points in the three discrete points with offset point numbers k-1, k, and k+1 in the offset reference optimization baseline discrete point set are collinear. That is, perform collinearity judgment on the above-mentioned first vector and the above-mentioned second vector to obtain the collinearity judgment result. That is, |COSθ|>0.99, which can also be expressed as |(XR(k)-XR(k-1))*(XR(k+1)-XR(k))-(YR(k)-YR(k-1))*(YR(k+1)-YR(k))| / (d1*d2)>0.999. If they are collinear, execute step S11041-2-6; if they are not collinear, jump to step S11041-2-7.

[0172] Step S11041-2-6: Calculate the coordinates of the offset point of the discrete point with the offset point number K in the discrete point set of the offset reference optimization baseline as (XR1(K), YR1(K)). That is, when the collinearity judgment result is collinearity, the first over-offset point and the second over-offset point are used as the fourth element of the original set. It is equal to over-offset point 1 (XG1, YG1), and also equal to over-offset point 2 (XG2, YG2), and jumps to step S11041-2-10 for execution. The calculation formula of (XR1(K), YR1(K)) is:

[0173] (XR1(K),YR1(K))=(XG1,YG1)=(XG2,YG2)

[0174] Step S11041-2-7: Obtain straight line 1 passing through over-offset point 1 (XG1, YG1) and with direction of vector 1 and straight line 2 passing through over-offset point 1 (XG2, YG2) and with direction of vector 2, that is, when the above-mentioned collinearity judgment result is non-collinearity, establish the first straight line 1 with the above-mentioned first unit normal vector and the above-mentioned first over-offset point; establish the second straight line 2 with the above-mentioned second unit normal vector and the above-mentioned second over-offset point.

[0175] The equation of line 1 is: (X-XG1)*YQ1=(Y-YG1)*XQ1

[0176] The equation of line 2 is: (X-XG2)*YQ2=(Y-YG2)*XQ2

[0177] Step S11041-2-8: Calculate the coordinates of the intersection of line 1 and line (XG, YG). That is, calculate the coordinates of the intersection of the first line and the second line, and use the coordinates of the intersection as the fifth element of the original set. The calculation formula of (XG, YG) is:

[0178] XG=((XG1*YQ1-YG1*XQ1)*XQ2-(XG2*YQ2-YG2*XQ1)*XQ1) / (YQ1*XQ2-YQ2*XQ1)

[0179] YG=((XG1*YQ1-YG1*XQ1)*YQ2-(XG2*YQ2-YG2*XQ1)*YQ1) / (XQ2*YQ1-XQ1*YQ2)

[0180] Step S11041-2-9: The coordinates of the intersection of line 1 and line 1 (XG, YG) are the coordinates of the offset point of the discrete point with offset point number K in the discrete point set of the offset reference optimization baseline (XR1(K), YR1(K)). (XR1(K), YR1(K)) is expressed as: (XR1(K), YR1(K)) = (XG, YG)

[0181] Step S11041-2-10: If K=1, the offset point coordinates of the discrete point with offset point number 1 in the offset reference optimization baseline discrete point set are calculated as (XR1(1), YR1(1)), that is, the offset coordinates of the starting point are determined based on the horizontal coordinate of the starting point, the offset direction and the above offset distance; the offset coordinates of the end point are determined based on the horizontal coordinate of the end point, the offset direction and the above offset distance; the above starting point offset coordinates and the above end point offset coordinates are determined as the sixth element of the above original set. If K=N-1, the offset point coordinates of the discrete point with offset point number N in the offset reference optimization baseline discrete point set are calculated as (XR1(K), YR1(K)).

[0182] (XR1(1),YR1(1))=(XR(k),YR(k))+d*(XD1,YD1)

[0183] (XR1(N),YR1(N))=(XR(N),YR(k))+d*(XD2,YD2)

[0184] If k≠1 and K≠N-1, no processing is done.

[0185] Step S11041-2-11: setting the offset point number k in the offset reference optimization baseline discrete point set to be incremented by 1;

[0186] Step S11041-2-12: Determine whether the offset point number k in the offset reference optimization baseline discrete point set is greater than N-1. If not, it means that all discrete points have not been offset, and jump to step 4-2-2: If it is greater, it means that all discrete points have been offset, and execute step 4-2-13:

[0187] Step S11041-2-13: Successfully obtain the offset point coordinates corresponding to all discrete points in the offset reference optimization baseline discrete point set to form the original set PP after discrete point offset = {(XR1(k), YR1(k))|k∈[1,N]}.

[0188] S1105, calculating the minimum distance from each point in the above original set after discrete point offset to the above offset reference optimized baseline discrete point set, retaining the discrete points in the original set after discrete point offset whose minimum distance is greater than or equal to the above minimum distance, and forming all the retained points into the optimized set after discrete point offset.

[0189] Specifically, the minimum distance dmin(k) from each point in the original set PP={(XR1(k), YR1(k))|k∈[1,N]} after discrete point offset to the discrete point set of the offset reference optimization baseline is calculated, and the discrete points whose dmin(k) is less than d in the original set PP={(XR1(k), YR1(k))|k∈[1,N]} after discrete point offset are eliminated, and the discrete points whose dmin(k) is not less than d in the original set PP={(XR1(k), YR1(k))|k∈[1,N]} after discrete point offset are retained and named (XR2(h), XR2(h)). The coordinates of all discrete points are (XR2(h), XR2(h)) to form the optimized set PPH after discrete point offset.

[0190] Furthermore, if Figure 5 FIG. 1 is a flow chart of obtaining a discrete point offset optimized set provided by an embodiment of the present disclosure. The specific steps of the method for obtaining the discrete point offset optimized set PPH are as follows:

[0191] Step S11051: the initial value of the sequence number k in the original set after the discrete point offset is set to 1, and the sequence number h of the discrete point in the optimized set after the discrete point offset is set to 0.

[0192] Step S11052: If the sequence number k in the original set after the discrete point offset is not greater than the total number of elements N, if it is greater, the optimized set PPH after the discrete point offset is obtained and S11056 is executed; if it is not greater, step S11053 is executed.

[0193] Step S11053: Calculate the minimum value d_min(k) from the discrete point with sequence number k in the original set after the discrete point offset to all the discrete points in the offset reference optimization baseline discrete point set.

[0194] The specific calculation method of the minimum value d_min(k) is:

[0195] Step S11053-1: The initial value of the point number j in the discrete point set of the offset reference optimization baseline is 1.

[0196] Step S11053-2: Calculate the distance dkj between the discrete point with sequence number k in the original set after the discrete point offset and the discrete point with sequence number j in the offset reference optimization baseline discrete point set. According to the distance calculation formula of the plane coordinate, it can be known that the calculation formula of Dkj is:

[0197] dkj^2=(XR1(k)-XR(j))^2+(YR1(k)-YR(j))^2

[0198] Step S11053-3: If the point number j in the discrete point set of the offset reference optimization baseline is equal to 1, then d_min(k) is equal to dkj; if the point number j in the discrete point set of the offset reference optimization baseline is not equal to 1 and d_min(k) is greater than dkj, then d_min(k) is equal to dkj.

[0199] Step S11053-4: The point number j in the set of discrete points of the offset reference optimization baseline is incremented by 1. It is determined whether j is greater than N. If not, step S11053-2 is directly executed; if so, d_min(k) is obtained successfully, and the process jumps to step S11054.

[0200] Step S11054: Compare the minimum value d_min(k) of the discrete point with sequence number k in the original set after the discrete point offset to all the discrete points in the offset reference optimization baseline discrete point set with the offset distance d. If d_min(k) is not less than d, execute step S11055; if d_min(k) is less than d, execute step S11056.

[0201] Step S11055: The sequence number h in the optimized set after discrete point offset is incremented by 1, and then the discrete points whose dmin(k) is less than d in the original set PP={(XR1(k), YR1(k))|k∈[1,N]} after discrete point offset are eliminated, and the discrete points whose dmin(k) is not less than d in the original set PP={(XR1(k), YR1(k))|k∈[1,N]} after discrete point offset are retained and named (XR2(h), XR2(h)). That is, the coordinates of the point with sequence number h in the optimized set after discrete point offset are obtained (XR2(h), XR2(h)). And XR2(h)=XR1(k), YR2(h)=YR1(k). The sequence number k in the original set after discrete point offset is incremented by 1, and jump to step S11052.

[0202] S1106, using a quadratic programming method to optimize and average the above-mentioned discrete point offset optimization set to form a final set of offset discrete points, and generating a corresponding offset line based on the above-mentioned final set of discrete points.

[0203] Exemplarily, the above steps have performed an offset operation on some initial discrete points, generating a set of offset points. Since these offset points may be randomly or regularly offset, the distribution of the points may be uneven and a smooth path or curve cannot be directly formed. In order to generate a better curve, these offset points need to be optimized.

[0204] Quadratic programming is a method for solving optimization problems with quadratic objective functions and linear constraints. In the optimization process of quadratic programming, the offset discrete point set can be optimized by introducing constraints, such as the distance between adjacent discrete points, the smoothness of the path, etc. By solving the optimization problem, the distribution of the point set can be made more uniform and the deviation of local discrete points can be reduced. The result of this process is an "optimal average", that is, the position of each point in the offset point set will be adjusted to a certain extent after optimization, so that the entire point set is more regular and conforms to the expected curve or path shape. When the optimized discrete point set is formed, a smooth offset line can be generated based on these discrete points. This line is generated by fitting or interpolation. For example, common methods for generating curves include polynomial fitting and spline interpolation. Polynomial fitting: A lower-order polynomial can be used to fit discrete points to form a smooth curve. Spline interpolation: The commonly used method is cubic spline interpolation, which can generate a smooth curve that passes through each discrete point.

[0205] In some examples, the road generation module generates boundary lines of different lanes based on the offset lines, including:

[0206] Generate multiple B-spline curves based on the coordinates of multiple randomly generated control points to generate a lane center reference line;

[0207] Boundary lines of different lanes are generated based on the lane center reference line and the offset line.

[0208] For example, Figure 6 and Figure 7 As shown, Figure 6 A schematic diagram of the workflow of a road feature generation module provided in an embodiment of the present disclosure; Figure 7 A schematic diagram of a scenario of a two-lane simulated road model generated according to an embodiment of the present disclosure; taking the two-lane model as an example, the specific steps of the road feature generation module include:

[0209] Step S1201: randomly setting the coordinates of M control points generated by the center reference line of lane 1, and calculating the discrete point coordinate set of the center reference line of lane 1 in combination with the multi-segment B-spline curve generation method;

[0210] Step S1202: determine the coincidence points of the discrete point set of the center reference line of lane 1, remove redundant coincidence points, and then perform point spacing equalization processing to form an optimized discrete point set of the center reference line of lane 1.

[0211] Step S1203: The optimized discrete point set of the center reference line of lane 1 is set as the discrete points of the offset reference baseline, the offset distance is set to d1, and the reference baseline offset module is called to generate the optimized discrete point set of the right boundary line of lane 1. Where d1 is equal to the opposite of half of the width of lane 1.

[0212] Step S1204: The optimized discrete point set of the center reference line of lane 1 is set as the discrete points of the offset reference baseline, the offset distance is set to d2, and the reference baseline offset module is called to generate the optimized discrete point set of the common boundary line of lane 12. Where d2 is equal to half of the width of lane 1.

[0213] Step S1205: The optimized discrete point set of the center reference line of lane 1 is set as the discrete points of the offset reference baseline, the offset distance is set to d3, and the reference baseline offset module is called to generate the optimized discrete point set of the center reference line of lane 2. Where d3 is equal to the sum of half the width of lane 1 and half the width of lane 2.

[0214] Step S1206: The optimized discrete point set of the center reference line of lane 1 is set as the discrete points of the offset reference baseline, the offset distance is set to d4, and the reference baseline offset module is called to generate the optimized discrete point set of the left boundary line of lane 2. Where d4 is equal to the sum of half of the width of lane 1 and the width of lane 2.

[0215] Step S1207: The discrete point optimization set of the center reference line of lane 1, the discrete point optimization set of the center reference line of lane 2, the discrete point optimization set of the right boundary line of lane 1, the discrete point optimization set of the common boundary line of lane 12, and the discrete point optimization set of the left boundary line of lane 2 are taken as the sum of the features of the dual-lane road surface model.

[0216] See also Figure 8 , a structural schematic diagram of an intelligent driving simulation road model generation device 200 provided in an embodiment of the present disclosure may include:

[0217] The first generating unit 201 is used to generate a corresponding offset line based on the offset reference baseline discrete point set and the offset distance through a baseline offset module;

[0218] A second generating unit 202, configured to generate boundary lines of different lanes based on the offset lines through a road generating module;

[0219] The third generating unit 203 is used to generate a simulated road model based on all the above offset lines and all the above boundary lines.

[0220] like Fig. 9 As shown, an embodiment of the present disclosure also provides an electronic device 300, including a memory 310, a processor 320, and a computer program 311 stored in the memory 310 and executable on the processor. When the processor 320 executes the computer program 311, the steps of any method for generating the above-mentioned intelligent driving simulation road model are implemented.

[0221] Due to the specific implementation mode of the electronic device introduced in this embodiment and its various variations, how the electronic device implements the method in the embodiment of the present application will not be described in detail here. As long as the equipment used by technical personnel in this field to implement the method in the embodiment of the present application is within the scope of protection of this application.

[0222] During the specific implementation process, when the computer program 311 is executed by a processor, any implementation method in the embodiments corresponding to the first aspect can be implemented.

[0223] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and 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 the embodiments of the present disclosure may be provided as methods, systems, or computer program products. Therefore, the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present disclosure may take the form of a computer program product implemented on one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-readable program code.

[0225] The present disclosure 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 disclosure. 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 computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. 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.

[0226] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0227] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0228] The embodiment of the present disclosure also provides a computer program product, which includes computer software instructions. When the computer software instructions are executed on a processing device, the processing device executes the process of the intelligent drinking water service method.

[0229] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on the computer, the process or function according to the embodiment of the present disclosure is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can store or a data storage device such as a server or a data center that includes one or more available media integration. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state disk (SSD)), etc.

[0230] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0231] In the several embodiments provided in the present disclosure, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0232] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0233] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0234] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present disclosure is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the various embodiments of the present disclosure. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), disk or optical disk and other media that can store program codes.

[0235] In the present disclosure, the terms "first", "second", and "third" are used for descriptive purposes only and are not to be understood as indicating or implying relative importance; the term "plurality" refers to two or more, unless otherwise expressly defined. The terms "installed", "connected", "connected", "fixed", etc. should be understood in a broad sense. For example, "connected" can be a fixed connection, a detachable connection, or an integral connection; "connected" can be a direct connection or an indirect connection through an intermediate medium. For those of ordinary skill in the art, the specific meanings of the above terms in the present disclosure can be understood according to the specific circumstances.

[0236] In the description of this specification, the description of the terms "one embodiment", "some embodiments", "specific embodiments", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present disclosure. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0237] The above are only preferred embodiments of the present disclosure and are not intended to limit the present disclosure. For those skilled in the art, the present disclosure may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for generating a road model for intelligent driving simulation, characterized in that: include: Generate a corresponding offset line based on the offset reference baseline discrete point set and the offset distance through the baseline offset module; Generate boundary lines of different lanes based on the offset lines by a road generation module; A simulated road model is generated based on all the offset lines and all the boundary lines.

2. The method for generating an intelligent driving simulation road model according to claim 1, characterized in that: The base line offset module generates a corresponding offset line based on the offset reference base line discrete point set and the offset distance, including: Get the offset reference baseline discrete point set and offset distance; Detecting whether there are any overlapping points in the offset reference baseline discrete point set, and removing redundant overlapping points to form an offset reference optimization baseline discrete point set; Calculate the total number of discrete point elements in the discrete point set of the offset reference optimization baseline; Determine an original set of normal vectors of all points in the offset reference optimized baseline discrete point set at corresponding points and the offset distance, wherein the normal vectors include a single normal vector and two normal vectors; Calculate the minimum distance between each point in the original set after discrete point offset and the offset reference optimized baseline discrete point set, retain the discrete points in the original set after discrete point offset whose minimum distance is greater than or equal to the minimum distance, and form all the retained points into the optimized set after discrete point offset; The optimized set of discrete points after offset is optimized and averaged by using a quadratic programming method to form a final set of offset discrete points, and a corresponding offset line is generated based on the final set of discrete points.

3. The intelligent driving simulation road model generation method according to claim 2, characterized in that: In the case where the normal vector is a single normal vector, The step of determining an original set by using the normal vectors of all points in the offset reference optimized baseline discrete point set at corresponding points and the offset distance comprises: Selecting each group of three adjacent offset reference optimization baseline discrete points in the offset reference optimization baseline discrete point set to perform collinearity judgment; When the collinearity judgment result is collinearity, calculating the offset point coordinates of the middle offset reference optimization baseline discrete point in each group; When the middle discrete point of the offset reference optimization baseline in each group is not the starting point or the end point, the collinearity determination and offset point coordinate calculation operations of the next group are continued to obtain the first element in the original set.

4. The method for generating an intelligent driving simulation road model according to claim 3, characterized in that: Also includes: When the collinearity judgment result is non-collinearity, the outer circle center coordinates of the circumscribed circle formed by each group of three adjacent discrete points of the offset reference optimization baseline are calculated; Calculate the vector coordinates and the modulus length of the line connecting the circumscribed circle and the offset point of the offset reference optimization baseline discrete point in the middle of each group; The offset point coordinates of the middle offset reference optimized baseline discrete point in each group are calculated based on the vector coordinates, the module length, the offset distance and the coordinates of the middle offset reference optimized baseline discrete point in each group to obtain the second element in the original set.

5. The method for generating an intelligent driving simulation road model according to claim 3, characterized in that: Also includes: When the collinearity judgment result is collinearity, calculating the offset point coordinates of the middle offset reference optimization baseline discrete point in each group; In the case where the middle discrete point of the offset reference optimization baseline in each group is the starting point or the end point, the offset point coordinates of the starting point or the end point are calculated to obtain the third element in the original set.

6. The method for generating an intelligent driving simulation road model according to claim 2, characterized in that: In the case where the normal vector is two normal vectors, The step of determining an original set by using the normal vectors of all points in the offset reference optimized baseline discrete point set at corresponding points and the offset distance comprises: Establishing a first vector and a second vector based on each group of three adjacent offset reference optimized baseline discrete points in the offset reference optimized baseline discrete point set, wherein the middle point in each group of three adjacent offset reference optimized baseline discrete points is the starting point of the first vector and is the end point of the second vector; calculating a first unit normal vector for the first vector; calculating a second unit normal vector for the second vector; Performing an offset based on the offset distance according to the first unit normal vector to obtain a first excessive offset point; Performing an offset based on the offset distance according to the second unit normal vector to obtain a second excessive offset point; Performing collinearity determination on the first vector and the second vector to obtain a collinearity determination result; When the collinearity determination result is collinearity, the first over-offset point and the second over-offset point are used as the fourth element of the original set.

7. The method for generating an intelligent driving simulation road model according to claim 6, characterized in that: Also includes: When the collinearity determination result is non-collinearity, establishing a first straight line by using the first unit normal vector and the first excessive offset point; Establishing a second straight line using the second unit normal vector and the second over-offset point; The coordinates of the intersection of the first straight line and the second straight line are calculated, and the coordinates of the intersection are used as the fifth element of the original set.

8. The method for generating an intelligent driving simulation road model according to claim 7, characterized in that: Also includes: Determine the starting point offset coordinates based on the starting point horizontal coordinate, the offset direction and the offset distance; Determine the end point offset coordinate based on the end point horizontal coordinate, the offset direction and the offset distance; The starting point offset coordinate and the ending point offset coordinate are determined as the sixth element of the original set.

9. The method for generating an intelligent driving simulation road model according to claim 1, characterized in that: The step of generating boundary lines of different lanes based on the offset lines by a road generation module includes: Generate multiple B-spline curves based on the coordinates of multiple randomly generated control points to generate a lane center reference line; Boundary lines of different lanes are generated based on the lane center reference line and the offset line.

10. An intelligent driving simulation road model generation device, characterized in that: include: A first generating unit, configured to generate a corresponding offset line based on an offset reference baseline discrete point set and an offset distance through a baseline offset module; A second generating unit, configured to generate boundary lines of different lanes based on the offset line through a road generating module; The third generating unit is used to generate a simulated road model based on all the offset lines and all the boundary lines.

11. An electronic device, comprising: A memory and a processor, characterized in that the processor is used to implement the steps of the intelligent driving simulation road model generation method as described in any one of claims 1 to 8 when executing the computer program stored in the memory.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the intelligent driving simulation road model generation method as described in any one of claims 1 to 8 are implemented.

Images