A method, apparatus, device, and readable storage medium for determining lane centerlines

Abstract

This invention discloses a method, apparatus, device, and readable storage medium for determining lane centerlines, applicable to the field of intelligent transportation. The method includes: determining a first lateral coordinate point corresponding to a first longitudinal sampling point based on a target model; determining the weight of the lateral coordinate point corresponding to the first lateral coordinate point; determining the coordinate point corresponding to the forward lane centerline based on the weight of the lateral coordinate point in the target model and the first lateral coordinate point; filtering the second lateral coordinate point determined based on a fourth trajectory model and the coordinates of a second longitudinal sampling point to obtain a filtered second lateral coordinate point; determining the coordinate point corresponding to the backward lane centerline based on the coordinates of the second longitudinal sampling point and the filtered second lateral coordinate point; and determining the target lane centerline based on the coordinate points corresponding to the forward and backward lane centerlines. This invention integrates multiple models to calculate the lane centerline, enabling accurate determination of the lane centerline without relying entirely on sensors.

Description

Technical Field

[0001] This invention relates to the field of intelligent transportation technology, and in particular to a method, apparatus, device, and readable storage medium for determining lane centerlines. Background Technology

[0002] Current methods for calculating lane centerlines largely rely on road topology data from high-precision maps or visual perception of road edges to infer the centerline. This approach is highly sensor-dependent and requires precise understanding of road geometry. In situations with limited sensor coverage, unstructured roads, or tunnels, the sensor's effective range is restricted, significantly impacting driver assistance functions and resulting in a poor intelligent driving experience. Furthermore, when sensors cannot provide accurate information, the road centerline cannot be accurately determined.

[0003] It is evident that accurately determining the lane centerline under sensor limitations is a technical problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to provide a method, apparatus, device and readable storage medium for determining lane center lines, which solves the technical problem of low accuracy in determining lane center lines in the prior art.

[0005] To solve the above-mentioned technical problems, the present invention provides a method for determining the lane centerline, comprising:

[0006] At least one of the following three trajectory models is selected as the target model: a first trajectory model, a second trajectory model, and a third trajectory model. The first trajectory model is determined based on the curvature of the current trajectory of the vehicle. The second trajectory model is obtained by polynomial fitting based on the coordinates of the historical trajectory points of the target vehicle. The third trajectory model is a lane centerline model determined based on a visual sensor.

[0007] Based on the target model, determine the first lateral coordinate point corresponding to the first longitudinal sampling point coordinate, and determine the weight of the lateral coordinate point corresponding to the first lateral coordinate point. Based on the weight of the lateral coordinate point in the target model and the first lateral coordinate point, determine the coordinate point corresponding to the center line of the forward lane.

[0008] The second lateral coordinate point determined based on the fourth trajectory model and the coordinates of the second longitudinal sampling point is filtered to obtain the filtered second lateral coordinate point. The coordinate point corresponding to the center line of the rearward lane is determined based on the coordinates of the second longitudinal sampling point and the filtered second lateral coordinate point. The fourth trajectory model is a trajectory model obtained by polynomial fitting based on the coordinates corresponding to the historical trajectory points of the vehicle.

[0009] The target lane centerline is determined based on the coordinates of the centerline of the forward lane and the centerline of the backward lane.

[0010] Optionally, before determining that at least one of the first trajectory model, the second trajectory model, and the third trajectory model is selected as the target model, the method further includes:

[0011] Based on the curvature of the vehicle trajectory, a quadratic function model is constructed to obtain the dynamic first trajectory model;

[0012] The lateral coordinates of the historical trajectory points of the target vehicle in each cycle are filtered to obtain the filtered lateral coordinates of the target vehicle. Based on the filtered lateral coordinates, the historical trajectory points of the target vehicle are obtained.

[0013] The second trajectory model is obtained by performing polynomial curve fitting based on the historical trajectory points of the target vehicle.

[0014] The third trajectory model is determined based on the rate of change of lane centerline curvature, lane centerline curvature, lane centerline orientation angle, and lane centerline offset distance determined by the visual sensor.

[0015] Optionally, before filtering the lateral coordinates of the historical trajectory points of the target vehicle for each cycle to obtain the filtered lateral coordinates of the target vehicle, and before obtaining the historical trajectory points of the target vehicle based on the filtered lateral coordinates, the method further includes:

[0016] A preset number of vehicles are selected as target vehicles based on a target vehicle selection rule; wherein, the target vehicle selection rule is determined based on the vehicle's coordinate values ​​and the time the vehicle is within the driver's field of vision.

[0017] The target vehicle selection rules include:

[0018] The vehicle's longitudinal coordinate values ​​are within the set range.

[0019] The difference between the vehicle's lateral coordinate value and the lateral coordinate value of its own vehicle is within the set difference threshold;

[0020] The vehicle remains within the driver's field of vision for a period exceeding a set time threshold.

[0021] The standard deviation of the vehicle's lateral coordinate values ​​is less than the set standard deviation threshold.

[0022] Optionally, determining to select at least one of the first trajectory model, the second trajectory model, and the third trajectory model as the target model includes:

[0023] The first trajectory model, the second trajectory model, and the third trajectory model are determined as the target models.

[0024] Accordingly, based on the target model, the first lateral coordinate point corresponding to the first longitudinal sampling point coordinate is determined, and the weight of the lateral coordinate point corresponding to the first lateral coordinate point is determined. Based on the weight of the lateral coordinate point in the target model and the first lateral coordinate point, the coordinate point corresponding to the center line of the forward lane is determined, including:

[0025] Based on the first trajectory model, the second trajectory model, and the third trajectory model, the first lateral coordinate point of the vehicle, the first lateral coordinate point of the target vehicle, and the first lateral coordinate point of the sensor corresponding to the coordinates of the first longitudinal sampling point are determined respectively;

[0026] Based on the first lateral coordinate point of the vehicle, the first lateral coordinate point of the target vehicle, and the first lateral coordinate point of the sensor, determine the average value of the first lateral coordinate point corresponding to the coordinates of each first longitudinal sampling point;

[0027] Based on the first lateral coordinate point of the vehicle, the first lateral coordinate point of the target vehicle, the first lateral coordinate point of the sensor, and the average value of the first lateral coordinate point, the variance of the lateral coordinate points under the three models corresponding to the coordinates of each first longitudinal sampling point is determined;

[0028] The weighted average value of the first horizontal coordinate points corresponding to each first vertical sampling point is determined based on the variance of the horizontal coordinate points.

[0029] The weight of each first horizontal coordinate point is determined based on the weighted average value.

[0030] Based on the weight of each of the lateral coordinate points, the target first lateral coordinate point corresponding to each first longitudinal sampling point is determined, and the coordinate point corresponding to the center line of the forward lane is obtained based on the first longitudinal sampling point and the target first lateral coordinate point.

[0031] Optionally, before determining the first horizontal coordinate point corresponding to the first vertical sampling point coordinate based on the target model, and determining the weight of the horizontal coordinate point corresponding to the first horizontal coordinate point, the method further includes:

[0032] Determine whether the vision sensor can determine the endpoint of the lane centerline;

[0033] When the endpoint of the lane centerline can be determined, the maximum value of the coordinates of the first longitudinal sampling point is set based on the endpoint determined by the visual sensor.

[0034] When the endpoint of the lane centerline cannot be determined, the endpoint of the lane centerline is calculated by linear interpolation of the vehicle speed, and the maximum point of the coordinates of the first longitudinal sampling point is set based on the endpoint determined by linear interpolation of the vehicle speed.

[0035] Optionally, the process of determining the coordinates of the second longitudinal sampling point includes:

[0036] Determine the minimum point of the centerline of the rearward lane;

[0037] The coordinates of the second longitudinal sampling point are determined based on the minimum point.

[0038] Optionally, the process for determining the fourth trajectory model includes:

[0039] Obtain a set number of historical trajectory points of the vehicle;

[0040] Based on the selection criteria for vehicle history trajectory points, the target vehicle history trajectory point is obtained by selecting from the set number of vehicle history trajectory points.

[0041] The fourth trajectory model is obtained by performing polynomial fitting based on the coordinates corresponding to the historical trajectory points of the target vehicle.

[0042] The selection criteria for the vehicle's historical trajectory points include:

[0043] Points whose horizontal coordinates are greater than a set horizontal coordinate threshold;

[0044] The vertical coordinate at the current moment is greater than the vertical coordinate at the previous moment;

[0045] The vertical coordinate at the current moment is less than zero;

[0046] The current vertical coordinate is less than the minimum value of the vertical coordinate of the vehicle's historical trajectory points;

[0047] The vertical coordinate at the current moment is not equal to the value of the vertical coordinate at the previous moment;

[0048] The difference between the absolute values ​​of the x-coordinates of the previous and current times is greater than the set absolute value difference threshold.

[0049] Optionally, determining the target lane centerline based on the coordinates of the centerlines of the forward lane and the rear lane includes:

[0050] The forward lane centerline model is determined based on the coordinate points corresponding to the forward lane centerline.

[0051] The rear lane centerline model is determined based on the coordinate points corresponding to the rear lane centerline.

[0052] The target lane centerline is determined based on the forward lane centerline model and the backward lane centerline model.

[0053] This application also provides a device for determining the center line of a lane, comprising:

[0054] The target model determination module is used to determine at least one of the first trajectory model, the second trajectory model, and the third trajectory model as the target model; wherein, the first trajectory model is a first trajectory model determined based on the curvature of the current trajectory of the vehicle; the second trajectory model is a second trajectory model obtained by polynomial fitting based on the coordinates corresponding to the historical trajectory points of the target vehicle; and the third trajectory model is a lane centerline model determined based on the visual sensor.

[0055] The first information determination module is used to determine the first lateral coordinate point corresponding to the first longitudinal sampling point coordinate based on the target model, and to determine the weight of the lateral coordinate point corresponding to the first lateral coordinate point. Based on the weight of the lateral coordinate point in the target model and the first lateral coordinate point, the module determines the coordinate point corresponding to the center line of the forward lane.

[0056] The second information determination module is used to filter the second lateral coordinate point determined based on the fourth trajectory model and the coordinates of the second longitudinal sampling point to obtain the filtered second lateral coordinate point, and to determine the coordinate point corresponding to the rearward lane centerline based on the coordinates of the second longitudinal sampling point and the filtered second lateral coordinate point; wherein, the fourth trajectory model is a trajectory model obtained by polynomial fitting based on the coordinates corresponding to the historical trajectory points of the vehicle.

[0057] The third information determination module is used to determine the target lane centerline based on the coordinate points corresponding to the forward lane centerline and the coordinate points corresponding to the backward lane centerline.

[0058] This application also provides a device for determining the center line of a lane, comprising:

[0059] Memory, used to store computer programs;

[0060] A processor for executing the computer program to implement the steps of the method for determining the lane centerline as described above.

[0061] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the lane centerline determination method described above.

[0062] This invention also provides a computer program product, including a computer program / instructions, characterized in that, when the computer program / instructions are executed by a processor, they implement the steps of the lane centerline determination method described above.

[0063] As can be seen, the present invention selects at least one of a first trajectory model, a second trajectory model, and a third trajectory model as the target model; wherein, the first trajectory model is a first trajectory model determined based on the curvature of the current trajectory of the vehicle; the second trajectory model is a second trajectory model obtained by polynomial fitting based on the coordinates corresponding to the historical trajectory points of the target vehicle; the third trajectory model is a lane centerline model determined based on a visual sensor; the first lateral coordinate point corresponding to the first longitudinal sampling point coordinate is determined based on the target model, and the weight of the lateral coordinate point corresponding to the first lateral coordinate point is determined; the coordinate point corresponding to the forward lane centerline is determined based on the lateral coordinate point weight of the target model and the first lateral coordinate point; the second lateral coordinate point determined based on the fourth trajectory model and the second longitudinal sampling point coordinate is filtered to obtain the filtered second lateral coordinate point, and the coordinate point corresponding to the backward lane centerline is determined based on the second longitudinal sampling point coordinate and the filtered second lateral coordinate point; wherein, the fourth trajectory model is a trajectory model obtained by polynomial fitting based on the coordinates corresponding to the historical trajectory points of the vehicle; the target lane centerline is determined based on the coordinate points corresponding to the forward lane centerline and the coordinate points corresponding to the backward lane centerline.

[0064] The beneficial effects of this invention are as follows: Compared with current methods that rely entirely on sensors to generate lane centerlines, this application uses multiple models to determine the lane centerline. The first trajectory model, the second trajectory model, and the fourth trajectory model can all be determined without the use of sensors, thus enabling independent determination of lane centerlines without complete reliance on visual sensors and high-precision maps. Furthermore, this application uses the target trajectory model and the fourth trajectory model to determine the forward and backward lane centerlines, obtaining the target lane centerline. Therefore, even when sensors cannot provide accurate information, lane centerline determination can be achieved without complete reliance on information provided by visual sensors and high-precision maps, allowing for accurate lane centerline determination even under sensor limitations.

[0065] In addition, the present invention also provides a lane centerline determination device, equipment, and readable storage medium, which also have the above-mentioned beneficial effects. Attached Figure Description

[0066] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0067] Figure 1 A flowchart illustrating a method for determining a lane centerline provided in an embodiment of the present invention;

[0068] Figure 2 A schematic diagram of the nearest and farthest points output by a visual sensor, provided in an embodiment of the present invention;

[0069] Figure 3 A schematic diagram of an Ackermann steering model provided in an embodiment of the present invention;

[0070] Figure 4 A flowchart illustrating a method for determining a lane centerline provided in an embodiment of the present invention;

[0071] Figure 5 A trajectory diagram provided for an embodiment of the present invention;

[0072] Figure 6 This is a schematic diagram of a lane centerline determination device provided in an embodiment of the present invention;

[0073] Figure 7 This is a schematic diagram of a lane centerline determination device provided in an embodiment of the present invention. Detailed Implementation

[0074] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0075] Please refer to Figure 1 , Figure 1 A flowchart illustrating a method for determining a lane centerline according to an embodiment of the present invention. The method may include:

[0076] S101, determine that at least one of the first trajectory model, the second trajectory model, and the third trajectory model is selected as the target model; wherein, the first trajectory model is a first trajectory model determined based on the curvature of the current trajectory of the vehicle; the second trajectory model is a second trajectory model obtained by polynomial fitting based on the coordinates corresponding to the historical trajectory points of the target vehicle; and the third trajectory model is a lane centerline model determined based on the visual sensor.

[0077] The execution subject of this embodiment is an electronic device. This electronic device can be a tablet; or it can also be a computer, etc. The first trajectory model in this embodiment is a model determined based on the curvature of the vehicle trajectory; therefore, the first trajectory model in this embodiment is a vehicle trajectory model. In this embodiment, the curvature of the vehicle trajectory refers to the degree to which the curve deviates from a straight line, mathematically representing the numerical value of the curvature of the curve at a certain point. The greater the curvature, the greater the curvature of the curve at that point. In this embodiment, a quadratic function model can be constructed based on the curvature of the vehicle trajectory to obtain the first trajectory model. For example, the first trajectory model can be y = kappa*x. 2 Wherein, kappa represents the curvature of the vehicle's trajectory, x represents the coordinate value in the x-direction, y represents the coordinate value in the y-direction, x represents the longitudinal coordinate, and y represents the lateral coordinate. In this embodiment, the second trajectory model is a polynomial equation, and the second trajectory model in this embodiment is the target vehicle's historical trajectory model. The third trajectory model in this embodiment is a model obtained by determining the coefficients of the polynomial equation based on a visual sensor; therefore, the third trajectory model in this embodiment is a visual sensor model.

[0078] It should be further noted that, in order to improve the accuracy of the target model determination, before selecting at least one of the first trajectory model, the second trajectory model, and the third trajectory model as the target model, the following may also be included:

[0079] Step 1: Construct a quadratic function model based on the curvature of the vehicle trajectory to obtain the dynamic first trajectory model.

[0080] Step 2: Filter the lateral coordinates of the historical trajectory points of the target vehicle for each cycle to obtain the filtered lateral coordinates of the target vehicle. Based on the filtered lateral coordinates, obtain the historical trajectory points of the target vehicle.

[0081] This embodiment performs a first-order low-pass filter on the lateral coordinates of the target vehicle's historical trajectory points and the lateral coordinates of the previous cycle to obtain the filtered lateral coordinates. y0 = ay + (1-a)y'; where a is the filtering coefficient of the previous moment (e.g., 0.9, 0.85, 0.95, etc.), and y0 and y' represent the lateral coordinates of the current cycle and the previous cycle, respectively. The target vehicle's historical trajectory points are determined based on a certain number of recorded longitudinal coordinates and their corresponding filtered lateral coordinates.

[0082] Step 3: Perform polynomial curve fitting based on the historical trajectory points of the target vehicle to obtain the second trajectory model.

[0083] This embodiment can perform polynomial curve fitting based on the historical trajectory points of the target vehicle to obtain the historical trajectory equation of the target vehicle; y = c3x 3 +c2x2 +c1x 3 +c0.

[0084] Step 4: Determine the third trajectory model based on the rate of change of lane centerline curvature, lane centerline curvature, lane centerline orientation angle, and lane centerline offset distance determined by the visual sensor.

[0085] In this embodiment, the third trajectory model determined based on the rate of change of lane centerline curvature, lane centerline curvature, lane centerline orientation angle, and lane centerline offset distance can be y = a3x. 3 +a2x 2 +a1x 3 +a0, where a3 represents the rate of change of the lane centerline curvature, a2 represents the lane centerline curvature, a1 represents the lane centerline orientation angle, and a0 represents the lane centerline offset distance.

[0086] This embodiment improves the accuracy of determining various models in the target model by providing specific methods for determining these models, thereby improving the accuracy of subsequent calculations of lane centerlines.

[0087] It should be further explained that, in order to improve the accuracy of target vehicle determination, the lateral coordinates of the historical trajectory points of the target vehicle in each cycle are filtered to obtain the filtered lateral coordinates of the target vehicle. Before obtaining the historical trajectory points of the target vehicle based on the filtered lateral coordinates, the method may further include: selecting a preset number of vehicles as target vehicles based on target vehicle selection rules; wherein, the target vehicle selection rules are determined based on the vehicle's coordinate values ​​and the time the vehicle is within the driver's field of vision. In this embodiment, the vehicle's coordinate values ​​can refer to the defined conditions of the vehicle's longitudinal and lateral coordinate values. The target vehicle selection rules in this embodiment include: the vehicle's longitudinal coordinate value is within a set longitudinal coordinate value range; the difference between the vehicle's lateral coordinate value and the driver's lateral coordinate value is within a set difference threshold; the time the vehicle is within the driver's field of vision is greater than a set time threshold; and the standard deviation of the vehicle's lateral coordinate value is less than a set standard deviation threshold. This embodiment does not limit the specific range of longitudinal coordinate values; for example, the range of longitudinal coordinate values ​​can be between 4 meters and 120 meters; or the range of longitudinal coordinate values ​​can also be between 4 meters and 150 meters. This embodiment does not limit the specific difference threshold. For example, the difference threshold in this embodiment can be 1.5 meters and -1.5 meters; or the difference threshold in this embodiment can also be 1.4 meters to -1.5 meters, that is, the difference is between 1.5 meters and -1.5 meters, or the difference is between 1.4 meters and -1.5 meters. The time threshold in this embodiment can be 0.06 seconds, that is, not less than 0.06 seconds; or the time threshold can also be 0.07 seconds. This embodiment does not limit a specific standard deviation threshold. The standard deviation in this embodiment needs to be less than the standard deviation threshold. For example, the standard deviation threshold in this embodiment can be 0.05; or the standard deviation threshold in this embodiment can be 0.04. This embodiment improves the accuracy of target vehicle determination by setting a specific target vehicle selection method.

[0088] S102, determine the first lateral coordinate point corresponding to the first longitudinal sampling point coordinate based on the target model, and determine the weight of the lateral coordinate point corresponding to the first lateral coordinate point. Determine the coordinate point corresponding to the center line of the forward lane based on the weight of the lateral coordinate point of the target model and the first lateral coordinate point.

[0089] This embodiment does not limit the specific target model. For example, the target model in this embodiment can be any one of the first trajectory model, the second trajectory model, and the third trajectory model; or the target model in this embodiment can be at least two of the first trajectory model, the second trajectory model, and the third trajectory model; or the target model in this embodiment can be all three models: the first trajectory model, the second trajectory model, and the third trajectory model. This embodiment does not limit the specific method for determining the coordinates of the first longitudinal sampling point. In this embodiment, the coordinates of the first longitudinal sampling point are coordinates related to the lane centerline. For example, in this embodiment, the start and end points of the first longitudinal sampling point coordinates can be determined first, and then the coordinates of the first longitudinal sampling point can be determined. This embodiment does not limit the specific method for determining the weights of the lateral coordinate points corresponding to the first lateral coordinates. For example, in this embodiment, the weights of the lateral coordinate points can be determined based on requirements; or in this embodiment, the weights of the lateral coordinate points can be determined based on variance. In this embodiment, the process of determining the coordinate points corresponding to the forward lane centerline based on the weights of the lateral coordinate points of the target model and the first lateral coordinate points can be: determining the target lateral coordinate points based on the weights of the lateral coordinate points and the first lateral coordinate points; and determining the forward lane centerline based on the target lateral coordinate points and the coordinates of the first longitudinal sampling points. In this embodiment, the forward lane centerline refers to the reference line corresponding to the current first trajectory model. That is, the current first trajectory model and the fourth trajectory model are used as a method to distinguish the forward lane centerline and the rear lane centerline. In this embodiment, each coordinate point can be determined based on the rear axle center of the vehicle.

[0090] It should be further explained that when the first trajectory model, the second trajectory model, and the third trajectory model are selected as the target models, the first lateral coordinate point corresponding to the first longitudinal sampling point is determined based on the target models, and the weight of the lateral coordinate point corresponding to the first lateral coordinate point is determined. The coordinate point corresponding to the center line of the forward lane is determined based on the weight of the lateral coordinate point of the target models and the first lateral coordinate point, which may include:

[0091] S1021, Based on the first trajectory model, the second trajectory model and the third trajectory model, determine the first lateral coordinate point of the vehicle, the first lateral coordinate point of the target vehicle and the first lateral coordinate point of the sensor corresponding to the coordinates of the first longitudinal sampling point.

[0092] This embodiment can perform forward longitudinal distance sampling, sampling a longitudinal coordinate at regular intervals (e.g., 2 meters) to obtain the coordinates of the first longitudinal sampling point. For example, the longitudinal sampling point coordinates in this embodiment can be Δx, 2Δx, 3Δx, 4Δx, ..., nΔx. Based on the coordinates of the first longitudinal sampling point and three trajectory models (trajectory line 1, trajectory line 2, and trajectory line 3 represent the first trajectory model, the second trajectory model, and the third trajectory model, respectively), the first lateral coordinate point under the coordinates of the first longitudinal sampling point is calculated, as shown in Table 1: Table 1 is a schematic table of the first lateral coordinate point provided by this embodiment of the invention.

[0093] Table 1. Schematic diagram of a first horizontal coordinate point.

[0094]

[0095] S1022, based on the first lateral coordinate point of the self-vehicle, the first lateral coordinate point of the target vehicle, and the first lateral coordinate point of the sensor, determine the average value of the first lateral coordinate point corresponding to the coordinates of each first longitudinal sampling point.

[0096] The average value of the first horizontal coordinate point determined in this embodiment is shown in Table 2. Table 2 is a schematic table of the average value of the first horizontal coordinate point provided by the embodiment of the present invention.

[0097] Table 2. Schematic diagram of the average value of the first horizontal coordinate point.

[0098]

[0099] S1023, based on the first lateral coordinate point of the self-vehicle, the first lateral coordinate point of the target vehicle, the first lateral coordinate point of the sensor, and the average value of the first lateral coordinate point, determine the variance of the lateral coordinate points under the three models corresponding to the coordinates of each first longitudinal sampling point.

[0100] The variances of the lateral coordinate points corresponding to the three trajectory models in this embodiment are shown in Table 3. Table 3 is a schematic table of the variances of lateral coordinate points provided by an embodiment of the present invention.

[0101] Table 3. A schematic diagram of the variance of a horizontal coordinate point.

[0102] Δx 2Δx 3Δx 4Δx 5Δx 6Δx 7Δx …… nΔx Trajectory Line 1 <![CDATA[σ 11 ]]> <![CDATA[σ 12 ]]> <![CDATA[σ 13 ]]> <![CDATA[σ 14 ]]> <![CDATA[σ 15 ]]> <![CDATA[σ 16 ]]> <![CDATA[σ 17 ]]> …… <![CDATA[σ 1n ]]> Trajectory Line 2 <![CDATA[σ 21 ]]> <![CDATA[σ 22 ]]> <![CDATA[σ 23 ]]> <![CDATA[σ 24 ]]> <![CDATA[σ 25 ]]> <![CDATA[σ2x]]> <![CDATA[σ 27 ]]> …… <![CDATA[σ 2n ]]> Trajectory Line 3 <![CDATA[σ 31 ]]> <![CDATA[σ 32 ]]> <![CDATA[σ 33 ]]> <![CDATA[σ 34 ]]> <![CDATA[σ 35 ]]> <![CDATA[σ 36 ]]> <![CDATA[σ 37 ]]> …… <![CDATA[σ 3n ]]>

[0103] S1024, determine the weighted average of the first horizontal coordinate points corresponding to each first vertical sampling point based on the variance of the horizontal coordinate points.

[0104] Understandably, in statistics, each data point has a corresponding weight value. This weight value determines the importance of the data point in calculating the average. By multiplying the values ​​of each data point by their weight values, summing the results, and then dividing by the sum of all weight values, the weighted average can be obtained. Here, the inverse variance weighting method is used, meaning that the weight of the data is inversely proportional to its variance, to determine the weighted average for each first horizontal coordinate point.

[0105] S1025, determine the weight of the horizontal coordinate point corresponding to each first horizontal coordinate point based on the weighted average value.

[0106] This embodiment uses a weighted average as the weight for the horizontal coordinate points. This embodiment provides a specific method for determining the weights, thus improving the accuracy of weight determination.

[0107] S1026, Based on the weight of each lateral coordinate point, determine the target first lateral coordinate point corresponding to each first longitudinal sampling point, and obtain the coordinate point corresponding to the center line of the forward lane based on the coordinates of the first longitudinal sampling point and the target first lateral coordinate point.

[0108] In this embodiment, the target first lateral coordinate point corresponding to the coordinates of the first longitudinal sampling point can be obtained, and the two have a one-to-one correspondence. This embodiment can improve the accuracy of determining the coordinate point corresponding to the center line of the forward lane through the above processing.

[0109] It should be further explained that, in order to improve the accuracy of determining the coordinates of the first longitudinal sampling point, before determining the first lateral coordinate point corresponding to the coordinates of the first longitudinal sampling point based on the target model, the method may further include: determining whether the visual sensor can determine the endpoint of the lane centerline; when it is determined that the endpoint of the lane centerline can be determined, setting the maximum point of the coordinates of the first longitudinal sampling point based on the endpoint determined by the visual sensor; when it is determined that the endpoint of the lane centerline cannot be determined, calculating the endpoint of the lane centerline through linear interpolation of the vehicle's speed, and setting the maximum point of the coordinates of the first longitudinal sampling point based on the endpoint determined by linear interpolation of the vehicle speed. In this embodiment, the linear speed interpolation refers to determining the distance corresponding to the current speed based on the given speed and corresponding distance, and using this distance as the endpoint. For ease of understanding, please refer to Table 3, which is a linear speed interpolation table provided by an embodiment of the present invention. For example, if the position corresponding to a speed of 75 is determined as the endpoint, the distance value corresponding to this endpoint is determined based on speeds of 60 and 80 and distances d2 and d3.

[0110] Table 4. A linear interpolation table for vehicle speed.

[0111] speed distance 20 d0 40 d1 60 d2 80 d3 100 d4 120 d5

[0112] For easier understanding, please refer to Figure 2 , Figure 2This is a schematic diagram of the nearest and farthest points (end points) output by a visual sensor according to an embodiment of the present invention; wherein, the nearest point can be used as the starting point of the first longitudinal sampling point coordinates, or simply the farthest point can be used as the end point of the first longitudinal sampling point coordinates. In the figure, d-low represents the nearest point and d-up represents the farthest point.

[0113] S103, the second lateral coordinate point determined based on the fourth trajectory model and the coordinates of the second longitudinal sampling point is filtered to obtain the filtered second lateral coordinate point, and the coordinate point corresponding to the center line of the rear lane is determined based on the coordinates of the second longitudinal sampling point and the filtered second lateral coordinate point; wherein, the fourth trajectory model is a trajectory model obtained by polynomial fitting based on the coordinates corresponding to the historical trajectory points of the vehicle.

[0114] The fourth trajectory model in this embodiment can be obtained by polynomial fitting based on the coordinates corresponding to the vehicle's historical trajectory points. This embodiment does not limit the specific process of obtaining the fourth trajectory model. For example, this embodiment can select historical trajectory points to obtain target historical trajectory points, and obtain the fourth trajectory model based on the target historical trajectory points; or this embodiment can directly determine the fourth trajectory model based on the vehicle's historical trajectory points. This embodiment does not limit the specific method for determining the coordinates of the second longitudinal sampling point. For example, the coordinates of the second longitudinal sampling point in this embodiment can be determined based on the endpoint related to the determined rear lane centerline; or this embodiment can be determined based on the start and end points related to the rear lane centerline. To suppress noise, this embodiment does not limit the specific method for filtering the second lateral coordinate points. For example, this embodiment can perform filtering based on the current second lateral coordinate point (which can be understood as the currently used historical second lateral coordinate point) and the second lateral coordinate point of the previous cycle to obtain the filtered second lateral coordinate point.

[0115] It should be further explained that the process of determining the coordinates of the second longitudinal sampling point may include: determining the minimum point of the rearward lane centerline; and determining the coordinates of the second longitudinal sampling point based on the minimum point. This embodiment does not limit the specific minimum value; for example, the minimum value can be -20; or the minimum value can also be -50, the negative sign indicating it is the rearward lane centerline. This embodiment can use this minimum value as... The endpoint of the second longitudinal sampling point is used to determine the second longitudinal sampling point based on the endpoint of the second longitudinal sampling point and the set interval distance. For example, it can be done by... As a set sampling distance (the sampling distance corresponding to the second longitudinal sampling point), the coordinates of the second longitudinal sampling point can be represented as -Δx, -2Δx, -3Δx, -4Δx, ..., -nΔx. This embodiment provides a specific method for determining the left coordinate of the second longitudinal sampling point, improving the accuracy of the determination of the coordinates of the second longitudinal sampling point.

[0116] It should be further explained that, in order to improve the accuracy of the fourth trajectory model, the above-mentioned polynomial fitting based on the coordinates corresponding to the vehicle's historical trajectory points yields the fourth trajectory model, which may include:

[0117] S1, acquire a set number of historical trajectory points of the vehicle; select from the set number of historical trajectory points based on the selection criteria of the historical trajectory points to obtain the target historical trajectory point of the vehicle. The selection criteria of the historical trajectory points include: the horizontal coordinate of the trajectory point is greater than a set horizontal coordinate threshold; the vertical coordinate of the current moment is greater than the vertical coordinate of the previous moment; the vertical coordinate of the current moment is less than zero; the vertical coordinate of the current moment is less than the minimum value of the vertical coordinate of the historical trajectory point; the vertical coordinate of the current moment is not equal to the value of the vertical coordinate of the previous moment; the difference between the absolute values ​​of the horizontal coordinates of the previous moment and the current moment is greater than a set absolute value difference threshold.

[0118] The lateral coordinate threshold in this embodiment can include a maximum and a minimum lateral coordinate value, where the minimum value can be -1, -1.5, etc.; the maximum lateral coordinate value in this embodiment can be 1, 1.5, etc. This embodiment does not limit the minimum value of the longitudinal coordinate of the vehicle's historical trajectory points; for example, the minimum value can be 50, 51, etc. The absolute value difference threshold in this embodiment can be 0.05, 0.06, etc. This embodiment does not limit the specific method for determining the vehicle's historical trajectory points; for example, this embodiment can determine them based on the Ackerman steering model. For ease of understanding, please refer to... Figure 3 , Figure 3 This is a schematic diagram of an Ackermann steering model provided in an embodiment of the present invention. Figure 3 In this context, δi and δo represent the turning angles of the inner and outer front wheels, respectively. Lb and Lw represent the length and width of the vehicle, respectively. delt-x = egoCurneRadius * sina; delt-y = egoCurneRadius * cosa. Here, α represents the radius of curvature of the vehicle's historical trajectory, α represents the angle of rotation during curvilinear motion, and delt-x and delt-y represent the positional offsets in the x and y directions, respectively.

[0119] S2, based on the coordinates corresponding to the historical trajectory points of the target vehicle, a polynomial fitting is performed to obtain the fourth trajectory model.

[0120] This embodiment performs polynomial fitting based on the obtained historical trajectory points of the vehicle, resulting in a polynomial equation for the historical trajectory that includes cubic coefficients, quadratic coefficients, linear coefficients, and a constant term. This embodiment also provides a detailed process for determining the fourth trajectory model, improving its accuracy.

[0121] S104, determine the target lane centerline based on the coordinates of the centerline of the forward lane and the centerline of the rear lane.

[0122] This embodiment does not limit the specific method for determining the target lane centerline. For example, this embodiment can directly determine the target lane centerline by using the coordinates of the rear lane centerline and the coordinates of the front lane centerline; or this embodiment can also determine the rear lane centerline model based on the coordinates of the rear lane centerline, determine the front lane centerline model based on the coordinates of the front lane centerline, and determine the target lane centerline based on the front lane centerline model and the rear lane centerline model.

[0123] It should be further explained that the above-mentioned determination of the target lane centerline based on the coordinate points corresponding to the centerlines of the forward and rear lanes can include: determining a forward lane centerline model based on the coordinate points corresponding to the centerlines of the forward lane; determining a rear lane centerline model based on the coordinate points corresponding to the centerlines of the rear lane; and determining the target lane centerline based on the forward and rear lane centerline models. This embodiment can determine the target lane centerline based on the forward and rear lane centerline models.

[0124] This invention provides a method for determining a lane centerline, which may include: S101, selecting at least one of a first trajectory model, a second trajectory model, and a third trajectory model as a target model; wherein, the first trajectory model is determined based on the curvature of the vehicle's trajectory; and a second trajectory model is obtained by polynomial fitting based on the coordinates corresponding to the historical trajectory points of the target vehicle. S102, determining a first lateral coordinate point corresponding to the coordinates of a first longitudinal sampling point based on the target model, and determining the weight of the lateral coordinate point corresponding to the first lateral coordinate point; and determining the coordinate point corresponding to the forward lane centerline based on the weight of the lateral coordinate point of the target model and the first lateral coordinate point. S103, determining a second lateral coordinate point corresponding to the coordinates of a second longitudinal sampling point based on a fourth trajectory model, and performing filtering processing on the corresponding second lateral coordinate point of the previous cycle to obtain a filtered second lateral coordinate point; wherein, a fourth trajectory model is obtained by polynomial fitting based on the coordinates corresponding to the historical trajectory points of the vehicle. S104, determining the coordinate point corresponding to the backward lane centerline based on the coordinates of the second longitudinal sampling point and the filtered second lateral coordinate point, and determining the target lane centerline based on the coordinate points corresponding to the forward lane centerline and the backward lane centerline. Compared to current methods that rely entirely on sensors to generate lane centerlines, this application uses parameters that can be obtained without relying on sensors when generating lane centerlines. This allows for accurate determination of lane centerlines based on multiple models without relying on sensors. Furthermore, specific methods for determining the first, second, and third trajectory models are provided, improving the accuracy of model determination. This embodiment also determines the target vehicle based on set conditions, enabling accurate determination of the lane centerline based on the accurate target vehicle. Moreover, this embodiment provides a specific process for determining the coordinate points corresponding to the forward lane centerline based on the three trajectory models (first, second, and third), improving the accuracy of determining the coordinate points corresponding to the forward lane centerline. Additionally, specific methods for determining the coordinates of the first and second longitudinal sampling points are provided, improving sampling accuracy. Finally, a specific method for determining the fourth trajectory model is provided, improving the accuracy of the fourth trajectory model determination.

[0125] For a clearer understanding of this invention, please refer to the following details. Figure 4 , Figure 4 A flowchart illustrating a method for determining a lane centerline provided in an embodiment of the present invention may specifically include:

[0126] S201, Select from the historical trajectory points of the vehicle to obtain the target historical trajectory point of the vehicle, and perform polynomial fitting based on the coordinates corresponding to the target historical trajectory point of the vehicle to obtain the historical trajectory model of the vehicle (corresponding to the fourth trajectory model above).

[0127] For easier understanding, please refer to Figure 5 , Figure 5 This invention provides a trajectory diagram, which includes the target vehicle's historical trajectory, the vehicle's trajectory, the vehicle's historical trajectory, and the visual lane centerline. The selection criteria in this invention include: ① points with abscissas greater than a threshold abscissa; ② the current ordinate is greater than the previous ordinate; ③ the current ordinate is less than 0; ④ the current ordinate is less than the minimum value of the ordinate of a point on the vehicle's historical trajectory; ⑤ the current ordinate is not equal to the value of the previous ordinate; ⑥ the difference between the absolute values ​​of the abscissas of the previous and current times is greater than an absolute value difference threshold.

[0128] S202, Determine the current trajectory model of the vehicle based on the curvature of the vehicle trajectory.

[0129] The current trajectory model of the vehicle in this embodiment corresponds to the vehicle trajectory model mentioned above (corresponding to the first trajectory model mentioned above).

[0130] S203: Based on the selection rules, the target vehicle is determined from the adjacent vehicles. A first-order low-pass filter is performed on the lateral coordinates of the target vehicle's historical trajectory points in the current period and the previous period to obtain the filtered historical trajectory points of the target vehicle.

[0131] In this embodiment, the selection rules include: ① the longitudinal coordinate x of the target vehicle is within a set range; ② the difference between the horizontal coordinate of the target vehicle and the horizontal coordinate of the vehicle is within a set difference threshold; ③ the period of the target's presence in the field of view is greater than a set time threshold; ④ the standard deviation of the target's horizontal coordinate is less than a set standard deviation threshold.

[0132] S204. Based on the filtered historical trajectory points of the target vehicle, a polynomial curve fitting is performed to obtain the historical trajectory model of the target vehicle (corresponding to the second trajectory model mentioned above).

[0133] The target vehicle historical trajectory model in this embodiment is:

[0134] y3=c3x3 3 +c2x3 2 +c1x3+c0.

[0135] S205, the visual sensor model (corresponding to the third trajectory model above) is determined based on the data collected by the visual sensor as parameters.

[0136] The visual sensor model in this embodiment is y4 = a3x4 3 +a2x4 2 +a1x4+a0; where a3 represents the rate of change of the lane centerline curvature, a2 represents the lane centerline curvature, a1 represents the lane line orientation angle, and a0 represents the lane centerline offset distance.

[0137] S206, determine the endpoint of the forward lane centerline based on a visual sensor or a vehicle speed linear interpolation table, and determine the coordinates of the first longitudinal sampling point based on the endpoint of the forward lane centerline.

[0138] In this embodiment, ① the quality of the lane line is determined by a visual sensor. If it meets the requirements, the start and end points of the lane center line in the visual sensor are taken as the start and end points of the forward lane center line; ② if it does not meet the requirements, the start and end points of the forward lane center line are determined by linear interpolation of the vehicle speed.

[0139] S207. Based on the coordinates of the first longitudinal sampling point, determine the first lateral coordinate points corresponding to the three trajectory models: the current trajectory model of the vehicle, the historical trajectory model of the target, and the visual sensor model, and calculate the average value of the first lateral coordinate points.

[0140] S208. Based on the first horizontal coordinate point and the average value of the first horizontal coordinate point for each trajectory line model, determine the variance of the first horizontal coordinate point, determine the weight of the weighted average value based on the variance of the first horizontal coordinate point, and determine the target first horizontal coordinate corresponding to the coordinate of each first vertical sampling point based on the weight.

[0141] S209, determine the coordinates of the forward lane centerline based on the target's first lateral coordinates and the coordinates of the first longitudinal sampling point.

[0142] S210, determine the coordinates of the second longitudinal sampling point based on the minimum value of the rear lane centerline, and perform first-order low-pass filtering based on the coordinates of the second longitudinal sampling point and the vehicle's historical trajectory points in the current historical period and the corresponding historical trajectory points in the previous period of the vehicle's historical trajectory model to obtain the filtered second lateral coordinate points.

[0143] The vehicle history trajectory model in this embodiment corresponds to the fourth trajectory model mentioned above.

[0144] S211, the coordinates of the rearward lane centerline are determined based on the filtered coordinates of the second lateral coordinate point and the second longitudinal sampling point.

[0145] S212, determine the target lane centerline based on the coordinates of the forward lane centerline and the rear lane centerline.

[0146] This invention utilizes multiple trajectory line models to sample forward and backward trajectories, and integrates multiple models to calculate the lane centerline, thereby improving the accuracy of determining the target lane centerline in situations such as intersections with poor lane line quality or no lane lines, unstructured roads, and curves.

[0147] The lane centerline determination device provided in the embodiments of the present invention will be described below. The lane centerline determination device described below and the lane centerline determination method described above can be referred to in correspondence.

[0148] Please refer to the details. Figure 6 , Figure 6 A schematic diagram of a lane centerline determination device provided in an embodiment of the present invention may include:

[0149] The target model determination module 100 is used to determine at least one of a first trajectory model, a second trajectory model, and a third trajectory model as the target model; wherein, the first trajectory model is determined based on the curvature of the vehicle trajectory; and the second trajectory model is obtained by polynomial fitting based on the coordinates corresponding to the historical trajectory points of the target vehicle.

[0150] The first information determination module 200 is used to determine the first lateral coordinate point corresponding to the first longitudinal sampling point coordinate based on the target model, and to determine the weight of the lateral coordinate point corresponding to the first lateral coordinate point. Based on the weight of the lateral coordinate point in the target model and the first lateral coordinate point, the coordinate point corresponding to the center line of the forward lane is determined.

[0151] The second information determination module 300 is used to determine the second lateral coordinate point corresponding to the second longitudinal sampling point based on the fourth trajectory model, and to filter the second lateral coordinate point of the previous cycle to obtain the filtered second lateral coordinate point; wherein, the fourth trajectory model is obtained by performing polynomial fitting based on the coordinates corresponding to the historical trajectory points of the vehicle.

[0152] The third information determination module 400 is used to determine the coordinate point corresponding to the rearward lane centerline based on the coordinates of the second longitudinal sampling point and the filtered second lateral coordinate point, and to determine the target lane centerline based on the coordinate point corresponding to the forward lane centerline and the coordinate point corresponding to the rearward lane centerline.

[0153] Furthermore, based on the above embodiments, the lane centerline determining device may further include:

[0154] The first trajectory model determination module is used to construct a quadratic function model based on the curvature of the vehicle trajectory to obtain the dynamic first trajectory model.

[0155] The target vehicle historical trajectory point determination module is used to filter the lateral coordinate points of the historical trajectory points of the target vehicle in each cycle to obtain the filtered lateral coordinate points corresponding to the target vehicle, and to obtain the target vehicle historical trajectory points based on the filtered lateral coordinate points.

[0156] The second trajectory model determination module is used to perform polynomial curve fitting based on the historical trajectory points of the target vehicle to obtain the second trajectory model.

[0157] The third trajectory model determination module is used to determine the third trajectory model based on the rate of change of lane centerline curvature, lane centerline curvature, lane centerline orientation angle, and lane centerline offset distance determined by the visual sensor.

[0158] Furthermore, based on the above embodiments, the lane centerline determining device may further include:

[0159] The target vehicle determination module is used to select a preset number of vehicles as target vehicles based on target vehicle selection rules; wherein, the target vehicle selection rules are determined based on the vehicle's coordinate values ​​and the time the vehicle is within the driver's field of vision; wherein, the target vehicle selection rules may include: the vehicle's longitudinal coordinate value is within a set longitudinal coordinate value range; the difference between the vehicle's lateral coordinate value and the driver's lateral coordinate value is within a set difference threshold; the vehicle is within the driver's field of vision for a time greater than a set time threshold; and the standard deviation of the vehicle's lateral coordinate value is less than a set standard deviation threshold.

[0160] Furthermore, based on any of the above embodiments, the target model determination module 100 includes:

[0161] The target model determination unit is used to determine the first trajectory model, the second trajectory model, and the third trajectory model as the target models.

[0162] Accordingly, the first information determination module 200 includes:

[0163] The lateral coordinate point determination unit is used to determine the first lateral coordinate point of the vehicle, the first lateral coordinate point of the target vehicle, and the first lateral coordinate point of the sensor corresponding to the coordinates of the first longitudinal sampling point, based on the first trajectory model, the second trajectory model, and the third trajectory model.

[0164] The average value determination unit is used to determine the average value of the first lateral coordinate point corresponding to each first longitudinal sampling point based on the first lateral coordinate point of the vehicle, the first lateral coordinate point of the target vehicle, and the first lateral coordinate point of the sensor.

[0165] The variance determination unit is used to determine the variance of the lateral coordinate points under the three models corresponding to the coordinates of each first longitudinal sampling point based on the first lateral coordinate point of the self-vehicle, the first lateral coordinate point of the target vehicle, the first lateral coordinate point of the sensor, and the average value of the first lateral coordinate points.

[0166] The weighted average determination unit is used to determine the weighted average of the first horizontal coordinate points corresponding to each first vertical sampling point based on the variance of the horizontal coordinate points.

[0167] The weight determination unit is used to determine the weight of the horizontal coordinate point corresponding to each first horizontal coordinate point based on the weighted average value.

[0168] The coordinate point determination unit corresponding to the center line of the forward lane is used to determine the target first lateral coordinate point corresponding to each first longitudinal sampling point based on the weight of each lateral coordinate point, and to obtain the coordinate point corresponding to the center line of the forward lane based on the first longitudinal sampling point and the target first lateral coordinate point.

[0169] Furthermore, based on any of the above embodiments, the lane centerline determining device may further include:

[0170] The judgment module is used to determine whether the vision sensor can determine the end point of the lane center line;

[0171] The first type of first longitudinal sampling point coordinate setting module is used to set the maximum value point of the first longitudinal sampling point coordinate based on the endpoint determined by the visual sensor when it is determined that the endpoint of the lane center line can be determined.

[0172] The second type of first longitudinal sampling point coordinate setting module is used to calculate the end point of the lane center line by linear interpolation of the vehicle speed when the end point of the lane center line cannot be determined, and to set the maximum point of the first longitudinal sampling point coordinates based on the end point determined by linear interpolation of the vehicle speed.

[0173] Furthermore, based on any of the above embodiments, the lane centerline determining device may further include:

[0174] The minimum point determination module is used to determine the minimum point of the center line of the rear lane;

[0175] The second longitudinal sampling point coordinate determination module is used to determine the coordinates of the second longitudinal sampling point based on the minimum point.

[0176] Furthermore, based on any of the above embodiments, the second information determination module 300 may include:

[0177] A set number of vehicle historical trajectory point determination units are used to obtain a set number of vehicle historical trajectory points;

[0178] The target vehicle historical trajectory point determination unit is used to select from the set number of vehicle historical trajectory points based on the vehicle historical trajectory point selection conditions to obtain the target vehicle historical trajectory point.

[0179] The fourth trajectory model determination unit is used to perform polynomial fitting based on the coordinates corresponding to the historical trajectory points of the target vehicle to obtain the fourth trajectory model.

[0180] The selection criteria for the vehicle's historical trajectory points include:

[0181] Points whose horizontal coordinates are greater than a set horizontal coordinate threshold;

[0182] The vertical coordinate at the current moment is greater than the vertical coordinate at the previous moment;

[0183] The vertical coordinate at the current moment is less than zero;

[0184] The current vertical coordinate is less than the minimum value of the vertical coordinate of the vehicle's historical trajectory points;

[0185] The vertical coordinate at the current moment is not equal to the value of the vertical coordinate at the previous moment;

[0186] The difference between the absolute values ​​of the x-coordinates of the previous and current times is greater than the set absolute value difference threshold.

[0187] Furthermore, based on any of the above embodiments, the third information determination module 400 may include:

[0188] A forward lane centerline model determination unit is used to determine the forward lane centerline model based on the coordinate points corresponding to the forward lane centerline.

[0189] The rear lane centerline model determination unit is used to determine the rear lane centerline model based on the coordinate points corresponding to the rear lane centerline.

[0190] The target lane centerline determination unit is used to determine the target lane centerline based on the forward lane centerline model and the backward lane centerline model.

[0191] It should be noted that the order of the modules and units in the above-mentioned lane centerline determination device can be changed without affecting the logic.

[0192] The lane centerline determination device provided in this embodiment of the invention may include: a target model determination module 100, used to determine at least one of a first trajectory model, a second trajectory model, and a third trajectory model as a target model; wherein, the first trajectory model is determined based on the curvature of the vehicle trajectory; and the second trajectory model is obtained by polynomial fitting based on the coordinates corresponding to the historical trajectory points of the target vehicle; and a first information determination module 200, used to determine a first lateral coordinate point corresponding to the coordinates of a first longitudinal sampling point based on the target model, and determine the weight of the lateral coordinate point corresponding to the first lateral coordinate point, and determine the forward vehicle based on the weight of the lateral coordinate point of the target model and the first lateral coordinate point. The system comprises three information determination modules: a first module 300 and a second information determination module 400. The first module 300 determines the coordinates of the second longitudinal sampling point based on the fourth trajectory model, and filters the second lateral coordinates of the corresponding second lateral coordinates from the previous cycle to obtain the filtered second lateral coordinates. The fourth trajectory model is obtained by performing polynomial fitting based on the coordinates of the vehicle's historical trajectory points. The second module 400 determines the coordinates of the rearward lane centerline based on the second longitudinal sampling point coordinates and the filtered second lateral coordinates, and determines the target lane centerline based on the coordinates of the forward lane centerline and the rearward lane centerline. Compared to current methods that rely entirely on sensors to generate lane centerlines, this application uses parameters that can be obtained without relying on sensors when generating lane centerlines, enabling accurate determination of lane centerlines based on multiple models without relying on sensors.

[0193] The following describes a lane centerline determination device provided by an embodiment of the present invention. The lane centerline determination device described below can be referred to in correspondence with the lane centerline determination method described above.

[0194] Please refer to Figure 7 , Figure 7 A schematic diagram of a lane centerline determination device provided in an embodiment of the present invention may include:

[0195] Memory 10 is used to store computer programs;

[0196] Processor 20 is used to execute computer programs to implement the above-described method for determining the lane centerline.

[0197] The memory 10, processor 20, and communication interface 30 all communicate with each other through the communication bus 40.

[0198] In this embodiment of the invention, the memory 10 is used to store one or more programs. The programs may include program code, which includes computer operation instructions. In this embodiment of the invention, the memory 10 may store programs for implementing the following functions:

[0199] At least one of the first trajectory model, the second trajectory model, and the third trajectory model is selected as the target model; wherein, the first trajectory model is determined based on the curvature of the vehicle trajectory; and the second trajectory model is obtained by polynomial fitting based on the coordinates corresponding to the historical trajectory points of the target vehicle.

[0200] Based on the target model, determine the first lateral coordinate point corresponding to the first longitudinal sampling point coordinate, and determine the weight of the lateral coordinate point corresponding to the first lateral coordinate point. Based on the weight of the lateral coordinate point of the target model and the first lateral coordinate point, determine the coordinate point corresponding to the center line of the forward lane.

[0201] Based on the fourth trajectory model, the second lateral coordinate point corresponding to the second longitudinal sampling point is determined, and the second lateral coordinate point of the previous cycle is filtered to obtain the filtered second lateral coordinate point; among them, the fourth trajectory model is obtained by polynomial fitting based on the coordinates corresponding to the historical trajectory points of the vehicle.

[0202] The coordinates of the rear lane centerline are determined based on the coordinates of the second longitudinal sampling point and the filtered second lateral coordinates, and the target lane centerline is determined based on the coordinates of the front lane centerline and the rear lane centerline.

[0203] In one possible implementation, the memory 10 may include a program storage area and a data storage area, wherein the program storage area may store the operating system and applications required for at least one function; and the data storage area may store data created during use.

[0204] Furthermore, memory 10 may include read-only memory and random access memory, providing instructions and data to the processor. A portion of the memory may also include NVRAM. The memory stores operating systems and operating instructions, executable modules, or data structures, or subsets thereof, or extended sets thereof, wherein the operating instructions may include various operating instructions for implementing various operations. The operating system may include various system programs for implementing various basic tasks and handling hardware-based tasks.

[0205] Processor 20 can be a central processing unit (CPU), an application-specific integrated circuit, a digital signal processor, a field-programmable gate array, or other programmable logic device. Processor 20 can be a microprocessor or any conventional processor. Processor 20 can call programs stored in memory 10.

[0206] The communication interface 30 can be an interface for the communication module, used to connect with other devices or systems.

[0207] Of course, it should be noted that, Figure 7 The structure shown does not constitute a limitation on the lane centerline determination device in the embodiments of the present invention. In practical applications, the lane centerline determination device may include devices that are more advanced than those described above. Figure 7 More or fewer components as shown, or combinations of certain components.

[0208] The readable storage medium provided in the embodiments of the present invention is described below. The readable storage medium described below and the method for determining the lane center line described above can be referred to in correspondence.

[0209] The present invention also provides a readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-described method for determining the lane centerline.

[0210] The readable storage medium may include various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0211] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to in the method section.

[0212] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0213] Finally, it should be noted that in this document, relationships such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0214] The present invention provides a detailed description of a method, apparatus, device, and readable storage medium for determining a lane centerline. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, those skilled in the art will recognize that, based on the ideas of the present invention, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for determining the center line of a lane, characterized in that, include: At least one of the following three trajectory models is selected as the target model: a first trajectory model, a second trajectory model, and a third trajectory model. The first trajectory model is determined based on the curvature of the current trajectory of the vehicle. The second trajectory model is obtained by polynomial fitting based on the coordinates of the historical trajectory points of the target vehicle. The third trajectory model is a lane centerline model determined based on a visual sensor. Based on the target model, determine the first lateral coordinate point corresponding to the first longitudinal sampling point coordinate, and determine the weight of the lateral coordinate point corresponding to the first lateral coordinate point. Based on the weight of the lateral coordinate point in the target model and the first lateral coordinate point, determine the coordinate point corresponding to the center line of the forward lane. The second lateral coordinate point determined based on the fourth trajectory model and the coordinates of the second longitudinal sampling point is filtered to obtain the filtered second lateral coordinate point. The coordinate point corresponding to the center line of the rearward lane is determined based on the coordinates of the second longitudinal sampling point and the filtered second lateral coordinate point. The fourth trajectory model is a trajectory model obtained by polynomial fitting based on the coordinates corresponding to the historical trajectory points of the vehicle. The target lane centerline is determined based on the coordinates of the centerline of the forward lane and the centerline of the backward lane.

2. The method for determining the lane centerline according to claim 1, characterized in that, Before determining that at least one of the first trajectory model, the second trajectory model, and the third trajectory model is selected as the target model, the method further includes: Based on the curvature of the vehicle trajectory, a quadratic function model is constructed to obtain the dynamic first trajectory model; The lateral coordinates of the historical trajectory points of the target vehicle in each cycle are filtered to obtain the filtered lateral coordinates of the target vehicle. Based on the filtered lateral coordinates, the historical trajectory points of the target vehicle are obtained. The second trajectory model is obtained by performing polynomial curve fitting based on the historical trajectory points of the target vehicle. The third trajectory model is determined based on the rate of change of lane centerline curvature, lane centerline curvature, lane centerline orientation angle, and lane centerline offset distance determined by the visual sensor.

3. The method for determining the lane centerline according to claim 2, characterized in that, Before obtaining the target vehicle's historical trajectory points for each cycle by filtering the lateral coordinates of the historical trajectory points of the target vehicle, and before obtaining the target vehicle's historical trajectory points based on the filtered lateral coordinates, the process further includes: A preset number of vehicles are selected as target vehicles based on a target vehicle selection rule; wherein, the target vehicle selection rule is determined based on the vehicle's coordinate values ​​and the time the vehicle is within the driver's field of vision. The target vehicle selection rules include: The vehicle's longitudinal coordinate values ​​are within the set range. The difference between the vehicle's lateral coordinate value and the lateral coordinate value of its own vehicle is within the set difference threshold; The vehicle remains within the driver's field of vision for a period exceeding a set time threshold. The standard deviation of the vehicle's lateral coordinate values ​​is less than the set standard deviation threshold.

4. The method for determining the lane centerline according to claim 1, characterized in that, The step of determining to select at least one of the first trajectory model, the second trajectory model, and the third trajectory model as the target model includes: The first trajectory model, the second trajectory model, and the third trajectory model are determined as the target models. Accordingly, based on the target model, the first lateral coordinate point corresponding to the first longitudinal sampling point coordinate is determined, and the weight of the lateral coordinate point corresponding to the first lateral coordinate point is determined. Based on the weight of the lateral coordinate point in the target model and the first lateral coordinate point, the coordinate point corresponding to the center line of the forward lane is determined, including: Based on the first trajectory model, the second trajectory model, and the third trajectory model, the first lateral coordinate point of the vehicle, the first lateral coordinate point of the target vehicle, and the first lateral coordinate point of the sensor corresponding to the coordinates of the first longitudinal sampling point are determined respectively; Based on the first lateral coordinate point of the vehicle, the first lateral coordinate point of the target vehicle, and the first lateral coordinate point of the sensor, determine the average value of the first lateral coordinate point corresponding to the coordinates of each first longitudinal sampling point; Based on the first lateral coordinate point of the vehicle, the first lateral coordinate point of the target vehicle, the first lateral coordinate point of the sensor, and the average value of the first lateral coordinate point, the variance of the lateral coordinate points under the three models corresponding to the coordinates of each first longitudinal sampling point is determined; The weighted average value of the first horizontal coordinate points corresponding to each first vertical sampling point is determined based on the variance of the horizontal coordinate points. The weight of each first horizontal coordinate point is determined based on the weighted average value. Based on the weight of each of the lateral coordinate points, the target first lateral coordinate point corresponding to each first longitudinal sampling point is determined, and the coordinate point corresponding to the center line of the forward lane is obtained based on the first longitudinal sampling point and the target first lateral coordinate point.

5. The method for determining the lane centerline according to claim 1, characterized in that, Before determining the first horizontal coordinate point corresponding to the first vertical sampling point coordinate based on the target model, and before determining the weight of the horizontal coordinate point corresponding to the first horizontal coordinate point, the process also includes: Determine whether the vision sensor can determine the endpoint of the lane centerline; When the endpoint of the lane centerline can be determined, the maximum value of the coordinates of the first longitudinal sampling point is set based on the endpoint determined by the visual sensor. When the endpoint of the lane centerline cannot be determined, the endpoint of the lane centerline is calculated by linear interpolation of the vehicle speed, and the maximum point of the coordinates of the first longitudinal sampling point is set based on the endpoint determined by linear interpolation of the vehicle speed.

6. The method for determining the lane centerline according to claim 1, characterized in that, The process of determining the coordinates of the second longitudinal sampling point includes: Determine the minimum point of the centerline of the rearward lane; The coordinates of the second longitudinal sampling point are determined based on the minimum point.

7. The method for determining the lane centerline according to claim 1, characterized in that, The process of determining the fourth trajectory model includes: Obtain a set number of historical trajectory points of the vehicle; Based on the selection criteria for vehicle history trajectory points, the target vehicle history trajectory point is obtained by selecting from the set number of vehicle history trajectory points. The fourth trajectory model is obtained by performing polynomial fitting based on the coordinates corresponding to the historical trajectory points of the target vehicle. The selection criteria for the vehicle's historical trajectory points include: Points whose horizontal coordinates are greater than a set horizontal coordinate threshold; The vertical coordinate at the current moment is greater than the vertical coordinate at the previous moment; The vertical coordinate at the current moment is less than zero; The current vertical coordinate is less than the minimum value of the vertical coordinate of the vehicle's historical trajectory points; The vertical coordinate at the current moment is not equal to the value of the vertical coordinate at the previous moment; The difference between the absolute values ​​of the x-coordinates of the previous and current times is greater than the set absolute value difference threshold.

8. The method for determining the lane centerline according to any one of claims 1 to 7, characterized in that, Determining the target lane centerline based on the coordinates of the forward lane centerline and the rear lane centerline includes: The forward lane centerline model is determined based on the coordinate points corresponding to the forward lane centerline. The rear lane centerline model is determined based on the coordinate points corresponding to the rear lane centerline. The target lane centerline is determined based on the forward lane centerline model and the backward lane centerline model.

9. A device for determining the center line of a lane, characterized in that, include: The target model determination module is used to determine at least one of the first trajectory model, the second trajectory model, and the third trajectory model as the target model; wherein, the first trajectory model is a first trajectory model determined based on the curvature of the current trajectory of the vehicle; the second trajectory model is a second trajectory model obtained by polynomial fitting based on the coordinates corresponding to the historical trajectory points of the target vehicle; and the third trajectory model is a lane centerline model determined based on the visual sensor. The first information determination module is used to determine the first lateral coordinate point corresponding to the first longitudinal sampling point coordinate based on the target model, and to determine the weight of the lateral coordinate point corresponding to the first lateral coordinate point. Based on the weight of the lateral coordinate point in the target model and the first lateral coordinate point, the module determines the coordinate point corresponding to the center line of the forward lane. The second information determination module is used to filter the second lateral coordinate point determined based on the fourth trajectory model and the coordinates of the second longitudinal sampling point to obtain the filtered second lateral coordinate point, and to determine the coordinate point corresponding to the rearward lane centerline based on the coordinates of the second longitudinal sampling point and the filtered second lateral coordinate point; wherein, the fourth trajectory model is a trajectory model obtained by polynomial fitting based on the coordinates corresponding to the historical trajectory points of the vehicle. The third information determination module is used to determine the target lane centerline based on the coordinate points corresponding to the forward lane centerline and the coordinate points corresponding to the backward lane centerline.

10. A device for determining the center line of a lane, characterized in that, include: Memory, used to store computer programs; A processor for executing the computer program to implement the steps of the method for determining the lane centerline as described in any one of claims 1 to 8.

11. A readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the method for determining the lane centerline as described in any one of claims 1 to 8.

Images