A method for predicting a lane centerline and related apparatus

Abstract

The application discloses a lane center line prediction method, and relates to the technical field of intelligent driving assistance, and comprises the following steps: when left and right lane lines satisfy a first preset condition, recording an original track curve of a lane center line and motion parameters of a vehicle; the original track curve is calculated according to the left and right lane lines; when the left and right lane lines satisfy a second preset condition, calculating a motion change amount of the vehicle according to the motion parameters of the vehicle; performing coordinate transformation according to the original track curve and the motion change amount to obtain a new track curve of the lane center line in a new vehicle coordinate system after the vehicle moves. The method can solve the problem that there is no target track after the left and right lane lines at a crossroad are lost, and the problem that when a lane is a straight lane, a left lane is a left-turn lane and a left-turn waiting lane line exists, the vehicle follows the left-turn waiting lane line to move forward. The application also discloses a lane center line prediction device, equipment and a computer readable storage medium, which all have the above technical effects.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent driving assistance, in particular to a lane center line prediction method; and relates to a lane center line prediction device, equipment and computer readable storage medium. BACKGROUND

[0002] Intelligent driving assistance is to use various sensors on the vehicle to sense the environment around the vehicle at any time during driving, collect data, and combine with navigation map data to perform system operation and analysis, thereby effectively increasing the comfort and safety of automobile driving. The existing intelligent driving assistance scheme currently loses lane lines at the intersection, and there is no suitable target vehicle in front to follow the control, so the following two solutions are mainly used: 1. According to the double line loss information output by the visual sensor, remind the driver to take over the vehicle, and at the same time exit the lane keeping function. 2. According to the predicted center line information output by the visual sensor, follow for a distance and then prompt the driver to take over the vehicle and exit the lane keeping function.

[0003] However, the former directly exits the function after identifying the loss of left and right lane lines at the intersection, and the time reserved for the driver's reaction and control is very short, which will give the driver a sense of tension in taking over. The latter uses the predicted center line output by the visual sensor, and when the current lane is a straight lane, the left lane is a left turn lane, and there is a left turn standby lane line, the visual sensor outputs the predicted center line along the left turn standby lane line. When the vehicle follows this curve, there will be a left turn trend.

[0004] Therefore, how to solve the above technical defects has become a technical problem to be solved by those skilled in the art. SUMMARY

[0005] The purpose of the present application is to provide a lane center line prediction method, which can effectively solve the problem of no target trajectory after the loss of left and right lane lines at the intersection, and the problem of the vehicle following the left turn standby lane line when the current lane is a straight lane, the left lane is a left turn lane, and there is a left turn standby lane line. Another purpose of the present application is to provide a lane center line prediction device, equipment and computer readable storage medium, which all have the above technical effects.

[0006] To solve the above technical problems, the present application provides a lane center line prediction method, comprising:

[0007] When the left and right lane lines satisfy a first preset condition, record the original trajectory curve of the lane center line and the motion parameters of the vehicle; the original trajectory curve is calculated according to the left and right lane lines;

[0008] When the left and right lane lines satisfy a second preset condition, a motion change amount of the vehicle is calculated according to motion parameters of the vehicle;

[0009] A new trajectory curve of the lane center line in a new vehicle coordinate system after the vehicle moves is obtained by coordinate transformation according to the original trajectory curve and the motion change amount.

[0010] Optionally, the calculation of the motion change amount of the vehicle according to the motion parameters of the vehicle comprises:

[0011] A yaw angle change amount of the vehicle is calculated according to a yaw angular velocity of the vehicle;

[0012] A lateral motion distance and a longitudinal motion distance of the vehicle are respectively calculated according to a vehicle speed, the yaw angular velocity and the yaw angle change amount of the vehicle.

[0013] Optionally, the coordinate transformation according to the original trajectory curve and the motion change amount to obtain the new trajectory curve of the lane center line in the new vehicle coordinate system after the vehicle moves comprises:

[0014] A preset number of points are selected from the original trajectory curve, and the points are subjected to coordinate transformation according to the motion change amount to obtain corresponding points of the points on the original trajectory curve in the new vehicle coordinate system;

[0015] The new trajectory curve of the lane center line in the new coordinate system is calculated according to the corresponding points of the points on the original trajectory curve in the new vehicle coordinate system.

[0016] Optionally, the method further comprises:

[0017] When the left and right lane lines satisfy a third preset condition, the new trajectory curve is output.

[0018] Optionally, the method further comprises, before the output of the new trajectory curve:

[0019] It is judged whether a new trajectory curve output condition is satisfied;

[0020] If the new trajectory curve output condition is satisfied, the new trajectory curve is output.

[0021] Optionally, the judgment of whether the new trajectory curve output condition is satisfied comprises:

[0022] It is judged whether the longitudinal motion distance of the vehicle is less than a first preset threshold value, whether a difference between a first target parameter of the new trajectory curve and a first target parameter of the original trajectory curve is less than a second preset threshold value, and whether a difference between a second target parameter of the new trajectory curve and a second target parameter of the original trajectory curve is less than a third preset threshold value;

[0023] If the longitudinal movement distance of the vehicle is less than the first preset threshold, and the difference between the first target parameter of the new trajectory curve and the first target parameter of the original trajectory curve is less than the second preset threshold, and the difference between the second target parameter of the new trajectory curve and the second target parameter of the original trajectory curve is less than the third preset threshold, the new trajectory curve output condition is met.

[0024] Optionally, the method further comprises:

[0025] According to the longitudinal movement distance of the vehicle, a confidence degree of the new trajectory curve is calculated.

[0026] If the confidence degree of the new trajectory curve is lower than a preset threshold, the driver is prompted to take over the vehicle, and the lane center keeping function is exited.

[0027] To solve the above technical problem, the application further provides a lane center line prediction device, comprising:

[0028] A recording module is configured to record an original trajectory curve of a lane center line and movement parameters of a vehicle when left and right lane lines meet a first preset condition; the original trajectory curve is calculated according to the left and right lane lines.

[0029] A calculation module is configured to calculate a movement change amount of the vehicle according to the movement parameters of the vehicle when the left and right lane lines meet a second preset condition.

[0030] A conversion module is configured to perform coordinate transformation according to the original trajectory curve and the movement change amount, to obtain a new trajectory curve of the lane center line in a new vehicle coordinate system after the vehicle moves.

[0031] To solve the above technical problem, the application further provides a lane center line prediction device, comprising:

[0032] A memory is configured to store a computer program.

[0033] A processor is configured to execute the computer program to implement the steps of the lane center line prediction method according to any one of the above.

[0034] To solve the above technical problem, the application further provides a computer readable storage medium, which stores a computer program; when the computer program is executed by a processor, the steps of the lane center line prediction method according to any one of the above are implemented.

[0035] The lane center line prediction method provided in the application comprises: when the left and right lane lines satisfy a first preset condition, recording an original track curve of the lane center line and motion parameters of a vehicle; the original track curve is calculated according to the left and right lane lines; after the left and right lane lines satisfy a second preset condition, calculating a motion change amount of the vehicle according to the motion parameters of the vehicle; and performing coordinate transformation according to the original track curve and the motion change amount to obtain a new track curve of the lane center line in a new vehicle coordinate system after the vehicle moves.

[0036] It can be seen that the lane center line prediction method provided in the application is based on an effective original track curve before the lane line is lost, and a new track curve of the original track curve in a current vehicle coordinate system is obtained through coordinate transformation according to the motion change of the vehicle, so that the effect of extending along the original lane direction after the lane line is lost is realized, the problem of no target track after the left and right lane lines at the intersection are lost is solved, and the problem of following the left-turn lane waiting line is avoided.

[0037] The lane center line prediction device, equipment and computer readable storage medium provided in the application all have the above technical effects. BRIEF DESCRIPTION OF DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the application, the drawings needed in the prior art and the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the application, and other drawings can be obtained by those skilled in the art without creative labor.

[0039] Figure 1 A flowchart of a lane center line prediction method provided in an embodiment of the application;

[0040] Figure 2 A schematic diagram of a lane center line prediction device provided in an embodiment of the application;

[0041] Figure 3 A schematic diagram of a lane center line prediction device provided in an embodiment of the application. DETAILED DESCRIPTION

[0042] The core of the application is to provide a lane center line prediction method, which can effectively solve the problem of no target track after the left and right lane lines at the intersection are lost, and the problem of the vehicle following the left-turn waiting line when the current lane is a straight lane, the left side is a left-turn lane, and there is a left-turn waiting lane line. Another core of the application is to provide a lane center line prediction device, equipment and computer readable storage medium, which all have the above technical effects.

[0043] The technical solutions and advantages of the embodiments of the present application will be more clearly understood from the following description of the embodiments of the present application with reference to the drawings. Obviously, the described embodiments are only some of the embodiments of the present application, but not all of the embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0044] Please refer to Figure 1 , Figure 1 The flowchart of a lane center line prediction method provided by the embodiments of the present application is shown in FIG. 1. The method comprises the following steps. Figure 1

[0045] S101: When the left and right lane lines satisfy a first preset condition, record the original trajectory curve of the lane center line and the motion parameters of the vehicle; the original trajectory curve is calculated according to the left and right lane lines.

[0046] The first preset condition can be that the line quality of the left and right lane lines is greater than a preset threshold and lasts for a preset time length. When the lane centering function is in an activated state and the activated duration exceeds 5s (which can be differentiated), if the line quality of the left and right lane lines of the current lane is greater than the preset threshold and lasts for the preset time length, it can be considered that the original trajectory curve of the lane center line calculated according to the left and right lane lines is valid, and at this time, the parameters of the original trajectory curve and the current motion parameters of the vehicle are recorded. The motion parameters can include the vehicle speed and the yaw rate. The line quality is an index of the recognition clarity and rationality of the lane line, and the range of the line quality is 0-1, 0 means that the lane line cannot be recognized at all, and 1 means that the recognized lane line is very clear and accurate.

[0047] The above-mentioned preset threshold and preset time length can be differentiated. For example, when the lane centering function is in an activated state and the activated time lasts for more than 5s, if the line quality of the left and right lane lines of the current lane is greater than 0.75 and lasts for 3s, it can be considered that the original trajectory curve of the lane center line calculated according to the left and right lane lines is valid, and at this time, the parameters of the original trajectory curve and the current vehicle speed and yaw rate are recorded.

[0048] The original trajectory curve of the lane center line can be a cubic spline curve, or a quintic spline curve, etc. The cubic spline curve is expressed as y=y0+a*x+b*x 2 +c*x 3 In the case of the original trajectory curve being a cubic spline curve, the parameters y0, a, b, and c of the cubic spline curve are recorded.

[0049] ​In addition, the way of calculating the cubic spline curve or the quintic spline curve of the lane center line according to the left and right lane lines can refer to the prior art, and the present application will not be described here.

[0050] S102: When the left and right lane lines satisfy the second preset condition, a motion change amount of the vehicle is calculated according to a motion parameter of the vehicle.

[0051] The second preset condition can be that the line quality of any lane line is lower than a preset value and the recognition distance of any lane line is less than a preset distance value. For example, when the line quality of any lane line is lower than 0.5 and the recognition distance of any lane line is less than 20 m, the parameters of the original trajectory curve recorded at the last time (denoted as t0 time) are locked, and the motion change amount of the vehicle from the last time is calculated.

[0052] In a specific embodiment, the calculation of the motion change amount of the vehicle according to the motion parameter of the vehicle includes:

[0053] According to the yaw rate of the vehicle, a yaw angle change amount of the vehicle is calculated.

[0054] According to the vehicle speed, the yaw rate and the yaw angle change amount of the vehicle, a lateral motion distance and a longitudinal motion distance of the vehicle are respectively calculated.

[0055] The calculation method of the yaw angle change amount is:

[0056] Δθ = yawrate * Δt.

[0057] Δθ represents the yaw angle change amount, yawrate represents the yaw rate, and Δt represents the algorithm running period.

[0058] The calculation method of the longitudinal motion distance is:

[0059]

[0060] Δx represents the longitudinal motion distance, v represents the vehicle speed, Δθ represents the yaw angle change amount, and yawrate represents the yaw rate.

[0061] The calculation method of the lateral motion distance is:

[0062]

[0063] Δy represents the lateral motion distance, v represents the vehicle speed, Δθ represents the yaw angle change amount, and yawrate represents the yaw rate.

[0064] S103: Coordinate transformation is performed according to the original trajectory curve and the motion change amount, to obtain a new trajectory curve of the lane center line in a new vehicle coordinate system after the vehicle moves.

[0065] In some embodiments, the coordinate transformation according to the original trajectory curve and the motion change amount to obtain a new trajectory curve of the lane center line in a new vehicle coordinate system after the vehicle moves includes:

[0066] A preset number of points are selected from the original trajectory curve, and coordinate transformation is performed on the points according to the motion change amount, to obtain corresponding points of the points on the original trajectory curve in the new vehicle coordinate system;

[0067] The new trajectory curve of the lane center line in the new coordinate system is calculated according to the corresponding points of the points on the original trajectory curve in the new vehicle coordinate system.

[0068] In the case of a cubic spline curve as the original trajectory curve, four points can be selected from the original trajectory curve. For example, four points with x values of 0, 5, 10, and 15 are selected from the original trajectory curve, and the corresponding y values can be calculated according to the cubic spline curve to obtain points (x1, y1), (x2, y2), (x3, y3), and (x4, y4).

[0069] The center of the rear axle of the ego vehicle is taken as the coordinate origin. With the change of the position of the ego vehicle, the vehicle coordinate system can be considered to have undergone coordinate system translation and rotation. The calculation method of the points in the new vehicle coordinate system after translation and rotation is as follows:

[0070]

[0071] In the above formula, Δθ represents the yaw angle change amount, Δx represents the longitudinal motion distance, Δy represents the lateral motion distance, x and y represent the horizontal and vertical coordinates of the point in the vehicle coordinate system before translation and rotation, and x' and y' represent the horizontal and vertical coordinates of the corresponding point in the new vehicle coordinate system after translation and rotation.

[0072] According to the above formula, the corresponding four points in the new vehicle coordinate system can be calculated as follows:

[0073] (x1', y1'), (x2', y2'), (x3', y3'), and (x4', y4').

[0074] In the case of a cubic spline curve as the original trajectory curve, the following matrix can be listed according to the formula of the cubic spline curve:

[0075]

[0076] For the above matrix X*A=Y, matrix A=X -1Y, thus the four parameters of the cubic spline curve in the new vehicle coordinate system after translation and rotation can be obtained, and then the cubic spline curve of the lane center line in the new coordinate system can be obtained.

[0077] The continuous prediction of the lane center line can be realized by continuously running the corresponding algorithm, and the new trajectory curve of the ego vehicle at the current position is continuously calculated when the algorithm is continuously running.

[0078] On the basis of the above-mentioned embodiments, in some embodiments, further comprising:

[0079] When the left and right lane lines satisfy the third preset condition, output the new trajectory curve.

[0080] The third preset condition can be that the line quality of one lane line is lower than the first preset value, the line quality of the other lane line is lower than the second preset value, and the recognition distance of the two lane lines is less than the third preset value. For example, when the line quality of one of the left and right lane lines of the current lane is lower than 0.25, the line quality of the other lane line is lower than 0.75, and the recognition distance of the two lane lines is less than 20m, the predicted lane center line can be further output at this time for the lane center keeping function. The time when the left and right lane lines satisfy the third preset condition can be recorded as t1.

[0081] In order to guarantee the rationality of the trajectory, in some embodiments, before outputting the new trajectory curve, further comprising:

[0082] determining whether a new trajectory curve output condition is satisfied;

[0083] If the new trajectory curve output condition is satisfied, output the new trajectory curve.

[0084] On the contrary, if the new trajectory curve output condition is not satisfied, it indicates that the deviation of the prediction is too large, and the new trajectory curve cannot be used, at which time the algorithm can be exited.

[0085] The determination of whether the new trajectory curve output condition is satisfied can include:

[0086] determining whether the longitudinal motion distance of the vehicle is less than a first preset threshold, and whether the difference between the first target parameter of the new trajectory curve and the first target parameter of the original trajectory curve is less than a second preset threshold, and whether the difference between the second target parameter of the new trajectory curve and the second target parameter of the original trajectory curve is less than a third preset threshold;

[0087] If the longitudinal motion distance of the vehicle is less than the first preset threshold, and the difference between the first target parameter of the new trajectory curve and the first target parameter of the original trajectory curve is less than the second preset threshold, and the difference between the second target parameter of the new trajectory curve and the second target parameter of the original trajectory curve is less than the third preset threshold, the new trajectory curve output condition is satisfied. If the above three conditions cannot be met at the same time, the new trajectory curve output condition is not satisfied.

[0088] For example, if the longitudinal motion distance of the vehicle from t0 to t1 is less than 10 m, and the difference between the parameter y0 of the new trajectory curve and the parameter y0 of the original trajectory curve is less than 0.1 m, and the difference between the parameter a of the new trajectory curve and the parameter a of the original trajectory curve is less than 0.04, the new trajectory curve output condition is satisfied, and the new trajectory curve can be output.

[0089] By reasonably judging the predicted new trajectory curve, the problem of vehicle deviation caused by recording the original trajectory curve to the complete disappearance of the lane line, large lane change, and using unreasonable trajectory for extension can be avoided.

[0090] Further, in some embodiments, the method further comprises:

[0091] calculating a confidence degree of the new trajectory curve according to the longitudinal motion distance of the vehicle;

[0092] If the confidence degree of the new trajectory curve is lower than a preset threshold, prompting the driver to take over the vehicle, and exiting the lane centering and keeping function.

[0093] The embodiment aims to calculate the confidence degree of the new trajectory curve according to the longitudinal motion distance of the vehicle after t1. The calculation method of the confidence degree is:

[0094] confidence = 1 - distance / 10, distance < 10;

[0095] confidence = 0, distance >= 10.

[0096] confidence represents the confidence degree, and distance represents the longitudinal motion distance.

[0097] If the calculated confidence degree is lower than 0.5, it is considered that the confidence degree of the predicted new trajectory curve is low, at which time the driver is prompted to take over the vehicle, and the lane centering and keeping function is exited.

[0098] The embodiment calculates the confidence degree according to the running distance of the vehicle, which is more consistent with the actual situation that the confidence degree of the predicted center line decreases with the increase of the running distance, and can avoid the problem of long-time vehicle deviation caused by the non-correspondence of the opposite lane at the intersection.

[0099] In addition, when the line quality of the left and right lane lines of the current lane is greater than 0.7 (which can be calibrated differently), the algorithm can be exited, and the confidence of the lane center line output by the algorithm can be set to 0.

[0100] In summary, the lane center line prediction method provided by the present application is based on the effective original trajectory curve before the lane line is lost, and a new trajectory curve of the original trajectory curve in the current vehicle coordinate system is obtained through coordinate conversion according to the motion change of the vehicle, thereby realizing the effect of extending along the original lane direction after the lane line is lost, solving the problem of no target trajectory after the left and right lane lines of the intersection are lost, and avoiding the problem of following the left turn lane waiting line.

[0101] The present application also provides a lane center line prediction device, which can be mutually corresponding with the method described above. Please refer to Figure 2 , Figure 2 The schematic diagram of the lane center line prediction device provided by the embodiment of the present application is shown in combination with Figure 2 The device comprises:

[0102] The recording module 10 is configured to record the original trajectory curve of the lane center line and the motion parameters of the vehicle when the left and right lane lines meet the first preset condition; the original trajectory curve is calculated according to the left and right lane lines;

[0103] The calculation module 20 is configured to calculate the motion change amount of the vehicle according to the motion parameters of the vehicle when the left and right lane lines meet the second preset condition;

[0104] The conversion module 30 is configured to perform coordinate transformation according to the original trajectory curve and the motion change amount, to obtain a new trajectory curve of the lane center line in the new vehicle coordinate system after the vehicle moves.

[0105] On the basis of the above-mentioned embodiment, as a specific implementation, the calculation module 20 comprises:

[0106] The first calculation unit is configured to calculate the yaw angle change amount of the vehicle according to the yaw angular velocity of the vehicle;

[0107] The second calculation unit is configured to calculate the lateral motion distance and the longitudinal motion distance of the vehicle according to the vehicle speed, the yaw angular velocity and the yaw angle change amount of the vehicle, respectively.

[0108] On the basis of the above-mentioned embodiment, as a specific implementation, the conversion module 30 comprises:

[0109] a coordinate transformation unit configured to select a preset number of points from the original trajectory curve, and perform coordinate transformation on the points according to the motion change amount, to obtain corresponding points of the points on the original trajectory curve in the new vehicle coordinate system;

[0110] a curve calculation unit configured to calculate the new trajectory curve of the lane center line in the new coordinate system according to the corresponding points of the points on the original trajectory curve in the new vehicle coordinate system.

[0111] On the basis of the above embodiment, as a specific implementation, the method further includes:

[0112] an output module configured to output the new trajectory curve when the left and right lane lines satisfy a third preset condition.

[0113] On the basis of the above embodiment, as a specific implementation, the method further includes:

[0114] a judgment module configured to judge whether a new trajectory curve output condition is satisfied;

[0115] If the new trajectory curve output condition is satisfied, the output module outputs the new trajectory curve.

[0116] On the basis of the above embodiment, as a specific implementation, the judgment module is specifically configured to:

[0117] judge whether a longitudinal motion distance of the vehicle is less than a first preset threshold, whether a difference between a first target parameter of the new trajectory curve and a first target parameter of the original trajectory curve is less than a second preset threshold, and whether a difference between a second target parameter of the new trajectory curve and a second target parameter of the original trajectory curve is less than a third preset threshold;

[0118] If the longitudinal motion distance of the vehicle is less than the first preset threshold, the difference between the first target parameter of the new trajectory curve and the first target parameter of the original trajectory curve is less than the second preset threshold, and the difference between the second target parameter of the new trajectory curve and the second target parameter of the original trajectory curve is less than the third preset threshold, the new trajectory curve output condition is satisfied.

[0119] On the basis of the above embodiment, as a specific implementation, the method further includes:

[0120] a confidence degree calculation module configured to calculate a confidence degree of the new trajectory curve according to the longitudinal motion distance of the vehicle;

[0121] a prompt module configured to, if the confidence degree of the new trajectory curve is lower than a preset threshold, prompt a driver to take over the vehicle and exit a lane center keeping function.

[0122] The lane center line prediction device provided in the application is based on the effective original track curve before the lane line loss, and a new track curve of the original track curve in the current vehicle coordinate system is obtained through coordinate conversion according to the motion change of the vehicle, so that the effect of extending along the original lane direction after the lane line loss is realized, the problem of no target track after the left and right lane lines of the intersection are lost is solved, and the problem of advancing along the left-turn lane waiting line is avoided.

[0123] The application further provides a lane center line prediction device, as shown in the figure, the device comprises a memory 1 and a processor 2. Figure 3

[0124] The memory 1 is used for storing a computer program.

[0125] The processor 2 is used for executing the computer program to realize the following steps:

[0126] When the left and right lane lines meet the first preset condition, the original track curve of the lane center line and the motion parameters of the vehicle are recorded; the original track curve is calculated according to the left and right lane lines; when the left and right lane lines meet the second preset condition, the motion change amount of the vehicle is calculated according to the motion parameters of the vehicle; and the new track curve of the lane center line in the new vehicle coordinate system after the vehicle moves is obtained through coordinate transformation according to the original track curve and the motion change amount.

[0127] For the device provided in the application, please refer to the above method embodiment, which will not be repeated here.

[0128] The application further provides a computer readable storage medium, which stores a computer program, and the computer program can realize the following steps when executed by a processor:

[0129] When the left and right lane lines meet the first preset condition, the original track curve of the lane center line and the motion parameters of the vehicle are recorded; the original track curve is calculated according to the left and right lane lines; when the left and right lane lines meet the second preset condition, the motion change amount of the vehicle is calculated according to the motion parameters of the vehicle; and the new track curve of the lane center line in the new vehicle coordinate system after the vehicle moves is obtained through coordinate transformation according to the original track curve and the motion change amount.

[0130] The computer readable storage medium can include a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0131] ​The computer readable storage medium provided in the present application is described above with reference to the method embodiments. The present application will not be repeated here.

[0132] The embodiments in the specification are described progressively, and each embodiment focuses on the difference from other embodiments. The same or similar parts between embodiments can be referred to each other. For the apparatus, device and computer readable storage medium disclosed by the embodiments, since they correspond to the method disclosed by the embodiments, the description is relatively simple, and the relevant part can be referred to the method part.

[0133] The skilled person can further realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be realized by electronic hardware, computer software or a combination of the two. In order to clearly show the interchangeability of hardware and software, the components and steps of the examples have been described in the above description. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. The skilled person can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0134] The steps of the method or algorithm described in combination with the embodiments disclosed herein can be directly implemented by hardware, software modules executed by a processor, or a combination of the two. The software modules can be placed in random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disks, removable disks, CD-ROMs, or any other form of storage medium known in the art.

[0135] The lane center line prediction method, device, equipment and computer readable storage medium provided by the present application are described in detail above. The principles and implementation modes of the present application are described by applying specific examples. The above description of the embodiments is only to help understand the method and its core idea of the present application. It should be pointed out that for those skilled in the art, without departing from the principles of the present application, some improvements and modifications can be made to the present application, and these improvements and modifications also fall within the protection scope of the claims of the present application.

Claims

1. A method for predicting lane centerline, characterized in that: include: When the left and right lane lines meet a first preset condition, the original trajectory curve of the lane centerline and the motion parameters of the vehicle are recorded; the original trajectory curve is calculated based on the left and right lane lines; the first preset condition is that the line quality of the left and right lane lines is greater than a preset threshold and lasts for a preset period of time; the motion parameters include vehicle speed and yaw rate; When the left and right lane lines meet a second preset condition, a motion change of the vehicle is calculated based on the motion parameters of the vehicle; The second preset condition is that the line quality of any lane line is lower than a preset value and the recognition sight distance of any lane line is less than a preset distance value; Performing coordinate transformation based on the original trajectory curve and the motion variation to obtain a new trajectory curve of the lane centerline in a new vehicle coordinate system after the vehicle moves; Calculating the confidence of the new trajectory curve according to the longitudinal movement distance of the vehicle; If the confidence level of the new trajectory curve is lower than a preset threshold, the driver is prompted to take over the vehicle and exit the lane centering function.

2. The lane centerline prediction method according to claim 1, characterized in that: The calculating of the motion variation of the vehicle according to the motion parameters of the vehicle includes: Calculating a yaw angle change of the vehicle according to the yaw angular velocity of the vehicle; The lateral movement distance and the longitudinal movement distance of the vehicle are respectively calculated according to the vehicle speed, the yaw angular velocity, and the yaw angle variation.

3. The lane centerline prediction method according to claim 1, characterized in that: The coordinate transformation is performed based on the original trajectory curve and the motion variation to obtain a new trajectory curve of the lane centerline in a new vehicle coordinate system after the vehicle moves, comprising: Selecting a preset number of points from the original trajectory curve, and performing coordinate transformation on the points according to the motion change amount to obtain corresponding points of the points on the original trajectory curve in the new vehicle coordinate system; The new trajectory curve of the lane centerline in the new vehicle coordinate system is calculated based on the points corresponding to the points on the original trajectory curve in the new vehicle coordinate system.

4. The lane centerline prediction method according to claim 1, characterized in that: Also includes: When the left and right lane lines meet the third preset condition, the new trajectory curve is output.

5. The lane centerline prediction method according to claim 4, characterized in that: Before outputting the new trajectory curve, the method further includes: Determine whether the new trajectory curve output conditions are met; If satisfied, the new trajectory curve is output.

6. The lane centerline prediction method according to claim 5, characterized in that: The determination of whether the new trajectory curve output condition is met includes: determining whether the longitudinal movement distance of the vehicle is less than a first preset threshold, whether a difference between a first target parameter of the new trajectory curve and the first target parameter of the original trajectory curve is less than a second preset threshold, and whether a difference between a second target parameter of the new trajectory curve and the second target parameter of the original trajectory curve is less than a third preset threshold; If the longitudinal movement distance of the vehicle is less than the first preset threshold, and the difference between the first target parameter of the new trajectory curve and the first target parameter of the original trajectory curve is less than the second preset threshold, and the difference between the second target parameter of the new trajectory curve and the second target parameter of the original trajectory curve is less than the third preset threshold, then the new trajectory curve output condition is met.

7. A lane centerline prediction device, characterized in that: include: a recording module configured to record an original trajectory curve of the lane centerline and motion parameters of the vehicle when the left and right lane lines meet a first preset condition; the original trajectory curve is calculated based on the left and right lane lines; the first preset condition is that the line quality of the left and right lane lines is greater than a preset threshold and persists for a preset duration; the motion parameters include vehicle speed and yaw rate; a calculation module, configured to calculate a motion change of the vehicle based on the motion parameters of the vehicle when the left and right lane lines meet a second preset condition; The second preset condition is that the line quality of any lane line is lower than a preset value and the recognition sight distance of any lane line is less than a preset distance value; a conversion module, configured to perform coordinate transformation based on the original trajectory curve and the motion variation to obtain a new trajectory curve of the lane centerline in a new vehicle coordinate system after the vehicle moves; A confidence calculation module, configured to calculate the confidence of the new trajectory curve based on the longitudinal movement distance of the vehicle; The prompt module is configured to prompt the driver to take over the vehicle and exit the lane centering function if the confidence level of the new trajectory curve is lower than a preset threshold.

8. A lane centerline prediction device, characterized in that: include: Memory for storing computer programs; A processor, configured to implement the steps of the lane centerline prediction method according to any one of claims 1 to 6 when executing the computer program.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the lane centerline prediction method according to any one of claims 1 to 6.

Images