Target screening method for optimizing lane line according to own vehicle motion state

Abstract

The invention discloses a target screening method for optimizing a lane line according to a self-vehicle motion state, and the method comprises the steps: taking the motion trend of a self-vehicle into consideration on the basis of an existing lane line during target screening, updating a corresponding lane line, and enabling the corresponding lane line to serve as a lane line for target screening, employing the information of the lane line, and comprehensively considering the motion state of the self-vehicle. The accuracy of target screening is ensured, reliable target parameters are provided for longitudinal control of the ACC, the comfort of the whole longitudinal control is improved, unexpected deceleration and braking actions and the like of the longitudinal control caused by target screening are avoided, meanwhile, deceleration is carried out in time according to the target vehicle when deceleration and braking are needed, and the accuracy of target screening is improved. And collision in longitudinal control is avoided.

Description

Technical Field

[0001] The present invention belongs to the field of vehicle longitudinal control, and in particular relates to a target screening method for optimizing lane lines according to the motion state of a vehicle. Background Art

[0002] After the adaptive cruise control ACC of the current vehicle is activated, it is necessary to select the front vehicle to be followed according to the target screening algorithm; in the target screening algorithm, it is necessary to determine whether the front vehicle is in the lane based on the positional relationship between the lane line and the front target vehicle, and select the nearest target as the target to follow from all target vehicles in the lane. When screening targets, the current conventional methods for processing lane lines are mainly the following: 1. When there are lane lines, directly use the lane line where the vehicle is located as the lane line for target screening. After the vehicle changes lanes, use the lane line after the lane change. When the vehicle turns, use the trajectory of the vehicle to calculate the trajectory of the vehicle as the lane line. 2. Do not rely on the actual lane line, calculate the lane line based on the movement trajectory of the vehicle, and screen targets based on the lane line.

[0003] At present, these two lane line processing methods have the following main problems: When scheme 1 directly uses lane lines as target screening, it will lead to inaccurate target screening in some cases. When a vehicle moves in a lane, it sometimes deviates to one side, or when the vehicle changes roads or turns, there will be some deviations between the vehicle's movement and the lane line. Directly using the lane line where the vehicle is located to screen targets often results in the selection of some unwanted targets, or the non-selection of some desired targets. In scheme 2, the lane line is calculated directly using the vehicle's movement trend. Since the vehicle's sensors often have some errors, this will cause a certain deviation in the vehicle's trajectory calculation, which often leads to instability in target screening. In addition, the lane line widths and shapes of each road section are different. Failure to use the lane line information often leads to misselection. Therefore, the present invention provides a target screening method that optimizes lane lines according to the vehicle's motion state to solve the above problems. Summary of the invention

[0004] In order to solve at least one of the problems raised in the above background technology, the present invention provides a target screening method for optimizing lane lines according to the motion state of the vehicle.

[0005] To achieve the above object, the present invention provides the following technical solution: a target screening method for optimizing lane lines according to the motion state of a vehicle, comprising the following steps:

[0006] Step 1: Obtain the vehicle's sensor input information and calculate the vehicle's motion formula;

[0007] Step 2: Based on the input information from the camera, calculate the lane centerline based on the left and right lane lines;

[0008] Step 3: According to Step 1 and Step 2, the starting position, the lateral position error from the vehicle to the center line of the lane, the lateral position of the vehicle at the preview point, the lane line position at the preview point, and the distance from the vehicle at the preview point to the center line of the lane are calculated;

[0009] Step 4: Based on the information in step 3, the lateral position error at the starting point and the lateral position error at the preview point are used to calculate the vehicle's motion state: the vehicle is driving in the center, the vehicle is maintaining a stable offset, the vehicle is changing lanes to the left without crossing the line, the vehicle is changing lanes to the left without crossing the line, the vehicle is changing lanes to the right without crossing the line, and the vehicle is changing lanes to the right without crossing the line;

[0010] Step 5: Based on the information in step 4, update the lane centerline and use the updated lane centerline to find the preview point position parameter information for lane change;

[0011] Step 6: Based on the information in step 5, the motion parameters of the current point and the lane change preview point are used to fit the lane centerline using a fifth-order polynomial;

[0012] Step 7: Based on the information in steps 4 and 5, a cubic polynomial is used to fit the lane centerline within the effective distance from the lane change preview point to the lane line;

[0013] Step 8: Based on the information in step 7, for positions that exceed the effective length of the lane line, use Taylor expansion at the vanishing point of the lane line to extend the lane line.

[0014] Preferably, the sensor input information of the vehicle is obtained including but not limited to data collected by the vehicle's speed sensor, acceleration sensor, and gyroscope sensor, and these data are fused to calculate the vehicle's motion formula, wherein the speed sensor is used to obtain the vehicle's real-time driving speed, the acceleration sensor is used to obtain the vehicle's acceleration magnitude and direction, and the gyroscope sensor is used to obtain the vehicle's angular velocity information.

[0015] Preferably, when calculating the lane centerline based on the input information of the camera, the image captured by the camera is preprocessed, including image grayscale and filtering and noise reduction processing, so as to improve the recognition of the lane line information in the image, and then an edge detection algorithm is used to extract the edge contour of the lane line, and then the extracted edge contour is screened and fitted based on geometric features and prior knowledge of the lane line, so as to accurately calculate the lane centerline.

[0016] Preferably, the step 3: according to step 1 and step 2, calculate the starting position, the lateral position error from the vehicle to the center line of the lane, the lateral position of the vehicle at the preview point, the lane line position at the preview point, and calculate the distance from the vehicle at the preview point to the center line of the lane; mainly use the preview point for calculation.

[0017] Preferably, in step 4, the lateral position error at the starting point and the lateral position error at the preview point are used to calculate the motion state of the vehicle; the threshold for calculating the vehicle motion trend is optimized according to the actual situation of the vehicle.

[0018] Preferably, the step 5: updates the lane centerline based on the information in step 4, and uses the updated lane centerline to find the preview point position parameter information for lane change, and the distance of the preview point is determined based on the actual vehicle.

[0019] Preferably, step 6: based on the information in step 5, using the motion parameters of the current point and the lane change preview point, use a quintic polynomial to fit the lane center line, wherein the fitting of the lane line includes but is not limited to using a quintic polynomial to fit.

[0020] Preferably, step 7: based on the information in steps 4 and 5, a cubic polynomial is used to fit the lane centerline within the effective distance from the lane change preview point to the lane line. The lane line fitting for this section includes but is not limited to fitting using a cubic polynomial.

[0021] Preferably, step 8: based on the information in step 7, the position exceeding the effective length of the lane line is extended by using Taylor expansion at the vanishing point of the lane line; the extension of this section of the lane line includes but is not limited to using Taylor expansion.

[0022] Compared with the prior art, the present invention has the following beneficial effects:

[0023] 1. On urban roads or roads with heavy traffic, or when the vehicle is moving and deviates within the lane, when the vehicle is changing lanes or turning, the adaptive cruise control ACC target screening accuracy is higher when using the optimized lane centerline. Taking into account the various motion states of the vehicle, the assisted driving function can be more intelligent and more in line with the driver's needs. The target screening method of the present invention improves the accuracy of the longitudinal control target screening of intelligent driving vehicles, and can screen out real dangerous targets; it improves the stability of the longitudinal control target screening of intelligent driving vehicles, and provides reliable input for the stable following of the adaptive cruise control ACC;

[0024] 2. At the same time, the target screening method of the present invention improves the comfort of intelligent driving vehicles, more effectively reflects the driver's driving intention, and is conducive to improving the public's trust and acceptance of intelligent driving; and improves the robustness and real-time performance of the longitudinal control algorithm. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0026] Figure 1 A flowchart of a target screening method for optimizing lane lines according to the motion state of the vehicle;

[0027] Figure 2 A schematic diagram of vehicle dynamics when a vehicle turns in the present invention;

[0028] Figure 3 A schematic diagram of a state machine for a vehicle motion state in the present invention;

[0029] Figure 4 This is the lane line fitting effect diagram. DETAILED DESCRIPTION

[0030] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0031] First, refer to Figures 1 to 4 A target screening method for optimizing lane lines according to the motion state of a vehicle according to an embodiment of the present invention is specifically described.

[0032] The present invention is further described in detail below in conjunction with the overall technical solution flow chart:

[0033] A target screening method for optimizing lane lines according to a vehicle motion state comprises the following steps:

[0034] Step 1: Obtain the vehicle's sensor input information and calculate the vehicle's motion formula;

[0035] Step 2: Based on the input information from the camera, calculate the lane centerline based on the left and right lane lines;

[0036] Step 3: According to Step 1 and Step 2, the starting position, the lateral position error from the vehicle to the center line of the lane, the lateral position of the vehicle at the preview point, the lane line position at the preview point, and the distance from the vehicle at the preview point to the center line of the lane are calculated;

[0037] Step 4: Based on the information in step 3, the lateral position error at the starting point and the lateral position error at the preview point are used to calculate the vehicle's motion state: the vehicle is driving in the center, the vehicle is maintaining a stable offset, the vehicle is changing lanes to the left without crossing the line, the vehicle is changing lanes to the left without crossing the line, the vehicle is changing lanes to the right without crossing the line, and the vehicle is changing lanes to the right without crossing the line;

[0038] Step 5: Based on the information in step 4, the lane centerline is updated and the updated lane centerline is used to find the preview point position parameter information for lane change;

[0039] Step 6: Based on the information in step 5, the motion parameters of the current point and the lane change preview point are used to fit the lane centerline using a quintic polynomial;

[0040] Step 7: Based on the information in steps 4 and 5, a cubic polynomial is used to fit the lane centerline within the effective distance from the lane change preview point to the lane line;

[0041] Step 8: Based on the information in step 7, for positions that exceed the effective length of the lane line, use Taylor expansion at the vanishing point of the lane line to extend the lane line.

[0042] The main goal of target screening is to provide a reliable following target for the adaptive cruise control ACC system. The adaptive cruise control ACC uses the information of the target vehicle given by the target screening. When the cruising speed set by the driver is greater than the speed of the target vehicle, the adaptive cruise control ACC controls the vehicle to follow the following time interval set by the driver, and controls the speed of the vehicle to be consistent with the speed of the target vehicle, and follows the vehicle in front.

[0043] The main principles of the target screening algorithm are as follows:

[0044] When there are lane lines and the lane line quality is valid, determine whether the vehicle ahead is within the lane line in which the vehicle is traveling.

[0045] When the target is within the lane line of the vehicle, the vehicle closest to the vehicle is calculated as the target vehicle;

[0046] In this algorithm, the movement trend of the ego vehicle is considered. When the lane line does not exist, the movement trajectory of the ego vehicle is used to calculate the lane line as the lane line for target screening. When the lane line exists, the lane line is optimized according to the movement trend of the ego vehicle to ensure that the lane line is the driving area of ​​the ego vehicle. The algorithm for the movement trend of the ego vehicle is as follows:

[0047] The schematic diagram of the vehicle's state parameters when turning is as follows: Figure 2 As shown, according to the motion parameters of the vehicle's current state, the longitudinal speed v x , yaw rate ω, vehicle wheelbase + front overhang length is L, vehicle speed is constant speed V, the angle between the front bumper center and the rear axle center at the turn is θ, R fcis the distance from the front protection center to the rotation center, R r is the distance from the rear wheel to the center of rotation, R f is the distance from the front wheel to the center of rotation, then the lateral speed of the front wheel is:

[0048]

[0049] Centripetal acceleration a:

[0050]

[0051] v y is the initial lateral velocity of the vehicle, a is the acceleration of the vehicle's lateral motion, and the longitudinal velocity is uniform. The motion parameters of the front guard of the vehicle are:

[0052]

[0053] Where: K is the curvature,

[0054] C1=L*K

[0055]

[0056] Then: y=C1*x+C2*x 2 (4)

[0057] In this algorithm, the distance ey from the current position to the lane line is calculated based on the current position of the vehicle. current ,ey current The calculation method is as follows:

[0058] According to the left and right lane lines of the vehicle, the lane center line is calculated. The formula for the calculated lane center line is:

[0059] y=a0+a1*x+a2*x 2 +a3*x 3 (5)

[0060] The vehicle is at the starting position, and the longitudinal position x is 0. Substituting into equation (4), the lateral position y of the vehicle is current =0;

[0061] When the vehicle is at the starting position, the longitudinal position x is 0. Substituting into equation (5), the lateral position of the lane centerline is y current_lane =a0;

[0062] Find the first-order derivative of the lane line, and the expression after finding it is:

[0063] dy=a1+2*a2*x+a3*x 2 (6)

[0064] Then set x to 0 and substitute it into equation (6) to obtain dy at the starting position. current_lane =a1;

[0065] Then when the vehicle is at the starting position, the distance from the vehicle to the lane line is:

[0066]

[0067] According to the vehicle speed, calculate the distance between the vehicle and the lane line at the preview position. The specific calculation method is as follows:

[0068] The preview point can be obtained by multiplying the vehicle speed by the preview time 3s, or by looking up the table based on the vehicle speed and road radius, that is, x preview =v x *3, or get x by looking up the table preview Since the vehicle's motion state needs to be judged, the preview point needs to be placed a certain distance in front of the vehicle, so x preview The value of is used to limit the maximum and minimum values;

[0069] Calculate the vehicle's motion position and the lane line position at the preview point respectively, and then calculate the distance ey from the front center of the vehicle at the preview point to the lane line preview :

[0070] First, according to formula (4), calculate the lateral position ey of the vehicle at the preview point preview :

[0071]

[0072] According to formula (5), the position y of the lane centerline at the preview point of the vehicle is calculated preview_lane :

[0073]

[0074] According to formula (6), the first-order derivative dy of the lane centerline at the preview point is calculated preview_lane :

[0075]

[0076] At the preview point, the distance between the front center of the vehicle and the lane line is ey preview It can be obtained by the following formula:

[0077]

[0078] According to the position error ey at the vehicle starting point calculated previously current and the position error ey at the preview point previewLet's discuss the situation and judge the movement trend of the vehicle. According to different movement trends, the center line of the lane is offset for a certain period. The movement of the vehicle is divided into: the vehicle is driving in the center, the vehicle is stable and offset, the vehicle changes lanes to the left without crossing the line, the vehicle changes lanes to the left and has crossed the line, the vehicle changes lanes to the right without crossing the line, and the vehicle changes lanes to the right and has crossed the line. The following discusses the judgment of the vehicle's movement state according to each condition:

[0079] The vehicle changes lanes left without crossing the line: ey current <0&&ey preview -ey current <-0.7 determines that the vehicle is changing lanes to the left without crossing the line.

[0080] The vehicle changes lanes right without crossing the line: ey current >0&&ey preview -ey current >0.7 determines that the vehicle is changing lanes right without crossing the line.

[0081] The vehicle has crossed the line when changing lanes to the left: When the vehicle was changing lanes to the left and did not cross the line in the previous cycle, the a0 of the lane centerline at this moment and a at the previous moment are used to calculate the value of the a0 of the lane centerline at this moment and a at the previous moment. 0last To determine whether the vehicle has crossed the line, specifically a0-a 0last <-0.6*W, W is the width of the lane.

[0082] The vehicle has crossed the line when changing lanes right: When the vehicle was changing lanes right and did not cross the line in the previous cycle, the a0 of the lane centerline at this moment and a at the previous moment are used to calculate the value of the lane centerline. 0last To determine whether the vehicle has crossed the line, specifically a0-a 0last >0.6*W, W is the width of the lane.

[0083] Vehicle Stability Offset Hold: When the vehicle is not in the front four states, when the condition (ey current <0&&ey preview <-0.5)||(ey current >0&&ey preview >0.5).

[0084] The vehicle is driving in the center: When the previous five conditions are not met, the vehicle is driving in the center.

[0085] The state machine diagram of the vehicle motion state is as follows Figure 3 As shown;

[0086] The calculated vehicle motion state is used to optimize the lane centerline. The specific algorithm is as follows:

[0087] The lane centerline equation is expressed in equation (5) to optimize the lane line according to various situations.

[0088] 1. The vehicle changes lanes to the left without crossing the lane line: the lane center line a0 uses the left lane line a0.

[0089] 2. The vehicle changes lanes right without crossing the line: the lane center line a0 uses the a0 of the right lane line.

[0090] 3. The vehicle has crossed the line when changing lanes to the left: the center line a0 of the lane remains unchanged, and the center line a0 of the lane is used.

[0091] 4. The vehicle has crossed the line when changing lanes right: the center line a0 of the lane remains unchanged, and the center line a0 of the lane is used.

[0092] 5. Vehicle Stability Offset Maintenance: The a0 offset of the lane centerline is the a0 of the current lane line plus the lateral offset value y at the preview point preview .

[0093] 6. The vehicle is driving in the center: the center line of the lane remains unchanged.

[0094] In the above case, the values ​​of a1, a2 and a3 of the vehicle centerline are all based on the lane centerline parameters. The updated lane centerline equation (5) is used to calculate the parameters at the lane change preview point. The lane change preview distance can be calculated using x preview =v x *4.5, that is, preview 4.5s; using the current motion parameters of the vehicle and the parameters at the lane change preview point, a fifth-order polynomial is used to fit the lane line. From the starting point after the lane change to the effective distance of the lane line, a third-order polynomial is used to fit. For the part exceeding the lane line, the lane line at the vanishing point is expanded for estimation. The schematic diagram after specific implementation is shown below. Figure 4 shown.

[0095] Use the updated lane centerline and the lane width of the vehicle's lane line, and then use the updated lane centerline for target screening of adaptive cruise control ACC.

[0096] The present invention considers the movement trend of the vehicle and uses different lane center lines according to different movement states of the vehicle. This makes target screening more accurate. The screening target reflects the driving intention of the vehicle and can make the assisted driving function more intelligent.

[0097] Although the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the claims and their equivalents.

Claims

1. A target screening method for optimizing lane lines according to the motion state of a vehicle, characterized in that: The following steps are involved: Step 1: Obtain the vehicle's sensor input information and calculate the vehicle's motion formula; Step 2: Based on the input information from the camera, calculate the lane centerline based on the left and right lane lines; Step 3: According to Step 1 and Step 2, the starting position, the lateral position error from the vehicle to the center line of the lane, the lateral position of the vehicle at the preview point, the lane line position at the preview point, and the distance from the vehicle at the preview point to the center line of the lane are calculated; Step 4: Based on the information in step 3, the lateral position error at the starting point and the lateral position error at the preview point are used to calculate the vehicle's motion state: the vehicle is driving in the center, the vehicle is maintaining a stable offset, the vehicle is changing lanes to the left without crossing the line, the vehicle is changing lanes to the left without crossing the line, the vehicle is changing lanes to the right without crossing the line, and the vehicle is changing lanes to the right without crossing the line; Step 5: Based on the information in step 4, the lane centerline is updated and the updated lane centerline is used to find the preview point position parameter information for lane change; Step 6: Based on the information in step 5, the motion parameters of the current point and the lane change preview point are used to fit the lane centerline using a quintic polynomial; Step 7: Based on the information in steps 4 and 5, a cubic polynomial is used to fit the lane centerline within the effective distance from the lane change preview point to the lane line; Step 8: Based on the information in step 7, for positions that exceed the effective length of the lane line, use Taylor expansion at the vanishing point of the lane line to extend the lane line.

2. The target screening method for optimizing lane lines according to the motion state of the vehicle according to claim 1, characterized in that: The sensor input information obtained from the vehicle includes but is not limited to data collected by the vehicle's speed sensor, acceleration sensor, and gyroscope sensor. These data are fused to calculate the vehicle's motion formula, wherein the speed sensor is used to obtain the vehicle's real-time driving speed, the acceleration sensor is used to obtain the vehicle's acceleration magnitude and direction, and the gyroscope sensor is used to obtain the vehicle's angular velocity information.

3. The target screening method for optimizing lane lines according to the motion state of the vehicle according to claim 1, characterized in that: When calculating the lane centerline based on the input information from the camera, the image captured by the camera is preprocessed, including image grayscale and filtering and noise reduction processing, to improve the recognition of the lane line information in the image. The edge detection algorithm is then used to extract the edge contour of the lane line. The extracted edge contour is then screened and fitted based on geometric features and prior knowledge of the lane line, so as to accurately calculate the lane centerline.

4. The target screening method for optimizing lane lines according to the motion state of the vehicle according to claim 1, characterized in that: Step 3: According to step 1 and step 2, the starting position, the lateral position error from the vehicle to the center line of the lane, the lateral position of the vehicle at the preview point, the lane line position at the preview point are calculated, and the distance from the vehicle at the preview point to the center line of the lane is calculated; The preview point is mainly used for calculation.

5. The target screening method for optimizing lane lines according to the motion state of the vehicle according to claim 1, characterized in that: In step 4, the lateral position error at the starting point and the lateral position error at the preview point are used to calculate the motion state of the vehicle; the threshold for calculating the vehicle motion trend is optimized according to the actual situation of the vehicle.

6. The target screening method for optimizing lane lines according to the motion state of the vehicle according to claim 1, characterized in that: Step 5: Based on the information in step 4, update the a0 of the lane centerline, and use the updated lane centerline to find the preview point position parameter information for lane change, and the distance of the preview point is determined based on the actual vehicle.

7. The target screening method for optimizing lane lines according to the motion state of the vehicle according to claim 1, characterized in that: Step 6: Based on the information in step 5, the motion parameters of the current point and the lane change preview point are used to fit the lane center line using a quintic polynomial, wherein the fitting of the lane line includes but is not limited to the use of a quintic polynomial fitting.

8. The target screening method for optimizing lane lines according to the motion state of the vehicle according to claim 1, characterized in that: Step 7: Based on the information in steps 4 and 5, a cubic polynomial is used to fit the lane centerline within the effective distance from the lane change preview point to the lane line. The lane line fitting for this section includes but is not limited to fitting using a cubic polynomial.

9. The target screening method for optimizing lane lines according to the motion state of the vehicle according to claim 1, characterized in that: Step 8: Based on the information in step 7, the lane line is extended by using Taylor expansion at the vanishing point of the lane line at a position exceeding the effective length of the lane line; the extension of this section of the lane line includes but is not limited to using Taylor expansion.

Images