Lane line estimation method and related device

Abstract

This application discloses a lane line estimation method, which includes: when a target vehicle is detected in front of the self-vehicle, obtaining the self-vehicle's speed, yaw rate, steering wheel angle, and longitudinal and lateral relative distances from the target vehicle; calculating the self-vehicle's driving trajectory after a preset time period based on the self-vehicle's speed, yaw rate, steering wheel angle, distance from the self-vehicle's center of mass to the front axle, and distance from the self-vehicle's center of mass to the rear axle; calculating the position of the target vehicle in the self-vehicle coordinate system after a preset time period based on the self-vehicle's driving trajectory, longitudinal relative distance from the target vehicle, and lateral relative distance from the target vehicle; and estimating the lane line in front of the self-vehicle based on the position of the target vehicle in the self-vehicle coordinate system. In this method, lane lines can be accurately estimated even when there are other vehicles in front of the self-vehicle, thereby providing more complete lane line information for intelligent driving technology.

Description

Technical Field

[0001] The present invention relates to the field of vehicle intelligent driving technology, and in particular to a lane line estimation method and related devices. Background Art

[0002] Intelligent driving generally includes autonomous driving and assisted driving. As users demand a better driving experience, more and more vehicles are equipped with intelligent driving features. In traffic congestion, drivers can enable the vehicle's intelligent driving features, freeing their hands and feet on congested roads, eliminating the need to overly focus on road conditions and improving the driver's driving experience.

[0003] With the in-depth development of intelligent driving technology, vehicles' intelligent driving functions have an increasingly high demand for environmental awareness. For example, the lane markings ahead of the vehicle are a key piece of environmental information in the development of intelligent driving functions. Lane markings ahead play a crucial role in Advanced Driving Assistance Systems (ADAS). The industry generally installs visual sensors on vehicles to capture lane markings ahead for intelligent driving.

[0004] However, when there are other vehicles in front of the vehicle, the other vehicles will block the lane lines, and the visual sensor will not be able to collect accurate lane lines, making it difficult to provide complete lane line information for intelligent driving technology, which will lead to the inability to use intelligent driving normally and even cause traffic accidents. Summary of the Invention

[0005] To address the above issues, the present application provides a lane line estimation method and related devices, which can accurately estimate lane lines even when there are other vehicles in front of the vehicle, thereby providing more complete lane line information for intelligent driving technology.

[0006] In a first aspect, the present application provides a lane line estimation method, the method comprising:

[0007] When a target vehicle is detected in front of the ego vehicle, the ego vehicle speed, ego vehicle yaw rate, ego vehicle steering wheel angle, and the longitudinal relative distance and lateral relative distance of the target vehicle are obtained; wherein the longitudinal relative distance of the target vehicle is the longitudinal distance between the target vehicle and the ego vehicle in the ego vehicle coordinate system, and the lateral relative distance of the target vehicle is the lateral distance between the target vehicle and the ego vehicle in the ego vehicle coordinate system;

[0008] Calculating a trajectory of the vehicle after a preset time period based on the vehicle speed, the vehicle yaw rate, the vehicle steering wheel angle, the distance from the vehicle center of mass to the front axle, and the distance from the vehicle center of mass to the rear axle;

[0009] Calculating the position of the target vehicle in the ego vehicle coordinate system after a preset time period based on the ego vehicle's driving trajectory, the longitudinal relative distance to the target vehicle, and the lateral relative distance to the target vehicle;

[0010] The lane line in front of the ego vehicle is estimated based on the position of the target vehicle in the ego vehicle coordinate system.

[0011] In one possible implementation, calculating the vehicle's driving trajectory after a preset time period based on the vehicle speed, the vehicle's yaw rate, the vehicle's steering wheel angle, the distance from the vehicle's center of mass to the front axle, and the distance from the vehicle's center of mass to the rear axle includes:

[0012]

[0013]

[0014]

[0015]

[0016] in, is the yaw angular velocity of the vehicle, T is the preset time period, The vehicle heading angle at time t0 is calculated based on the data at time t1; The vehicle's center of mass side slip angle at time t0 is calculated based on the data at time t1, l r is the distance from the vehicle's center of mass to the rear axle, l f is the distance from the vehicle's center of mass to the front axle, is the steering wheel angle of the vehicle at time t1; is the vehicle speed at time t1;

[0017] The longitudinal displacement of the vehicle's driving trajectory at time t0 is calculated based on the data at time t1, The lateral displacement of the vehicle in the driving trajectory at time t0 is calculated based on the data at time t1.

[0018] In one possible implementation, calculating the position of the target vehicle in the ego vehicle coordinate system after a preset time period based on the ego vehicle's driving trajectory, the longitudinal relative distance to the target vehicle, and the lateral relative distance to the target vehicle includes:

[0019] Performing coordinate transformation on the longitudinal displacement and the lateral displacement in the driving trajectory of the self-vehicle, and performing coordinate transformation on the longitudinal relative distance of the target vehicle and the lateral relative distance of the target vehicle;

[0020] The position of the target vehicle in the ego vehicle coordinate system after a preset time period is calculated based on the ego vehicle coordinates after the coordinate transformation and the target vehicle coordinates after the coordinate transformation.

[0021] In one possible implementation, performing coordinate conversion on the longitudinal displacement and the lateral displacement in the driving trajectory of the ego vehicle, and performing coordinate conversion on the longitudinal relative distance of the target vehicle and the lateral relative distance of the target vehicle, include:

[0022]

[0023]

[0024]

[0025]

[0026] in, is the longitudinal coordinate of the target vehicle after coordinate transformation at time t1, is the longitudinal relative distance of the target vehicle at time t1;

[0027] is the lateral coordinate of the target vehicle after coordinate transformation at time t1, is the lateral relative distance of the target vehicle at time t1;

[0028] The longitudinal coordinate of the vehicle after coordinate transformation at time t0 is calculated based on the data at time t1;

[0029] The lateral coordinates of the vehicle after coordinate transformation at time t0 are calculated based on the data at time t1.

[0030] In one possible implementation, calculating the position of the target vehicle in the ego vehicle coordinate system after a preset time period based on the ego vehicle coordinates after coordinate transformation and the target vehicle coordinates after coordinate transformation includes:

[0031]

[0032] in, The longitudinal coordinate of the target vehicle at time t0 in the vehicle coordinate system is calculated based on the data at time t1. The lateral coordinate of the target vehicle at time t0 in the vehicle coordinate system is calculated based on the data at time t1.

[0033] In one possible implementation, estimating the lane line ahead of the ego vehicle based on the position of the target vehicle in the ego vehicle coordinate system includes:

[0034] The lane line in front of the vehicle is segmented according to the total length of the calibrated lane line, the effective length of the lane line collected by the visual sensor, and the segment length;

[0035] Assigning a plurality of trajectory points corresponding to the position of the target vehicle in the ego vehicle coordinate system to lane line segments;

[0036] The curvature of the lane line and the curvature change rate of the lane line are calculated based on the multiple trajectory points.

[0037] In one possible implementation, segmenting the lane line ahead of the vehicle based on the calibrated total lane line length, the effective lane line length captured by the visual sensor, and the segment length includes:

[0038] like Add a length of (L total -L lend )

[0039] like Add two segments of length Segmentation;

[0040] like Add three segments of length segmentation.

[0041] In a second aspect, the present application provides a lane line estimation device, comprising:

[0042] a vehicle information acquisition unit, configured to acquire the vehicle speed, yaw rate, steering wheel angle, longitudinal distance, and lateral distance of the target vehicle when a target vehicle is detected in front of the vehicle; wherein the longitudinal distance is the longitudinal distance between the target vehicle and the vehicle in the vehicle coordinate system, and the lateral distance is the lateral distance between the target vehicle and the vehicle in the vehicle coordinate system;

[0043] a vehicle driving trajectory calculation unit, configured to calculate the vehicle driving trajectory after a preset time period based on the vehicle speed, the vehicle yaw rate, the vehicle steering wheel angle, the distance from the vehicle center of mass to the front axle, and the distance from the vehicle center of mass to the rear axle;

[0044] a target vehicle position calculation unit, configured to calculate the position of the target vehicle in the ego vehicle coordinate system after a preset time period based on the ego vehicle's driving trajectory, the longitudinal relative distance of the target vehicle, and the lateral relative distance of the target vehicle;

[0045] The lane line estimation unit is used to estimate the lane line in front of the vehicle according to the position of the target vehicle in the vehicle coordinate system.

[0046] In a possible implementation, the vehicle driving trajectory calculation unit is specifically configured to calculate the vehicle driving trajectory after a preset time period using the following formula:

[0047]

[0048]

[0049]

[0050]

[0051] in, is the yaw angular velocity of the vehicle, T is the preset time period, The vehicle heading angle at time t0 is calculated based on the data at time t1; The vehicle's center of mass side slip angle at time t0 is calculated based on the data at time t1, l r is the distance from the vehicle's center of mass to the rear axle, l f is the distance from the vehicle's center of mass to the front axle, is the steering wheel angle of the vehicle at time t1; is the vehicle speed at time t1;

[0052] The longitudinal displacement of the vehicle's driving trajectory at time t0 is calculated based on the data at time t1, The lateral displacement of the vehicle in the driving trajectory at time t0 is calculated based on the data at time t1.

[0053] In one possible implementation, the target vehicle position calculation unit is specifically used to perform coordinate conversion on the longitudinal displacement and lateral displacement in the driving trajectory of the ego vehicle, and to perform coordinate conversion on the longitudinal relative distance of the target vehicle and the lateral relative distance of the target vehicle; and calculate the position of the target vehicle in the ego vehicle coordinate system after a preset time period based on the ego vehicle coordinates after coordinate conversion and the target vehicle coordinates after coordinate conversion.

[0054] In a possible implementation, the target vehicle position calculation unit is specifically configured to perform coordinate conversion using the following formula:

[0055]

[0056]

[0057]

[0058]

[0059] in, is the longitudinal coordinate of the target vehicle after coordinate transformation at time t1, is the longitudinal relative distance of the target vehicle at time t1;

[0060] is the lateral coordinate of the target vehicle after coordinate transformation at time t1, is the lateral relative distance of the target vehicle at time t1;

[0061] The longitudinal coordinate of the vehicle after coordinate transformation at time t0 is calculated based on the data at time t1;

[0062] The lateral coordinates of the vehicle after coordinate transformation at time t0 are calculated based on the data at time t1.

[0063] In a possible implementation, the target vehicle position calculation unit is specifically configured to calculate the position of the target vehicle in the vehicle coordinate system after a preset time period using the following formula:

[0064]

[0065] in, The longitudinal coordinate of the target vehicle at time t0 in the vehicle coordinate system is calculated based on the data at time t1. The lateral coordinate of the target vehicle at time t0 in the vehicle coordinate system is calculated based on the data at time t1.

[0066] In one possible implementation, the lane line estimation unit is specifically used to segment the lane line in front of the vehicle according to the total length of the calibrated lane line, the effective length of the lane line collected by the visual sensor, and the segment length; assign multiple trajectory points corresponding to the position of the target vehicle in the vehicle coordinate system to the lane line segments; and calculate the curvature of the lane line and the curvature change rate of the lane line based on the multiple trajectory points.

[0067] In one possible implementation, the lane line estimation unit is specifically configured to segment the lane line in the following manner:

[0068] like Add a length of (L total -L lend )

[0069] like Add two segments of length Segmentation;

[0070] like Add three segments of length segmentation.

[0071] In a third aspect, the present application provides a vehicle, wherein the device includes a processor and a memory:

[0072] The memory is used to store a computer program and transmit the computer program to the processor;

[0073] The processor is configured to execute any one of the above methods according to instructions in the computer program.

[0074] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium is used to store a computer program, and the computer program is used to execute any one of the methods described above.

[0075] Compared with the prior art, the advantages of the above technical solution of this application are:

[0076] The method obtains the vehicle speed, yaw rate, steering wheel angle, longitudinal distance and lateral distance of the target vehicle in the vehicle coordinate system when a target vehicle is detected in front of the vehicle. The longitudinal distance is the longitudinal distance between the target vehicle and the vehicle in the vehicle coordinate system, and the lateral distance is the lateral distance between the target vehicle and the vehicle in the vehicle coordinate system. The method then calculates the vehicle's driving trajectory after a preset time period based on the vehicle speed, yaw rate, steering wheel angle, distance from the vehicle's center of mass to the front axle, and distance from the vehicle's center of mass to the rear axle. The method then calculates the position of the target vehicle in the vehicle coordinate system after the preset time period based on the vehicle's driving trajectory, the longitudinal distance and lateral distance of the target vehicle. The method then estimates the lane line in front of the vehicle based on the position of the target vehicle in the vehicle coordinate system. This method can estimate the lane line in front of the vehicle when there is a vehicle in front of the vehicle. Even if the lane line in front of the vehicle is blocked, it can provide complete lane line information for intelligent driving technology, such as the curvature of the lane line and the curvature change rate of the lane line. BRIEF DESCRIPTION OF THE DRAWINGS

[0077] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments recorded in this application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0078] Figure 1 A flowchart of a lane line estimation method provided in an embodiment of the present application;

[0079] Figure 2A schematic diagram of a vehicle heading angle, center of mass sideslip angle, and yaw angle provided in an embodiment of the present application;

[0080] Figure 3 A schematic diagram of a target vehicle in a self-vehicle coordinate system provided in an embodiment of the present application;

[0081] Figure 4 A schematic diagram of a lane curve provided in an embodiment of the present application;

[0082] Figure 5 A schematic diagram of a lane line estimation device provided in an embodiment of the present application;

[0083] Figure 6 A schematic diagram of a lane line estimation device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0084] In order to help those skilled in the art better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0085] Intelligent driving (e.g., autonomous driving and assisted driving) has become a hot topic, driving rapid development in this field and its widespread application in mass-produced vehicles. Lane keeping functions can make it easier for drivers to control the vehicle at highway speeds, alleviating fatigue caused by long hours of driving. As intelligent driving technology advances, the demand for environmental awareness is increasing.

[0086] When a vehicle is driving, the lane markings ahead are crucial environmental information for intelligent driving. Traditionally, a visual sensor located ahead of the vehicle collects lane marking information. However, if other vehicles are in front of the vehicle, these vehicles will obstruct the lane markings, preventing the visual sensor from providing comprehensive lane information.

[0087] In view of this, an embodiment of the present application provides a lane line estimation method. The method can be executed by a processing device. Specifically, when detecting the presence of a target vehicle in front of an ego vehicle, the processing device obtains the ego vehicle's speed, ego vehicle's yaw rate, ego vehicle's steering wheel angle, and the target vehicle's longitudinal relative distance and lateral relative distance; wherein the target vehicle's longitudinal relative distance is the longitudinal distance between the target vehicle and the ego vehicle in the ego vehicle coordinate system, and the target vehicle's lateral relative distance is the lateral distance between the target vehicle and the ego vehicle in the ego vehicle coordinate system. The processing device then calculates the ego vehicle's driving trajectory after a preset time period based on the ego vehicle's speed, the ego vehicle's yaw rate, the ego vehicle's steering wheel angle, the distance from the ego vehicle's center of mass to the front axle, and the distance from the ego vehicle's center of mass to the rear axle. The processing device then calculates the target vehicle's position in the ego vehicle coordinate system after the preset time period based on the ego vehicle's driving trajectory, the target vehicle's longitudinal relative distance, and the target vehicle's lateral relative distance. Finally, the processing device estimates the lane line in front of the ego vehicle, such as the curvature of the lane line in front, the curvature change rate, etc., based on the position of the target vehicle in the ego vehicle coordinate system.

[0088] When a target vehicle (e.g., another vehicle) is in front of the ego vehicle, this method estimates the obscured lane markings in front of the ego vehicle based on the collected ego vehicle information and the target vehicle information. This method can then obtain relatively complete lane marking information for use in intelligent driving. Furthermore, this method uses a dual-sensor approach to estimate lane marking information ahead. For example, a visual sensor collects lane marking information, while a range sensor collects target vehicle information. This information is then combined with the ego vehicle information to estimate the lane marking ahead, thereby improving the accuracy of lane marking estimation ahead.

[0089] The processing device may be a server or a vehicle-mounted controller on a vehicle, which is not limited in this application.

[0090] In order to make the technical solution of the present application clearer and easier to understand, the lane line estimation method provided in the embodiment of the present application is introduced from the perspective of the processing equipment below.

[0091] like Figure 1 As shown in FIG, the figure shows a flow chart of a lane line estimation method provided in an embodiment of the present application, the method comprising the following steps:

[0092] S101: When the processing device detects that there is a target vehicle in front of the ego vehicle, the ego vehicle speed, ego vehicle yaw rate, ego vehicle steering wheel angle, and the longitudinal relative distance and lateral relative distance of the target vehicle are obtained.

[0093] The longitudinal relative distance of the target vehicle is the longitudinal distance between the target vehicle and the own vehicle in the own vehicle coordinate system, and the lateral relative distance of the target vehicle is the lateral distance between the target vehicle and the own vehicle in the own vehicle coordinate system.

[0094] For ease of understanding, the following Figure 2 , the heading angle, center of mass sideslip angle and yaw angle of the vehicle involved in this application are introduced.

[0095] like Figure 2 As shown, θ is the heading angle, which is the angle between the vehicle's center of mass velocity and the horizontal axis in the ground coordinate system; β is the center of mass slip angle, which is the angle between the direction of the vehicle's center of mass velocity and the direction of the vehicle's front; is the yaw angle, which is the heading angle minus the sideslip angle of the center of mass.

[0096] In some embodiments, the processing device can use a visual sensor to detect the presence of a target vehicle in front of the ego vehicle, and then obtain the ego vehicle's speed, yaw rate, and steering wheel angle. The processing device can also use a distance sensor to obtain the longitudinal and lateral relative distances to the target vehicle.

[0097] S102: The processing device calculates a driving trajectory of the vehicle after a preset time period based on the vehicle speed, the vehicle yaw rate, the vehicle steering wheel angle, the distance from the vehicle center of mass to the front axle, and the distance from the vehicle center of mass to the rear axle.

[0098] In some embodiments, the processing device may calculate the vehicle's driving trajectory after a preset time period using the following formula:

[0099]

[0100]

[0101]

[0102]

[0103] in, is the yaw angular velocity of the vehicle, T is the preset time period, The vehicle heading angle at time t0 is calculated based on the data at time t1; The vehicle's center of mass side slip angle at time t0 is calculated based on the data at time t1, l r is the distance from the vehicle's center of mass to the rear axle, l f is the distance from the vehicle's center of mass to the front axle, is the steering wheel angle of the vehicle at time t1; is the vehicle speed at time t1.

[0104] The longitudinal displacement of the vehicle's driving trajectory at time t0 is calculated based on the data at time t1, The lateral displacement of the vehicle in the driving trajectory at time t0 is calculated based on the data at time t1.

[0105] Among them, the vehicle's driving trajectory can be and To characterize.

[0106] S103: The processing device calculates the position of the target vehicle in the ego vehicle coordinate system after a preset time period based on the ego vehicle's driving trajectory, the longitudinal relative distance to the target vehicle, and the lateral relative distance to the target vehicle.

[0107] In some embodiments, the processing device performs coordinate conversion on the longitudinal displacement and lateral displacement in the driving trajectory of the ego vehicle, and performs coordinate conversion on the longitudinal relative distance of the target vehicle and the lateral relative distance of the target vehicle. Then, the processing device calculates the position of the target vehicle in the ego vehicle coordinate system after a preset time period based on the ego vehicle coordinates after the coordinate conversion and the target vehicle coordinates after the coordinate conversion.

[0108] In some possible implementations, the processing device may perform coordinate conversion using the following formula:

[0109]

[0110]

[0111]

[0112]

[0113] in, is the longitudinal coordinate of the target vehicle after coordinate transformation at time t1, is the longitudinal relative distance of the target vehicle at time t1.

[0114] is the lateral coordinate of the target vehicle after coordinate transformation at time t1, is the lateral relative distance of the target vehicle at time t1.

[0115] The longitudinal coordinate of the vehicle after coordinate transformation at time t0 is calculated based on the data at time t1.

[0116] The lateral coordinates of the vehicle after coordinate transformation at time t0 are calculated based on the data at time t1.

[0117] In some possible implementations, the processing device may calculate the position of the target vehicle in the ego vehicle coordinate system after a preset time period using the following formula:

[0118]

[0119] in, The longitudinal coordinate of the target vehicle at time t0 in the vehicle coordinate system is calculated based on the data at time t1. The lateral coordinate of the target vehicle at time t0 in the vehicle coordinate system is calculated based on the data at time t1.

[0120] The position of the target vehicle in the ego vehicle coordinate system can be obtained by and To characterize.

[0121] like Figure 3 As shown, Figure 3 A schematic diagram of a target vehicle in the ego-vehicle coordinate system is shown.

[0122] The solid line represents the coordinate system at the current moment (for example, time t0), and the dotted line represents the coordinate system at the previous moment (for example, time t1).

[0123] In some embodiments, the processing device may sequentially calculate multiple historical positions of the target vehicle corresponding to the current position of the vehicle in the coordinate system. For ease of understanding, the following description will take the calculation of two historical positions as an example.

[0124] First historical position:

[0125]

[0126] in, The longitudinal coordinate of the target vehicle at time t0 in the vehicle coordinate system is calculated based on the data at time t2. The lateral coordinate of the target vehicle at time t0 in the vehicle coordinate system is calculated based on the data at time t2. The longitudinal coordinate of the vehicle after coordinate transformation at time t1 is calculated based on the data at time t2; The lateral coordinates of the vehicle after coordinate transformation at time t1 are calculated based on the data at time t2.

[0127] Second historical location:

[0128]

[0129] The longitudinal coordinate of the target vehicle at time t0 in the vehicle coordinate system is calculated based on the data at time t3. The lateral coordinate of the target vehicle at time t0 in the vehicle coordinate system is calculated based on the data at time t3. The longitudinal coordinate of the vehicle after coordinate transformation at time t2 is calculated based on the data at time t3; The lateral coordinates of the vehicle after coordinate transformation at time t2 are calculated based on the data at time t3.

[0130] Of course, in the embodiment of the present application, the processing device can also calculate more historical locations, such as 4, 5, or 40, 50, and the present application does not limit this.

[0131] S104: The processing device estimates the lane line in front of the ego vehicle based on the position of the target vehicle in the ego vehicle coordinate system.

[0132] In some embodiments, the processing device segments the lane line in front of the ego-vehicle according to the total length of the calibrated lane line, the effective length of the lane line collected by the visual sensor, and the segment length; then the processing device assigns multiple trajectory points corresponding to the position of the target vehicle in the ego-vehicle coordinate system to the lane line segments; then the processing device calculates the curvature of the lane line and the curvature change rate of the lane line based on the multiple trajectory points.

[0133] In some implementations, the processing device may segment the lane marking ahead in the following manner:

[0134] like Add a length of (L total -L lend )

[0135] like Add two segments of length Segmentation;

[0136] like Add three segments of length Segmentation;

[0137] Among them, L total is the total length of the lane line, L lend is the effective length of the lane line collected by the visual sensor, L th is the segment length.

[0138] Of course, in some embodiments, if L total ≤L lend , it means that the effective length captured by the visual sensor includes the total length of the calibrated lane lines, that is, the visual sensor has captured all the lane lines and no further lane line estimation processing is required.

[0139] In other implementations, the processing device may also set a fourth multiple threshold, a fifth multiple threshold, and so on. Taking setting the fourth multiple threshold as an example, specifically:

[0140] like Add four segments of length segmentation.

[0141] Next, the processing device assigns the multiple trajectory points corresponding to the calculated positions in the ego-vehicle coordinate system to the lane line segments, thereby obtaining the lane line curve.

[0142] like Figure 4 As shown in FIG. , the figure shows a schematic diagram of a lane line curve.

[0143] Among them, segment x0 is the segment corresponding to the effective length of the lane line collected by the visual sensor, and x1, x2, and x3 are segments obtained based on the total length of the lane line, the effective length of the lane line collected by the visual sensor, and the segment length, respectively.

[0144] In some implementations, the processing device may fit the trajectory points of the target vehicle in each segment separately: Among them, k is the curvature of the lane line, and then we get (i,k i ,Valid). i represents the i-th segment, κ i Represents the curvature of the i-th segment. Valid=0 means that the trajectory points of the i-th segment are lower than the preset threshold (i.e., the number of trajectory points is small). Valid=1 means that the i-th segment is greater than or equal to the preset threshold (i.e., the number of trajectory points is large).

[0145] In some implementations, the processing device can also fit the trajectory points of multiple target vehicles in each segment to obtain multiple sets of (i, k i ,Valid), then for each segment, median filtering is performed from multiple sets of curvatures to obtain the filtered curvature of each segment (like Figure 4 The midpoint of each segment in the lane is obtained by further reducing the error of lane curvature.

[0146] Next, the processing device can also calculate the lane curvature change rate for each segment:

[0147]

[0148] Among them, λ i+1 is the curvature change rate of the i+1th segment, is the curvature value after filtering of the i+1th segment, κ i (end) is the curvature value at the end point of segment i, x i+1 (end) is the curvature value at the starting point of the i+1 segment, x i (start) is the curvature value at the starting point of the i-th segment.

[0149] In some implementations, the ego vehicle heading angle can be approximately calculated using the following formula:

[0150]

[0151] In some embodiments, it is necessary to ensure that the curvature and heading angles at the connection point between the two segments are equal, that is, κ i (end) = κ i+1 (start), θ i (end) = θ i+1 In some embodiments, the target vehicle coordinates corresponding to the end point of the previous segment at the connection point between two segments should be equal to the values corresponding to the starting point of the next segment.

[0152] Based on the above description, when there is a target vehicle (such as another vehicle) in front of the ego vehicle, this method estimates the obscured lane line in front of the ego vehicle based on the collected ego vehicle information and target vehicle information, thereby obtaining relatively complete lane line information for use in intelligent driving. Furthermore, this method uses a dual-sensor approach to estimate the lane line information ahead, for example, using a visual sensor to collect lane line information and a distance sensor to collect target vehicle information. This information is then combined with the ego vehicle information to estimate the lane line ahead, thereby improving the accuracy of the lane line estimation ahead.

[0153] The present application also provides a lane line estimation device. Figure 5 , which shows a schematic diagram of a lane line estimation device, the device comprising:

[0154] The vehicle information acquisition unit 501 is configured to acquire the vehicle speed, yaw rate, steering wheel angle, longitudinal distance, and lateral distance of the target vehicle when a target vehicle is detected in front of the vehicle. The longitudinal distance is the longitudinal distance between the target vehicle and the vehicle in the vehicle coordinate system, and the lateral distance is the lateral distance between the target vehicle and the vehicle in the vehicle coordinate system.

[0155] The vehicle driving trajectory calculation unit 502 is configured to calculate the vehicle driving trajectory after a preset time period based on the vehicle speed, the vehicle yaw rate, the vehicle steering wheel angle, the distance from the vehicle center of mass to the front axle, and the distance from the vehicle center of mass to the rear axle;

[0156] The target vehicle position calculation unit 503 is used to calculate the position of the target vehicle in the ego vehicle coordinate system after a preset time period based on the ego vehicle's driving trajectory, the longitudinal relative distance of the target vehicle, and the lateral relative distance of the target vehicle;

[0157] The lane line estimation unit 504 is used to estimate the lane line in front of the ego vehicle based on the position of the target vehicle in the ego vehicle coordinate system.

[0158] In a possible implementation, the vehicle driving trajectory calculation unit is specifically configured to calculate the vehicle driving trajectory after a preset time period using the following formula:

[0159]

[0160]

[0161]

[0162]

[0163] in, is the yaw angular velocity of the vehicle, T is the preset time period, The vehicle heading angle at time t0 is calculated based on the data at time t1; The vehicle's center of mass side slip angle at time t0 is calculated based on the data at time t1, l r is the distance from the vehicle's center of mass to the rear axle, l f is the distance from the vehicle's center of mass to the front axle, is the steering wheel angle of the vehicle at time t1; is the vehicle speed at time t1;

[0164] The longitudinal displacement of the vehicle's driving trajectory at time t0 is calculated based on the data at time t1, The lateral displacement of the vehicle in the driving trajectory at time t0 is calculated based on the data at time t1.

[0165] In one possible implementation, the target vehicle position calculation unit is specifically used to perform coordinate conversion on the longitudinal displacement and lateral displacement in the driving trajectory of the ego vehicle, and to perform coordinate conversion on the longitudinal relative distance of the target vehicle and the lateral relative distance of the target vehicle; and calculate the position of the target vehicle in the ego vehicle coordinate system after a preset time period based on the ego vehicle coordinates after coordinate conversion and the target vehicle coordinates after coordinate conversion.

[0166] In a possible implementation, the target vehicle position calculation unit is specifically configured to perform coordinate conversion using the following formula:

[0167]

[0168]

[0169]

[0170]

[0171] in, is the longitudinal coordinate of the target vehicle after coordinate transformation at time t1, is the longitudinal relative distance of the target vehicle at time t1;

[0172] is the lateral coordinate of the target vehicle after coordinate transformation at time t1, is the lateral relative distance of the target vehicle at time t1;

[0173] The longitudinal coordinate of the vehicle after coordinate transformation at time t0 is calculated based on the data at time t1;

[0174] The lateral coordinates of the vehicle after coordinate transformation at time t0 are calculated based on the data at time t1.

[0175] In a possible implementation, the target vehicle position calculation unit is specifically configured to calculate the position of the target vehicle in the vehicle coordinate system after a preset time period using the following formula:

[0176]

[0177] in, The longitudinal coordinate of the target vehicle at time t0 in the vehicle coordinate system is calculated based on the data at time t1. The lateral coordinate of the target vehicle at time t0 in the vehicle coordinate system is calculated based on the data at time t1.

[0178] In one possible implementation, the lane line estimation unit is specifically used to segment the lane line in front of the vehicle according to the total length of the calibrated lane line, the effective length of the lane line collected by the visual sensor, and the segment length; assign multiple trajectory points corresponding to the position of the target vehicle in the vehicle coordinate system to the lane line segments; and calculate the curvature of the lane line and the curvature change rate of the lane line based on the multiple trajectory points.

[0179] In one possible implementation, the lane line estimation unit is specifically configured to segment the lane line in the following manner:

[0180] like Add a length of (L total -L lend )

[0181] like Add two segments of length Segmentation;

[0182] like Add three segments of length segmentation.

[0183] The present application embodiment provides a device, see Figure 6, which shows a structural diagram of a device for displaying pictures provided by an embodiment of the present application, such as Figure 6 As shown, the device includes a processor 610 and a memory 620:

[0184] The memory 610 is used to store computer programs and transmit the computer programs to the processor;

[0185] The processor 620 is configured to execute the lane line estimation method described in the above embodiment according to the instructions in the computer program.

[0186] An embodiment of the present application provides a computer-readable storage medium, which is used to store a computer program, and the computer program is used to execute the lane line estimation method described in the above embodiment.

[0187] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. The device embodiment described above is merely illustrative, and the units and modules described as separate components may or may not be physically separated. In addition, some or all of the units and modules can be selected according to actual needs to achieve the purpose of the scheme of this embodiment. A person of ordinary skill in the art can understand and implement it without paying any creative work.

[0188] The above is only a specific implementation method of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A lane line estimation method, characterized in that: The method comprises: When a target vehicle is detected in front of the ego vehicle, the ego vehicle speed, ego vehicle yaw rate, ego vehicle steering wheel angle, and the longitudinal relative distance and lateral relative distance of the target vehicle are obtained; wherein the longitudinal relative distance of the target vehicle is the longitudinal distance between the target vehicle and the ego vehicle in the ego vehicle coordinate system, and the lateral relative distance of the target vehicle is the lateral distance between the target vehicle and the ego vehicle in the ego vehicle coordinate system; Calculating a trajectory of the vehicle after a preset time period based on the vehicle speed, the vehicle yaw rate, the vehicle steering wheel angle, the distance from the vehicle center of mass to the front axle, and the distance from the vehicle center of mass to the rear axle; Calculating the position of the target vehicle in the ego vehicle coordinate system after a preset time period based on the ego vehicle's driving trajectory, the longitudinal relative distance to the target vehicle, and the lateral relative distance to the target vehicle; estimating a lane line in front of the ego vehicle based on the position of the target vehicle in the ego vehicle coordinate system; The estimating the lane line in front of the ego vehicle according to the position of the target vehicle in the ego vehicle coordinate system includes: The lane line in front of the vehicle is segmented according to the total length of the calibrated lane line, the effective length of the lane line collected by the visual sensor, and the segment length; Assigning a plurality of trajectory points corresponding to the position of the target vehicle in the ego vehicle coordinate system to lane line segments; The curvature of the lane line and the curvature change rate of the lane line are calculated based on the multiple trajectory points.

2. The method according to claim 1, characterized in that The calculating of the vehicle's driving trajectory after a preset time period based on the vehicle's speed, the vehicle's yaw rate, the vehicle's steering wheel angle, the distance from the vehicle's center of mass to the front axle, and the distance from the vehicle's center of mass to the rear axle includes: in, is the yaw angular velocity of the vehicle, T is the preset time period, The vehicle heading angle at time t0 is calculated based on the data at time t1; The vehicle's center of mass side slip angle at time t0 is calculated based on the data at time t1, l r is the distance from the vehicle's center of mass to the rear axle, l f is the distance from the vehicle's center of mass to the front axle, is the steering wheel angle of the vehicle at time t1; is the vehicle speed at time t1; The longitudinal displacement of the vehicle's driving trajectory at time t0 is calculated based on the data at time t1, The lateral displacement of the vehicle in the driving trajectory at time t0 is calculated based on the data at time t1.

3. The method according to claim 2, characterized in that The calculating, based on the ego vehicle's driving trajectory, the longitudinal relative distance to the target vehicle, and the lateral relative distance to the target vehicle, a position of the target vehicle in the ego vehicle coordinate system after a preset time period includes: Performing coordinate transformation on the longitudinal displacement and the lateral displacement in the driving trajectory of the self-vehicle, and performing coordinate transformation on the longitudinal relative distance of the target vehicle and the lateral relative distance of the target vehicle; The position of the target vehicle in the ego vehicle coordinate system after a preset time period is calculated based on the ego vehicle coordinates after the coordinate transformation and the target vehicle coordinates after the coordinate transformation.

4. The method according to claim 3, characterized in that The coordinate conversion of the longitudinal displacement and the lateral displacement in the driving trajectory of the vehicle, and the coordinate conversion of the longitudinal relative distance of the target vehicle and the lateral relative distance of the target vehicle include: in, is the longitudinal coordinate of the target vehicle after coordinate transformation at time t1, is the longitudinal relative distance of the target vehicle at time t1; is the lateral coordinate of the target vehicle after coordinate transformation at time t1, is the lateral relative distance of the target vehicle at time t1; The longitudinal coordinate of the vehicle after coordinate transformation at time t0 is calculated based on the data at time t1; The lateral coordinates of the vehicle after coordinate transformation at time t0 are calculated based on the data at time t1.

5. The method according to claim 4, characterized in that The calculating, based on the coordinates of the ego vehicle after coordinate conversion and the coordinates of the target vehicle after coordinate conversion, a position of the target vehicle in the ego vehicle coordinate system after a preset time period includes: in, The longitudinal coordinate of the target vehicle at time t0 in the vehicle coordinate system is calculated based on the data at time t1. The lateral coordinate of the target vehicle at time t0 in the vehicle coordinate system is calculated based on the data at time t1.

6. The method according to claim 5, characterized in that The segmenting of the lane line in front of the vehicle according to the total length of the calibrated lane line, the effective length of the lane line collected by the visual sensor, and the segment length includes: like Add a length of (L total -L lend ) like Add two segments of length Segmentation; like Add three segments of length Segmentation; Among them, L total is the total length of the lane line, L lend is the effective length of the lane line collected by the visual sensor, L th is the segment length.

7. A lane line estimation device, characterized in that: include: a vehicle information acquisition unit, configured to acquire the vehicle speed, yaw rate, steering wheel angle, longitudinal distance, and lateral distance of the target vehicle when a target vehicle is detected in front of the vehicle; wherein the longitudinal distance is the longitudinal distance between the target vehicle and the vehicle in the vehicle coordinate system, and the lateral distance is the lateral distance between the target vehicle and the vehicle in the vehicle coordinate system; a vehicle driving trajectory calculation unit, configured to calculate the vehicle driving trajectory after a preset time period based on the vehicle speed, the vehicle yaw rate, the vehicle steering wheel angle, the distance from the vehicle center of mass to the front axle, and the distance from the vehicle center of mass to the rear axle; a target vehicle position calculation unit, configured to calculate the position of the target vehicle in the ego vehicle coordinate system after a preset time period based on the ego vehicle's driving trajectory, the longitudinal relative distance of the target vehicle, and the lateral relative distance of the target vehicle; A lane line estimation unit, configured to estimate the lane line in front of the ego vehicle based on the position of the target vehicle in the ego vehicle coordinate system; The lane line estimation unit is specifically used to segment the lane line in front of the vehicle according to the total length of the calibrated lane line, the effective length of the lane line collected by the visual sensor, and the segment length; assign multiple trajectory points corresponding to the position of the target vehicle in the vehicle coordinate system to the lane line segments; and calculate the curvature of the lane line and the curvature change rate of the lane line based on the multiple trajectory points.

8. A device, characterized in that The device includes a processor and a memory: The memory is used to store a computer program and transmit the computer program to the processor; The processor is configured to execute the method according to any one of claims 1 to 6 according to instructions in the computer program.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium is used to store a computer program, and the computer program is used to execute the method according to any one of claims 1 to 6.

Images