A method and system for identifying a side lane cut-in vehicle

Abstract

The application provides a kind of identification method and system of side lane cut-in vehicle, the method comprises: the first motion state information of control vehicle and the second motion state information of other vehicle are collected;According to the first motion state information and the second motion state information, determine the vehicle to be identified from other vehicles;Determine the historical motion state information of the vehicle to be identified;Determine the first driving intention of the vehicle to be identified by the historical motion state information;The first driving intention is corrected to obtain the second driving intention;Predict the predicted driving track of the vehicle to be identified, and determine the first driving intention or the second driving intention as the final driving intention based on the predicted driving track;According to the recent in-vehicle information of control vehicle, the second motion state information and the final driving intention, identify the side lane cut-in vehicle from the vehicle to be identified, so that adaptive cruise control function can take corresponding strategy in advance for side lane cut-in vehicle, thereby improving vehicle comfort and safety.

Description

Technical Field

[0001] This invention relates to the field of adaptive cruise control technology, specifically to a method and system for identifying vehicles cutting into the adjacent lane. Background Technology

[0002] Existing adaptive cruise control functions mainly use sensors and perception fusion systems to identify the nearest vehicle on the path to achieve functions such as maintaining distance to the target and stopping. However, existing adaptive cruise control functions generally lack attention to vehicles cutting in from the adjacent lane. If a vehicle from the adjacent lane cuts into the current lane and is then selected as the nearest vehicle on the path, it will lead to untimely control of the vehicle, resulting in delayed braking and forced braking, which will result in poor vehicle comfort and safety. Summary of the Invention

[0003] In view of this, embodiments of the present invention provide a method and system for identifying vehicles cutting in from the adjacent lane, in order to solve the problems of poor vehicle comfort and safety caused by the general lack of attention to vehicles cutting in from the adjacent lane in adaptive cruise control functions.

[0004] To achieve the above objectives, the embodiments of the present invention provide the following technical solutions:

[0005] The first aspect of this invention discloses a method for identifying vehicles cutting in from the adjacent lane, the method comprising:

[0006] Collect and control the first motion state information of the vehicle and the second motion state information of other vehicles. The first motion state information includes at least speed and yaw rate, and the second motion state information includes at least relative lateral position, relative longitudinal position, heading angle and track information.

[0007] Based on the first motion state information and the second motion state information, determine the vehicle to be identified from the other vehicles;

[0008] Based on the position coordinates of the vehicle to be identified in a specific coordinate system, the historical motion state information of the vehicle to be identified is determined, wherein the specific coordinate system is a coordinate system with the control vehicle as the origin;

[0009] Based on the historical motion state information, the first driving intention of the vehicle to be identified is determined, which is to change lanes to the left, change lanes to the right, or keep the lane.

[0010] The first driving intention is modified to obtain the second driving intention of the vehicle to be identified, which is to change lanes to the left, change lanes to the right, or keep the lane.

[0011] Predict the predicted driving trajectory of the vehicle to be identified, and determine the first driving intention or the second driving intention as the final driving intention based on the predicted driving trajectory;

[0012] Based on the information of the nearest vehicle on the path of the controlled vehicle, the second motion state information of the vehicle to be identified, and the final driving intention, the vehicle cutting in from the adjacent lane is identified from the vehicles to be identified.

[0013] Preferably, determining the vehicle to be identified from the other vehicles based on the first motion state information and the second motion state information includes:

[0014] Based on the first motion state information and the second motion state information, determine the absolute speed of the other vehicles, and determine the relative lateral distance and relative longitudinal distance between the other vehicles and the controlled vehicle;

[0015] If the absolute speed of the other vehicle is not 0, and if the relative lateral distance between the other vehicle and the controlled vehicle is less than a lateral distance threshold, and if the relative longitudinal distance between the other vehicle and the controlled vehicle is less than a longitudinal distance threshold, then the other vehicle is determined to be the vehicle to be identified.

[0016] If the absolute speed of the other vehicle is 0, and / or if the relative lateral distance between the other vehicle and the controlled vehicle is greater than or equal to the lateral distance threshold, and / or if the relative longitudinal distance between the other vehicle and the controlled vehicle is greater than or equal to the longitudinal distance threshold, then the other vehicle is determined not to be the vehicle to be identified.

[0017] Preferably, determining the historical motion state information of the vehicle to be identified based on its position coordinates in a specific coordinate system includes:

[0018] The historical driving trajectory of the vehicle to be identified is obtained, and the historical driving trajectory includes at least the position coordinates and heading angle of the vehicle to be identified at the current time and other times.

[0019] Calculate the lateral distance, longitudinal distance, and heading angle changes of the controlled vehicle within a unit sampling time.

[0020] Based on the changes in the lateral distance, longitudinal distance, and heading angle of the controlled vehicle within a unit sampling time, the position coordinates and heading angles at other times in the historical driving trajectory are transformed to a specific coordinate system.

[0021] By using the position coordinates and heading angles of other times in the historical driving trajectory transformed to the specific coordinate system, the historical motion state information of the vehicle to be identified is determined. The historical motion state information includes at least the historical longitudinal position, the historical lateral position, and the historical heading angle.

[0022] Preferably, determining the first driving intention of the vehicle to be identified based on the historical motion state information includes:

[0023] Obtain the lane centerline equation Y = C0 + C1*x + C2*x of the lane where the vehicle to be identified is located. 2 +C3*x 3 C0 is the lateral distance from the controlled vehicle to the center line of the lane where the vehicle to be identified is located, C1 is the slope, C2 is the curvature, and C3 is the rate of change of curvature.

[0024] Based on the lane centerline equation and the historical motion state information, combined with dθ t＝1:n =heading Hist -atan(Y' t＝1:n ) and dy t＝1:n =y Hist -Y t＝1:n Calculate the identification components, y Hist and heading Hist These represent the historical lateral position and historical heading angle of the vehicle to be identified, respectively. t=1 represents the current time, and t=n represents the last time of the historical motion state information. The identification component includes: the heading angle deviation dθ between the heading angle and the lane angle of the vehicle to be identified. t＝1:n And the lateral distance deviation dy between the vehicle to be identified and the lane centerline of the lane where the vehicle to be identified is located. t＝1:n ;

[0025] The identified components are normalized.

[0026] The first value is obtained by calculating the sum of the distances between the normalized identification component and the two foci of the left lane change boundary ellipse; and the second value is obtained by calculating the sum of the distances between the normalized identification component and the two foci of the right lane change boundary ellipse.

[0027] If the first value is greater than the specified threshold, it is determined that the first driving intention of the vehicle to be identified is to change lanes to the left;

[0028] If the second value is greater than the specified threshold, the first driving intention of the vehicle to be identified is determined to be to change lanes to the right;

[0029] If the first value and the second value are not greater than the specified threshold, the first driving intention of the vehicle to be identified is determined to be lane keeping.

[0030] Preferably, the step of modifying the first driving intention to obtain the second driving intention of the vehicle to be identified includes:

[0031] For the lateral distance deviation between the vehicle to be identified and the lane centerline of the lane where the vehicle to be identified is located, the lateral distance deviation is divided into m segments according to the time sequence;

[0032] When the first driving intention is to change lanes to the left, if the lateral distance deviations in the m segments decrease sequentially, then the second driving intention of the vehicle to be identified is determined to be to change lanes to the left; if the lateral distance deviations in the m segments do not decrease sequentially, then the second driving intention is determined to be to keep the lane.

[0033] When the first driving intention is to change lanes to the right, if the lateral distance deviations in the m segments increase sequentially, then the second driving intention of the vehicle to be identified is determined to be to change lanes to the right; if the lateral distance deviations in the m segments do not increase sequentially, then the second driving intention is determined to be to keep the lane.

[0034] Preferably, the lateral distance deviation between the vehicle to be identified and the lane centerline of the lane where the vehicle to be identified is located is divided into m segments according to time sequence, including:

[0035] The lateral distance deviation dy between the vehicle to be identified and the lane centerline of the lane in which the vehicle to be identified is located. t＝1:n ,pass The lateral distance deviation is divided into m segments according to time sequence, and each segment contains n / m points.

[0036] Preferably, predicting the predicted driving trajectory of the vehicle to be identified, and determining the first driving intention or the second driving intention as the final driving intention based on the predicted driving trajectory, includes:

[0037] The lateral position of the vehicle to be identified is recursively calculated using a uniform motion model, and the longitudinal position of the vehicle to be identified is recursively calculated using a uniform acceleration motion model to obtain the predicted driving trajectory of the vehicle to be identified. The predicted driving trajectory includes multiple future trajectory points.

[0038] Calculate the lateral distance between the last future trajectory point in the predicted driving trajectory and the lane line of the lane where the controlled vehicle is located;

[0039] If the last future trajectory point is within the lane where the controlled vehicle is located, and if the lateral distance between the last future trajectory point and the lane line of the controlled vehicle is greater than a distance threshold, the first driving intention is determined to be the final driving intention.

[0040] If the last future trajectory point is not in the lane where the controlled vehicle is located, or if the lateral distance between the last future trajectory point and the lane line of the controlled vehicle is less than or equal to the distance threshold, the second driving intention is determined to be the final driving intention.

[0041] Preferably, identifying the vehicle cutting in from the adjacent lane from the vehicles to be identified based on the nearest oncoming vehicle information of the controlled vehicle, the second motion state information of the vehicle to be identified, and the final driving intention includes:

[0042] When there is no nearest vehicle in the path, the vehicle to be identified is in the right lane of the controlled vehicle, and the final driving intention of the vehicle to be identified is to change lanes to the left, the vehicle to be identified is determined to be a vehicle cutting in from the adjacent lane.

[0043] When there is no nearest vehicle in the path, the vehicle to be identified is in the left lane of the controlled vehicle, and the final driving intention of the vehicle to be identified is to change lanes to the right, the vehicle to be identified is determined to be a vehicle cutting in from the adjacent lane.

[0044] When there is a nearest vehicle on the path, calculate the longitudinal distance between the vehicle to be identified and the controlled vehicle based on the relative longitudinal position of the vehicle to be identified, and calculate the longitudinal distance between the nearest vehicle on the path and the controlled vehicle.

[0045] If the vehicle to be identified is in the right lane of the vehicle under control, the final driving intention of the vehicle to be identified is to change lanes to the left, and the longitudinal distance between the vehicle to be identified and the vehicle under control is less than the longitudinal distance between the nearest oncoming vehicle and the vehicle under control, then the vehicle to be identified is determined to be a vehicle cutting in from the side lane.

[0046] If the vehicle to be identified is in the left lane of the vehicle under control, the final driving intention of the vehicle to be identified is to change lanes to the right, and the longitudinal distance between the vehicle to be identified and the vehicle under control is less than the longitudinal distance between the nearest oncoming vehicle and the vehicle under control, then the vehicle to be identified is determined to be a vehicle cutting in from the side lane.

[0047] Preferably, after identifying the vehicle cutting in from the adjacent lane from the vehicles to be identified, the method further includes:

[0048] The identification results of vehicles cutting into the adjacent lane are output to the adaptive cruise control function.

[0049] A second aspect of this invention discloses a system for recognizing vehicles cutting into adjacent lanes, the system comprising:

[0050] The acquisition unit is used to acquire first motion state information of the control vehicle and second motion state information of other vehicles. The first motion state information includes at least speed and yaw rate, and the second motion state information includes at least relative lateral position, relative longitudinal position, heading angle and track information.

[0051] The first determining unit is configured to determine the vehicle to be identified from the other vehicles based on the first motion state information and the second motion state information.

[0052] The second determining unit is used to determine the historical motion state information of the vehicle to be identified based on the position coordinates of the vehicle to be identified in a specific coordinate system, wherein the specific coordinate system is a coordinate system with the control vehicle as the origin.

[0053] The third determining unit is used to determine the first driving intention of the vehicle to be identified through the historical motion state information, wherein the first driving intention is to change lanes to the left, change lanes to the right, or keep the lane.

[0054] The correction unit is used to correct the first driving intention to obtain a second driving intention of the vehicle to be identified, wherein the second driving intention is to change lanes to the left, change lanes to the right, or keep the lane.

[0055] The prediction unit is used to predict the predicted driving trajectory of the vehicle to be identified, and determine the first driving intention or the second driving intention as the final driving intention based on the predicted driving trajectory.

[0056] The identification unit is used to identify vehicles cutting in from the adjacent lane from the vehicles to be identified based on the information of the nearest vehicle on the path of the controlled vehicle, the second motion state information of the vehicle to be identified, and the final driving intention.

[0057] The present invention provides a method and system for identifying vehicles cutting into other lanes, based on the above embodiments. The method includes: collecting first motion state information of a controlled vehicle and second motion state information of other vehicles; determining a vehicle to be identified from the other vehicles based on the first and second motion state information; determining the historical motion state information of the vehicle to be identified based on its position coordinates in a specific coordinate system; determining a first driving intention of the vehicle to be identified through the historical motion state information; correcting the first driving intention to obtain a second driving intention of the vehicle to be identified; predicting the predicted driving trajectory of the vehicle to be identified, and determining the first or second driving intention as the final driving intention based on the predicted driving trajectory; and identifying the vehicle cutting into other lanes from the vehicles to be identified based on the information of the nearest vehicle on the controlled vehicle's path, the second motion state information, and the final driving intention. This solution improves vehicle comfort and safety by identifying vehicles cutting into other lanes in advance, enabling adaptive cruise control to take appropriate strategies against such vehicles. Attached Figure Description

[0058] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0059] Figure 1 A flowchart illustrating a method for identifying vehicles cutting in from the adjacent lane, provided as an embodiment of the present invention;

[0060] Figure 2 This is a schematic diagram illustrating the post-processing of entry recognition based on entry trend and predicted driving trajectory provided in an embodiment of the present invention.

[0061] Figure 3 A flowchart for determining historical motion state information provided in an embodiment of the present invention;

[0062] Figure 4 This is an example diagram illustrating the acquisition of historical driving trajectories provided in an embodiment of the present invention;

[0063] Figure 5 A flowchart for determining a first driving intention provided in an embodiment of the present invention;

[0064] Figure 6 This is a schematic diagram illustrating vehicle cut-in recognition for adaptive cruise control provided in an embodiment of the present invention;

[0065] Figure 7 This is a schematic diagram of the driving intent recognition boundary provided in an embodiment of the present invention;

[0066] Figure 8 This is a structural block diagram of a vehicle identification system for vehicles cutting into the side lane, provided as an embodiment of the present invention. Detailed Implementation

[0067] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0068] In this application, the terms "comprising," "including," or any other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0069] As can be seen from the background technology, the existing adaptive cruise control (ACC) function mainly uses sensors and perception fusion systems to identify the nearest vehicle on the path to achieve functions such as maintaining distance to the target and stopping. However, the existing adaptive cruise control functions generally lack attention to vehicles cutting in from the adjacent lane. If a vehicle from the adjacent lane cuts into the current lane and is then selected as the nearest vehicle on the path, it will lead to untimely control of the vehicle, resulting in delayed braking and forced braking, and even causing accidents. The vehicle's comfort and safety are poor.

[0070] The inventors discovered that adaptive cruise control needs to consider not only the nearest vehicle in the vehicle's path but also vehicles that might cut in from the adjacent lane. By adding the ability to identify vehicles cutting in from the adjacent lane, adaptive cruise control can take appropriate control strategies earlier, resulting in smoother control parameters and an optimized passenger experience. Therefore, this solution proposes a method and system for identifying vehicles cutting in from the adjacent lane. By identifying such vehicles in advance, the adaptive cruise control can take appropriate strategies in advance, thereby improving vehicle comfort and safety.

[0071] See Figure 1 The flowchart illustrates a method for identifying vehicles cutting into the side lane according to an embodiment of the present invention. The method includes:

[0072] Step S101: Collect and control the first motion state information of the vehicle and the second motion state information of other vehicles.

[0073] In the specific implementation step S101, the first motion state information of the controlled vehicle (i.e., the vehicle itself) and the second motion state information of other vehicles within the recognition range are collected through the sensor and perception fusion system.

[0074] The first motion state information includes at least speed and yaw rate; the second motion state information includes at least relative lateral position, relative longitudinal position, heading angle, and course information.

[0075] Step S102: Based on the first motion state information and the second motion state information, determine the vehicle to be identified from other vehicles.

[0076] In the specific implementation of step S102, for each other vehicle, the absolute speed of the other vehicle is determined based on the first motion state information and the second motion state information of the other vehicle, and the relative lateral distance and relative longitudinal distance between the other vehicle and the control vehicle are determined.

[0077] If the absolute speed of the other vehicle is not 0 (equivalent to the other vehicle being a non-stationary vehicle), and if the relative lateral distance between the other vehicle and the control vehicle is less than the lateral distance threshold, and if the relative longitudinal distance between the other vehicle and the control vehicle is less than the longitudinal distance threshold, then the other vehicle is determined to be the vehicle to be identified; wherein, the relative lateral distance being less than the lateral distance threshold and the relative longitudinal distance being less than the longitudinal distance threshold indicate that the other vehicle is within the identification distance range.

[0078] If the absolute speed of the other vehicle is 0 (equivalent to the other vehicle being stationary), and / or if the relative lateral distance between the other vehicle and the controlling vehicle is greater than or equal to a lateral distance threshold, and / or if the relative longitudinal distance between the other vehicle and the controlling vehicle is greater than or equal to a longitudinal distance threshold, then the other vehicle is determined not to be the vehicle to be identified.

[0079] In other words, the absolute speed of other vehicles is used to determine whether they are stationary; if they are stationary, they are not identified (equivalent to determining that they are not the vehicles to be identified); by using the set horizontal and vertical distance thresholds and the relative position information of other vehicles, it is determined whether other vehicles are within the identification distance range; if they are not within the identification distance range, they are not identified; other vehicles not included in the above two categories are the vehicles to be identified.

[0080] Step S103: Determine the historical motion state information of the vehicle to be identified based on its position coordinates in a specific coordinate system.

[0081] It should be noted that the specific coordinate system is a coordinate system with the control vehicle as the origin.

[0082] In the specific implementation step S103, the historical driving trajectory of the vehicle to be identified is obtained. The historical driving trajectory includes at least the position coordinates and heading angle of the vehicle to be identified at the current time and other times.

[0083] The position coordinates of other moments in the historical driving trajectory are transformed to a specific coordinate system, and the historical motion state information of the vehicle to be identified is determined based on the position coordinates of the vehicle to be identified in the specific coordinate system. The historical motion state information includes at least the historical longitudinal position, historical lateral position and historical heading angle.

[0084] Step S104: Determine the first driving intention of the vehicle to be identified by using historical motion state information.

[0085] It should be noted that the primary driving intention is to change lanes to the left, change lanes to the right, or stay in the lane.

[0086] In the specific implementation step S104, the lane centerline equation of the lane where the vehicle to be identified is located is obtained, and based on the lane centerline equation and the historical motion state information of the vehicle to be identified, the identification component is calculated. The identification component includes: the deviation of the heading angle of the vehicle to be identified from the lane line angle during the historical trajectory time period, and the lateral distance deviation between the vehicle to be identified and the lane centerline of the lane where the vehicle to be identified is located.

[0087] Based on the identified components, the primary driving intent of the vehicle to be identified is determined to be changing lanes to the left (also known as changing lanes to the left), changing lanes to the right (also known as changing lanes to the right), or keeping in the lane.

[0088] Step S105: Modify the first driving intention to obtain the second driving intention of the vehicle to be identified.

[0089] It should be noted that the second driving intention is to change lanes to the left, change lanes to the right, or stay in the lane.

[0090] In the specific implementation step S105, the lateral distance deviation dy between the vehicle to be identified and the lane centerline of the lane where the vehicle to be identified is located is... t＝1:n The sequence formed by the lateral distance deviation is divided into m segments (denoted as T1-T) according to the time order. m Each horizontal distance deviation contains multiple (specifically "n / m") points; the details of the horizontal distance deviations of the 1st to the mth segments are shown in formulas (1) to (3).

[0091]

[0092]

[0093]

[0094] That is, the lateral distance deviation dy between the vehicle to be identified and the lane centerline of the lane in which the vehicle is located. t＝1:n The sequence formed by the lateral distance deviation is divided into m segments (denoted as T1-T) according to the time order using formulas (1)-(3). m ).

[0095] When the first driving intention is to change lanes to the left, if the lateral distance deviations of the m segments decrease sequentially, then the second driving intention of the vehicle to be identified is determined to be to change lanes to the left; if the lateral distance deviations of the m segments do not decrease sequentially, then the second driving intention is determined to be to keep the lane.

[0096] That is, when the first driver's intention is to change lanes to the left, if T1>T2>…>T m If the second driving intention of the vehicle to be identified is determined to be to change lanes to the left, then the second driving intention is determined to be to keep the lane.

[0097] When the first driving intention is to change lanes to the right, if the lateral distance deviations of the m segments increase sequentially, then the second driving intention of the vehicle to be identified is determined to be to change lanes to the right; if the lateral distance deviations of the m segments do not increase sequentially, then the second driving intention is determined to be to keep the lane.

[0098] That is, when the first driver's intention is to change lanes to the right, if T1 <T2<…<T m If the second driving intention of the vehicle to be identified is determined to be changing lanes to the right, then the second driving intention is determined to be keeping the lane.

[0099] Step S106: Predict the predicted driving trajectory of the vehicle to be identified, and determine the first driving intention or the second driving intention as the final driving intention based on the predicted driving trajectory.

[0100] In the specific implementation step S106, the lateral position of the vehicle to be identified is recursively calculated using a uniform motion model, and the longitudinal position of the vehicle to be identified is recursively calculated using a uniform acceleration motion model to obtain the predicted driving trajectory of the vehicle to be identified. The predicted driving trajectory contains multiple future trajectory points (denoted as a future trajectory points). The specific contents of a future trajectory points are shown in formula (4).

[0101]

[0102] In formula (4), x t and y t These are the longitudinal and lateral coordinates of the last future trajectory point in the predicted driving trajectory, respectively. vx is the longitudinal velocity, vy is the lateral velocity, ax is the longitudinal acceleration, and ay is the lateral acceleration.

[0103] Calculate the lateral distance Dis between the last future trajectory point in the predicted driving trajectory and the lane line of the controlled vehicle's lane. Specifically, x t Substitute the lane centerline equation and the lane width into the equation to calculate the lateral distance Dis between the last future trajectory point and the lane line of the controlled vehicle (self-vehicle). The specific calculation process is shown in formula (5).

[0104] Dis = L / 2 - |y t -(C0+C1*x t +C2*x t 2 +C3*x t 3 (5)

[0105] In formula (5), L is the lane width, C0 is the lateral distance from the controlled vehicle (self-vehicle) to the lane, C1 is the slope, C2 is the curvature, and C3 is the rate of change of curvature.

[0106] If the last future trajectory point is within the lane where the controlled vehicle is located, and if the lateral distance between the last future trajectory point and the lane line where the controlled vehicle is located is greater than the distance threshold, the first driving intention is determined to be the final driving intention.

[0107] If the last future trajectory point is not in the lane where the controlled vehicle is located, or if the lateral distance between the last future trajectory point and the lane line where the controlled vehicle is located is less than or equal to the distance threshold, the second driving intention is determined as the final driving intention.

[0108] Specifically, if the last future trajectory point is within the lane where the controlled vehicle is located and Dis is greater than the distance threshold (equivalent to the last future trajectory point encroaching into the lane by a certain amount), then the first driving intention is retained as the final driving intention, and the second driving intention obtained by correction is discarded; otherwise, the second driving intention is retained as the final driving intention.

[0109] For example Figure 2 The diagram illustrating the cutting trend and predicted driving trajectory for post-processing of cutting recognition shows that the historical driving trajectory of the vehicle to be identified (i.e., ...) is obtained. Figure 2 The historical trajectory in the data is used to predict the predicted driving trajectory of the vehicle to be identified through steps S103-S106 above. Figure 2 (Short-term predicted trajectory in the middle); due to Figure 2 If the last future trajectory point is within the lane where the controlled vehicle is located, and the lateral distance between the last future trajectory point and the lane line where the controlled vehicle is located is greater than the distance threshold, the first driving intention is determined to be the final driving intention.

[0110] Step S107: Based on the information of the nearest vehicle on the controlled vehicle, the second motion state information of the vehicle to be identified, and the final driving intention, identify the vehicle that cuts in from the adjacent lane from the vehicles to be identified.

[0111] In the specific implementation of step S107, based on the position of the nearest vehicle on the path of the controlled vehicle, the second motion state information of the vehicle to be identified, and the final driving intention, it is determined whether the vehicle to be identified (equivalent to the vehicle in the adjacent lane) has cut in, thereby identifying the vehicle that cut in from the adjacent lane.

[0112] The specific method for identifying vehicles cutting in from the adjacent lane from the vehicle to be identified is as follows:

[0113] If there is no nearest vehicle on the path, the vehicle to be identified is in the right lane of the controlling vehicle, and the final driving intention of the vehicle to be identified is to change lanes to the left, the vehicle to be identified is determined to be a vehicle cutting in from the adjacent lane; that is, if the adaptive cruise control function has no nearest vehicle on the path, and the vehicle to be identified is in the right lane of the controlling vehicle, and the final driving intention is to change lanes to the left, then the vehicle to be identified can be determined to be a vehicle cutting in from the adjacent lane.

[0114] If there is no nearest vehicle on the path, the vehicle to be identified is in the left lane of the controlling vehicle, and the final driving intention of the vehicle to be identified is to change lanes to the right, the vehicle to be identified is determined to be a vehicle cutting in from the adjacent lane; that is, if the adaptive cruise control function has no nearest vehicle on the path, and the vehicle to be identified is in the left lane of the controlling vehicle, and the final driving intention is to change lanes to the right, then the vehicle to be identified can be determined to be a vehicle cutting in from the adjacent lane.

[0115] When there is a nearest vehicle on the path, calculate the longitudinal distance between the vehicle to be identified and the controlled vehicle based on the relative longitudinal position of the vehicle to be identified, and calculate the longitudinal distance between the nearest vehicle on the path and the controlled vehicle.

[0116] If the nearest oncoming vehicle exists, and the vehicle to be identified is in the right lane of the controlling vehicle, the final driving intention of the vehicle to be identified is to change lanes to the left, and the longitudinal distance between the vehicle to be identified and the controlling vehicle is less than the longitudinal distance between the nearest oncoming vehicle and the controlling vehicle, then the vehicle to be identified is determined to be a vehicle cutting in from the adjacent lane. That is, if the adaptive cruise control function has a nearest oncoming vehicle, and the vehicle to be identified is in the right lane of the controlling vehicle, and the final driving intention is to change lanes to the left, and the longitudinal position of the vehicle to be identified is closer to the controlling vehicle than the nearest oncoming vehicle, then the vehicle to be identified can be determined to be a vehicle cutting in from the adjacent lane.

[0117] If the nearest oncoming vehicle exists, and the vehicle to be identified is in the left lane of the controlling vehicle, the final driving intention of the vehicle to be identified is to change lanes to the right, and the longitudinal distance between the vehicle to be identified and the controlling vehicle is less than the longitudinal distance between the nearest oncoming vehicle and the controlling vehicle, then the vehicle to be identified is determined to be a vehicle cutting in from the adjacent lane. That is, if the adaptive cruise control function has a nearest oncoming vehicle, and the vehicle to be identified is in the left lane of the controlling vehicle, and the final driving intention is to change lanes to the right, and the longitudinal position of the vehicle to be identified is closer to the controlling vehicle than the nearest oncoming vehicle, then the vehicle to be identified can be determined to be a vehicle cutting in from the adjacent lane.

[0118] In cases other than those described above, determine that the vehicle to be identified is not a vehicle cutting in from the adjacent lane.

[0119] In some embodiments, the identification result of the vehicle cutting in from the adjacent lane is output to the adaptive cruise control function, so that the adaptive cruise control function can take corresponding control strategies for the controlled vehicle based on the identified vehicle cutting in from the adjacent lane.

[0120] In this embodiment of the invention, the solution identifies vehicles cutting into the adjacent lane in advance, enabling the adaptive cruise control function to take appropriate strategies against such vehicles, thereby improving vehicle comfort and safety.

[0121] The above embodiments of the present invention Figure 1 The process of determining the historical motion state information of the vehicle to be identified in step S103 is described in [reference needed]. Figure 3 The flowchart illustrating the determination of historical motion state information provided by an embodiment of the present invention includes the following steps:

[0122] Step S301: Obtain the historical driving trajectory of the vehicle to be identified.

[0123] It should be noted that the historical driving trajectory includes at least the position coordinates and heading angle of the vehicle to be identified at the current time and other times.

[0124] In the specific implementation step S301, the historical driving trajectory of the vehicle to be identified is obtained. Specifically, the method of storing and deleting point by point is adopted. The position coordinates and heading angle of the vehicle to be identified at the current moment are stored in the historical driving trajectory, and the position coordinates and heading angle at the end of the historical driving trajectory are deleted, thereby obtaining the historical driving trajectory of the vehicle to be identified.

[0125] For example Figure 4 As shown in the example diagram for obtaining historical driving trajectories, P1 is stored in the historical driving trajectory, and Pn of the historical driving trajectory is discarded; P1 is the state information stored at the current time, and Pn is the state information discarded at the last time; the state information includes the position coordinates and heading angle of the vehicle to be identified.

[0126] After obtaining the historical driving trajectory in the above manner, the position coordinates and heading angles of other times (except the current time) in the historical driving trajectory are transformed to a specific coordinate system. This specific coordinate system is the coordinate system with the controlled vehicle (self-vehicle) as the origin at the current time. For details, please refer to the following steps S302 and subsequent related steps.

[0127] Step S302: Calculate the changes in lateral distance, longitudinal distance, and heading angle of the controlled vehicle within a unit sampling time.

[0128] In the specific implementation of step S302, the changes in the lateral distance, longitudinal distance and heading angle of the controlled vehicle within a unit sampling time are calculated. Specifically, the changes in the longitudinal distance, lateral distance and heading angle of the controlled vehicle within a unit sampling time are calculated using formulas (6)-(8).

[0129] dx ego =Vx ego *dt (6)

[0130] dy ego =Vy ego *dt (7)

[0131] dθ ego =YawRate ego *dt (8)

[0132] In formulas (6)-(8), dx ego Vx represents the longitudinal distance traveled by the vehicle per unit sampling time. ego For longitudinal velocity, dy ego Vy represents the lateral distance traveled by the vehicle within a unit sampling time. ego Let dθ be the transverse velocity. ego YawRate is used to control the change in the heading angle of the vehicle within a unit sampling time. ego This is the heading angle.

[0133] Step S303: Based on the changes in the lateral distance, longitudinal distance, and heading angle of the vehicle during the unit sampling time, the position coordinates and heading angles at other times in the historical driving trajectory are transformed to a specific coordinate system.

[0134] In the specific implementation of step S303, based on the changes in the lateral distance, longitudinal distance and heading angle of the vehicle during the unit sampling time, the position coordinates and heading angles at other times in the historical driving trajectory are transformed to a specific coordinate system.

[0135] Specifically, the position coordinates and heading angles at other times in the historical driving trajectory, excluding the current time, are calculated in the current vehicle coordinate system (specific coordinate system) to realize the transformation of the position coordinates and heading angles at other times in the historical driving trajectory to the specific coordinate system; the specific transformation process is detailed in formulas (9)-(11).

[0136] x t＝2:n =(x t＝2:n -dx ego )*cos(dθ ego )+(y t＝2:n -dy ego )*sin(dθ ego (9)

[0137] y t＝2:n =(x t＝2:n -dx ego )*(-sin(dθ ego ))+(y t＝2:n -dy ego )*cos(dθ ego (10)

[0138] heading t＝2:n =heading t＝2:n -dθ ego (11)

[0139] In formulas (9)-(11), x on the right side of the equation t＝2:n y t＝2:n and heading t＝2:n These represent the lateral position coordinates, longitudinal position coordinates, and heading angle of the vehicle to be identified before conversion; x on the left side of the equation... t＝2:n y t＝2:n and heading t＝2:n These are the lateral position coordinates, longitudinal position coordinates, and heading angle of the vehicle to be identified, transformed into a specific coordinate system.

[0140] Step S304: Using the position coordinates and heading angles of other times in the historical driving trajectory transformed to a specific coordinate system, determine the historical motion state information of the vehicle to be identified.

[0141] It should be noted that historical motion status information includes at least historical longitudinal position, historical lateral position, and historical heading angle.

[0142] In the specific implementation step S304, the position coordinates and heading angle of the vehicle to be identified at the current moment are spliced ​​with the position coordinates and heading angles at other moments transformed into a specific coordinate system, thereby determining the historical motion state information of the vehicle to be identified.

[0143] That is, by splicing the position coordinates and heading angle of the vehicle to be identified at the current moment, and the contents calculated by formula (9)-formula (11), the historical motion state information of the vehicle to be identified is determined. For details of the splicing process, please refer to formula (12)-formula (14).

[0144] x Hist =[x t＝1 x t＝2:n (12)

[0145] y Hist =[y t＝1 y t＝2:n (13)

[0146] heading Hist =[heading t＝1 heading t＝2:n (14)

[0147] In formulas (12)-(14), x Hist y Histand heading Hist These represent the historical longitudinal position, historical lateral position, and historical heading angle of the vehicle to be identified. Here, t=1 represents the current time, and t=n represents the last moment of the historical motion state information.

[0148] The above embodiments of the present invention Figure 1 The process of determining the first driving intent of the vehicle to be identified in step S104 is described in [reference needed]. Figure 5 The flowchart illustrating the determination of a first driving intention provided by an embodiment of the present invention includes the following steps:

[0149] Step S501: Obtain the lane centerline equation of the lane where the vehicle to be identified is located.

[0150] In the specific implementation of step S501, the lane centerline equation (the equation of the lane centerline) of the lane where the vehicle to be identified is located is obtained by the sensor. The specific content of the lane centerline equation can be found in formula (15).

[0151] Y = C0 + C1*x + C2*x 2 +C3*x 3 (15)

[0152] In formula (15), x and y are the longitudinal and lateral position coordinates of the vehicle in the rectangular coordinate system. The direction of the x-axis is the driving direction of the vehicle, and the y-axis is perpendicular to the driving direction of the vehicle. C0 is the lateral distance from the control vehicle to the center line of the lane where the vehicle to be identified is located. C1 is the slope, C2 is the curvature, and C3 is the rate of change of curvature.

[0153] Step S502: Calculate the identification components based on the lane centerline equation and historical motion state information.

[0154] In the specific implementation step S502, the recognition components required for driving intention recognition are calculated based on the lane centerline equation and the historical motion state information of the vehicle to be identified.

[0155] The identification components include: the deviation of the heading angle of the vehicle to be identified from the lane angle during the historical trajectory time period, and the lateral distance deviation between the vehicle to be identified and the lane centerline of the lane where the vehicle is located.

[0156] Specifically, the recognition components required for driving intention recognition can be calculated using formulas (16) and (17).

[0157] dθ t＝1:n =heading Hist -atan(Y' t＝1:n (16)

[0158] dy t＝1:n =yHist -Y t＝1:n (17)

[0159] In formulas (16) and (17), t = 1 represents the current time, t = n represents the last time of the historical motion state information, and dθ t＝1:n dy is the deviation of the heading angle of the vehicle to be identified (equivalent to a vehicle in the adjacent lane) from the lane angle within the historical driving trajectory. t＝1:n The lateral distance deviation between the vehicle to be identified and the center line of the lane in which the vehicle is located.

[0160] In other words, the identification component is calculated based on the lane centerline equation and historical motion state information, combined with formulas (16) and (17).

[0161] For example Figure 6 As shown in the provided diagram for vehicle cut-in recognition in adaptive cruise control, the recognition components (dy and dθ) can be calculated using the above formulas (16) and (17), where, Figure 6 In this context, the "self-controlled vehicle" refers to the vehicle being controlled, while the "target vehicle" refers to the vehicle to be identified.

[0162] Step S503: Normalize the identified components.

[0163] In the specific implementation of step S503, the vehicle lane-changing trajectory is determined to be a cosine function curve, and the specific content of the vehicle lane-changing trajectory is shown in formula (18).

[0164] y=L / 2*cos(π / vτ*x) (18)

[0165] In formula (18), L is the lane width and τ is the set time required for a vehicle to change lanes.

[0166] The normalized parameters for the heading angle deviation are shown in formula (19), and the normalized parameters for the lateral distance deviation are shown in formula (20).

[0167] dθ Normth =(π) 2 *L) / (2v*τ 2 (19)

[0168] dy Normth =(LW car ) / 2 (20)

[0169] In formula (20), W car The width of the vehicle to be identified.

[0170] The identification components are normalized using the above formulas (19) and (20). The specific process of normalization can be found in formulas (21) and (22).

[0171]

[0172]

[0173] Step S504: Calculate the sum of the distances between the normalized recognition component and the two foci of the left lane change boundary ellipse to obtain the first value; and calculate the sum of the distances between the normalized recognition component and the two foci of the right lane change boundary ellipse to obtain the second value.

[0174] It should be noted that, based on actual driving experience, the closer a vehicle is to the lane line, the smaller the heading angle is required to change lanes. In this scheme, an elliptical recognition boundary is set with the lateral distance deviation as the horizontal axis and the heading angle deviation as the vertical axis. The lateral coordinate is positive on the left and negative on the right, and the yaw angle is positive counterclockwise.

[0175] like Figure 7 As shown in the provided schematic diagram of the driving intention recognition boundary, the boundary for changing lanes to the left in the driving intention recognition boundary is an ellipse with its center at (1,1), major axis of 1, and minor axis of 0.5 (called the left lane change boundary ellipse); the boundary for changing lanes to the right in the driving intention recognition boundary is an ellipse with its center at (-1,-1), major axis of 1, and minor axis of 0.5 (called the right lane change boundary ellipse).

[0176] That is, Figure 7 As shown, two fixed ellipses and a square are used to divide the areas for changing lanes to the right, maintaining the lane, and changing lanes to the left; wherein, the above... Figure 7 The ellipse parameters given are for illustrative purposes only, and can be set according to actual conditions.

[0177] In the specific implementation step S504, the sum of the distances between the normalized recognition component and the two foci of the left lane change boundary ellipse is calculated to obtain the first value; and the sum of the distances between the normalized recognition component and the two foci of the right lane change boundary ellipse is calculated to obtain the second value.

[0178] Specifically, the first and second values ​​are obtained by calculating the sum of the distances between the normalized identification component and the foci of the two classification boundary ellipses (left lane change boundary ellipse and right lane change boundary ellipse) using formulas (23) and (24).

[0179]

[0180]

[0181] In formulas (23) and (24), dL (The first value) is the sum of the distances from the normalized recognition component to the two foci of the left lane change boundary ellipse, d R (Second value) is the sum of the distances from the normalized identification component to the two foci of the right lane change boundary ellipse; the first and second values ​​are used to determine whether the identification component is inside the corresponding boundary ellipse.

[0182] Step S505: If the first value is greater than the specified threshold, determine that the first driving intention of the vehicle to be identified is to change lanes to the left.

[0183] Step S506: If the second value is greater than the specified threshold, determine that the first driving intention of the vehicle to be identified is to change lanes to the right.

[0184] Step S507: If the first value and the second value are not greater than the specified threshold, determine that the first driving intention of the vehicle to be identified is to keep the lane.

[0185] In the specific implementation, if the first value is greater than a specified threshold, the primary driving intention of the vehicle to be identified is determined to be changing lanes to the left. For example: if d L >2. Determine that the primary driving intention of the vehicle to be identified is to change lanes to the left.

[0186] If the second value is greater than the specified threshold, the primary driving intention of the vehicle to be identified is determined to be changing lanes to the right. For example: if d R >2. Determine that the primary driving intention of the vehicle to be identified is to change lanes to the right.

[0187] In other cases, the primary driving intent of the vehicle to be identified is determined to be to keep its lane.

[0188] The above embodiments are descriptions of this solution. As can be seen from the above, compared with the existing adaptive cruise control function which only focuses on the nearest vehicle in the current lane, this solution adds the identification of vehicles entering from adjacent lanes. Specifically, the driving intention of the vehicle in the adjacent lane is first identified, and then, based on the driving intention, the relative position of the vehicle in the adjacent lane and the nearest vehicle in the current lane, it is determined whether the vehicle in the adjacent lane has entered the current lane. This allows for the implementation of appropriate control strategies in advance for vehicles entering the lane, resulting in smoother control parameters, optimized driving experience, and increased vehicle driving safety.

[0189] Corresponding to the method for identifying vehicles cutting into the side lane provided in the above embodiments of the present invention, see also... Figure 8 The present invention also provides a structural block diagram of a vehicle identification system for vehicles cutting into the side lane. The identification system includes: a data acquisition unit 801, a first determination unit 802, a second determination unit 803, a third determination unit 804, a correction unit 805, a prediction unit 806, and an identification unit 807.

[0190] The acquisition unit 801 is used to acquire the first motion state information of the control vehicle and the second motion state information of other vehicles. The first motion state information includes at least speed and yaw rate, and the second motion state information includes at least relative lateral position, relative longitudinal position, heading angle and track information.

[0191] The first determining unit 802 is used to determine the vehicle to be identified from other vehicles based on the first motion state information and the second motion state information.

[0192] In a specific implementation, the first determining unit 802 is specifically used to: determine the absolute speed of other vehicles based on the first motion state information and the second motion state information, and determine the relative lateral distance and relative longitudinal distance between other vehicles and the controlled vehicle;

[0193] If the absolute speed of other vehicles is not 0, and if the relative lateral distance between other vehicles and the controlled vehicle is less than the lateral distance threshold, and if the relative longitudinal distance between other vehicles and the controlled vehicle is less than the longitudinal distance threshold, then other vehicles are identified as vehicles to be identified.

[0194] If the absolute speed of other vehicles is 0, and / or if the relative lateral distance between other vehicles and the controlled vehicle is greater than or equal to the lateral distance threshold, and / or if the relative longitudinal distance between other vehicles and the controlled vehicle is greater than or equal to the longitudinal distance threshold, then other vehicles are determined not to be identified vehicles.

[0195] The second determining unit 803 is used to determine the historical motion state information of the vehicle to be identified based on the position coordinates of the vehicle to be identified in a specific coordinate system, wherein the specific coordinate system is a coordinate system with the control vehicle as the origin.

[0196] The third determining unit 804 is used to determine the first driving intention of the vehicle to be identified through historical motion state information. The first driving intention is to change lanes to the left, change lanes to the right, or keep the lane.

[0197] The correction unit 805 is used to correct the first driving intention to obtain the second driving intention of the vehicle to be identified, which is to change lanes to the left, change lanes to the right, or keep the lane.

[0198] In a specific implementation, the correction unit 805 is specifically used to: divide the lateral distance deviation between the vehicle to be identified and the lane centerline of the lane where the vehicle to be identified is located into m segments according to the time sequence;

[0199] When the first driving intention is to change lanes to the left, if the lateral distance deviations of the m segments decrease sequentially, then the second driving intention of the vehicle to be identified is determined to be to change lanes to the left; if the lateral distance deviations of the m segments do not decrease sequentially, then the second driving intention is determined to be to keep the lane.

[0200] When the first driving intention is to change lanes to the right, if the lateral distance deviations of the m segments increase sequentially, then the second driving intention of the vehicle to be identified is determined to be to change lanes to the right; if the lateral distance deviations of the m segments do not increase sequentially, then the second driving intention is determined to be to maintain the lane.

[0201] The prediction unit 806 is used to predict the predicted driving trajectory of the vehicle to be identified, and determine the first driving intention or the second driving intention as the final driving intention based on the predicted driving trajectory.

[0202] In a specific implementation, the prediction unit 806 is specifically used to: recursively calculate the lateral position of the vehicle to be identified using a uniform motion model, and recursively calculate the longitudinal position of the vehicle to be identified using a uniform acceleration motion model, so as to obtain the predicted driving trajectory of the vehicle to be identified, which includes multiple future trajectory points.

[0203] Calculate the lateral distance between the last future trajectory point in the predicted driving trajectory and the lane line of the lane where the controlled vehicle is located;

[0204] If the last future trajectory point is within the lane where the controlled vehicle is located, and if the lateral distance between the last future trajectory point and the lane line where the controlled vehicle is located is greater than the distance threshold, the first driving intention is determined to be the final driving intention.

[0205] If the last future trajectory point is not in the lane where the controlled vehicle is located, or if the lateral distance between the last future trajectory point and the lane line where the controlled vehicle is located is less than or equal to the distance threshold, the second driving intention is determined as the final driving intention.

[0206] The identification unit 807 is used to identify vehicles cutting in from the adjacent lane from the vehicles to be identified based on the information of the nearest vehicle on the controlled vehicle, the second motion state information of the vehicle to be identified, and the final driving intention.

[0207] In a specific implementation, the identification unit 807 is specifically used to: determine the vehicle to be identified as a vehicle cutting in from the adjacent lane when there is no nearest vehicle on the path, the vehicle to be identified is in the right lane of the controlled vehicle, and the final driving intention of the vehicle to be identified is to change lanes to the left.

[0208] If there is no nearest vehicle in the path, the vehicle to be identified is in the left lane of the vehicle being controlled, and the final driving intention of the vehicle to be identified is to change lanes to the right, the vehicle to be identified is determined to be a vehicle cutting in from the adjacent lane.

[0209] When there is a nearest vehicle on the path, calculate the longitudinal distance between the vehicle to be identified and the controlled vehicle based on the relative longitudinal position of the vehicle to be identified, and calculate the longitudinal distance between the nearest vehicle on the path and the controlled vehicle.

[0210] If the vehicle to be identified is in the right lane of the controlling vehicle, the final driving intention of the vehicle to be identified is to change lanes to the left, and the longitudinal distance between the vehicle to be identified and the controlling vehicle is less than the longitudinal distance between the nearest oncoming vehicle and the controlling vehicle, the vehicle to be identified is determined to be a vehicle cutting in from the adjacent lane.

[0211] If the vehicle to be identified is in the left lane of the controlling vehicle, the final driving intention of the vehicle to be identified is to change lanes to the right, and the longitudinal distance between the vehicle to be identified and the controlling vehicle is less than the longitudinal distance between the nearest oncoming vehicle and the controlling vehicle, the vehicle to be identified is determined to be a vehicle cutting in from the adjacent lane.

[0212] The identification unit 807 is also used to output the identification results of vehicles cutting into the adjacent lane to the adaptive cruise function.

[0213] In this embodiment of the invention, the solution identifies vehicles cutting into the adjacent lane in advance, enabling the adaptive cruise control function to take appropriate strategies against such vehicles, thereby improving vehicle comfort and safety.

[0214] Preferred, combined Figure 8 The second determining unit 803, as shown, includes an acquisition module, a calculation module, a conversion module, and a determining module. The execution principle of each module is as follows:

[0215] The acquisition module is used to acquire the historical driving trajectory of the vehicle to be identified. The historical driving trajectory includes at least the position coordinates and heading angle of the vehicle to be identified at the current time and other times.

[0216] The calculation module is used to calculate the changes in lateral distance, longitudinal distance, and heading angle of the controlled vehicle within a unit sampling time.

[0217] The conversion module is used to convert the position coordinates and heading angles of other moments in the historical driving trajectory to a specific coordinate system based on the changes in the lateral distance, longitudinal distance and heading angle of the controlled vehicle during a unit sampling time.

[0218] The determination module is used to determine the historical motion state information of the vehicle to be identified by using the position coordinates and heading angles of other times in the historical driving trajectory transformed to a specific coordinate system. The historical motion state information includes at least the historical longitudinal position, historical lateral position and historical heading angle.

[0219] Preferred, combined Figure 8 The third determining unit 804, as shown, includes an acquisition module, a calculation module, a normalization processing module, a processing module, and a determining module; the execution principles of each module are as follows:

[0220] The acquisition module is used to obtain the lane centerline equation of the lane where the vehicle to be identified is located.

[0221] The calculation module is used to calculate the identification components based on the lane centerline equation and historical motion state information. The identification components include: the deviation of the heading angle of the vehicle to be identified from the lane line angle, and the lateral distance deviation between the vehicle to be identified and the lane centerline of the lane where the vehicle is located.

[0222] The normalization module is used to normalize the identified components.

[0223] The processing module is used to calculate the sum of the distances between the normalized recognition component and the two foci of the left lane change boundary ellipse to obtain the first value; and to calculate the sum of the distances between the normalized recognition component and the two foci of the right lane change boundary ellipse to obtain the second value.

[0224] The determination module is used to determine the first driving intention of the vehicle to be identified as changing lanes to the left if the first value is greater than a specified threshold; to determine the first driving intention of the vehicle to be identified as changing lanes to the right if the second value is greater than the specified threshold; and to determine the first driving intention of the vehicle to be identified as keeping lanes if the first value and the second value are not greater than the specified threshold.

[0225] It should be noted that the execution principle of the vehicle identification system for vehicles cutting into the adjacent lane has been explained in detail in the above method embodiments, which can be referred to, and will not be repeated here.

[0226] In summary, the embodiments of the present invention provide a method and system for identifying vehicles cutting into the adjacent lane. By identifying vehicles cutting into the adjacent lane in advance, the adaptive cruise control function can take corresponding strategies in advance for vehicles cutting into the adjacent lane, thereby improving vehicle comfort and safety.

[0227] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, for system or system embodiments, since they are basically similar to method embodiments, the description is relatively simple, and relevant parts can be referred to the descriptions in the method embodiments. The systems and system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0228] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0229] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for identifying vehicles cutting into a side lane, characterized in that, The method includes: Collect and control the first motion state information of the vehicle and the second motion state information of other vehicles. The first motion state information includes at least speed and yaw rate, and the second motion state information includes at least relative lateral position, relative longitudinal position, heading angle and track information. Based on the first motion state information and the second motion state information, determine the vehicle to be identified from the other vehicles; Based on the position coordinates of the vehicle to be identified in a specific coordinate system, the historical motion state information of the vehicle to be identified is determined, wherein the specific coordinate system is a coordinate system with the control vehicle as the origin; Based on the historical motion state information, the first driving intention of the vehicle to be identified is determined, which is to change lanes to the left, change lanes to the right, or keep the lane. The first driving intention is modified to obtain the second driving intention of the vehicle to be identified, which is to change lanes to the left, change lanes to the right, or keep the lane. Predict the predicted driving trajectory of the vehicle to be identified, and determine the first driving intention or the second driving intention as the final driving intention based on the predicted driving trajectory; Based on the information of the nearest vehicle on the path of the controlled vehicle, the second motion state information of the vehicle to be identified, and the final driving intention, the vehicle cutting in from the adjacent lane is identified from the vehicles to be identified. Determining the first driving intention of the vehicle to be identified through the historical motion state information includes: Obtain the lane centerline equation of the lane where the vehicle to be identified is located. C0 is the lateral distance from the controlled vehicle to the center line of the lane where the vehicle to be identified is located, C1 is the slope, C2 is the curvature, and C3 is the rate of change of curvature. Based on the lane centerline equation and the historical motion state information, combined with and Calculate the identification components, y Hist and heading Hist These represent the historical lateral position and historical heading angle of the vehicle to be identified, respectively. t=1 represents the current time, and t=n represents the last time of the historical motion state information. The identification component includes: the heading angle deviation between the heading angle of the vehicle to be identified and the lane angle. The lateral distance deviation between the vehicle to be identified and the lane centerline of the lane in which the vehicle to be identified is located. ; The identified components are normalized. The first value is obtained by calculating the sum of the distances between the normalized identification component and the two foci of the left lane change boundary ellipse; and the second value is obtained by calculating the sum of the distances between the normalized identification component and the two foci of the right lane change boundary ellipse. If the first value is greater than the specified threshold, it is determined that the first driving intention of the vehicle to be identified is to change lanes to the left; If the second value is greater than the specified threshold, the first driving intention of the vehicle to be identified is determined to be to change lanes to the right; If the first value and the second value are not greater than the specified threshold, the first driving intention of the vehicle to be identified is determined to be lane keeping.

2. The method for identifying vehicles cutting into the side lane according to claim 1, characterized in that, The step of determining the vehicle to be identified from the other vehicles based on the first motion state information and the second motion state information includes: Based on the first motion state information and the second motion state information, determine the absolute speed of the other vehicles, and determine the relative lateral distance and relative longitudinal distance between the other vehicles and the controlled vehicle; If the absolute speed of the other vehicle is not 0, and if the relative lateral distance between the other vehicle and the controlled vehicle is less than a lateral distance threshold, and if the relative longitudinal distance between the other vehicle and the controlled vehicle is less than a longitudinal distance threshold, then the other vehicle is determined to be the vehicle to be identified. If the absolute speed of the other vehicle is 0, and / or if the relative lateral distance between the other vehicle and the controlled vehicle is greater than or equal to the lateral distance threshold, and / or if the relative longitudinal distance between the other vehicle and the controlled vehicle is greater than or equal to the longitudinal distance threshold, then the other vehicle is determined not to be the vehicle to be identified.

3. The method for identifying vehicles cutting into the side lane according to claim 1, characterized in that, The step of determining the historical motion state information of the vehicle to be identified based on its position coordinates in a specific coordinate system includes: The historical driving trajectory of the vehicle to be identified is obtained, and the historical driving trajectory includes at least the position coordinates and heading angle of the vehicle to be identified at the current time and other times. Calculate the lateral distance, longitudinal distance, and heading angle changes of the controlled vehicle within a unit sampling time. Based on the changes in the lateral distance, longitudinal distance, and heading angle of the controlled vehicle within a unit sampling time, the position coordinates and heading angles at other times in the historical driving trajectory are transformed to a specific coordinate system. By using the position coordinates and heading angles of other times in the historical driving trajectory transformed to the specific coordinate system, the historical motion state information of the vehicle to be identified is determined. The historical motion state information includes at least the historical longitudinal position, the historical lateral position, and the historical heading angle.

4. The method for identifying vehicles cutting into the adjacent lane according to claim 1, characterized in that, The step of modifying the first driving intention to obtain the second driving intention of the vehicle to be identified includes: For the lateral distance deviation between the vehicle to be identified and the lane centerline of the lane where the vehicle to be identified is located, the lateral distance deviation is divided into m segments according to the time sequence; When the first driving intention is to change lanes to the left, if the lateral distance deviations in the m segments decrease sequentially, then the second driving intention of the vehicle to be identified is determined to be to change lanes to the left; if the lateral distance deviations in the m segments do not decrease sequentially, then the second driving intention is determined to be to keep the lane. When the first driving intention is to change lanes to the right, if the lateral distance deviations in the m segments increase sequentially, then the second driving intention of the vehicle to be identified is determined to be to change lanes to the right; if the lateral distance deviations in the m segments do not increase sequentially, then the second driving intention is determined to be to keep the lane.

5. The method for identifying vehicles cutting into the side lane according to claim 4, characterized in that, The lateral distance deviation between the vehicle to be identified and the lane centerline of the lane where the vehicle is located is divided into m segments according to time sequence, including: The lateral distance deviation dy between the vehicle to be identified and the lane centerline of the lane in which the vehicle to be identified is located. t=1:n ,pass , , The lateral distance deviation is divided into m segments according to time sequence, and each segment contains n / m points.

6. The method for identifying vehicles cutting into the side lane according to any one of claims 1-3, characterized in that, The step of predicting the predicted driving trajectory of the vehicle to be identified, and determining the first driving intention or the second driving intention as the final driving intention based on the predicted driving trajectory, includes: The lateral position of the vehicle to be identified is recursively calculated using a uniform motion model, and the longitudinal position of the vehicle to be identified is recursively calculated using a uniform acceleration motion model to obtain the predicted driving trajectory of the vehicle to be identified. The predicted driving trajectory includes multiple future trajectory points. Calculate the lateral distance between the last future trajectory point in the predicted driving trajectory and the lane line of the lane where the controlled vehicle is located; If the last future trajectory point is within the lane where the controlled vehicle is located, and if the lateral distance between the last future trajectory point and the lane line of the controlled vehicle is greater than a distance threshold, the first driving intention is determined to be the final driving intention. If the last future trajectory point is not in the lane where the controlled vehicle is located, or if the lateral distance between the last future trajectory point and the lane line of the controlled vehicle is less than or equal to the distance threshold, the second driving intention is determined to be the final driving intention.

7. The method for identifying vehicles cutting into the side lane according to any one of claims 1-3, characterized in that, The step of identifying vehicles cutting in from the adjacent lane from the vehicles to be identified based on the nearest oncoming vehicle information of the controlled vehicle, the second motion state information of the vehicle to be identified, and the final driving intention includes: When there is no nearest vehicle in the path, the vehicle to be identified is in the right lane of the controlled vehicle, and the final driving intention of the vehicle to be identified is to change lanes to the left, the vehicle to be identified is determined to be a vehicle cutting in from the adjacent lane. When there is no nearest vehicle in the path, the vehicle to be identified is in the left lane of the controlled vehicle, and the final driving intention of the vehicle to be identified is to change lanes to the right, the vehicle to be identified is determined to be a vehicle cutting in from the adjacent lane. When there is a nearest vehicle on the path, calculate the longitudinal distance between the vehicle to be identified and the controlled vehicle based on the relative longitudinal position of the vehicle to be identified, and calculate the longitudinal distance between the nearest vehicle on the path and the controlled vehicle. If the vehicle to be identified is in the right lane of the vehicle under control, the final driving intention of the vehicle to be identified is to change lanes to the left, and the longitudinal distance between the vehicle to be identified and the vehicle under control is less than the longitudinal distance between the nearest oncoming vehicle and the vehicle under control, then the vehicle to be identified is determined to be a vehicle cutting in from the side lane. If the vehicle to be identified is in the left lane of the vehicle under control, the final driving intention of the vehicle to be identified is to change lanes to the right, and the longitudinal distance between the vehicle to be identified and the vehicle under control is less than the longitudinal distance between the nearest oncoming vehicle and the vehicle under control, then the vehicle to be identified is determined to be a vehicle cutting in from the side lane.

8. The method for identifying vehicles cutting into the side lane according to any one of claims 1-3, characterized in that, After identifying the vehicle cutting in from the adjacent lane from the vehicles to be identified, the process further includes: The identification results of vehicles cutting into the adjacent lane are output to the adaptive cruise control function.

9. A system for recognizing vehicles cutting into adjacent lanes, characterized in that, The system includes: The acquisition unit is used to acquire first motion state information of the control vehicle and second motion state information of other vehicles. The first motion state information includes at least speed and yaw rate, and the second motion state information includes at least relative lateral position, relative longitudinal position, heading angle and track information. The first determining unit is configured to determine the vehicle to be identified from the other vehicles based on the first motion state information and the second motion state information. The second determining unit is used to determine the historical motion state information of the vehicle to be identified based on the position coordinates of the vehicle to be identified in a specific coordinate system, wherein the specific coordinate system is a coordinate system with the control vehicle as the origin. The third determining unit is used to determine the first driving intention of the vehicle to be identified through the historical motion state information, wherein the first driving intention is to change lanes to the left, change lanes to the right, or keep the lane. The correction unit is used to correct the first driving intention to obtain a second driving intention of the vehicle to be identified, wherein the second driving intention is to change lanes to the left, change lanes to the right, or keep the lane. The prediction unit is used to predict the predicted driving trajectory of the vehicle to be identified, and determine the first driving intention or the second driving intention as the final driving intention based on the predicted driving trajectory. The identification unit is used to identify vehicles cutting in from the vehicle to be identified from the vehicles to be identified based on the information of the nearest vehicle on the path of the controlled vehicle, the second motion state information of the vehicle to be identified, and the final driving intention. The third determining unit includes: The acquisition module is used to acquire the lane centerline equation of the lane where the vehicle to be identified is located. C0 is the lateral distance from the controlled vehicle to the center line of the lane where the vehicle to be identified is located, C1 is the slope, C2 is the curvature, and C3 is the rate of change of curvature. The calculation module is used to combine the lane centerline equation and the historical motion state information with... and Calculate the identification components, y Hist and heading Hist These represent the historical lateral position and historical heading angle of the vehicle to be identified, respectively. t=1 represents the current time, and t=n represents the last time of the historical motion state information. The identification component includes: the heading angle deviation between the heading angle of the vehicle to be identified and the lane angle. The lateral distance deviation between the vehicle to be identified and the lane centerline of the lane in which the vehicle to be identified is located. ; A normalization processing module is used to normalize the identified components; The processing module is used to calculate the sum of the distances between the normalized identification component and the two foci of the left lane change boundary ellipse to obtain a first value; and to calculate the sum of the distances between the normalized identification component and the two foci of the right lane change boundary ellipse to obtain a second value. The determination module is configured to determine the first driving intention of the vehicle to be identified as changing lanes to the left if the first value is greater than a specified threshold; determine the first driving intention of the vehicle to be identified as changing lanes to the right if the second value is greater than the specified threshold; and determine the first driving intention of the vehicle to be identified as keeping lanes if the first value and the second value are not greater than the specified threshold.

Images