Self-adaptive cruise target selection method and device, computer equipment and medium

Abstract

The invention provides a self-adaptive cruise target selection method and device, computer equipment and a medium, and relates to a self-adaptive cruise technology, and the method comprises the steps: obtaining historical tracks of a plurality of targets under a self-vehicle coordinate system; determining a predicted driving track of the vehicle; for each target, calculating a deviation average value EAvg and a deviation maximum value EMax of a target historical track and a self-vehicle prediction track at each point; traversing each target, judging whether the own vehicle follows the historical track of the target or not, and determining the target of which the own vehicle follows the historical track; and determining a self-vehicle following target in the targets of the self-vehicle following historical track. The method is suitable for high-speed or low-speed lane changing; target historical trajectories are introduced to be fused with self-vehicle predicted driving trajectories, and target selection is more stable; according to the target selection method, the target selection track is adopted only for the current target which is the lane changing scene that the vehicle follows the target vehicle and is judged to be recently followed by the vehicle, and the target selection tracks of other targets are not influenced, so that the flexibility of target selection is improved.

Description

Technical Field

[0001] The present invention relates to the field of adaptive cruise technology, and in particular to an adaptive cruise target selection method, device, computer equipment and medium. Background Art

[0002] The Adaptive Cruise Control (ACC) function is a basic function of the Advanced Driving Assistant System (ADAS). It can identify and analyze the traffic conditions ahead in the driving direction through a single camera or a camera and radar fusion method, and automatically control the acceleration and deceleration of the vehicle in the longitudinal direction according to the traffic conditions in the vehicle's driving direction, thereby reducing the driver's operating burden. When the target selection module determines that there is no main target or the main target is far away, the ACC function can drive at the cruising speed set by the driver; when the target selection module determines that there is a main target and the main target is close, the ACC function can automatically maintain the relative distance with the vehicle ahead according to the following time interval set by the driver.

[0003] In an intelligent driving system that does not rely on high-precision maps, the existing target selection technical solution (such as the technical solution disclosed in patent CN110803163A) is: 1. Obtain the motion state information of the vehicle and the lane line information of the lane in which the vehicle is located; 2. Based on the lane line information, calculate an evaluation value for characterizing the effectiveness of the lane line; 3. Based on the motion state information and the lane line information, calculate a matching value for characterizing the degree of matching between the lane line and the current driving trajectory of the vehicle; 4. Under the condition that it is determined that the evaluation value is greater than a first preset threshold and the matching value is less than a second preset threshold, use the lane line as the driving trajectory of the vehicle; otherwise, predict the driving trajectory of the vehicle with the driving curvature radius calculated based on the motion state information. However, this solution does not handle the lane change scenario of following the vehicle ahead, which will cause the following problems: 1. The matching degree between the lane line and the vehicle's current driving trajectory needs to be determined to determine the vehicle's driving trajectory. When the vehicle changes lanes slowly, the lane line and the vehicle's current driving trajectory are usually not much different and difficult to distinguish; 2. When the vehicle is driving normally along the road and the target in front is in the cut-out state, the target usually needs to be released in advance because of the need to ensure the timeliness of acceleration. Therefore, if the lane change scenario of following the vehicle ahead is not handled separately, the target selection of following the lane change may be interrupted or unstable; 3. The stability of target selection based on only the curvature of the vehicle's driving to predict the vehicle's driving trajectory is insufficient; 4. The same target selection method is used for all valid targets, which is not flexible enough. Summary of the invention

[0004] In view of this, an embodiment of the present invention provides an adaptive cruise target selection method to solve the problem of insufficient stability and low accuracy of target selection in the prior art, including: obtaining historical trajectories of multiple targets in the vehicle coordinate system;

[0005] Obtaining the vehicle's travel parameters, and determining the vehicle's predicted travel trajectory based on the vehicle's travel parameters;

[0006] For each target, according to the predicted driving trajectory of the ego vehicle and the historical trajectory of the target, multiple points are evenly selected between the longitudinal distance between the ego vehicle and the target, and the average deviation E between the target historical trajectory and the predicted trajectory of the ego vehicle at each point is calculated. Avg and the maximum deviation E Max ;

[0007] The target vehicle width and the vehicle width are obtained through the camera, and the deviation average value E is calculated based on the target vehicle width, the vehicle width, and the deviation average value E. Avg and the maximum deviation E Max Traverse each target, determine whether the vehicle follows the historical trajectory of the target, and determine the target of the historical trajectory followed by the vehicle;

[0008] The ego vehicle following target is determined among the targets of the ego vehicle following the historical trajectory.

[0009] The adaptive cruise target selection method provided by the present invention also has the following characteristics: according to the predicted driving trajectory of the self-vehicle and the historical trajectory of the target, multiple points are evenly selected between the longitudinal distance between the self-vehicle and the target, and the deviation average value E at each point between the target historical trajectory and the predicted trajectory of the self-vehicle is calculated. Avg and the maximum deviation E Max include:

[0010] For a single target, multiple points are evenly selected between the longitudinal distances between the vehicle and the target to obtain a longitudinal distance array;

[0011] Substitute the longitudinal distance data into the trajectory parameter equation of the historical trajectory and the trajectory equation of the predicted driving trajectory of the vehicle, respectively, to obtain the lateral distance array of the historical trajectory and the lateral distance array of the predicted driving trajectory of the vehicle, respectively;

[0012] According to the longitudinal distance array, the lateral distance array of the historical trajectory and the lateral distance array of the self-vehicle predicted driving trajectory, the average deviation E of the target's historical trajectory and the self-vehicle predicted driving trajectory at each point is calculated. Avg and the actual maximum value E Max ;

[0013] After traversing each target, obtain E Avg and E Max Array of .

[0014] The adaptive cruise target selection method provided by the present invention also has the following characteristics: the deviation average value E of the target's historical trajectory and the vehicle's predicted driving trajectory at each point is calculated based on the longitudinal distance array, the historical trajectory lateral distance array and the vehicle's predicted driving trajectory lateral distance array. Avg and the maximum deviation E Max , calculated according to the following formula:

[0015]

[0016] E Max =max(|a i -b i |), i = 1, 2, .., n,

[0017] Among them, a is the historical lateral distance of the target in the historical trajectory lateral distance array, b is the lateral distance of the ego vehicle in the lateral distance array of the predicted driving trajectory, and n is the number of points uniformly selected between the longitudinal distances of the ego vehicle and the target.

[0018] The adaptive cruise target selection method provided by the present invention also has the following characteristics: according to the vehicle width of the target, the vehicle width, the deviation average value E Avg and the maximum deviation E Max Traverse each target and determine whether the vehicle follows the historical trajectory of the target, including:

[0019] If the average deviation E between the target's valid historical trajectory and the vehicle's predicted driving trajectory Avg Does not exceed the sum of the half width of the ego vehicle and the half width of the target vehicle; and

[0020] The maximum deviation error E between the target effective historical trajectory and the vehicle predicted trajectory Max If it does not exceed the sum of the half-width of the ego vehicle and the half-width of the target vehicle, then it is judged that the ego vehicle follows the historical trajectory of the target.

[0021] The adaptive cruise target selection method provided by the present invention also has the following characteristics: determining the target to be followed by the vehicle from the targets of the historical trajectory followed by the vehicle includes:

[0022] The targets of the ego vehicle’s historical trajectory are sorted based on the longitudinal distance, and the target with the shortest longitudinal distance is selected as the nearest ego vehicle following target;

[0023] If the longitudinal distance of the nearest ego vehicle following the target is greater than the set longitudinal distance threshold, it is determined that the current ego vehicle is not following the target.

[0024] The adaptive cruise target selection method provided by the present invention also has the following characteristics, and further includes:

[0025] Determine whether the current scene is the self-vehicle following the target vehicle in changing lanes;

[0026] If yes, the historical trajectory of the ego vehicle following the target vehicle and the current predicted trajectory of the ego vehicle are fused to obtain the target selection trajectory of the ego vehicle following the target; if no, the predicted trajectory of the ego vehicle is used as the target selection trajectory of each target.

[0027] The adaptive cruise target selection method provided by the present invention also has the following characteristics: the historical trajectory of the ego vehicle following the target vehicle and the current predicted trajectory of the ego vehicle are integrated to obtain the target selection trajectory of the ego vehicle following the target, including:

[0028] y=B1*x+B2*x 2

[0029] Among them, y is the lateral distance in the ego vehicle coordinate system, x is the longitudinal distance in the ego vehicle coordinate system, B1 is the first-order coefficient of the target selection trajectory equation, and B2 is the second-order coefficient of the target selection trajectory equation.

[0030] Among them, B1=α·A1+(1-α)·D1;

[0031] B2=α·A2+(1-α)·D2;

[0032] α is the trajectory fusion weight, A1 is the linear coefficient of the historical trajectory equation of the ego vehicle following the target, A2 is the quadratic coefficient of the historical trajectory equation of the ego vehicle following the target, D1 is the linear coefficient of the ego vehicle prediction trajectory equation, D2 is the quadratic coefficient of the ego vehicle prediction trajectory equation,

[0033] The historical trajectory equation of the vehicle following the target is y1=A0+A1*x+A2*x 2 ,

[0034] The current vehicle prediction trajectory equation y2 = D1*x + D2*x 2 ,

[0035] Among them, A0 is the zero-order coefficient of the historical trajectory equation of the ego vehicle following the target.

[0036] A second object of the present invention is to provide an adaptive cruise target selection device, comprising:

[0037] The target history track acquisition module is used to obtain the target history track and target vehicle width;

[0038] A self-vehicle traveling parameter acquisition module, used to obtain the self-vehicle traveling parameters;

[0039] The calculation module is used to calculate the average deviation E of the target historical trajectory and the predicted trajectory of the vehicle at each point through the vehicle's travel parameters and the target historical trajectory. Avg and the maximum deviation EMax ;

[0040] The judgment module is used to determine the average value of the deviation E Avg and the maximum deviation E Max , the width of the target vehicle and the width of the ego vehicle determine whether the ego vehicle follows the target historical trajectory, and determine the ego vehicle follows the target in the target of the ego vehicle following the historical trajectory;

[0041] The fusion module is used to obtain the target selection trajectory by judging whether the ego vehicle has the target to follow.

[0042] The third object of the present invention is to provide a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements any of the aforementioned adaptive cruise target selection methods when executing the computer program.

[0043] A fourth object of the present invention is to provide a computer-readable storage medium, wherein the computer-readable storage medium stores a method for executing any one of the aforementioned adaptive cruise target selection methods.

[0044] Compared with the prior art, the beneficial effects achieved by at least one of the above technical solutions adopted in the embodiments of this specification include at least: obtaining the historical trajectories of multiple targets in the ego vehicle coordinate system; obtaining the ego vehicle travel parameters, and determining the ego vehicle predicted driving trajectory according to the ego vehicle travel parameters; for each target, according to the ego vehicle predicted driving trajectory and the historical trajectory of the target, evenly taking multiple points between the longitudinal distance between the ego vehicle and the target, and calculating the average deviation E of the target historical trajectory and the ego vehicle predicted trajectory at each point Avg and the maximum deviation E Max ; Obtain the target vehicle width and the vehicle width through the camera, and calculate the deviation average value E according to the target vehicle width, the vehicle width, and the deviation average value E Avg and the maximum deviation E Max Traverse each target, determine whether the ego vehicle follows the historical trajectory of the target, determine the target of the ego vehicle following the historical trajectory; determine the target that the ego vehicle follows among the targets of the ego vehicle following the historical trajectory. This application improves the accuracy, stability and flexibility of target selection for the scenario of following the lane change of the preceding vehicle without increasing any software and hardware costs. This method is applicable to both fast and slow lane changes; this method introduces the target historical trajectory to fuse the ego vehicle's predicted driving trajectory, making the target selection more stable; this target selection trajectory is only used for the target that is currently following the target vehicle in the lane change scenario and is determined to be the target that the ego vehicle has followed most recently, while the target selection trajectories of other targets are not affected, thereby improving the flexibility of target selection. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0046] Figure 1 is a flow chart of an adaptive cruise target selection method provided by an embodiment of the present invention;

[0047] Figure 2 is a structural block diagram of a computer device provided by an embodiment of the present invention;

[0048] Figure 3 It is a structural block diagram of an adaptive cruise target selection method device provided by an embodiment of the present invention;

[0049] Figure 4 It is a flow chart of a driving trajectory prediction method provided by prior art 1. DETAILED DESCRIPTION

[0050] The embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0051] The following describes the implementation methods of the present application through specific specific examples, and those skilled in the art can easily understand other advantages and effects of the present application from the content disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The present application can also be implemented or applied through other different specific implementation methods, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present application. It should be noted that, in the absence of conflict, the following embodiments and the features in the embodiments can be combined with each other. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work belong to the scope of protection of the present application.

[0052] In an embodiment of the present invention, an adaptive cruise target selection method is provided, such as Figure 1 As shown, including:

[0053] S1: Obtain the historical trajectories of multiple targets in the ego-vehicle coordinate system;

[0054] S2: Obtain the vehicle's travel parameters, and determine the vehicle's predicted travel trajectory based on the vehicle's travel parameters;

[0055] S3: For each target, according to the predicted driving trajectory of the ego vehicle and the historical trajectory of the target, multiple points are evenly selected between the longitudinal distance between the ego vehicle and the target, and the average deviation E of the target historical trajectory and the predicted trajectory of the ego vehicle at each point is calculated.Avg and the maximum deviation E Max ;

[0056] S4: Obtain the target vehicle width and the own vehicle width through the camera, and calculate the target vehicle width, the own vehicle width, and the average deviation E. Avg and the maximum deviation E Max Traverse each target, determine whether the vehicle follows the historical trajectory of the target, and determine the target of the historical trajectory followed by the vehicle;

[0057] S5: Determine the self-vehicle following target among the targets of the self-vehicle following historical trajectory.

[0058] In some embodiments, obtaining the target historical trajectory parameter equation in the vehicle coordinate system includes: obtaining the historical trajectory parameter equations of multiple targets in the vehicle coordinate system through a camera, and each historical trajectory parameter equation can be expressed as:

[0059] y=A0+A1*x+A2*x 2

[0060] Among them, x is the longitudinal distance in the ego-vehicle coordinate system, y is the lateral distance in the ego-vehicle coordinate system, A0 is the zero-order coefficient of the historical trajectory equation of the ego-vehicle following the target, A1 is the first-order coefficient of the historical trajectory equation of the ego-vehicle following the target, and A2 is the second-order coefficient of the historical trajectory equation of the ego-vehicle following the target.

[0061] In some embodiments, the step of obtaining the vehicle's travel parameters and defining the vehicle's predicted travel trajectory equation according to the vehicle's travel parameters includes:

[0062] Calculate the side slip angle λ of the front center point of the vehicle through the vehicle's travel parameters;

[0063]

[0064] Among them, θ is the steering wheel angle, K is the transmission ratio from the steering wheel to the front wheels, L is the wheelbase, k f is the front axle cornering stiffness coefficient, k r is the rear axle cornering stiffness coefficient, v is the vehicle speed, M is the vehicle mass, L f is the distance from the front axle to the center of mass, C r is the rear axle cornering stiffness, L 0 is the distance from the rear axle to the front center point, R is the turning radius of the vehicle, α r is the rear wheel slip angle.

[0065] The predicted driving trajectory equation of the vehicle is defined in the vehicle coordinate system as follows:

[0066] y=D0+D1*x+D2*x 2 +D3*x 3

[0067] Among them, D0 is the zero-order coefficient of the self-vehicle prediction trajectory equation, D1 is the first-order coefficient of the self-vehicle prediction trajectory equation, D2 is the second-order coefficient of the self-vehicle prediction trajectory equation, and D3 is the third-order coefficient of the self-vehicle prediction trajectory equation. The self-vehicle can be equivalent to circular motion when turning in a steady state. The curvature of the self-vehicle is a constant, so D3 = 0; the front center point of the self-vehicle is the origin of the self-vehicle coordinate system, so D0 = 0. Therefore, the self-vehicle prediction trajectory equation can be simplified as follows:

[0068] y=D1*x+D2*x 2

[0069] Where D1 = tanλ,

[0070] In some embodiments, according to the predicted driving trajectory of the vehicle and the historical trajectory of the target, multiple points are evenly selected between the longitudinal distance between the vehicle and the target, and the average deviation E of the target historical trajectory and the predicted trajectory of the vehicle at each point is calculated. Avg and the maximum deviation E Max include:

[0071] For a single target, multiple points are evenly selected between the longitudinal distances between the vehicle and the target to obtain a longitudinal distance array;

[0072] Substitute the longitudinal distance data into the trajectory parameter equation of the historical trajectory and the trajectory equation of the predicted driving trajectory of the vehicle, respectively, to obtain the lateral distance array of the historical trajectory and the lateral distance array of the predicted driving trajectory of the vehicle, respectively;

[0073] According to the longitudinal distance array, the lateral distance array of the historical trajectory and the lateral distance array of the self-vehicle predicted driving trajectory, the average deviation E of the target's historical trajectory and the self-vehicle predicted driving trajectory at each point is calculated. Avg and the actual maximum value E Max ;

[0074] After traversing each target, obtain E Avg and E Max Array of .

[0075] In some embodiments, the average deviation E of the target's historical trajectory and the vehicle's predicted driving trajectory at each point is calculated based on the longitudinal distance array, the historical trajectory lateral distance array, and the vehicle's predicted driving trajectory lateral distance array. Avg and the maximum deviation E Max , calculated according to the following formula:

[0076]

[0077] E Max =max(|a i-b i |), i = 1, 2, .., n,

[0078] Among them, a is the historical lateral distance of the target in the historical trajectory lateral distance array, b is the lateral distance of the ego vehicle in the lateral distance array of the predicted driving trajectory, and n is the number of points uniformly selected between the longitudinal distances of the ego vehicle and the target.

[0079] In some embodiments, 10 points are evenly selected between the longitudinal distance between the vehicle and the target, and the average deviation E of the target historical trajectory and the predicted trajectory of the vehicle at each point is calculated. Avg and the maximum value E Max include:

[0080] For a single target, 10 points are evenly selected between the longitudinal distance between the vehicle and the target to obtain a longitudinal distance array [x1, x2, x3, x4, …, x10];

[0081] Substitute the longitudinal distance data into the historical trajectory parameter equation and the ego vehicle predicted driving trajectory equation to obtain the historical trajectory lateral distance array [a1, a2, a3, a4, …, a10] and the ego vehicle predicted driving trajectory lateral distance array [b1, b2, b3, b4, …, b10] respectively;

[0082] According to the longitudinal distance array, the lateral distance array of the historical trajectory and the lateral distance array of the self-vehicle predicted driving trajectory, the average deviation E at each point between the target historical trajectory and the self-vehicle predicted trajectory equation is calculated. Avg and the maximum value E Max ;

[0083] After traversing each target, obtain E Avg and E Max Array of

[0084] Then, according to the longitudinal distance array, the lateral distance array of the historical trajectory and the lateral distance array of the self-vehicle predicted driving trajectory, the average deviation E of the target historical trajectory and the self-vehicle predicted trajectory equation at each point is calculated. Avg and the maximum value E Max Calculated according to the following formula:

[0085]

[0086] E Max =max(|a i -b i |), i=1,2,..,10.

[0087] In some embodiments, according to the target vehicle width, the own vehicle width, the deviation average value E Avg and the maximum deviation E MaxTraverse each target and determine whether the vehicle follows the historical trajectory of the target, including:

[0088] If the average deviation E between the target's valid historical trajectory and the vehicle's predicted driving trajectory Avg Does not exceed the sum of the half width of the ego vehicle and the half width of the target vehicle; and

[0089] The maximum deviation error E between the target effective historical trajectory and the vehicle predicted trajectory Max If it does not exceed the sum of the half-width of the ego vehicle and the half-width of the target vehicle, then it is judged that the ego vehicle follows the historical trajectory of the target.

[0090] In some embodiments,

[0091] The step of determining the self-vehicle following target from the targets of the self-vehicle following historical trajectories includes:

[0092] The targets of the ego vehicle’s historical trajectory are sorted based on the longitudinal distance, and the target with the shortest longitudinal distance is selected as the nearest ego vehicle following target;

[0093] If the longitudinal distance of the nearest ego vehicle following the target is greater than the set longitudinal distance threshold, it is determined that the current ego vehicle is not following the target.

[0094] In some embodiments, it also includes:

[0095] Determine whether the current scene is the self-vehicle following the target vehicle in changing lanes;

[0096] If so, the historical trajectory of the ego vehicle following the target vehicle and the current predicted trajectory of the ego vehicle are fused to obtain the target selection trajectory of the ego vehicle following the target.

[0097] If not, the ego vehicle predicted trajectory is used as the target selection trajectory for each target.

[0098] In some embodiments, determining whether the current scene is a lane change of the ego vehicle following the target vehicle includes: determining whether the current scene is a lane change of the ego vehicle following the target vehicle according to the following conditions:

[0099] According to the result of judging whether the ego vehicle is following the target trajectory, judging whether the current ego vehicle has a target to follow and the nearest ego vehicle following target selected is valid;

[0100] The vehicle speed is greater than the threshold;

[0101] The lane lines exist and are valid, as determined by the camera;

[0102] The vehicle is currently following the target and is in the state of cutting out of the lane, which is determined and output by the camera.

[0103] In some embodiments, the historical trajectory of the ego vehicle following the target vehicle and the current predicted trajectory of the ego vehicle are integrated to obtain the target selection trajectory of the ego vehicle following the target, including: if the current scene is the ego vehicle following the target vehicle changing lanes, obtain the most recent ego vehicle following target historical trajectory equation y = A0 + A1*x + A2*x 2 And the current vehicle prediction trajectory equation y = D1*x + D2*x 2 , and fusion is performed according to the following formula:

[0104] B1=α·A1+(1-α)·D1

[0105] B2=α·A2+(1-α)·D2

[0106] Among them, α is the trajectory fusion weight, which determines whether the current scene is the self-vehicle following the target vehicle to change lanes. If so, α takes the value (0, 1), that is, 0<α<1; otherwise, α takes the value of 0.

[0107] Get the target selection trajectory of the self-vehicle following the target: y = B1*x + B2*x 2

[0108] In some embodiments, a computer device is provided, such as Figure 2 As shown, it includes a memory 201, a processor 202, and a computer program stored in the memory 201 and executable on the processor 202. When the processor 202 executes the computer program, the adaptive cruise target selection method for a lane-free scene in any of the above embodiments is implemented.

[0109] Specifically, the computer device may be a computer terminal, a server or a similar computing device.

[0110] In some embodiments, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a method for executing the adaptive cruise target selection method described in any of the above embodiments.

[0111] Specifically, computer-readable storage media include permanent and non-permanent, removable and non-removable media that can be used to store information by any method or technology. Information can be computer-readable instructions, data structures, program modules or other data. Examples of computer-readable storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable storage media does not include temporary computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0112] Based on the same inventive concept, an adaptive cruise target selection device is also provided in an embodiment of the present invention, as described in the following embodiments. Since the principle of solving the problem by an adaptive cruise target selection device is similar to that of an adaptive cruise target selection method, the implementation of an adaptive cruise target selection device can refer to the implementation of the adaptive cruise target selection method, and the repeated parts will not be repeated. As used below, the term "unit" or "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0113] An adaptive cruise target selection device, the structural block diagram is as follows Figure 3 As shown, including:

[0114] The target historical trajectory acquisition module 301 is used to obtain the target historical trajectory parameter equation and the target vehicle width;

[0115] The vehicle travel parameter acquisition module 302 is used to acquire the vehicle travel parameters;

[0116] A calculation module 303 is used to generate a predicted driving trajectory equation of the vehicle according to the vehicle travel parameters;

[0117] The judgment module 304 is used to judge whether the ego vehicle has a following target by using the ego vehicle predicted driving trajectory equation and the data obtained by the target historical trajectory acquisition module.

[0118] The fusion module 305 is used to obtain the target selection trajectory by judging whether the ego vehicle has a target to follow.

[0119] Obviously, those skilled in the art should understand that the modules or steps of the above-mentioned embodiments of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, and optionally, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order from that here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. In this way, the embodiments of the present invention are not limited to any specific combination of hardware and software.

[0120] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the embodiments of the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An adaptive cruise target selection method, It is characterized in that include: Obtain the historical trajectories of multiple targets in the ego-vehicle coordinate system; Obtaining the vehicle's travel parameters, and determining the vehicle's predicted travel trajectory based on the vehicle's travel parameters; For each target, according to the predicted driving trajectory of the ego vehicle and the historical trajectory of the target, multiple points are evenly selected between the longitudinal distance between the ego vehicle and the target, and the average deviation E between the target historical trajectory and the predicted trajectory of the ego vehicle at each point is calculated. Avg and the maximum deviation E Max ; The target vehicle width and the vehicle width are obtained through the camera, and the deviation average value E is calculated based on the target vehicle width, the vehicle width, and the deviation average value E. Avg and the maximum deviation E Max Traverse each target, determine whether the vehicle follows the historical trajectory of the target, and determine the target of the historical trajectory followed by the vehicle; The ego vehicle following target is determined among the targets of the ego vehicle following the historical trajectory.

2. The adaptive cruise target selection method according to claim 1, It is characterized in that According to the predicted driving trajectory of the vehicle and the historical trajectory of the target, multiple points are evenly selected between the longitudinal distance between the vehicle and the target, and the average deviation E between the historical trajectory of the target and the predicted trajectory of the vehicle at each point is calculated. Avg and the maximum deviation E Max include: For a single target, multiple points are evenly selected between the longitudinal distances between the vehicle and the target to obtain a longitudinal distance array; Substitute the longitudinal distance data into the trajectory parameter equation of the historical trajectory and the trajectory equation of the predicted driving trajectory of the vehicle, respectively, to obtain the lateral distance array of the historical trajectory and the lateral distance array of the predicted driving trajectory of the vehicle, respectively; According to the longitudinal distance array, the lateral distance array of the historical trajectory and the lateral distance array of the self-vehicle predicted driving trajectory, the average deviation E of the target's historical trajectory and the self-vehicle predicted driving trajectory at each point is calculated. Avg and the actual maximum value E Max ; After traversing each target, obtain E Avg and E Max Array of .

3. The adaptive cruise target selection method according to claim 2, It is characterized in that The method calculates the average deviation E of the target's historical trajectory and the self-vehicle predicted driving trajectory at each point based on the longitudinal distance array, the historical trajectory lateral distance array and the self-vehicle predicted driving trajectory lateral distance array. Avg and the maximum deviation E Max , calculated according to the following formula: E Max =max(|a i -b i |),i=1,2,..,n, Among them, a is the historical lateral distance of the target in the historical trajectory lateral distance array, b is the lateral distance of the ego vehicle in the lateral distance array of the predicted driving trajectory, and n is the number of points uniformly selected between the longitudinal distances of the ego vehicle and the target.

4. The adaptive cruise target selection method according to claim 1, It is characterized in that According to the target vehicle width, the own vehicle width, and the deviation average value E Avg and the maximum deviation E Max Traverse each target and determine whether the vehicle follows the historical trajectory of the target, including: If the average deviation E between the target's valid historical trajectory and the vehicle's predicted driving trajectory Avg Does not exceed the sum of the half width of the ego vehicle and the half width of the target vehicle; and The maximum deviation error E between the target effective historical trajectory and the vehicle predicted trajectory Max Does not exceed the sum of the half width of the vehicle and the half width of the target vehicle. Then determine the historical trajectory of the vehicle following the target.

5. The adaptive cruise target selection method according to claim 1, It is characterized in that The step of determining the self-vehicle following target from the targets of the self-vehicle following historical trajectories includes: The targets of the ego vehicle’s historical trajectory are sorted based on the longitudinal distance, and the target with the shortest longitudinal distance is selected as the nearest ego vehicle following target; If the longitudinal distance of the nearest ego vehicle following the target is greater than the set longitudinal distance threshold, it is determined that the current ego vehicle is not following the target.

6. The adaptive cruise target selection method according to any one of claims 1 to 5, It is characterized in that Also includes: Determine whether the current scene is the self-vehicle following the target vehicle in changing lanes; If yes, the historical trajectory of the ego vehicle following the target vehicle and the current predicted trajectory of the ego vehicle are fused to obtain the target selection trajectory of the ego vehicle following the target; if no, the predicted trajectory of the ego vehicle is used as the target selection trajectory of each target.

7. The adaptive cruise target selection method according to claim 6, It is characterized in that The historical trajectory of the ego vehicle following the target vehicle and the current predicted trajectory of the ego vehicle are integrated to obtain the target selection trajectory of the ego vehicle following the target, including: y=B1*x+B2*x 2 Among them, y is the lateral distance in the ego vehicle coordinate system, x is the longitudinal distance in the ego vehicle coordinate system, B1 is the first-order coefficient of the target selection trajectory equation, and B2 is the second-order coefficient of the target selection trajectory equation. B1=α·A1+(1-α)·D1; B2=α·A2+(1-α)·D2; Among them, α is the trajectory fusion weight, A1 is the linear coefficient of the historical trajectory equation of the ego vehicle following the target, A2 is the quadratic coefficient of the historical trajectory equation of the ego vehicle following the target, D1 is the linear coefficient of the ego vehicle prediction trajectory equation, and D2 is the quadratic coefficient of the ego vehicle prediction trajectory equation. The historical trajectory equation of the vehicle following the target is y1=A0+A1*x+A2*x 2 , The current vehicle prediction trajectory equation y2 = D1*x + D2*x 2 , Among them, A0 is the zero-order coefficient of the historical trajectory equation of the ego vehicle following the target.

8. An adaptive cruise target selection device, It is characterized in that include: The target history track acquisition module is used to obtain the target history track and target vehicle width; A self-vehicle traveling parameter acquisition module, used to obtain the self-vehicle traveling parameters; The calculation module is used to calculate the average deviation E of the target historical trajectory and the predicted trajectory of the vehicle at each point through the vehicle's travel parameters and the target historical trajectory. Avg and the maximum deviation E Max ; The judgment module is used to determine the average value of the deviation E Avg and the maximum deviation E Max , the width of the target vehicle and the width of the ego vehicle determine whether the ego vehicle follows the target historical trajectory, and determine the ego vehicle follows the target in the target of the ego vehicle following the historical trajectory; The fusion module is used to obtain the target selection trajectory by judging whether the ego vehicle has a target to follow.

9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, It is characterized in that When the processor executes the computer program, the adaptive cruise target selection method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores instructions for executing the adaptive cruise target selection method according to any one of claims 1 to 7.

Images