A method and apparatus for adaptive cruise primary target selection

Abstract

This invention discloses an adaptive cruise control primary target selection method and apparatus, comprising: estimating the vehicle's trajectory based on its yaw rate; correcting the motion parameters of each target vehicle within a target range according to the trajectory; calculating the motion index of the target vehicle based on the corrected motion parameters; determining the driving state of the target vehicle by comparing the motion index with a corresponding index threshold; determining a representative driving state for the current scenario based on the driving states of all target vehicles; and determining the target vehicle with the closest relative distance to the vehicle among those that meet the corresponding driving state as the primary target, and outputting the primary target distance and primary target speed. This invention incorporates multiple variable factors, refines the calculation corrections under different scenarios, and improves the control accuracy and safety of the adaptive cruise control system.

Description

Technical Field

[0001] This invention relates to the field of adaptive cruise technology, and in particular to an adaptive cruise primary target selection method and apparatus. Background Technology

[0002] With advancements in automotive intelligence technology, Adaptive Cruise Control (ACC) has gradually become a standard feature in many passenger vehicles. Adaptive Cruise Control relies on sensors mounted at the front of the vehicle to gather information. When the distance to the vehicle ahead is too close, the system controls the engine and braking system to maintain a safe distance; when the vehicle ahead is far enough away or there is no vehicle ahead, the system controls the vehicle to reach a set speed. Thanks to this, driver fatigue can be significantly reduced during long-distance driving.

[0003] Selecting the primary target vehicle is a prerequisite for the operation of adaptive cruise control systems. However, existing methods generally have low accuracy in selecting the primary target in complex road conditions. In particular, when there is a vehicle that suddenly cuts in, the primary target selection may jump back and forth between different vehicles. The system may control the vehicle's speed to increase due to the incorrect selection of the primary target, which may lead to a collision. This significantly affects the accuracy of adaptive cruise control and the safety of the system. Summary of the Invention

[0004] To overcome the problems existing in related technologies, the present invention provides an adaptive cruise primary target selection method and apparatus to solve the defects in related technologies.

[0005] According to a first aspect of the present invention, an adaptive cruise primary target selection method is provided, the method comprising:

[0006] Estimate the vehicle's trajectory based on its yaw rate;

[0007] Based on the motion trajectory, the motion parameters of each target vehicle within the target range are corrected; wherein, the motion parameters include lateral relative distance, longitudinal relative distance, lateral relative velocity, and longitudinal relative velocity;

[0008] Based on the corrected motion parameters, the motion index of the target vehicle is calculated; wherein, the motion index includes a longitudinal warning index, a collision time reciprocal, and a lane change probability. The longitudinal warning index is used to represent the risk index of a collision between the vehicle and the target vehicle in the current driving direction. The collision time reciprocal is used to represent the reciprocal of the time it would take for the vehicle to collide with the target vehicle while the driving speed remains constant. The lane change probability is used to represent the probability that the target vehicle will enter the lane where the vehicle is located.

[0009] The driving state of the target vehicle is determined by comparing the motion index with the corresponding index threshold; wherein the driving state is one of the following: adjacent vehicle, smoothly cutting in, dangerously cutting in, safe vehicle in lane, and dangerous vehicle in lane.

[0010] Based on the driving states of all target vehicles, determine the representative driving state of the current scenario; wherein the representative driving state is one of the following: normal driving state, smooth entry state, dangerous entry state, and dangerous state within the lane;

[0011] Based on the representative driving state, the target vehicle that is closest to the current vehicle among the target vehicles that meet the corresponding driving state is identified as the main target, and the distance and speed of the main target are output.

[0012] Preferably, calculating the motion index of the target vehicle based on the corrected motion parameters includes:

[0013] The longitudinal warning indicator x is calculated using the following formula:

[0014]

[0015] Among them, P long v is the longitudinal relative distance. long T is the longitudinal relative velocity. s,delay v is the delay time of the vehicle's braking system. s T is the speed of this vehicle. h,delay This is the reaction time for the driver of this vehicle.

[0016] Preferably, calculating the motion index of the target vehicle based on the corrected motion parameters includes:

[0017] The reciprocal of the collision time TTC is calculated using the following formula. -1 :

[0018]

[0019] Among them, P long v is the longitudinal relative distance. s v is the speed of this vehicle. p The target vehicle's speed in the current driving direction.

[0020] Preferably, calculating the motion index of the target vehicle based on the corrected motion parameters includes:

[0021] The lateral relative distance and the lateral relative speed are matched with preset fuzzy rules to obtain a fuzzy set of lane change probabilities, and then the lane change probability is obtained by defuzzification calculation.

[0022] Preferably, determining the driving state of the target vehicle by comparing the motion index with the corresponding index threshold specifically includes:

[0023] If the lane change probability is greater than a preset lane change probability threshold, and the longitudinal warning index is less than a preset warning index threshold or the reciprocal of the collision time is greater than a preset reciprocal of the collision time threshold, then the driving state of the target vehicle is determined to be a dangerous cutting vehicle.

[0024] If the lane change probability is greater than a preset lane change probability threshold, and the longitudinal warning index is not less than a preset warning index threshold and the reciprocal of the collision time is not greater than a preset collision time reciprocal threshold, then the driving state of the target vehicle is determined to be a smooth entry vehicle.

[0025] If the lane change probability is less than a preset lane change probability threshold and the lateral relative distance is less than a preset distance threshold, and the longitudinal warning index is less than a preset warning index threshold and the reciprocal of the collision time is greater than a preset collision time reciprocal threshold, then the driving state of the target vehicle is determined to be a dangerous vehicle in the lane.

[0026] If the lane change probability is less than a preset lane change probability threshold and the lateral relative distance is less than a preset distance threshold, and the longitudinal warning index is not less than a preset warning index threshold or the reciprocal of the collision time is not greater than a preset reciprocal of the collision time threshold, then the driving status of the target vehicle is determined to be a safe vehicle in the lane.

[0027] If the lane change probability is greater than a preset lane change probability threshold and the lateral relative distance is not less than a preset distance threshold, then the driving state of the target vehicle is determined to be that of a neighboring vehicle.

[0028] Preferably, the step of determining the target vehicle closest to the current vehicle among the target vehicles that meet the corresponding driving state as the primary target, and outputting the primary target distance and primary target speed, includes:

[0029] If the driving state is normal driving state, then the target vehicle with the smallest longitudinal relative distance in the lane where this vehicle is located is determined as the main target, and the longitudinal relative distance and longitudinal relative speed of the target vehicle are output as the main target distance and the main target speed.

[0030] Preferably, the step of determining the target vehicle closest to the current vehicle among the target vehicles that meet the corresponding driving state as the primary target, and outputting the primary target distance and primary target speed, includes:

[0031] If the driving state is a smooth entry state, then the target vehicle with the smallest longitudinal relative distance in the lane where this vehicle is located is identified as the first important target, and the first important target is identified as the main target.

[0032] The target vehicle in the driving state of a smoothly cutting-in vehicle is identified as the second important target, and the lateral relative distance of the second important target when it is identified is marked as the reference distance;

[0033] The weighting coefficients for the first important target and the second important target are calculated based on the ratio of the real-time lateral relative distance of the second important target to the reference distance.

[0034] The comprehensive longitudinal relative distance and comprehensive longitudinal relative velocity of the first important target and the second important target are calculated based on the weighting coefficients of the first important target and the second important target, and the comprehensive longitudinal relative distance and the comprehensive longitudinal relative velocity are output as the main target distance and the main target velocity;

[0035] When the real-time lateral relative distance of the second important target is less than the preset cut-in distance threshold, the main target is changed from the first important target to the second important target.

[0036] Preferably, the step of determining the target vehicle closest to the current vehicle among the target vehicles that meet the corresponding driving state as the primary target, and outputting the primary target distance and primary target speed, includes:

[0037] If the driving state is a dangerous entry state, then the target vehicle in the dangerous entry state is determined as the main target, and the longitudinal relative distance and longitudinal relative speed of the target vehicle are output as the main target distance and the main target speed.

[0038] Preferably, the step of determining the target vehicle closest to the current vehicle among the target vehicles that meet the corresponding driving state as the primary target, and outputting the primary target distance and primary target speed, includes:

[0039] If the driving state represented is a dangerous state within the lane, then the target vehicle whose driving state is a dangerous vehicle within the lane is identified as the first dangerous vehicle.

[0040] If there is no target vehicle whose driving state is a dangerous cutting vehicle, then the first dangerous vehicle is identified as the primary target;

[0041] If there is a target vehicle whose driving state is a dangerous cutting vehicle, then the target vehicle whose driving state is a dangerous cutting vehicle is identified as the second dangerous vehicle;

[0042] If the longitudinal warning index of the second dangerous vehicle is not less than a preset warning index threshold or the reciprocal of the collision time is not greater than a preset reciprocal of the collision time threshold, then the first dangerous vehicle is identified as the primary target.

[0043] If the longitudinal warning index of the second dangerous vehicle is less than a preset warning index threshold and the reciprocal of the collision time is greater than a preset collision time reciprocal threshold, then the second dangerous vehicle is identified as the primary target.

[0044] The longitudinal relative distance and longitudinal relative velocity of the main target are output as the distance and velocity of the main target.

[0045] According to a second aspect of the present invention, an adaptive cruise primary target selection device is provided, the device comprising:

[0046] The vehicle trajectory estimation module is used to estimate the vehicle's trajectory based on its yaw rate.

[0047] The target vehicle parameter correction module is used to correct the motion parameters of each target vehicle within the target range according to the motion trajectory; wherein, the motion parameters include lateral relative distance, longitudinal relative distance, lateral relative velocity, and longitudinal relative velocity;

[0048] The target vehicle motion analysis module is used to calculate the motion index of the target vehicle based on the corrected motion parameters. The motion index includes a longitudinal warning index, a collision time reciprocal, and a lane change probability. The longitudinal warning index represents the risk index of a collision between the current vehicle and the target vehicle in the current driving direction. The collision time reciprocal represents the reciprocal of the time it would take for the current vehicle to collide with the target vehicle while the driving speed remains constant. The lane change probability represents the probability that the target vehicle will enter the lane where the current vehicle is located.

[0049] The target vehicle state determination module is used to determine the driving state of the target vehicle by comparing the motion index with the corresponding index threshold; wherein the driving state is one of the following: adjacent vehicle, smoothly cutting in, dangerously cutting in, safe vehicle in lane, and dangerous vehicle in lane;

[0050] The representative state determination module is used to determine the representative driving state of the current scenario based on the driving states of all target vehicles; wherein the representative driving state is one of the following: normal driving state, smooth entry state, dangerous entry state, and dangerous state within the lane;

[0051] The main target selection module is used to determine the target vehicle that is closest to the current vehicle among the target vehicles that meet the corresponding driving state as the main target based on the representative driving state, and output the main target distance and the main target speed.

[0052] This invention discloses an adaptive cruise control primary target selection method and apparatus. It quantifies the motion state of a target vehicle in a scenario by generating three motion indicators: a longitudinal warning indicator, a collision time reciprocal indicator, and a lane change probability indicator. It comprehensively considers factors such as vehicle collision risk and vehicle cut-in probability, and determines the driving state of each vehicle by analyzing the motion indicators. A representative driving state is then obtained, and the primary target output strategy is determined based on this representative driving state. This invention incorporates multiple variable factors, refines the calculation corrections under different scenarios, and improves the control accuracy and safety of the adaptive cruise control system.

[0053] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit the invention. Attached Figure Description

[0054] Figure 1 This is a flowchart illustrating an adaptive cruise primary target selection method according to an embodiment of the present invention.

[0055] Figure 2 This is a schematic diagram illustrating an estimation of the vehicle's trajectory according to an embodiment of the present invention.

[0056] Figure 3 This is a schematic diagram illustrating a method for calculating lane change probability according to an embodiment of the present invention.

[0057] Figure 4 This is a schematic diagram illustrating a method for determining the driving status of a target vehicle according to an embodiment of the present invention.

[0058] Figure 5 This is a schematic diagram illustrating the change in the output main target speed when the driving state is a smooth entry state, according to an embodiment of the present invention.

[0059] Figure 6 This is a schematic diagram of the structure of an adaptive cruise primary target selection device according to an embodiment of the present invention.

[0060] Figure 7 This is a schematic diagram of the hardware structure of a computing device according to an embodiment of the present invention. Detailed Implementation

[0061] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the invention as detailed in the appended claims.

[0062] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The singular forms “a,” “the,” and “the” used in this invention and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0063] It should be understood that although the terms first, second, third, etc., may be used in this invention to describe various information, this information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, first information may also be referred to as second information without departing from the scope of this invention, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to a determination."

[0064] The present invention will now be described in detail with reference to the accompanying drawings and specific embodiments.

[0065] like Figure 1 As shown, Figure 1 This is a flowchart illustrating an adaptive cruise primary target selection method according to an embodiment of the present invention, comprising the following steps:

[0066] Step S101: Estimate the trajectory of the vehicle based on its yaw rate;

[0067] Step S102: Based on the motion trajectory, correct the motion parameters of each target vehicle within the target range;

[0068] Step S103: Calculate the motion index of the target vehicle based on the corrected motion parameters;

[0069] Step S104: Determine the driving status of the target vehicle by comparing the motion index with the corresponding index threshold.

[0070] Step S105: Determine the representative driving state of the current scenario based on the driving states of all target vehicles;

[0071] Step S106: Based on the representative driving state, determine the target vehicle that is closest to the current vehicle among the target vehicles that meet the corresponding driving state as the main target, and output the main target distance and main target speed.

[0072] The adaptive cruise primary target selection method of the present invention first estimates the motion trajectory of the vehicle to correct the speed and position information of the target vehicles in the scene, then calculates the driving state of all target vehicles and the representative driving state of the scene based on the corrected information, and selects the corresponding selection strategy according to the possible values ​​of the representative driving state.

[0073] In step S101, the yaw rate of the vehicle can be calculated based on the yaw rate and steering wheel angle. The trajectory of the vehicle can be predicted by the yaw rate. The trajectory of the vehicle will affect the relative motion relationship between the vehicle and other adjacent vehicles. Since the trajectory of the vehicle is different, the possible behaviors of other adjacent vehicles relative to the vehicle will be different. This is important for selecting the correct primary target. Therefore, the trajectory of the vehicle needs to be estimated before selecting the primary target.

[0074] like Figure 2 As shown, Figure 2 This is a schematic diagram illustrating an embodiment of the present invention for estimating the trajectory of a vehicle. The instantaneous trajectory of the vehicle can be simplified as an arc, the center of which depends on the direction of the vehicle's motion trend, and the radius of curvature of the arc can be calculated using the formula... Calculated. Wherein v is the radius of curvature estimated for the current vehicle. s Let be the vehicle speed, and γ be the vehicle's yaw rate. Specifically, when the estimated radius of curvature... When the value is infinite, the trajectory of the vehicle can be considered as a straight line.

[0075] In step S102, the motion parameters of each target vehicle within the target range are corrected to the virtual lane estimated based on its trajectory. The motion parameters to be corrected include position distance and speed, specifically lateral relative distance, longitudinal relative distance, lateral relative speed, and longitudinal relative speed. Specifically, the speed and position coordinates of the target vehicle can be converted to the virtual lane using the following formula:

[0076] Horizontal relative distance:

[0077]

[0078] Longitudinal relative distance:

[0079]

[0080] Lateral relative velocity:

[0081] v lat =v x cosα+v y sinα

[0082] Longitudinal relative velocity:

[0083] v long =v y cosα+v x sinα

[0084] in,

[0085]

[0086] In this invention, the target range refers to the range that the vehicle can observe during adaptive cruise control. The size of the target range is determined by the number and location of sensors installed on the vehicle body, and this invention does not impose any limitations on this. In some embodiments, the target range may include only the entire area in front of the vehicle, or it may also include a portion of the left and right sides, or it may also include a portion of the area behind the vehicle, and this invention does not impose any limitations on this.

[0087] In this invention, a target vehicle refers to all other adjacent vehicles detected within the target range. As vehicles also traveling on the road, target vehicles have a significant impact on the driving of the main vehicle. The target vehicle with the greatest impact is the primary target, such as the closest target vehicle or a target vehicle about to merge into the main vehicle's lane. Selecting the correct primary target is crucial for the safety of the vehicle under adaptive cruise control. In some embodiments, to avoid interference from too many target vehicles within the target range, adjacent vehicles meeting certain conditions can be considered as target vehicles. For example, only vehicles within a certain distance from the main vehicle can be considered as target vehicles, or only vehicles larger than a certain size in the image detected by the main vehicle can be considered as target vehicles. This filters out information about vehicles that are far away and have a relatively small impact on the main vehicle's driving. In some embodiments, other filtering rules can also be used to filter target vehicles, and this invention does not limit this.

[0088] In step S103, to measure the impact of the target vehicle on the driving of the current vehicle, three motion indicators are introduced. Two of these are longitudinal motion indicators, related to the collision between the current vehicle and the target vehicle; the other is a lateral motion indicator, related to the probability of the target vehicle entering the current lane. Specifically, the motion indicators include a longitudinal warning indicator, a collision time reciprocal, and a lane change probability. The longitudinal warning indicator represents the risk index of a collision between the current vehicle and the target vehicle in the current driving direction. The collision time reciprocal represents the reciprocal of the time it would take for the current vehicle to collide with the target vehicle at a constant driving speed. The lane change probability represents the probability of the target vehicle entering the current vehicle's lane.

[0089] Specifically, in some embodiments, the longitudinal warning index x can be calculated using the following formula:

[0090]

[0091] Among them, P long v is the longitudinal relative distance of the target vehicle. long Let T be the longitudinal relative velocity of the target vehicle. s,delayv is the delay time of the vehicle's braking system. s T is the speed of this vehicle. h,delay This refers to the driver's reaction time. Specifically, the longitudinal warning index x represents the ratio of the distance between the vehicle and the target vehicle minus the extra distance traveled by the vehicle during braking due to braking system delay to the extra distance traveled due to the driver's reaction time. In other words, it is the ratio of the safe distance the vehicle can travel to the distance the driver needs to react. Therefore, the larger the longitudinal warning index x, the greater the vehicle's reaction margin during braking, and the lower the risk of collision with the target vehicle; conversely, the smaller the longitudinal warning index x, the smaller the vehicle's reaction margin during braking, and the higher the risk of collision with the target vehicle.

[0092] Specifically, in some embodiments, the reciprocal of the collision time TTC can be calculated using the following formula. -1 :

[0093]

[0094] Among them, P long v is the longitudinal relative distance of the target vehicle. s v is the speed of this vehicle. p This refers to the target vehicle's speed in the current driving direction. If the speed of the vehicle in front is constant, and the vehicle's speed converges to the target vehicle's speed, the vehicle will follow the target vehicle with an almost constant following distance. Therefore, stable following by the driver corresponds to TTC (Traffic Traverse Control). -1 The case where it is a small value. Therefore, if the reciprocal of the collision time is TTC... -1 A positive value indicates that the vehicle is approaching the target vehicle ahead; if the collision time countdown is positive, it indicates that the vehicle is approaching the target vehicle ahead. -1 A large distance indicates that the vehicle is too close to the vehicle in front, and the risk of a collision between the vehicle and the target vehicle is relatively high.

[0095] Specifically, to describe the tendency of a target vehicle to enter the lane of the vehicle in question, this invention uses lane change probability to represent the movement of each target vehicle toward the lane. If the sign of the lateral relative distance of a target vehicle is opposite to the sign of its lateral relative velocity, it means that the target vehicle is approaching the lane of the vehicle in question. If a target vehicle is determined to have an approaching tendency, the probability of it entering the lane of the vehicle in question can then be calculated using fuzzy rules.

[0096] Specifically, in some embodiments, a fuzzy set of lane change probabilities can be obtained by matching the lateral relative distance and lateral relative velocity with preset fuzzy rules, and then the lane change probability can be obtained by defuzzification calculation. For example... Figure 3 As shown, Figure 3This is a schematic diagram illustrating a method for calculating lane change probability according to an embodiment of the present invention. First, the lateral relative distance and lateral relative speed of the target vehicle are calculated using corresponding distance fuzzy membership functions and speed fuzzy membership functions to obtain fuzzy representations of the lateral relative distance and lateral relative speed. Then, the fuzzy representations of the lateral relative distance and lateral relative speed are input into preset fuzzy rules for matching to obtain a fuzzy representation of the lane change probability. Defuzzification calculation is then performed using the corresponding lane change fuzzy membership function to obtain the lane change probability of the target vehicle. Furthermore, by obtaining the lateral relative distances and lateral relative speeds of multiple target vehicles over a period of time, a fuzzy set of lane change probabilities can be obtained. Defuzzification calculation further improves the accuracy of the obtained lane change probability of the target vehicle.

[0097] Specifically, in some embodiments, the preset fuzzy rules can be as shown in Table 1:

[0098] Table 1 Fuzzy Rules

[0099]

[0100] In this system, the leftmost two columns of the fuzzy rules are the inputs, and the rightmost column is the output, with each row representing a rule. The output is a fuzzy set of lane probabilities. Finally, a defuzzification method is used to calculate the probability of an adjacent target vehicle entering the lane where the current vehicle is located.

[0101] In step S104, to select the primary target among the target vehicles, indicators representing the driving state are introduced. Specifically, the driving state of the target vehicle can be divided into five types: adjacent vehicle, smoothly entering vehicle, dangerously entering vehicle, safe vehicle in lane, and dangerous vehicle in lane. By comparing the three motion indicators of the target vehicle with the corresponding indicator thresholds, one of the above five driving states of the target vehicle can be determined. Dangerous vehicle in lane indicates that the target vehicle is in the lane of the vehicle and there is a possibility of collision; adjacent vehicle and safe vehicle in lane indicate that the target vehicle does not have a lane-changing action related to the lane of the vehicle; smoothly entering vehicle indicates that the target vehicle has a lateral movement to enter the lane of the vehicle but there is no risk of collision; dangerously entering vehicle indicates that the target vehicle not only has a lateral movement to enter the lane of the vehicle but also has a risk of collision.

[0102] Specifically, in some embodiments, determining the driving state of a target vehicle by comparing motion indicators with corresponding indicator thresholds may include:

[0103] If the lane change probability is greater than the preset lane change probability threshold, and the longitudinal warning index is less than the preset warning index threshold or the reciprocal of the collision time is greater than the preset reciprocal of the collision time threshold, then the driving status of the target vehicle is determined to be a dangerous cutting vehicle.

[0104] If the lane change probability is greater than the preset lane change probability threshold, and the longitudinal warning index is not less than the preset warning index threshold and the reciprocal of the collision time is not greater than the preset reciprocal of the collision time threshold, then the driving state of the target vehicle is determined to be a smoothly cutting vehicle.

[0105] If the lane change probability is less than the preset lane change probability threshold and the lateral relative distance is less than the preset distance threshold, and the longitudinal warning index is less than the preset warning index threshold and the reciprocal of the collision time is greater than the preset reciprocal of the collision time threshold, then the target vehicle's driving status is determined to be a dangerous vehicle in the lane.

[0106] If the lane change probability is less than the preset lane change probability threshold and the lateral relative distance is less than the preset distance threshold, and the longitudinal warning index is not less than the preset warning index threshold or the reciprocal of the collision time is not greater than the preset reciprocal of the collision time threshold, then the driving status of the target vehicle is determined to be a safe vehicle in the lane.

[0107] If the lane change probability is greater than the preset lane change probability threshold and the lateral relative distance is not less than the preset distance threshold, then the target vehicle's driving status is determined to be that of an adjacent vehicle.

[0108] The preset lane change probability threshold, warning index threshold, collision time countdown threshold, and distance threshold can be set according to actual applications, and this invention does not impose any restrictions on them.

[0109] Specifically, in some embodiments, the index 'd' can be used to represent the driving state of the target vehicle. Specifically, d = -1 indicates the target vehicle is a neighboring vehicle; d = 0 indicates the target vehicle is a safe vehicle within its lane; d = 1 indicates the target vehicle is a smoothly merging vehicle; d = 2 indicates the target vehicle is a dangerously merging vehicle; and d = 3 indicates the target vehicle is a dangerous vehicle within its lane. Specifically, in some embodiments, the driving state of the target vehicle can also be represented in other ways, and this invention does not limit this.

[0110] Specifically, such as Figure 4 As shown, Figure 4 This invention illustrates a method for determining the driving status of a target vehicle. First, the probability P of the target vehicle changing lanes is determined. lane Is it greater than the preset lane change probability threshold P? TH If the probability P of the target vehicle changing lanes lane Greater than the preset lane change probability threshold P TH Then, it continues to determine whether the longitudinal warning indicator x of the target vehicle is less than the preset warning indicator threshold x. TH Or the countdown time to the collision of the target vehicle (TTC) -1 Is it greater than the preset reciprocal threshold T of the collision time? THIf the judgment is positive, then the index d = 2, meaning the target vehicle's driving state is a dangerous lane-changing vehicle; if the judgment is negative, then the index d = 1, meaning the target vehicle's driving state is a smooth lane-changing vehicle; if the target vehicle's lane-changing probability P lane Not greater than the preset lane change probability threshold P TH Then continue to determine the lateral relative distance P of the target vehicle. lat Is it less than the preset distance threshold P? TH,lat If the lateral relative distance P of the target vehicle lat If the distance is less than a preset distance threshold, then it continues to determine whether the longitudinal warning indicator x of the target vehicle is less than a preset warning indicator threshold x. TH Meanwhile, the countdown timer for the target vehicle's collision is approaching (TTC). -1 Is it greater than the preset reciprocal threshold T of the collision time? TH If the judgment is positive, then the index d = 3, meaning the target vehicle's driving status is a dangerous vehicle within the lane; if the judgment is negative, then the index d = 0, meaning the target vehicle's driving status is a safe vehicle within the lane; if the lateral relative distance P of the target vehicle... lat Not less than the preset distance threshold P TH,lat Then, we can determine the index d = -1, which means that the target car's driving status is that of the neighboring car.

[0111] In step S105, the driving state of each target vehicle is obtained after comparing various motion indicators. Based on the driving state of each target vehicle, the representative driving state for the current scenario can be determined. The representative driving state represents the driving state of the target vehicle that has the greatest impact on the current vehicle during its driving in the current scenario; that is, the driving state that the current vehicle needs to pay attention to and deal with. Specifically, the representative driving state is one of the following: normal driving state, smooth entry state, dangerous entry state, and dangerous state within the lane. Specifically, when the current scenario only has a target vehicle whose driving status is either an adjacent vehicle or a safe vehicle in the lane, the driving status is determined to be normal driving status; when the current scenario has a target vehicle whose driving status is either an adjacent vehicle or a safe vehicle in the lane, and also has a target vehicle whose driving status is a smoothly cutting-in vehicle, the driving status is determined to be smooth cutting-in status; when the current scenario has a target vehicle whose driving status is either an adjacent vehicle, a safe vehicle in the lane, or a smoothly cutting-in vehicle, and also has a target vehicle whose driving status is dangerous cutting-in vehicle, the driving status is determined to be dangerous cutting-in status; when the current scenario has a target vehicle whose driving status is dangerous vehicle in the lane, the driving status is determined to be dangerous in the lane.

[0112] Specifically, in some embodiments, each target vehicle passes through Figure 4 The comparison process shown yields the corresponding driving state d. iAfter (1≤i≤N, where N is the number of target vehicles in the scene), the representative driving state RDS at that moment in the scene can be calculated using the following formula:

[0113] RDS = max{d1,d2,…,d N}

[0114] The primary target can then be identified as the vehicle closest to our vehicle in the RDS state. Depending on the different values ​​of RDS, different strategies can be used to determine the primary target, and the distance and speed of the primary target can be output.

[0115] In step S106, after determining the representative driving state, the target vehicle that is closest to the current vehicle among the target vehicles that match the corresponding driving state is identified as the primary target, and the distance and speed of the primary target are output. The distance and speed of the primary target are output as important reference standards to the in-vehicle display screen or the adaptive cruise control system, so that the current vehicle can better understand the current road environment.

[0116] Specifically, if the driving state represents a normal driving state, then the target vehicle with the smallest longitudinal relative distance in the lane where this vehicle is located can be identified as the main target, and the longitudinal relative distance and longitudinal relative speed of the target vehicle can be output as the main target distance and the main target speed.

[0117] When RDS is in normal driving mode, it means that all adjacent target vehicles are in normal driving mode. At this time, the primary target is the vehicle with the smallest longitudinal relative distance within the lane where this vehicle is located. Furthermore, since no adjacent vehicles have entered this vehicle's lane, the system only needs to provide the longitudinal relative speed and longitudinal relative distance of the primary target vehicle within the lane.

[0118] Dist = p(t) long,inlane

[0119] V rel =v(t) long,inlane

[0120] Specifically, if the driving state represents a smooth cut-in state, the target vehicle with the smallest longitudinal relative distance within the lane where the current vehicle is located can be identified as the first important target and designated as the main target. Simultaneously, the target vehicle in the smooth cut-in state can be identified as the second important target, and the lateral relative distance of the second important target when it is identified can be marked as the reference distance. Then, based on the ratio of the real-time lateral relative distance of the second important target to the reference distance, a weighting coefficient between the first and second important targets is calculated. Based on the weighting coefficient between the first and second important targets, the comprehensive longitudinal relative distance and comprehensive longitudinal relative speed of the first and second important targets are calculated, and the comprehensive longitudinal relative distance and comprehensive longitudinal relative speed are output as the main target distance and main target speed. Furthermore, when the real-time lateral relative distance of the second important target is less than a preset cut-in distance threshold, the main target is changed from the first important target to the second important target.

[0121] When the RDS is in a smooth transition state, combining information about the second important target about to be entered and the nearest first important target within the lane can reduce jumps between the two, improving the stability of the adaptive cruise control system. Specifically, the system outputs the primary target distance Dist and the primary target speed V. rel as follows:

[0122] Dist = c·p(t) long,inlane +(1-c)·p(t) long,cutin

[0123] V rel =c·v(t) long,inlane +(1-c)·v(t) long,cutin

[0124] in,

[0125]

[0126] Specifically, such as Figure 5 As shown, Figure 5 This is a schematic diagram illustrating the change in the output primary target speed when the driving state is a smooth lane-entry state, according to an embodiment of the present invention. Once the RDS is determined to be in a smooth lane-entry state, the system identifies a second important target with a tendency to enter the lane and marks the lateral coordinate of this second important target at that moment as p. lat,ref At this point, it is p lat,cutin The weight α is set to 1. As the target vehicle gradually enters the lane, the numerator value gradually decreases, and the weighting coefficient c gradually approaches 0 from 1. Correspondingly, the distance to the main target increases from p... long,inlane Gradually become p long,cutin The relative velocity of the main target changes from v long,inlane Gradually becomes vlong,cutin In other words, the primary objective changes from the most important objective within the lane to the second most important objective.

[0127] Specifically, if the driving state represents a dangerous entry state, then the target vehicle in the dangerous entry state can be identified as the main target, and the longitudinal relative distance and longitudinal relative speed of the target vehicle can be output as the main target distance and main target speed.

[0128] When the RDS is in a dangerous approach state, the control objective is to treat the rapidly approaching target vehicle as the primary target to improve driving safety. Therefore, the system selects the relative speed and relative distance information of this target as output. That is, for this scenario, the system provides the relative speed and distance information of the approaching target vehicle as follows:

[0129] Dist = p(t) long,cutin

[0130] V y =v(t) long,cutin

[0131] Specifically, if the driving state represents a dangerous state within the lane, then the target vehicle with the driving state of a dangerous vehicle within the lane can be identified as the first dangerous vehicle; and if there is no target vehicle with the driving state of a dangerous cutting-in vehicle, then the first dangerous vehicle is identified as the primary target; and if there is a target vehicle with the driving state of a dangerous cutting-in vehicle, then the target vehicle with the driving state of a dangerous cutting-in vehicle is identified as the second dangerous vehicle; and if the longitudinal warning index of the second dangerous vehicle is not less than a preset warning index threshold or the reciprocal of the collision time is not greater than a preset reciprocal of the collision time threshold, then the first dangerous vehicle is identified as the primary target; and if the longitudinal warning index of the second dangerous vehicle is less than the preset warning index threshold and the reciprocal of the collision time is greater than the preset reciprocal of the collision time threshold, then the second dangerous vehicle is identified as the primary target; then the longitudinal relative distance and longitudinal relative speed of the primary target are output as the primary target distance and primary target speed.

[0132] When the vehicle in front of you is close enough to be moving slowly or completely stationary, if a vehicle in an adjacent lane quickly cuts into your lane, there are two possible scenarios:

[0133] The vehicle quickly cuts in, maintaining its current lane and rapidly decelerating to the speed level of the vehicle in front.

[0134] The vehicle quickly cuts into another lane after only briefly passing through its own lane.

[0135] Due to the presence of the vehicle ahead, if it is the primary target, the vehicle should respond by decelerating and braking. However, a rapidly approaching vehicle causes the vehicle to accelerate due to its higher speed, regardless of the situation. This undoubtedly reduces the reliability of the adaptive cruise control system and the driver's acceptance.

[0136] Thanks to the sensors' high mounting height, the perception system can simultaneously identify two vehicles that are close together in the same lane. It then compares the identified indicators with corresponding thresholds. If both indicators for a target vehicle exceed the threshold, that vehicle is considered the most dangerous primary target. In this scenario, the system directly provides the relative speed and distance information of the approaching vehicle. If multiple vehicles matching the characteristics are present, the closest one is designated as the primary target.

[0137] Dist = p(t) long,dangerous

[0138] V y =v(t) long,dangerous

[0139] Corresponding to the aforementioned embodiments of the adaptive cruise primary target selection method, the present invention also provides an adaptive cruise primary target selection device.

[0140] like Figure 6 As shown, Figure 6 This is a schematic diagram of an adaptive cruise primary target selection device according to an embodiment of the present invention, comprising the following modules:

[0141] The vehicle trajectory estimation module 610 is used to estimate the vehicle's trajectory based on its yaw rate.

[0142] The target vehicle parameter correction module 620 is used to correct the motion parameters of each target vehicle within the target range according to the motion trajectory; wherein, the motion parameters include lateral relative distance, longitudinal relative distance, lateral relative velocity, and longitudinal relative velocity;

[0143] The target vehicle motion analysis module 630 is used to calculate the motion index of the target vehicle based on the corrected motion parameters; wherein, the motion index includes a longitudinal warning index, a collision time reciprocal, and a lane change probability; the longitudinal warning index is used to represent the risk index of the collision between the vehicle and the target vehicle in the current driving direction; the collision time reciprocal is used to represent the reciprocal of the time when the vehicle and the target vehicle collide while the driving speed remains constant; and the lane change probability is used to represent the probability that the target vehicle enters the lane where the vehicle is located.

[0144] The target vehicle state determination module 640 is used to determine the driving state of the target vehicle by comparing the motion index with the corresponding index threshold; wherein the driving state is one of the following: adjacent vehicle, smoothly cutting in vehicle, dangerously cutting in vehicle, safe vehicle in lane, and dangerous vehicle in lane;

[0145] The representative state determination module 650 is used to determine the representative driving state of the current scenario based on the driving states of all target vehicles; wherein the representative driving state is one of the following: normal driving state, smooth entry state, dangerous entry state, and dangerous state within the lane;

[0146] The main target selection module 660 is used to determine the target vehicle that is closest to the current vehicle among the target vehicles that meet the corresponding driving state as the main target based on the representative driving state, and output the main target distance and the main target speed.

[0147] Preferably, calculating the motion index of the target vehicle based on the corrected motion parameters includes:

[0148] The longitudinal warning indicator x is calculated using the following formula:

[0149]

[0150] Among them, P long v is the longitudinal relative distance. long T is the longitudinal relative velocity. s,delay v is the delay time of the vehicle's braking system. s T is the speed of this vehicle. h,delay This is the reaction time for the driver of this vehicle.

[0151] Preferably, calculating the motion index of the target vehicle based on the corrected motion parameters includes:

[0152] The reciprocal of the collision time TTC is calculated using the following formula. -1 :

[0153]

[0154] Among them, P long v is the longitudinal relative distance. s v is the speed of this vehicle. p The target vehicle's speed in the current driving direction.

[0155] Preferably, calculating the motion index of the target vehicle based on the corrected motion parameters includes:

[0156] The lateral relative distance and the lateral relative speed are matched with preset fuzzy rules to obtain a fuzzy set of lane change probabilities, and then the lane change probability is obtained by defuzzification calculation.

[0157] Preferably, determining the driving state of the target vehicle by comparing the motion index with the corresponding index threshold specifically includes:

[0158] If the lane change probability is greater than a preset lane change probability threshold, and the longitudinal warning index is less than a preset warning index threshold or the reciprocal of the collision time is greater than a preset reciprocal of the collision time threshold, then the driving state of the target vehicle is determined to be a dangerous cutting vehicle.

[0159] If the lane change probability is greater than a preset lane change probability threshold, and the longitudinal warning index is not less than a preset warning index threshold and the reciprocal of the collision time is not greater than a preset collision time reciprocal threshold, then the driving state of the target vehicle is determined to be a smooth entry vehicle.

[0160] If the lane change probability is less than a preset lane change probability threshold and the lateral relative distance is less than a preset distance threshold, and the longitudinal warning index is less than a preset warning index threshold and the reciprocal of the collision time is greater than a preset collision time reciprocal threshold, then the driving state of the target vehicle is determined to be a dangerous vehicle in the lane.

[0161] If the lane change probability is less than a preset lane change probability threshold and the lateral relative distance is less than a preset distance threshold, and the longitudinal warning index is not less than a preset warning index threshold or the reciprocal of the collision time is not greater than a preset reciprocal of the collision time threshold, then the driving status of the target vehicle is determined to be a safe vehicle in the lane.

[0162] If the lane change probability is greater than a preset lane change probability threshold and the lateral relative distance is not less than a preset distance threshold, then the driving state of the target vehicle is determined to be that of a neighboring vehicle.

[0163] Preferably, the step of determining the target vehicle closest to the current vehicle among the target vehicles that meet the corresponding driving state as the primary target, and outputting the primary target distance and primary target speed, includes:

[0164] If the driving state is normal driving state, then the target vehicle with the smallest longitudinal relative distance in the lane where this vehicle is located is determined as the main target, and the longitudinal relative distance and longitudinal relative speed of the target vehicle are output as the main target distance and the main target speed.

[0165] Preferably, the step of determining the target vehicle closest to the current vehicle among the target vehicles that meet the corresponding driving state as the primary target, and outputting the primary target distance and primary target speed, includes:

[0166] If the driving state is a smooth entry state, then the target vehicle with the smallest longitudinal relative distance in the lane where this vehicle is located is identified as the first important target, and the first important target is identified as the main target.

[0167] The target vehicle in the driving state of a smoothly cutting-in vehicle is identified as the second important target, and the lateral relative distance of the second important target when it is identified is marked as the reference distance;

[0168] The weighting coefficients for the first important target and the second important target are calculated based on the ratio of the real-time lateral relative distance of the second important target to the reference distance.

[0169] The comprehensive longitudinal relative distance and comprehensive longitudinal relative velocity of the first important target and the second important target are calculated based on the weighting coefficients of the first important target and the second important target, and the comprehensive longitudinal relative distance and the comprehensive longitudinal relative velocity are output as the main target distance and the main target velocity;

[0170] When the real-time lateral relative distance of the second important target is less than the preset cut-in distance threshold, the main target is changed from the first important target to the second important target.

[0171] Preferably, the step of determining the target vehicle closest to the current vehicle among the target vehicles that meet the corresponding driving state as the primary target, and outputting the primary target distance and primary target speed, includes:

[0172] If the driving state is a dangerous entry state, then the target vehicle in the dangerous entry state is determined as the main target, and the longitudinal relative distance and longitudinal relative speed of the target vehicle are output as the main target distance and the main target speed.

[0173] Preferably, the step of determining the target vehicle closest to the current vehicle among the target vehicles that meet the corresponding driving state as the primary target, and outputting the primary target distance and primary target speed, includes:

[0174] If the driving state represented is a dangerous state within the lane, then the target vehicle whose driving state is a dangerous vehicle within the lane is identified as the first dangerous vehicle.

[0175] If there is no target vehicle whose driving state is a dangerous cutting vehicle, then the first dangerous vehicle is identified as the primary target;

[0176] If there is a target vehicle whose driving state is a dangerous cutting vehicle, then the target vehicle whose driving state is a dangerous cutting vehicle is identified as the second dangerous vehicle;

[0177] If the longitudinal warning index of the second dangerous vehicle is not less than a preset warning index threshold or the reciprocal of the collision time is not greater than a preset reciprocal of the collision time threshold, then the first dangerous vehicle is identified as the primary target.

[0178] If the longitudinal warning index of the second dangerous vehicle is less than a preset warning index threshold and the reciprocal of the collision time is greater than a preset collision time reciprocal threshold, then the second dangerous vehicle is identified as the primary target.

[0179] The longitudinal relative distance and longitudinal relative velocity of the main target are output as the distance and velocity of the main target.

[0180] The specific implementation process of the functions and roles of each module in the above device can be found in the implementation process of the corresponding steps in the above method, and will not be repeated here.

[0181] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of the present invention according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0182] The present invention also provides a computer device, which includes at least a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method described in any of the foregoing embodiments.

[0183] Figure 7 The diagram illustrates a more specific hardware structure of a computing device provided by the present invention. This device may include: a processor 701, a memory 702, an input / output interface 703, a communication interface 704, and a bus 705. The processor 701, memory 702, input / output interface 703, and communication interface 704 are interconnected internally via the bus 705.

[0184] The processor 701 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solution provided by this invention. The processor 701 may also include a graphics card, such as an Nvidia Titan X graphics card or a 1080Ti graphics card.

[0185] The memory 702 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 702 can store the operating system and other application programs. When the technical solution provided by this invention is implemented through software or firmware, the relevant program code is stored in the memory 702 and is called and executed by the processor 701.

[0186] The input / output interface 703 is used to connect input / output modules to enable information input and output. Input / output modules can be configured as components within the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Input devices may include keyboards, mice, touchscreens, microphones, various sensors, etc., while output devices may include displays, speakers, vibrators, indicator lights, etc.

[0187] Communication interface 704 is used to connect a communication module (not shown in the figure) to enable communication between this device and other devices. The communication module can communicate via wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0188] Bus 705 includes a pathway for transmitting information between various components of the device (e.g., processor 701, memory 702, input / output interface 703, and communication interface 704).

[0189] It should be noted that although the above-described device only shows the processor 701, memory 702, input / output interface 703, communication interface 704, and bus 705, in specific implementations, the device may also include other components necessary for normal operation. Furthermore, those skilled in the art will understand that the above-described device may only include the components necessary for implementing the present invention, and not necessarily all the components shown in the figures.

[0190] The present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the methods described in any of the foregoing embodiments.

[0191] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer 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 technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0192] As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that the present invention can be implemented by means of software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of the present invention.

[0193] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer, which can take the form of a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email sending and receiving device, game console, tablet computer, wearable device, or any combination of these devices.

[0194] The various embodiments in this invention 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, the device embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments. The device embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separate. In implementing the present invention, the functions of each module can be implemented in one or more software and / or hardware. Alternatively, 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.

[0195] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the implementation of the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the claims of the present invention.

Claims

1. A method of adaptive cruise main target selection, characterized in that, The method includes: Estimate the vehicle's trajectory based on its yaw rate; Based on the motion trajectory, the motion parameters of each target vehicle within the target range are corrected; wherein, the motion parameters include lateral relative distance, longitudinal relative distance, lateral relative velocity, and longitudinal relative velocity; Based on the corrected motion parameters, the motion index of the target vehicle is calculated; wherein, the motion index includes a longitudinal warning index, a collision time reciprocal, and a lane change probability. The longitudinal warning index is used to represent the risk index of a collision between the vehicle and the target vehicle in the current driving direction. The collision time reciprocal is used to represent the reciprocal of the time it would take for the vehicle to collide with the target vehicle while the driving speed remains constant. The lane change probability is used to represent the probability that the target vehicle will enter the lane where the vehicle is located. The driving state of the target vehicle is determined by comparing the motion index with the corresponding index threshold; wherein the driving state is one of the following: adjacent vehicle, smoothly cutting in, dangerously cutting in, safe vehicle in lane, and dangerous vehicle in lane. Based on the driving states of all target vehicles, determine the representative driving state of the current scenario; wherein the representative driving state is one of the following: normal driving state, smooth entry state, dangerous entry state, and dangerous state within the lane; Based on the representative driving state, the target vehicle that is closest to the current vehicle among the target vehicles that meet the corresponding driving state is identified as the main target, and the distance and speed of the main target are output.

2. The method of claim 1, wherein, The step of calculating the motion index of the target vehicle based on the corrected motion parameters includes: The longitudinal warning indicator x is calculated using the following formula: wherein P long is the longitudinal relative distance, v long is the longitudinal relative speed, T s,delay is the delay time of the braking system of the vehicle, v s is the driving speed of the vehicle, T h,delay is the reaction time of the driver of the vehicle.

3. The method of claim 1, wherein, The step of calculating the motion index of the target vehicle based on the corrected motion parameters includes: The time-to-collision inverse TTC is calculated by the following equation -1 : wherein P long is the longitudinal relative distance, v s is the driving speed of the host vehicle, v p is the driving speed of the target vehicle in the current driving direction.

4. The method of claim 1, wherein, The step of calculating the motion index of the target vehicle based on the corrected motion parameters includes: The lateral relative distance and the lateral relative speed are matched with preset fuzzy rules to obtain a fuzzy set of lane change probabilities, and then the lane change probability is obtained by defuzzification calculation.

5. The method of claim 1, wherein, The step of determining the driving state of the target vehicle by comparing the motion index with the corresponding index threshold specifically includes: If the lane change probability is greater than a preset lane change probability threshold, and the longitudinal warning index is less than a preset warning index threshold or the reciprocal of the collision time is greater than a preset reciprocal of the collision time threshold, then the driving state of the target vehicle is determined to be a dangerous cutting vehicle. If the lane change probability is greater than a preset lane change probability threshold, and the longitudinal warning index is not less than a preset warning index threshold and the reciprocal of the collision time is not greater than a preset collision time reciprocal threshold, then the driving state of the target vehicle is determined to be a smooth entry vehicle. If the lane change probability is less than a preset lane change probability threshold and the lateral relative distance is less than a preset distance threshold, and the longitudinal warning index is less than a preset warning index threshold and the reciprocal of the collision time is greater than a preset collision time reciprocal threshold, then the driving state of the target vehicle is determined to be a dangerous vehicle in the lane. If the lane change probability is less than a preset lane change probability threshold and the lateral relative distance is less than a preset distance threshold, and the longitudinal warning index is not less than a preset warning index threshold or the reciprocal of the collision time is not greater than a preset reciprocal of the collision time threshold, then the driving status of the target vehicle is determined to be a safe vehicle in the lane. If the lane change probability is greater than a preset lane change probability threshold and the lateral relative distance is not less than a preset distance threshold, then the driving state of the target vehicle is determined to be that of a neighboring vehicle.

6. The method of claim 1, wherein, The step of identifying the target vehicle closest to the current vehicle among the target vehicles that meet the corresponding driving state as the primary target, and outputting the primary target's distance and speed, includes: If the driving state is normal driving state, then the target vehicle with the smallest longitudinal relative distance in the lane where this vehicle is located is determined as the main target, and the longitudinal relative distance and longitudinal relative speed of the target vehicle are output as the main target distance and the main target speed.

7. The method of claim 1, wherein, The step of identifying the target vehicle closest to the current vehicle among the target vehicles that meet the corresponding driving state as the primary target, and outputting the primary target's distance and speed, includes: If the driving state is a smooth entry state, then the target vehicle with the smallest longitudinal relative distance in the lane where this vehicle is located is identified as the first important target, and the first important target is identified as the main target. The target vehicle in the driving state of a smoothly cutting-in vehicle is identified as the second important target, and the lateral relative distance of the second important target when it is identified is marked as the reference distance; The weighting coefficients for the first important target and the second important target are calculated based on the ratio of the real-time lateral relative distance of the second important target to the reference distance. The comprehensive longitudinal relative distance and comprehensive longitudinal relative velocity of the first important target and the second important target are calculated based on the weighting coefficients of the first important target and the second important target, and the comprehensive longitudinal relative distance and the comprehensive longitudinal relative velocity are output as the main target distance and the main target velocity; When the real-time lateral relative distance of the second important target is less than the preset cut-in distance threshold, the main target is changed from the first important target to the second important target.

8. The method of claim 1, wherein, The step of identifying the target vehicle closest to the current vehicle among the target vehicles that meet the corresponding driving state as the primary target, and outputting the primary target's distance and speed, includes: If the driving state is a dangerous entry state, then the target vehicle in the dangerous entry state is determined as the main target, and the longitudinal relative distance and longitudinal relative speed of the target vehicle are output as the main target distance and the main target speed.

9. The method of claim 1, wherein, The step of identifying the target vehicle closest to the current vehicle among the target vehicles that meet the corresponding driving state as the primary target, and outputting the primary target's distance and speed, includes: If the driving state represented is a dangerous state within the lane, then the target vehicle whose driving state is a dangerous vehicle within the lane is identified as the first dangerous vehicle. If there is no target vehicle whose driving state is a dangerous cutting vehicle, then the first dangerous vehicle is identified as the primary target; If there is a target vehicle whose driving state is a dangerous cutting vehicle, then the target vehicle whose driving state is a dangerous cutting vehicle is identified as the second dangerous vehicle; If the longitudinal warning index of the second dangerous vehicle is not less than a preset warning index threshold or the reciprocal of the collision time is not greater than a preset reciprocal of the collision time threshold, then the first dangerous vehicle is identified as the primary target. If the longitudinal warning index of the second dangerous vehicle is less than a preset warning index threshold and the reciprocal of the collision time is greater than a preset collision time reciprocal threshold, then the second dangerous vehicle is identified as the primary target. The longitudinal relative distance and longitudinal relative velocity of the main target are output as the distance and velocity of the main target.

10. An adaptive cruise main target selection apparatus characterized by comprising: The device includes: The vehicle trajectory estimation module is used to estimate the vehicle's trajectory based on its yaw rate. The target vehicle parameter correction module is used to correct the motion parameters of each target vehicle within the target range according to the motion trajectory; wherein, the motion parameters include lateral relative distance, longitudinal relative distance, lateral relative velocity, and longitudinal relative velocity; The target vehicle motion analysis module is used to calculate the motion index of the target vehicle based on the corrected motion parameters. The motion index includes a longitudinal warning index, a collision time reciprocal, and a lane change probability. The longitudinal warning index represents the risk index of a collision between the current vehicle and the target vehicle in the current driving direction. The collision time reciprocal represents the reciprocal of the time it would take for the current vehicle to collide with the target vehicle while the driving speed remains constant. The lane change probability represents the probability that the target vehicle will enter the lane where the current vehicle is located. The target vehicle state determination module is used to determine the driving state of the target vehicle by comparing the motion index with the corresponding index threshold; wherein the driving state is one of the following: adjacent vehicle, smoothly cutting in, dangerously cutting in, safe vehicle in lane, and dangerous vehicle in lane; The representative state determination module is used to determine the representative driving state of the current scenario based on the driving states of all target vehicles; wherein the representative driving state is one of the following: normal driving state, smooth entry state, dangerous entry state, and dangerous state within the lane; The main target selection module is used to determine the target vehicle that is closest to the current vehicle among the target vehicles that meet the corresponding driving state as the main target based on the representative driving state, and output the main target distance and the main target speed.

Images